popov/gogo2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

init

Browse Source
This commit is contained in:
Dobromir Popov
2025-03-18 09:23:09 +02:00
commit 3871afd4b8
100 changed files with 55180 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.env Normal file
View File

@@ -0,0 +1,9 @@
# MEXC Exchange API Keys
MEXC_API_KEY=mx0vglGymMT4iLpHXD
MEXC_SECRET_KEY=557300a85ae84cf6b927b86278905fd7
# Trading Parameters
MAX_LEVERAGE=50
INITIAL_BALANCE=1000
STOP_LOSS_PERCENT=0.5
TAKE_PROFIT_PERCENT=1.5

76
.vscode/launch.json vendored Normal file
View File

@@ -0,0 +1,76 @@
{
"version": "0.2.0",
"configurations": [
{
"name": "Train Bot",
"type": "python",
"request": "launch",
"program": "main.py",
"args": ["--mode", "train", "--episodes", "100"],
"console": "integratedTerminal",
"justMyCode": true
},
{
"name": "Evaluate Bot",
"type": "python",
"request": "launch",
"program": "main.py",
"args": ["--mode", "eval", "--episodes", "10"],
"console": "integratedTerminal",
"justMyCode": true
},
{
"name": "Live Trading (Demo)",
"type": "python",
"request": "launch",
"program": "main.py",
"args": [
"--mode", "live",
"--demo", "true",
"--symbol", "ETH/USDT",
"--timeframe", "1m"
],
"console": "integratedTerminal",
"justMyCode": true,
"env": {
"PYTHONUNBUFFERED": "1"
}
},
{
"name": "Live Trading (Real)",
"type": "python",
"request": "launch",
"program": "main.py",
"args": [
"--mode", "live",
"--demo", "false",
"--symbol", "ETH/USDT",
"--timeframe", "1m",
"--leverage", "50"
],
"console": "integratedTerminal",
"justMyCode": true,
"env": {
"PYTHONUNBUFFERED": "1"
}
},
{
"name": "Live Trading (BTC Futures)",
"type": "python",
"request": "launch",
"program": "main.py",
"args": [
"--mode", "live",
"--demo", "false",
"--symbol", "BTC/USDT",
"--timeframe", "5m",
"--leverage", "20"
],
"console": "integratedTerminal",
"justMyCode": true,
"env": {
"PYTHONUNBUFFERED": "1"
}
}
]
}

340
DISK_SPACE_OPTIMIZATION.md Normal file
View File

@@ -0,0 +1,340 @@
# Disk Space Optimization for Model Training
## Issue
The training process was encountering "No space left on device" errors during model saving operations, preventing successful completion of training cycles. Additionally, we identified matrix multiplication errors and TorchScript compatibility issues that were causing training crashes.
## Solution Implemented
A comprehensive set of improvements were implemented in the `main.py` file to address these issues:
1. Creating smaller checkpoint files with minimal model data
2. Providing multiple fallback mechanisms when primary save methods fail
3. Saving essential model parameters as JSON when full model saving fails
4. Automatic cleanup of old model files to free up disk space
5. **NEW**: Model quantization for even smaller file sizes
6. **NEW**: Fixed TorchScript compatibility issues with `CandlePatternCNN`
7. **NEW**: Fixed matrix multiplication errors in the `LSTMAttentionDQN` class
8. **NEW**: Added aggressive cleanup option for very low disk space situations
## Implementation Details
### Compact Save Function with Quantization
The updated `compact_save` function now includes an option to use model quantization for even smaller file sizes:
```python
def compact_save(model, optimizer, reward, epsilon, state_size, action_size, hidden_size, path, use_quantization=False):
"""
Save a model in a compact format suitable for low disk space environments.
Includes fallbacks if the primary save method fails.
"""
try:
# Create minimal checkpoint with essential data only
checkpoint = {
'model_state_dict': model.state_dict(),
'epsilon': epsilon,
'state_size': state_size,
'action_size': action_size,
'hidden_size': hidden_size
}
# Apply quantization if requested
if use_quantization:
try:
logging.info(f"Attempting quantized save to {path}")
# Quantize model to int8
quantized_model = torch.quantization.quantize_dynamic(
model, # the original model
{torch.nn.Linear}, # a set of layers to dynamically quantize
dtype=torch.qint8 # the target dtype for quantized weights
)
# Create quantized checkpoint
quantized_checkpoint = {
'model_state_dict': quantized_model.state_dict(),
'epsilon': epsilon,
'state_size': state_size,
'action_size': action_size,
'hidden_size': hidden_size,
'is_quantized': True
}
# Save with older pickle protocol and disable new zipfile serialization
torch.save(quantized_checkpoint, path, _use_new_zipfile_serialization=False, pickle_protocol=2)
logging.info(f"Quantized compact save successful to {path}")
return True
except Exception as e:
logging.warning(f"Quantized save failed, falling back to regular save: {str(e)}")
# Fall back to regular save if quantization fails
# Regular save with older pickle protocol and no zipfile serialization
torch.save(checkpoint, path, _use_new_zipfile_serialization=False, pickle_protocol=2)
logging.info(f"Compact save successful to {path}")
return True
except Exception as e:
logging.error(f"Compact save failed: {str(e)}")
logging.error(traceback.format_exc())
# Fallback: Save just the parameters as JSON if we can't save the full model
try:
params = {
'epsilon': epsilon,
'state_size': state_size,
'action_size': action_size,
'hidden_size': hidden_size
}
json_path = f"{path}.params.json"
with open(json_path, 'w') as f:
json.dump(params, f)
logging.info(f"Saved minimal parameters to {json_path}")
return False
except Exception as json_e:
logging.error(f"JSON parameter save failed: {str(json_e)}")
return False
```
### TorchScript Compatibility Fix
The `CandlePatternCNN` class was refactored to make it compatible with TorchScript by replacing the dictionary-based feature storage with tensor attributes:
```python
class CandlePatternCNN(nn.Module):
"""Convolutional neural network for detecting candlestick patterns"""
def __init__(self, input_channels=5, feature_dimension=512):
super(CandlePatternCNN, self).__init__()
# ... existing CNN layers ...
# Initialize intermediate features as empty tensors, not as a dict
# This makes the model TorchScript compatible
self.feature_1m = torch.zeros(1, feature_dimension)
self.feature_1h = torch.zeros(1, feature_dimension)
self.feature_1d = torch.zeros(1, feature_dimension)
def forward(self, x_1m, x_1h, x_1d):
# Process timeframe data
feat_1m = self.process_timeframe(x_1m)
feat_1h = self.process_timeframe(x_1h)
feat_1d = self.process_timeframe(x_1d)
# Store features as attributes instead of in a dictionary
self.feature_1m = feat_1m
self.feature_1h = feat_1h
self.feature_1d = feat_1d
# Concatenate features from different timeframes
combined_features = torch.cat([feat_1m, feat_1h, feat_1d], dim=1)
return combined_features
```
### Matrix Multiplication Error Fix
The `LSTMAttentionDQN` forward method was enhanced to handle different tensor shapes safely, preventing matrix multiplication errors:
```python
def forward(self, state, x_1m=None, x_1h=None, x_1d=None):
"""
Forward pass handling different input shapes and optional CNN features
"""
batch_size = state.size(0)
# Handle CNN features if provided
if x_1m is not None and x_1h is not None and x_1d is not None:
# Ensure all CNN features have batch dimension
if len(x_1m.shape) == 2:
x_1m = x_1m.unsqueeze(0)
if len(x_1h.shape) == 2:
x_1h = x_1h.unsqueeze(0)
if len(x_1d.shape) == 2:
x_1d = x_1d.unsqueeze(0)
# Ensure batch dimensions match
if x_1m.size(0) != batch_size:
x_1m = x_1m.expand(batch_size, -1, -1) if x_1m.size(0) == 1 else x_1m[:batch_size]
# ... additional shape handling ...
# Handle variable dimensions more gracefully
needed_features = 512
if x_1m_flat.size(1) < needed_features:
x_1m_flat = F.pad(x_1m_flat, (0, needed_features - x_1m_flat.size(1)))
else:
x_1m_flat = x_1m_flat[:, :needed_features]
```
### Enhanced File Cleanup
The file cleanup function now includes an aggressive mode and disk space reporting:
```python
def cleanup_model_files(keep_best=True, keep_latest_n=5, aggressive=False):
"""
Delete old model files to free up disk space.
Args:
keep_best (bool): Whether to keep the best model files (reward, pnl, net_pnl)
keep_latest_n (int): Number of latest checkpoint files to keep
aggressive (bool): If True, apply more aggressive cleanup in very low disk scenarios
"""
try:
logging.info(f"Running model file cleanup: keep_best={keep_best}, keep_latest_n={keep_latest_n}")
models_dir = "models"
# Get all files in the models directory
all_files = os.listdir(models_dir)
# Files to potentially delete
checkpoint_files = []
# Best files to keep if keep_best is True
best_patterns = [
"trading_agent_best_reward.pt",
"trading_agent_best_pnl.pt",
"trading_agent_best_net_pnl.pt",
"trading_agent_final.pt"
]
# Collect checkpoint files that can be deleted
for filename in all_files:
file_path = os.path.join(models_dir, filename)
# Skip directories
if os.path.isdir(file_path):
continue
# Skip current best files if keep_best is True
if keep_best and any(filename == pattern for pattern in best_patterns):
continue
# Collect checkpoint files
if "checkpoint" in filename and filename.endswith(".pt"):
checkpoint_files.append((filename, os.path.getmtime(file_path), file_path))
# If we have more checkpoint files than we want to keep
if len(checkpoint_files) > keep_latest_n:
# Sort by modification time (newest first)
checkpoint_files.sort(key=lambda x: x[1], reverse=True)
# Keep the newest N files
files_to_delete = checkpoint_files[keep_latest_n:]
# Delete old checkpoint files
bytes_freed = 0
for _, _, file_path in files_to_delete:
try:
file_size = os.path.getsize(file_path)
os.remove(file_path)
bytes_freed += file_size
logging.info(f"Deleted old checkpoint file: {file_path}")
except Exception as e:
logging.error(f"Failed to delete file {file_path}: {str(e)}")
logging.info(f"Cleanup complete. Deleted {len(files_to_delete)} files, freed {bytes_freed / (1024*1024):.2f} MB")
else:
logging.info(f"No cleanup needed. Found {len(checkpoint_files)} checkpoint files, keeping {keep_latest_n}")
except Exception as e:
logging.error(f"Error during file cleanup: {str(e)}")
logging.error(traceback.format_exc())
# Check available disk space after cleanup
try:
if platform.system() == 'Windows':
free_bytes = ctypes.c_ulonglong(0)
ctypes.windll.kernel32.GetDiskFreeSpaceExW(ctypes.c_wchar_p(os.path.abspath(models_dir)), None, None, ctypes.pointer(free_bytes))
free_mb = free_bytes.value / (1024 * 1024)
else:
st = os.statvfs(os.path.abspath(models_dir))
free_mb = (st.f_bavail * st.f_frsize) / (1024 * 1024)
logging.info(f"Available disk space after cleanup: {free_mb:.2f} MB")
# If space is still low, recommend aggressive cleanup
if free_mb < 200 and not aggressive: # Less than 200MB available
logging.warning("Disk space still critically low. Consider using aggressive cleanup.")
except Exception as e:
logging.error(f"Error checking disk space: {str(e)}")
```
### Train Agent Function Modification
The `train_agent` function was modified to include the `use_compact_save` option:
```python
def train_agent(episodes, max_steps, update_interval=10, training_iterations=10,
use_compact_save=False):
# ...existing code...
if use_compact_save:
compact_save(agent.policy_net, agent.optimizer, total_reward, agent.epsilon,
agent.state_size, agent.action_size, agent.hidden_size,
f"models/trading_agent_best_reward.pt")
else:
agent.save(f"models/trading_agent_best_reward.pt")
# ...similar modifications for other save points...
```
### Command Line Arguments
New command line arguments have been added to support these features:
```python
parser.add_argument('--compact_save', action='store_true', help='Use compact save to reduce disk usage')
parser.add_argument('--use_quantization', action='store_true', help='Use model quantization for even smaller file sizes')
parser.add_argument('--cleanup', action='store_true', help='Clean up old model files before training')
parser.add_argument('--aggressive_cleanup', action='store_true', help='Perform aggressive cleanup to free more space')
parser.add_argument('--keep_latest', type=int, default=5, help='Number of latest checkpoint files to keep when cleaning up')
```
## Results
### Effectiveness
The comprehensive approach to disk space optimization addresses multiple issues:
1. **Successful Saves**: Multiple successful save methods that adapt to different disk space conditions
2. **Fallback Mechanism**: Smaller fallback files when full model saving fails
3. **Training Stability**: Fixed TorchScript compatibility and matrix multiplication errors prevent crashes
4. **Automatic Cleanup**: Reduced disk usage through automatic cleanup of old files
### File Size Comparison
The optimization techniques create smaller files through multiple approaches:
- **Quantized Models**: Using INT8 quantization can reduce model size by up to 75%
- **Non-Optimizer Saves**: Excluding optimizer state reduces file size by ~50%
- **JSON Parameters**: Extremely small (under 100 bytes) for essential restart capability
- **Cleanup**: Automatic removal of old checkpoint files frees up disk space
## Usage Instructions
To use these disk space optimization features, run the training with the following command line options:
```bash
# Basic usage with compact save
python main.py --mode train --episodes 10 --max_steps 200 --compact_save
# With model quantization for even smaller files
python main.py --mode train --episodes 10 --max_steps 200 --compact_save --use_quantization
# With file cleanup before training
python main.py --mode train --episodes 10 --max_steps 200 --compact_save --cleanup
# With aggressive cleanup for very low disk space
python main.py --mode train --episodes 10 --max_steps 200 --compact_save --cleanup --aggressive_cleanup
# Specify how many checkpoint files to keep
python main.py --mode train --episodes 10 --max_steps 200 --compact_save --cleanup --keep_latest 3
```
## Additional Recommendations
1. **Disk Space Monitoring**: The code now reports available disk space after cleanup. Monitor this to ensure sufficient space is maintained.
2. **Regular Cleanup**: Schedule regular cleanup operations, especially for long training sessions.
3. **Model Pruning**: Consider implementing neural network pruning to remove unnecessary connections in the model, further reducing size.
4. **Remote Storage**: For very long training sessions, consider implementing automatic upload of checkpoint files to remote storage.
## Conclusion
The implemented disk space optimization features have successfully addressed multiple issues:
1. Fixed TorchScript compatibility and matrix multiplication errors that were causing crashes
2. Implemented model quantization for significantly smaller file sizes
3. Added aggressive cleanup options to manage disk space automatically
4. Provided multiple fallback mechanisms to ensure training progress isn't lost
These improvements allow training to continue even under severe disk space constraints, with minimal intervention required.

87
IMPLEMENTATION_SUMMARY.md Normal file
View File

@@ -0,0 +1,87 @@
# Implementation Summary: Training Stability and Disk Space Optimization
## Issues Addressed
1. **Disk Space Errors**: "No space left on device" errors during model saving operations
2. **Matrix Multiplication Errors**: Shape mismatches in neural network operations
3. **TorchScript Compatibility Issues**: Errors when attempting to use `torch.jit.save()`
4. **Training Crashes**: Unhandled exceptions in saving process
## Solutions Implemented
### Disk Space Optimization
1. **Compact Model Saving**
- Created minimal checkpoint files with essential data only
- Implemented multiple fallback mechanisms for different disk space scenarios
- Added JSON parameter saving as a last resort
- Integrated model quantization (INT8) for reduced file sizes
2. **Automatic File Cleanup**
- Added automatic cleanup of older checkpoint files
- Implemented "aggressive cleanup" mode for critically low disk space
- Added disk space monitoring to report available space
- Created retention policies to keep best models while removing unnecessary files
### Neural Network Improvements
1. **TorchScript Compatibility**
- Refactored `CandlePatternCNN` class to use tensor attributes instead of dictionaries
- Simplified layer architecture to ensure compatibility with TorchScript
- Fixed forward method to handle tensor shapes consistently
2. **Matrix Multiplication Fix**
- Enhanced tensor shape handling in `LSTMAttentionDQN` forward method
- Added robust dimension checking and correction
- Implemented padding/truncating for variable-sized inputs
- Fixed batch dimension handling for CNN features
## Results
The implemented changes resulted in:
1. **Improved Stability**: Training no longer crashes due to matrix multiplication errors or torch.jit issues
2. **Efficient Disk Usage**: Freed up 3.8 GB of disk space through aggressive cleanup
3. **Fallback Mechanisms**: Successfully created fallback files when primary saves failed
4. **Enhanced Monitoring**: Added disk space tracking to report remaining space after cleanup operations
## Command Line Usage
The improvements can be activated with the following command line arguments:
```bash
# Basic usage with compact save
python main.py --mode train --episodes 10 --compact_save
# With model quantization for smaller files
python main.py --mode train --episodes 10 --compact_save --use_quantization
# With file cleanup before training
python main.py --mode train --episodes 10 --compact_save --cleanup
# With aggressive cleanup for very low disk space
python main.py --mode train --episodes 10 --compact_save --cleanup --aggressive_cleanup
# Specify how many checkpoint files to keep
python main.py --mode train --episodes 10 --compact_save --cleanup --keep_latest 3
```
## Key Files Modified
1. `main.py`: Added new functions and modified existing ones:
- Added `compact_save()` function with quantization support
- Enhanced `cleanup_model_files()` function with aggressive mode
- Refactored `CandlePatternCNN` class for TorchScript compatibility
- Fixed shape handling in `LSTMAttentionDQN` forward method
2. `DISK_SPACE_OPTIMIZATION.md`: Comprehensive documentation of the disk space optimization features
- Detailed explanation of all implemented features
- Usage instructions and recommendations
- Performance analysis of the enhancements
## Future Recommendations
1. **Long-term Storage Solution**: Implement automatic upload to cloud storage for long training sessions
2. **Advanced Model Compression**: Explore neural network pruning and mixed-precision training
3. **Automatic Cleanup Scheduler**: Set up periodic cleanup based on disk usage thresholds
4. **Checkpoint Rotation Strategy**: Implement more sophisticated model retention policies

74
MODEL_SAVING_FIX.md Normal file
View File

@@ -0,0 +1,74 @@
# Model Saving Fix
## Issue
During training sessions, PyTorch model saving operations sometimes fail with errors like:
```
RuntimeError: [enforce fail at inline_container.cc:626] . unexpected pos 18278784 vs 18278680
```
or
```
RuntimeError: [enforce fail at inline_container.cc:820] . PytorchStreamWriter failed writing file data/75: file write failed
```
These errors occur in the PyTorch serialization mechanism when saving models using `torch.save()`.
## Solution
We've implemented a robust model saving approach that uses multiple fallback methods if the primary save operation fails:
1. **Attempt 1**: Save to a backup file first, then copy to the target path.
2. **Attempt 2**: Use an older pickle protocol (pickle protocol 2) which can be more compatible.
3. **Attempt 3**: Save without the optimizer state, which can reduce file size and avoid serialization issues.
4. **Attempt 4**: Use TorchScript's `torch.jit.save()` instead of `torch.save()`, which uses a different serialization mechanism.
## Implementation
The solution is implemented in two parts:
1. A `robust_save` function that tries multiple saving approaches with fallbacks.
2. A monkey patch that replaces the Agent's `save` method with our robust version.
### Example Usage
```python
# Import the robust_save function
from live_training import robust_save
# Save a model with fallbacks
success = robust_save(agent, "models/my_model.pt")
if success:
print("Model saved successfully!")
else:
print("All save attempts failed")
```
## Testing
We've created a test script `test_save.py` that demonstrates the robust saving approach and verifies that it works correctly.
To run the test:
```bash
python test_save.py
```
This script creates a simple model, attempts to save it using both the standard and robust methods, and reports on the results.
## Future Improvements
Possible future improvements to the model saving mechanism:
1. Additional fallback methods like serializing individual neural network layers.
2. Automatic retry mechanism with exponential backoff.
3. Asynchronous saving to avoid blocking the training loop.
4. Checksumming saved models to verify integrity.
## Related Issues
For more information on similar issues with PyTorch model saving, see:
- https://github.com/pytorch/pytorch/issues/27736
- https://github.com/pytorch/pytorch/issues/24045

72
MODEL_SAVING_RECOMMENDATIONS.md Normal file
View File

@@ -0,0 +1,72 @@
# Model Saving Recommendations
During training, several PyTorch model serialization errors were identified and fixed. Here's a summary of our findings and recommendations to ensure robust model saving:
## Issues Found
1. **PyTorch Serialization Errors**: Errors like `PytorchStreamWriter failed writing file data...` and `unexpected pos...` indicate issues with PyTorch's serialization mechanism.
2. **Disk Space Issues**: Our tests showed `No space left on device` errors, which can cause model corruption.
3. **Compatibility Issues**: Some serialization methods might not be compatible with specific PyTorch versions or environments.
## Implemented Solutions
1. **Robust Save Function**: We added a `robust_save` function that tries multiple saving approaches in sequence:
- First attempt: Standard save to a backup file, then copy to the target path
- Second attempt: Save with pickle protocol 2 (more compatible)
- Third attempt: Save without optimizer state (reduces file size)
- Fourth attempt: Use TorchScript's `jit.save()` (different serialization mechanism)
2. **Memory Management**: Implemented memory cleanup before saving:
- Clearing GPU cache with `torch.cuda.empty_cache()`
- Running garbage collection with `gc.collect()`
3. **Error Handling**: Added comprehensive error handling around all saving operations.
4. **Circuit Breaker Pattern**: Added circuit breakers to prevent consecutive failures during training.
## Recommendations
1. **Disk Space**: Ensure sufficient disk space is available (at least 1-2GB free). Large models can use several GB of disk space.
2. **Checkpoint Cleanup**: Periodically remove old checkpoints to free up space:
```bash
# Example script to keep only the most recent 5 checkpoints
Get-ChildItem -Path .\models\trading_agent_checkpoint_*.pt |
Sort-Object LastWriteTime -Descending |
Select-Object -Skip 5 |
Remove-Item
```
3. **File System Check**: If persistent errors occur, check the file system for errors or corruption.
4. **Use Smaller Models**: Consider reducing model size if saving large models is problematic.
5. **Alternative Serialization**: For very large models, consider saving key parameters separately rather than the entire model.
6. **Training Stability**: Use our improved training functions with memory management and error handling.
## How to Test Model Saving
We've provided a test script `test_model_save_load.py` that can verify if model saving is working correctly. Run it with:
```bash
python test_model_save_load.py
```
Or test all robust save methods with:
```bash
python test_model_save_load.py --test_robust
```
## Future Development
1. **Checksumming**: Add checksums to saved models to verify integrity.
2. **Compression**: Implement model compression to reduce file size.
3. **Distributed Saving**: For very large models, explore distributed saving mechanisms.
4. **Format Conversion**: Add ability to save models in ONNX or other portable formats.

BIN
__pycache__/compare_models.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/data_cache.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/enhanced_models.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/enhanced_training.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/exchange_simulator.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/main.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/mexc_trading.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/tests.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/visualize_trades.cpython-312.pyc Normal file
View File

Binary file not shown.

BIN
__pycache__/visualize_training.cpython-312.pyc Normal file
View File

Binary file not shown.

27
_notes.md Normal file
View File

@@ -0,0 +1,27 @@
https://github.com/mexcdevelop/mexc-api-sdk/blob/main/README.md#test-new-order
python mexc_tick_visualizer.py --symbol BTC/USDT --interval 1.0 --candle 60
ensure we use GPU if available to train faster. during training we need to have RL loop that looks at streaming data, and retrospective backtesting/training on predictions. sincr the start of the traing we're only loosing. implement robust penalty and analysis when closing a loosing trade and improve the reward function.
add 1h and 1d OHLCV data to let the model have the price action context
2025-03-10 12:11:28,651 - INFO - Initialized environment with 500 candles
C:\Users\popov\miniforge3\Lib\site-packages\torch\nn\modules\transformer.py:385: UserWarning: enable_nested_tensor is True, but self.use_nested_tensor is False because encoder_layer.self_attn.batch_first was not True(use batch_first for better inference performance)
warnings.warn(
main.py:1105: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.
self.scaler = amp.GradScaler()
C:\Users\popov\miniforge3\Lib\site-packages\torch\amp\grad_scaler.py:132: UserWarning: torch.cuda.amp.GradScaler is enabled, but CUDA is not available. Disabling.
warnings.warn(
2025-03-10 12:11:30,927 - INFO - Starting training for 1000 episodes...
2025-03-10 12:11:30,927 - INFO - Starting training on device: cpu
2025-03-10 12:11:30,928 - ERROR - Training failed: 'TradingEnvironment' object has no attribute 'initialize_price_predictor'
2025-03-10 12:11:30,928 - INFO - Exchange connection closed
Backend tkagg is interactive backend. Turning interactive mode on.

22
all_backtest_results.csv Normal file
View File

@@ -0,0 +1,22 @@
Period,Episode,Reward,Balance,PnL,Fees,Net_PnL
Day-1,1,0,100,0,0.0,0.0
Day-1,2,0,100,0,0.0,0.0
Day-1,3,0,100,0,0.0,0.0
Day-2,1,0,100,0,0.0,0.0
Day-2,2,0,100,0,0.0,0.0
Day-2,3,0,100,0,0.0,0.0
Day-3,1,0,100,0,0.0,0.0
Day-3,2,0,100,0,0.0,0.0
Day-3,3,0,100,0,0.0,0.0
Day-4,1,0,100,0,0.0,0.0
Day-4,2,0,100,0,0.0,0.0
Day-4,3,0,100,0,0.0,0.0
Day-5,1,0,100,0,0.0,0.0
Day-5,2,0,100,0,0.0,0.0
Day-5,3,0,100,0,0.0,0.0
Day-6,1,0,100,0,0.0,0.0
Day-6,2,0,100,0,0.0,0.0
Day-6,3,0,100,0,0.0,0.0
Day-7,1,0,100,0,0.0,0.0
Day-7,2,0,100,0,0.0,0.0
Day-7,3,0,100,0,0.0,0.0
1 Period Episode Reward Balance PnL Fees Net_PnL
2 Day-1 1 0 100 0 0.0 0.0
3 Day-1 2 0 100 0 0.0 0.0
4 Day-1 3 0 100 0 0.0 0.0
5 Day-2 1 0 100 0 0.0 0.0
6 Day-2 2 0 100 0 0.0 0.0
7 Day-2 3 0 100 0 0.0 0.0
8 Day-3 1 0 100 0 0.0 0.0
9 Day-3 2 0 100 0 0.0 0.0
10 Day-3 3 0 100 0 0.0 0.0
11 Day-4 1 0 100 0 0.0 0.0
12 Day-4 2 0 100 0 0.0 0.0
13 Day-4 3 0 100 0 0.0 0.0
14 Day-5 1 0 100 0 0.0 0.0
15 Day-5 2 0 100 0 0.0 0.0
16 Day-5 3 0 100 0 0.0 0.0
17 Day-6 1 0 100 0 0.0 0.0
18 Day-6 2 0 100 0 0.0 0.0
19 Day-6 3 0 100 0 0.0 0.0
20 Day-7 1 0 100 0 0.0 0.0
21 Day-7 2 0 100 0 0.0 0.0
22 Day-7 3 0 100 0 0.0 0.0

BIN
backtest_results.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 19 KiB

4
backtest_stats_Day-1.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-2.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-3.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-4.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-5.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-6.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

4
backtest_stats_Day-7.csv Normal file
View File

@@ -0,0 +1,4 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
3,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0
4 3 0 100 0 0.0 0.0 0 0 0

3
backtest_stats_Test-Day-1.csv Normal file
View File

@@ -0,0 +1,3 @@
Episode,Reward,Balance,PnL,Fees,Net PnL,Win Rate,Trades,Loss
1,0,100,0,0.0,0.0,0,0,0
2,0,100,0,0.0,0.0,0,0,0
1 Episode Reward Balance PnL Fees Net PnL Win Rate Trades Loss
2 1 0 100 0 0.0 0.0 0 0 0
3 2 0 100 0 0.0 0.0 0 0 0

166
check_live_trading.py Normal file
View File

@@ -0,0 +1,166 @@
import os
import sys
import logging
import importlib
import asyncio
from dotenv import load_dotenv
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[logging.StreamHandler()]
)
logger = logging.getLogger("check_live_trading")
def check_dependencies():
"""Check if all required dependencies are installed"""
required_packages = [
"numpy", "pandas", "matplotlib", "mplfinance", "torch",
"dotenv", "ccxt", "websockets", "tensorboard",
"sklearn", "PIL", "asyncio"
]
missing_packages = []
for package in required_packages:
try:
if package == "dotenv":
importlib.import_module("dotenv")
elif package == "PIL":
importlib.import_module("PIL")
else:
importlib.import_module(package)
logger.info(f"✅ {package} is installed")
except ImportError:
missing_packages.append(package)
logger.error(f"❌ {package} is NOT installed")
if missing_packages:
logger.error(f"Missing packages: {', '.join(missing_packages)}")
logger.info("Install missing packages with: pip install -r requirements.txt")
return False
return True
def check_api_keys():
"""Check if API keys are configured"""
load_dotenv()
api_key = os.getenv('MEXC_API_KEY')
secret_key = os.getenv('MEXC_SECRET_KEY')
if not api_key or api_key == "your_api_key_here" or not secret_key or secret_key == "your_secret_key_here":
logger.error("❌ API keys are not properly configured in .env file")
logger.info("Please update your .env file with valid MEXC API keys")
return False
logger.info("✅ API keys are configured")
return True
def check_model_files():
"""Check if trained model files exist"""
model_files = [
"models/trading_agent_best_pnl.pt",
"models/trading_agent_best_reward.pt",
"models/trading_agent_final.pt"
]
missing_models = []
for model_file in model_files:
if os.path.exists(model_file):
logger.info(f"✅ Model file exists: {model_file}")
else:
missing_models.append(model_file)
logger.error(f"❌ Model file missing: {model_file}")
if missing_models:
logger.warning("Some model files are missing. You need to train the model first.")
return False
return True
async def check_exchange_connection():
"""Test connection to MEXC exchange"""
try:
import ccxt
# Load API keys
load_dotenv()
api_key = os.getenv('MEXC_API_KEY')
secret_key = os.getenv('MEXC_SECRET_KEY')
if api_key == "your_api_key_here" or secret_key == "your_secret_key_here":
logger.warning("⚠️ Using placeholder API keys, skipping exchange connection test")
return False
# Initialize exchange
exchange = ccxt.mexc({
'apiKey': api_key,
'secret': secret_key,
'enableRateLimit': True
})
# Test connection by fetching markets
markets = exchange.fetch_markets()
logger.info(f"✅ Successfully connected to MEXC exchange")
logger.info(f"✅ Found {len(markets)} markets")
return True
except Exception as e:
logger.error(f"❌ Failed to connect to MEXC exchange: {str(e)}")
return False
def check_directories():
"""Check if required directories exist"""
required_dirs = ["models", "runs", "trade_logs"]
for directory in required_dirs:
if not os.path.exists(directory):
logger.info(f"Creating directory: {directory}")
os.makedirs(directory, exist_ok=True)
logger.info("✅ All required directories exist")
return True
async def main():
"""Run all checks"""
logger.info("Running pre-flight checks for live trading...")
checks = [
("Dependencies", check_dependencies()),
("API Keys", check_api_keys()),
("Model Files", check_model_files()),
("Directories", check_directories()),
("Exchange Connection", await check_exchange_connection())
]
# Count failed checks
failed_checks = sum(1 for _, result in checks if not result)
# Print summary
logger.info("\n" + "="*50)
logger.info("LIVE TRADING PRE-FLIGHT CHECK SUMMARY")
logger.info("="*50)
for check_name, result in checks:
status = "✅ PASS" if result else "❌ FAIL"
logger.info(f"{check_name}: {status}")
logger.info("="*50)
if failed_checks == 0:
logger.info("🚀 All checks passed! You're ready for live trading.")
logger.info("\nRun live trading with:")
logger.info("python main.py --mode live --demo true --symbol ETH/USDT --timeframe 1m")
logger.info("\nFor real trading (after updating API keys):")
logger.info("python main.py --mode live --demo false --symbol ETH/USDT --timeframe 1m --leverage 50")
return 0
else:
logger.error(f"❌ {failed_checks} check(s) failed. Please fix the issues before running live trading.")
return 1
if __name__ == "__main__":
exit_code = asyncio.run(main())
sys.exit(exit_code)

358
live_trading.log Normal file
View File

@@ -0,0 +1,358 @@
2025-03-17 02:49:17,843 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 02:49:17,844 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 02:49:17,847 - INFO - Exchange initialized with standard CCXT: mexc
2025-03-17 02:49:17,848 - INFO - Fetching initial data for ETH/USDT
2025-03-17 02:49:18,537 - ERROR - Error fetching OHLCV data: mexc {"code":700002,"msg":"Signature for this request is not valid."}
2025-03-17 02:49:18,537 - WARNING - No initial data received
2025-03-17 02:49:18,537 - ERROR - Failed to fetch initial data. Exiting.
2025-03-17 02:50:45,182 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 02:50:45,182 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 02:50:45,182 - INFO - Using mock data for demo mode (no API keys required)
2025-03-17 02:50:45,182 - INFO - Generating mock data for ETH/USDT (1m)
2025-03-17 02:50:45,189 - INFO - Generated 1000 mock candles
2025-03-17 02:50:45,217 - INFO - Using GPU: NVIDIA GeForce RTX 4060 Laptop GPU
2025-03-17 02:50:46,501 - WARNING - Failed to load with weights_only=True: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:50:46,566 - WARNING - Failed with safe_globals: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy.dtype was not an allowed global by default. Please use `torch.serialization.add_safe_globals([dtype])` or the `torch.serialization.safe_globals([dtype])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:50:46,623 - ERROR - Error in live trading: Error(s) in loading state_dict for DQN:
size mismatch for fc1.weight: copying a param with shape torch.Size([384, 40]) from checkpoint, the shape in current model is torch.Size([256, 64]).
size mismatch for fc1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for lstm.weight_ih_l0: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.weight_hh_l0: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.bias_ih_l0: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.bias_hh_l0: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.weight_ih_l1: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.weight_hh_l1: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.bias_ih_l1: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.bias_hh_l1: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for attention.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for attention.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for attention.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for attention.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for fc2.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for fc2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for fc3.weight: copying a param with shape torch.Size([192, 384]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for fc3.bias: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for value_stream.weight: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([1, 128]).
size mismatch for advantage_stream.weight: copying a param with shape torch.Size([4, 192]) from checkpoint, the shape in current model is torch.Size([3, 128]).
size mismatch for advantage_stream.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([3]).
size mismatch for transformer_encoder.layers.0.self_attn.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for transformer_encoder.layers.0.self_attn.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for transformer_encoder.layers.0.self_attn.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for transformer_encoder.layers.0.self_attn.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.linear1.weight: copying a param with shape torch.Size([2048, 384]) from checkpoint, the shape in current model is torch.Size([2048, 256]).
size mismatch for transformer_encoder.layers.0.linear2.weight: copying a param with shape torch.Size([384, 2048]) from checkpoint, the shape in current model is torch.Size([256, 2048]).
size mismatch for transformer_encoder.layers.0.linear2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.self_attn.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for transformer_encoder.layers.1.self_attn.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for transformer_encoder.layers.1.self_attn.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for transformer_encoder.layers.1.self_attn.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.linear1.weight: copying a param with shape torch.Size([2048, 384]) from checkpoint, the shape in current model is torch.Size([2048, 256]).
size mismatch for transformer_encoder.layers.1.linear2.weight: copying a param with shape torch.Size([384, 2048]) from checkpoint, the shape in current model is torch.Size([256, 2048]).
size mismatch for transformer_encoder.layers.1.linear2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
2025-03-17 02:50:46,625 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 236, in run_live_demo
agent.load(args.model)
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\main.py", line 1776, in load
self.policy_net.load_state_dict(checkpoint['policy_net'])
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\nn\modules\module.py", line 2581, in load_state_dict
raise RuntimeError(
RuntimeError: Error(s) in loading state_dict for DQN:
size mismatch for fc1.weight: copying a param with shape torch.Size([384, 40]) from checkpoint, the shape in current model is torch.Size([256, 64]).
size mismatch for fc1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for lstm.weight_ih_l0: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.weight_hh_l0: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.bias_ih_l0: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.bias_hh_l0: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.weight_ih_l1: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.weight_hh_l1: copying a param with shape torch.Size([1536, 384]) from checkpoint, the shape in current model is torch.Size([1024, 256]).
size mismatch for lstm.bias_ih_l1: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for lstm.bias_hh_l1: copying a param with shape torch.Size([1536]) from checkpoint, the shape in current model is torch.Size([1024]).
size mismatch for attention.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for attention.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for attention.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for attention.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for fc2.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for fc2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for ln2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for fc3.weight: copying a param with shape torch.Size([192, 384]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for fc3.bias: copying a param with shape torch.Size([192]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for value_stream.weight: copying a param with shape torch.Size([1, 192]) from checkpoint, the shape in current model is torch.Size([1, 128]).
size mismatch for advantage_stream.weight: copying a param with shape torch.Size([4, 192]) from checkpoint, the shape in current model is torch.Size([3, 128]).
size mismatch for advantage_stream.bias: copying a param with shape torch.Size([4]) from checkpoint, the shape in current model is torch.Size([3]).
size mismatch for transformer_encoder.layers.0.self_attn.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for transformer_encoder.layers.0.self_attn.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for transformer_encoder.layers.0.self_attn.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for transformer_encoder.layers.0.self_attn.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.linear1.weight: copying a param with shape torch.Size([2048, 384]) from checkpoint, the shape in current model is torch.Size([2048, 256]).
size mismatch for transformer_encoder.layers.0.linear2.weight: copying a param with shape torch.Size([384, 2048]) from checkpoint, the shape in current model is torch.Size([256, 2048]).
size mismatch for transformer_encoder.layers.0.linear2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.0.norm2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.self_attn.in_proj_weight: copying a param with shape torch.Size([1152, 384]) from checkpoint, the shape in current model is torch.Size([768, 256]).
size mismatch for transformer_encoder.layers.1.self_attn.in_proj_bias: copying a param with shape torch.Size([1152]) from checkpoint, the shape in current model is torch.Size([768]).
size mismatch for transformer_encoder.layers.1.self_attn.out_proj.weight: copying a param with shape torch.Size([384, 384]) from checkpoint, the shape in current model is torch.Size([256, 256]).
size mismatch for transformer_encoder.layers.1.self_attn.out_proj.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.linear1.weight: copying a param with shape torch.Size([2048, 384]) from checkpoint, the shape in current model is torch.Size([2048, 256]).
size mismatch for transformer_encoder.layers.1.linear2.weight: copying a param with shape torch.Size([384, 2048]) from checkpoint, the shape in current model is torch.Size([256, 2048]).
size mismatch for transformer_encoder.layers.1.linear2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm1.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm1.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm2.weight: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
size mismatch for transformer_encoder.layers.1.norm2.bias: copying a param with shape torch.Size([384]) from checkpoint, the shape in current model is torch.Size([256]).
2025-03-17 02:52:12,557 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 02:52:12,558 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 02:52:12,558 - INFO - Using mock data for demo mode (no API keys required)
2025-03-17 02:52:12,558 - INFO - Generating mock data for ETH/USDT (1m)
2025-03-17 02:52:12,565 - INFO - Generated 1000 mock candles
2025-03-17 02:52:12,607 - INFO - Extracted model architecture: state_size=40, action_size=4, hidden_size=384, lstm_layers=2, attention_heads=4
2025-03-17 02:52:12,636 - INFO - Using GPU: NVIDIA GeForce RTX 4060 Laptop GPU
2025-03-17 02:52:13,909 - WARNING - Failed to load with weights_only=True: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:52:13,973 - WARNING - Failed with safe_globals: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy.dtype was not an allowed global by default. Please use `torch.serialization.add_safe_globals([dtype])` or the `torch.serialization.safe_globals([dtype])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:52:14,032 - INFO - Model loaded from models/trading_agent_best_pnl.pt
2025-03-17 02:52:14,032 - INFO - Model loaded successfully
2025-03-17 02:52:14,035 - INFO - Starting live trading simulation...
2025-03-17 02:52:19,117 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:19,118 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:19,118 - INFO - Continuing after error...
2025-03-17 02:52:29,139 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:29,140 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:29,140 - INFO - Continuing after error...
2025-03-17 02:52:39,157 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:39,157 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:39,158 - INFO - Continuing after error...
2025-03-17 02:52:49,176 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:49,177 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:49,177 - INFO - Continuing after error...
2025-03-17 02:52:59,196 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:59,196 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:52:59,196 - INFO - Continuing after error...
2025-03-17 02:53:09,220 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:53:09,220 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:53:09,220 - INFO - Continuing after error...
2025-03-17 02:53:19,244 - ERROR - Error in live trading loop: not enough values to unpack (expected 4, got 3)
2025-03-17 02:53:19,245 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 367, in run_live_demo
next_state, reward, done, info = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: not enough values to unpack (expected 4, got 3)
2025-03-17 02:53:19,245 - INFO - Continuing after error...
2025-03-17 02:53:53,471 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 02:53:53,472 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 02:53:53,472 - INFO - Using mock data for demo mode (no API keys required)
2025-03-17 02:53:53,472 - INFO - Generating mock data for ETH/USDT (1m)
2025-03-17 02:53:53,479 - INFO - Generated 1000 mock candles
2025-03-17 02:53:53,520 - INFO - Extracted model architecture: state_size=40, action_size=4, hidden_size=384, lstm_layers=2, attention_heads=4
2025-03-17 02:53:53,552 - INFO - Using GPU: NVIDIA GeForce RTX 4060 Laptop GPU
2025-03-17 02:53:54,887 - WARNING - Failed to load with weights_only=True: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:53:54,958 - WARNING - Failed with safe_globals: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy.dtype was not an allowed global by default. Please use `torch.serialization.add_safe_globals([dtype])` or the `torch.serialization.safe_globals([dtype])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 02:53:55,016 - INFO - Model loaded from models/trading_agent_best_pnl.pt
2025-03-17 02:53:55,017 - INFO - Model loaded successfully
2025-03-17 02:53:55,019 - INFO - Starting live trading simulation...
2025-03-17 02:54:24,295 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:54:54,484 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:55:24,631 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:55:54,809 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:56:24,987 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:56:55,157 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:57:25,288 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:57:55,450 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:58:25,571 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:58:55,733 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:59:25,898 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 02:59:55,196 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 02:59:55,196 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 02:59:55,200 - INFO - Exchange initialized with standard CCXT: mexc
2025-03-17 02:59:55,200 - INFO - Fetching initial data for ETH/USDT
2025-03-17 02:59:55,844 - ERROR - Error fetching OHLCV data: mexc {"code":700002,"msg":"Signature for this request is not valid."}
2025-03-17 02:59:55,844 - WARNING - No initial data received
2025-03-17 02:59:55,844 - ERROR - Failed to fetch initial data. Exiting.
2025-03-17 02:59:56,090 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:00:26,253 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:00:56,413 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:01:26,591 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:01:56,732 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:02:26,890 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:02:57,233 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:03:27,392 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:03:57,555 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:04:27,713 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:04:57,867 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:05:28,019 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:05:58,171 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:06:28,323 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:06:58,510 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:07:28,695 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:07:58,884 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:08:29,079 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:08:59,295 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:09:29,452 - ERROR - Error creating chart: Line2D.set() got an unexpected keyword argument 'type'
2025-03-17 03:40:19,333 - INFO - Starting live trading demo for ETH/USDT on 1m timeframe
2025-03-17 03:40:19,333 - INFO - Using model: models/trading_agent_best_pnl.pt
2025-03-17 03:40:19,336 - INFO - Exchange initialized with standard CCXT: mexc
2025-03-17 03:40:19,336 - INFO - Fetching initial data for ETH/USDT
2025-03-17 03:40:24,689 - INFO - Fetched 500 candles for ETH/USDT (1m)
2025-03-17 03:40:24,693 - INFO - Initialized environment with 500 candles
2025-03-17 03:40:24,728 - INFO - Extracted model architecture: state_size=64, action_size=4, hidden_size=384, lstm_layers=2, attention_heads=4
2025-03-17 03:40:24,748 - INFO - Using GPU: NVIDIA GeForce RTX 4060 Laptop GPU
2025-03-17 03:40:25,795 - ERROR - Error loading model: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 03:40:25,797 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\main.py", line 1819, in load
checkpoint = torch.load(path, map_location=self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\serialization.py", line 1470, in load
raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 03:40:25,797 - WARNING - Failed to load model with weights_only=True: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
2025-03-17 03:40:25,860 - ERROR - Error loading model: 'str' object has no attribute '__module__'
2025-03-17 03:40:25,863 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 280, in run_live_demo
agent.load(args.model)
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\main.py", line 1819, in load
checkpoint = torch.load(path, map_location=self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\serialization.py", line 1470, in load
raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. This file can still be loaded, to do so you have two options, do those steps only if you trust the source of the checkpoint.
(1) In PyTorch 2.6, we changed the default value of the `weights_only` argument in `torch.load` from `False` to `True`. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
(2) Alternatively, to load with `weights_only=True` please check the recommended steps in the following error message.
WeightsUnpickler error: Unsupported global: GLOBAL numpy._core.multiarray.scalar was not an allowed global by default. Please use `torch.serialization.add_safe_globals([scalar])` or the `torch.serialization.safe_globals([scalar])` context manager to allowlist this global if you trust this class/function.
Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\main.py", line 1819, in load
checkpoint = torch.load(path, map_location=self.device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\serialization.py", line 1462, in load
return _load(
^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\serialization.py", line 1964, in _load
result = unpickler.load()
^^^^^^^^^^^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\_weights_only_unpickler.py", line 334, in load
elif full_path in _get_user_allowed_globals():
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\popov\miniforge3\Lib\site-packages\torch\_weights_only_unpickler.py", line 144, in _get_user_allowed_globals
module, name = f.__module__, f.__name__
^^^^^^^^^^^^
AttributeError: 'str' object has no attribute '__module__'. Did you mean: '__mod__'?
2025-03-17 03:40:25,863 - WARNING - Failed with safe_globals: 'str' object has no attribute '__module__'
2025-03-17 03:40:25,919 - INFO - Model loaded from models/trading_agent_best_pnl.pt
2025-03-17 03:40:25,920 - INFO - Model loaded successfully
2025-03-17 03:40:25,925 - INFO - Starting live trading simulation...
2025-03-17 03:40:26,348 - INFO - Fetched 1 candles for ETH/USDT (1m)
2025-03-17 03:40:26,406 - ERROR - Error in live trading loop: too many values to unpack (expected 3)
2025-03-17 03:40:26,406 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 370, in run_live_demo
next_state, reward, done = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: too many values to unpack (expected 3)
2025-03-17 03:40:26,406 - INFO - Continuing after error...
2025-03-17 03:40:31,926 - INFO - Fetched 1 candles for ETH/USDT (1m)
2025-03-17 03:40:31,933 - ERROR - Error in live trading loop: too many values to unpack (expected 3)
2025-03-17 03:40:31,933 - ERROR - Traceback (most recent call last):
File "D:\DEV\workspace\REPOS\git.d-popov.com\ai-kevin\crypto\gogo2\run_live_demo.py", line 370, in run_live_demo
next_state, reward, done = env.step(action)
^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: too many values to unpack (expected 3)
2025-03-17 03:40:31,933 - INFO - Continuing after error...

0
live_training.log Normal file
View File

593
live_training.py Normal file
View File

@@ -0,0 +1,593 @@
#!/usr/bin/env python
import asyncio
import logging
import sys
import platform
import argparse
import os
import datetime
import traceback
import numpy as np
import torch
import gc
from functools import partial
from main import initialize_exchange, TradingEnvironment, Agent
from torch.utils.tensorboard import SummaryWriter
# Fix for Windows asyncio issues with aiodns
if platform.system() == 'Windows':
try:
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
print("Using Windows SelectorEventLoopPolicy to fix aiodns issue")
except Exception as e:
print(f"Failed to set WindowsSelectorEventLoopPolicy: {e}")
# Setup logging function
def setup_logging():
"""Setup logging configuration for the application"""
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler("live_training.log"),
logging.StreamHandler(sys.stdout) # Added stdout handler for immediate feedback
]
)
# Set up logging
setup_logging()
logger = logging.getLogger(__name__)
# Implement a robust save function to handle PyTorch serialization errors
def robust_save(model, path):
"""
Robust model saving with multiple fallback approaches
Args:
model: The Agent model to save
path: Path to save the model
Returns:
bool: True if successful, False otherwise
"""
# Create directory if it doesn't exist
os.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)
# Backup path in case the main save fails
backup_path = f"{path}.backup"
# Clean up GPU memory before saving
if torch.cuda.is_available():
torch.cuda.empty_cache()
gc.collect()
# Attempt 1: Try with default settings in a separate file first
try:
logger.info(f"Saving model to {backup_path} (attempt 1)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'optimizer': model.optimizer.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, backup_path)
logger.info(f"Successfully saved to {backup_path}")
# If backup worked, copy to the actual path
if os.path.exists(backup_path):
import shutil
shutil.copy(backup_path, path)
logger.info(f"Copied backup to {path}")
return True
except Exception as e:
logger.warning(f"First save attempt failed: {e}")
# Attempt 2: Try with pickle protocol 2 (more compatible)
try:
logger.info(f"Saving model to {path} (attempt 2 - pickle protocol 2)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'optimizer': model.optimizer.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, path, pickle_protocol=2)
logger.info(f"Successfully saved to {path} with pickle_protocol=2")
return True
except Exception as e:
logger.warning(f"Second save attempt failed: {e}")
# Attempt 3: Try without optimizer state (which can be large and cause issues)
try:
logger.info(f"Saving model to {path} (attempt 3 - without optimizer)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, path)
logger.info(f"Successfully saved to {path} without optimizer state")
return True
except Exception as e:
logger.warning(f"Third save attempt failed: {e}")
# Attempt 4: Try with torch.jit.save instead
try:
logger.info(f"Saving model to {path} (attempt 4 - with jit.save)")
# Save policy network using jit
scripted_policy = torch.jit.script(model.policy_net)
torch.jit.save(scripted_policy, f"{path}.policy.jit")
# Save target network using jit
scripted_target = torch.jit.script(model.target_net)
torch.jit.save(scripted_target, f"{path}.target.jit")
# Save epsilon value separately
with open(f"{path}.epsilon.txt", "w") as f:
f.write(str(model.epsilon))
logger.info(f"Successfully saved model components with jit.save")
return True
except Exception as e:
logger.error(f"All save attempts failed: {e}")
return False
# Implement timeout wrapper for exchange operations
async def with_timeout(coroutine, timeout=30, default=None):
"""
Execute a coroutine with a timeout
Args:
coroutine: The coroutine to execute
timeout: Timeout in seconds
default: Default value to return on timeout
Returns:
The result of the coroutine or default value on timeout
"""
try:
return await asyncio.wait_for(coroutine, timeout=timeout)
except asyncio.TimeoutError:
logger.warning(f"Operation timed out after {timeout} seconds")
return default
except Exception as e:
logger.error(f"Operation failed: {e}")
return default
# Implement fetch_and_update_data function
async def fetch_and_update_data(exchange, env, symbol, timeframe):
"""
Fetch new candle data and update the environment
Args:
exchange: CCXT exchange instance
env: Trading environment instance
symbol: Trading pair symbol
timeframe: Timeframe for the candles
"""
logger.info(f"Fetching new data for {symbol} on {timeframe} timeframe")
try:
# Default to 100 candles if not specified
limit = 1000
# Fetch OHLCV data with timeout
candles = await with_timeout(
exchange.fetch_ohlcv(symbol, timeframe, limit=limit),
timeout=30,
default=[]
)
if not candles or len(candles) == 0:
logger.warning(f"No candles returned for {symbol} on {timeframe}")
return False
logger.info(f"Successfully fetched {len(candles)} candles")
# Convert to format expected by environment
formatted_candles = []
for candle in candles:
timestamp, open_price, high, low, close, volume = candle
formatted_candles.append({
'timestamp': timestamp,
'open': open_price,
'high': high,
'low': low,
'close': close,
'volume': volume
})
# Update environment data
env.data = formatted_candles
if hasattr(env, '_initialize_features'):
env._initialize_features()
logger.info(f"Updated environment with {len(formatted_candles)} candles")
# Print latest candle info
if formatted_candles:
latest = formatted_candles[-1]
dt = datetime.datetime.fromtimestamp(latest['timestamp']/1000).strftime('%Y-%m-%d %H:%M:%S')
logger.info(f"Latest candle: Time={dt}, Open={latest['open']}, High={latest['high']}, Low={latest['low']}, Close={latest['close']}, Volume={latest['volume']}")
return True
except Exception as e:
logger.error(f"Error fetching candle data: {e}")
logger.error(traceback.format_exc())
return False
# Implement memory management function
def manage_memory():
"""
Clean up memory to avoid memory leaks during long running sessions
"""
if torch.cuda.is_available():
torch.cuda.empty_cache()
gc.collect()
logger.debug("Memory cleaned")
async def live_training(
symbol="ETH/USDT",
timeframe="1m",
model_path="models/trading_agent_best_pnl.pt",
save_path="models/trading_agent_live_trained.pt",
initial_balance=1000,
update_interval=60,
training_iterations=100,
learning_rate=0.0001,
batch_size=64,
gamma=0.99,
window_size=30,
max_episodes=0, # 0 means unlimited
retry_delay=5, # Seconds to wait before retrying after an error
max_retries=3, # Maximum number of retries for operations
):
"""
Live training function that uses real market data to improve the model without executing real trades.
Args:
symbol: Trading pair symbol
timeframe: Timeframe for training
model_path: Path to the initial model to load
save_path: Path to save the improved model
initial_balance: Initial balance for simulation
update_interval: Interval to update data in seconds
training_iterations: Number of training iterations per data update
learning_rate: Learning rate for training
batch_size: Batch size for training
gamma: Discount factor for training
window_size: Window size for the environment
max_episodes: Maximum number of episodes (0 for unlimited)
retry_delay: Seconds to wait before retrying after an error
max_retries: Maximum number of retries for operations
"""
logger.info(f"Starting live training for {symbol} on {timeframe} timeframe")
# Initialize exchange (without sandbox mode)
exchange = None
# Retry loop for exchange initialization
for retry in range(max_retries):
try:
exchange = await initialize_exchange()
logger.info(f"Exchange initialized: {exchange.id}")
break
except Exception as e:
logger.error(f"Error initializing exchange (attempt {retry+1}/{max_retries}): {e}")
if retry < max_retries - 1:
logger.info(f"Retrying in {retry_delay} seconds...")
await asyncio.sleep(retry_delay)
else:
logger.error("Max retries reached. Could not initialize exchange.")
return
try:
# Initialize environment
env = TradingEnvironment(
initial_balance=initial_balance,
window_size=window_size,
symbol=symbol,
timeframe=timeframe,
)
# Fetch initial data (with retries)
logger.info(f"Fetching initial data for {symbol}")
success = False
for retry in range(max_retries):
success = await fetch_and_update_data(exchange, env, symbol, timeframe)
if success:
break
logger.warning(f"Failed to fetch initial data (attempt {retry+1}/{max_retries})")
if retry < max_retries - 1:
logger.info(f"Retrying in {retry_delay} seconds...")
await asyncio.sleep(retry_delay)
if not success:
logger.error("Failed to fetch initial data after multiple attempts, exiting")
return
# Initialize agent
STATE_SIZE = env.get_state().shape[0] if hasattr(env, 'get_state') else 64
ACTION_SIZE = env.action_space.n if hasattr(env.action_space, 'n') else 4
agent = Agent(state_size=STATE_SIZE, action_size=ACTION_SIZE, hidden_size=384)
# Load model if provided
if os.path.exists(model_path):
try:
agent.load(model_path)
logger.info(f"Model loaded successfully from {model_path}")
except Exception as e:
logger.warning(f"Error loading model: {e}")
logger.info("Starting with a new model")
else:
logger.warning(f"Model file {model_path} not found. Starting with a new model.")
# Initialize TensorBoard writer
run_id = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
writer = SummaryWriter(log_dir=f"runs/live_training_{run_id}")
agent.writer = writer
# Initialize training statistics
total_rewards = 0
episode_count = 0
best_reward = float('-inf')
best_pnl = float('-inf')
# Start live training loop
logger.info(f"Starting live training loop")
step_counter = 0
last_update_time = datetime.datetime.now()
# Track consecutive errors to enable circuit breaker
consecutive_errors = 0
max_consecutive_errors = 5
while True:
# Check if we've reached the maximum number of episodes
if max_episodes > 0 and episode_count >= max_episodes:
logger.info(f"Reached maximum episodes ({max_episodes}), stopping")
break
# Check if it's time to update data
current_time = datetime.datetime.now()
time_diff = (current_time - last_update_time).total_seconds()
if time_diff >= update_interval:
logger.info(f"Updating market data after {time_diff:.1f} seconds")
success = await fetch_and_update_data(exchange, env, symbol, timeframe)
if not success:
logger.warning("Failed to update data, will try again later")
# Wait a bit before trying again
await asyncio.sleep(retry_delay)
continue
last_update_time = current_time
# Clean up memory before running an episode
manage_memory()
# Run training iterations on the updated data
episode_reward = 0
env.reset()
done = False
# Run one simulated episode with the current data
steps_in_episode = 0
max_steps = len(env.data) - env.window_size - 1
logger.info(f"Starting episode {episode_count + 1} with {max_steps} steps")
while not done and steps_in_episode < max_steps:
try:
state = env.get_state()
action = agent.select_action(state, training=True)
try:
next_state, reward, done, info = env.step(action)
except ValueError as e:
logger.error(f"Error during env.step: {e}")
# If we get a ValueError, it might be because step is returning 3 values instead of 4
# Let's try to handle this case
if "too many values to unpack" in str(e):
logger.info("Trying alternative step format")
result = env.step(action)
if len(result) == 3:
next_state, reward, done = result
info = {}
else:
raise
else:
raise
# Save experience in replay memory
agent.memory.push(state, action, reward, next_state, done)
# Move to the next state
state = next_state
episode_reward += reward
step_counter += 1
steps_in_episode += 1
# Log action and results every 50 steps
if steps_in_episode % 50 == 0:
logger.info(f"Step {steps_in_episode}/{max_steps} | Action: {action} | Reward: {reward:.2f} | Balance: ${env.balance:.2f}")
# Train the agent on a batch of experiences
if len(agent.memory) > batch_size:
try:
agent.learn()
# Additional training iterations
if steps_in_episode % 10 == 0 and training_iterations > 1:
for _ in range(training_iterations - 1):
agent.learn()
# Reset consecutive errors counter on successful learning
consecutive_errors = 0
except Exception as e:
logger.error(f"Error during learning: {e}")
consecutive_errors += 1
if consecutive_errors >= max_consecutive_errors:
logger.warning(f"Circuit breaker triggered after {max_consecutive_errors} consecutive errors")
break
if done:
logger.info(f"Episode done after {steps_in_episode} steps")
break
except Exception as e:
logger.error(f"Error during episode step: {e}")
logger.error(traceback.format_exc())
consecutive_errors += 1
if consecutive_errors >= max_consecutive_errors:
logger.warning(f"Circuit breaker triggered after {max_consecutive_errors} consecutive errors")
break
# Update training statistics
episode_count += 1
total_rewards += episode_reward
avg_reward = total_rewards / episode_count
# Track metrics
writer.add_scalar('LiveTraining/Reward', episode_reward, episode_count)
writer.add_scalar('LiveTraining/AvgReward', avg_reward, episode_count)
writer.add_scalar('LiveTraining/Balance', env.balance, episode_count)
writer.add_scalar('LiveTraining/PnL', env.total_pnl, episode_count)
# Report progress
logger.info(f"""
Episode: {episode_count}
Reward: {episode_reward:.2f}
Avg Reward: {avg_reward:.2f}
Balance: ${env.balance:.2f}
PnL: ${env.total_pnl:.2f}
Memory Size: {len(agent.memory)}
Total Steps: {step_counter}
""")
# Save the model if it's the best so far (by reward or PnL)
if episode_reward > best_reward:
best_reward = episode_reward
reward_model_path = f"models/trading_agent_best_reward_{run_id}.pt"
if robust_save(agent, reward_model_path):
logger.info(f"New best reward model saved: {episode_reward:.2f} to {reward_model_path}")
else:
logger.error(f"Failed to save best reward model")
if env.total_pnl > best_pnl:
best_pnl = env.total_pnl
pnl_model_path = f"models/trading_agent_best_pnl_{run_id}.pt"
if robust_save(agent, pnl_model_path):
logger.info(f"New best PnL model saved: ${env.total_pnl:.2f} to {pnl_model_path}")
else:
logger.error(f"Failed to save best PnL model")
# Regularly save the model
if episode_count % 5 == 0:
if robust_save(agent, save_path):
logger.info(f"Model checkpoint saved to {save_path}")
else:
logger.error(f"Failed to save checkpoint")
# Update target network periodically
if episode_count % 5 == 0:
try:
agent.update_target_network()
logger.info("Target network updated")
except Exception as e:
logger.error(f"Error updating target network: {e}")
# Sleep to avoid excessive API calls
await asyncio.sleep(1)
except asyncio.CancelledError:
logger.info("Live training cancelled")
except KeyboardInterrupt:
logger.info("Live training stopped by user")
except Exception as e:
logger.error(f"Error in live training: {e}")
logger.error(traceback.format_exc())
finally:
# Save final model
if 'agent' in locals():
if robust_save(agent, save_path):
logger.info(f"Final model saved to {save_path}")
else:
logger.error(f"Failed to save final model")
# Close TensorBoard writer
try:
writer.close()
logger.info("TensorBoard writer closed")
except Exception as e:
logger.error(f"Error closing TensorBoard writer: {e}")
# Close exchange connection
if exchange:
try:
await with_timeout(exchange.close(), timeout=10)
logger.info("Exchange connection closed")
except Exception as e:
logger.error(f"Error closing exchange connection: {e}")
# Final memory cleanup
manage_memory()
logger.info("Live training completed")
async def main():
"""Main function to parse arguments and start live training"""
parser = argparse.ArgumentParser(description='Live Training with Real Market Data')
parser.add_argument('--symbol', type=str, default='ETH/USDT', help='Trading pair symbol')
parser.add_argument('--timeframe', type=str, default='1m', help='Timeframe for training')
parser.add_argument('--model_path', type=str, default='models/trading_agent_best_pnl.pt', help='Path to initial model')
parser.add_argument('--save_path', type=str, default='models/trading_agent_live_trained.pt', help='Path to save improved model')
parser.add_argument('--initial_balance', type=float, default=1000, help='Initial balance for simulation')
parser.add_argument('--update_interval', type=int, default=60, help='Interval to update data in seconds')
parser.add_argument('--training_iterations', type=int, default=100, help='Training iterations per update')
parser.add_argument('--max_episodes', type=int, default=0, help='Maximum number of episodes (0 for unlimited)')
parser.add_argument('--retry_delay', type=int, default=5, help='Seconds to wait before retrying after an error')
parser.add_argument('--max_retries', type=int, default=3, help='Maximum number of retries for operations')
args = parser.parse_args()
logger.info(f"Starting live training with {args.symbol} on {args.timeframe} timeframe")
await live_training(
symbol=args.symbol,
timeframe=args.timeframe,
model_path=args.model_path,
save_path=args.save_path,
initial_balance=args.initial_balance,
update_interval=args.update_interval,
training_iterations=args.training_iterations,
max_episodes=args.max_episodes,
retry_delay=args.retry_delay,
max_retries=args.max_retries,
)
# Override Agent's save method with our robust save function
def monkey_patch_agent_save():
"""Replace Agent's save method with our robust save approach"""
original_save = Agent.save
def patched_save(self, path):
return robust_save(self, path)
# Apply the patch
Agent.save = patched_save
logger.info("Monkey patched Agent.save with robust_save")
# Return the original method in case we need to restore it
return original_save
# Call the monkey patch function at the appropriate place
if __name__ == "__main__":
try:
print("Starting live training script")
# Apply the monkey patch before running the main function
original_save = monkey_patch_agent_save()
asyncio.run(main())
except KeyboardInterrupt:
logger.info("Live training stopped by user")
except Exception as e:
logger.error(f"Error in main function: {e}")
logger.error(traceback.format_exc())

5166
main.py Normal file
View File

File diff suppressed because it is too large Load Diff

240
mexc_tick_stream.py Normal file
View File

@@ -0,0 +1,240 @@
import os
import json
import asyncio
import logging
import datetime
import numpy as np
import pandas as pd
import websockets
from dotenv import load_dotenv
from torch.utils.tensorboard import SummaryWriter
# Configure logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[logging.FileHandler("mexc_tick_stream.log"), logging.StreamHandler()]
)
logger = logging.getLogger("mexc_tick_stream")
# Load environment variables
load_dotenv()
MEXC_API_KEY = os.getenv('MEXC_API_KEY')
MEXC_SECRET_KEY = os.getenv('MEXC_SECRET_KEY')
class MexcTickStreamer:
def __init__(self, symbol="ETH/USDT", update_interval=1.0):
"""
Initialize the MEXC tick data streamer
Args:
symbol: Trading pair symbol (e.g., "ETH/USDT")
update_interval: How often to update the TensorBoard visualization (in seconds)
"""
self.symbol = symbol.replace("/", "").upper() # Convert to MEXC format (e.g., ETHUSDT)
self.update_interval = update_interval
self.uri = "wss://wbs-api.mexc.com/ws"
self.writer = SummaryWriter(f'runs/mexc_ticks_{self.symbol}')
self.trades = []
self.last_update_time = 0
self.running = False
# For visualization
self.price_history = []
self.volume_history = []
self.buy_volume = 0
self.sell_volume = 0
self.step = 0
async def connect(self):
"""Connect to MEXC WebSocket and subscribe to tick data"""
try:
self.websocket = await websockets.connect(self.uri)
logger.info(f"Connected to MEXC WebSocket for {self.symbol}")
# Subscribe to trade stream (using non-protobuf endpoint for simplicity)
subscribe_msg = {
"method": "SUBSCRIPTION",
"params": [f"spot@public.deals.v3.api@{self.symbol}"]
}
await self.websocket.send(json.dumps(subscribe_msg))
logger.info(f"Subscribed to {self.symbol} tick data")
# Start ping task to keep connection alive
asyncio.create_task(self.ping_loop())
return True
except Exception as e:
logger.error(f"Error connecting to MEXC WebSocket: {e}")
return False
async def ping_loop(self):
"""Send ping messages to keep the connection alive"""
while self.running:
try:
await self.websocket.send(json.dumps({"method": "PING"}))
await asyncio.sleep(30) # Send ping every 30 seconds
except Exception as e:
logger.error(f"Error in ping loop: {e}")
break
async def process_message(self, message):
"""Process incoming WebSocket messages"""
try:
# Try to parse as JSON
try:
data = json.loads(message)
# Handle PONG response
if data.get("msg") == "PONG":
return
# Handle subscription confirmation
if data.get("code") == 0:
logger.info(f"Subscription confirmed: {data.get('msg')}")
return
# Handle trade data in the non-protobuf format
if "c" in data and "d" in data and "deals" in data["d"]:
for trade in data["d"]["deals"]:
# Extract trade data
price = float(trade["p"])
quantity = float(trade["v"])
trade_type = 1 if trade["S"] == 1 else 2 # 1 for buy, 2 for sell
timestamp = trade["t"]
# Store trade data
self.trades.append({
"price": price,
"quantity": quantity,
"type": "buy" if trade_type == 1 else "sell",
"timestamp": timestamp
})
# Update volume counters
if trade_type == 1: # Buy
self.buy_volume += quantity
else: # Sell
self.sell_volume += quantity
# Store for visualization
self.price_history.append(price)
self.volume_history.append(quantity)
# Limit history size to prevent memory issues
if len(self.price_history) > 10000:
self.price_history = self.price_history[-5000:]
self.volume_history = self.volume_history[-5000:]
# Update TensorBoard if enough time has passed
current_time = datetime.datetime.now().timestamp()
if current_time - self.last_update_time >= self.update_interval:
await self.update_tensorboard()
self.last_update_time = current_time
except json.JSONDecodeError:
# If it's not valid JSON, it might be binary protobuf data
logger.debug("Received binary data, skipping (protobuf not implemented)")
except Exception as e:
logger.error(f"Error processing message: {e}")
async def update_tensorboard(self):
"""Update TensorBoard visualizations"""
try:
if not self.price_history:
return
# Calculate metrics
current_price = self.price_history[-1]
avg_price = np.mean(self.price_history[-100:]) if len(self.price_history) >= 100 else np.mean(self.price_history)
price_std = np.std(self.price_history[-100:]) if len(self.price_history) >= 100 else np.std(self.price_history)
# Calculate VWAP (Volume Weighted Average Price)
if len(self.price_history) >= 100 and len(self.volume_history) >= 100:
vwap = np.sum(np.array(self.price_history[-100:]) * np.array(self.volume_history[-100:])) / np.sum(self.volume_history[-100:])
else:
vwap = np.sum(np.array(self.price_history) * np.array(self.volume_history)) / np.sum(self.volume_history) if np.sum(self.volume_history) > 0 else current_price
# Calculate buy/sell ratio
total_volume = self.buy_volume + self.sell_volume
buy_ratio = self.buy_volume / total_volume if total_volume > 0 else 0.5
# Log to TensorBoard
self.writer.add_scalar('Price/Current', current_price, self.step)
self.writer.add_scalar('Price/VWAP', vwap, self.step)
self.writer.add_scalar('Price/StdDev', price_std, self.step)
self.writer.add_scalar('Volume/BuyRatio', buy_ratio, self.step)
self.writer.add_scalar('Volume/Total', total_volume, self.step)
# Create a candlestick-like chart for the last 100 ticks
if len(self.price_history) >= 100:
prices = np.array(self.price_history[-100:])
self.writer.add_histogram('Price/Distribution', prices, self.step)
# Create a custom scalars panel
layout = {
"Price": {
"Current vs VWAP": ["Multiline", ["Price/Current", "Price/VWAP"]],
},
"Volume": {
"Buy Ratio": ["Multiline", ["Volume/BuyRatio"]],
}
}
self.writer.add_custom_scalars(layout)
self.step += 1
logger.info(f"Updated TensorBoard: Price={current_price:.2f}, VWAP={vwap:.2f}, Buy Ratio={buy_ratio:.2f}")
except Exception as e:
logger.error(f"Error updating TensorBoard: {e}")
async def run(self):
"""Main loop to receive and process WebSocket messages"""
self.running = True
self.last_update_time = datetime.datetime.now().timestamp()
if not await self.connect():
logger.error("Failed to connect. Exiting.")
return
try:
while self.running:
message = await self.websocket.recv()
await self.process_message(message)
except websockets.exceptions.ConnectionClosed:
logger.warning("WebSocket connection closed")
except Exception as e:
logger.error(f"Error in run loop: {e}")
finally:
self.running = False
await self.cleanup()
async def cleanup(self):
"""Clean up resources"""
try:
if hasattr(self, 'websocket'):
await self.websocket.close()
self.writer.close()
logger.info("Cleaned up resources")
except Exception as e:
logger.error(f"Error during cleanup: {e}")
async def main():
"""Main entry point"""
# Parse command line arguments
import argparse
parser = argparse.ArgumentParser(description='MEXC Tick Data Streamer')
parser.add_argument('--symbol', type=str, default='ETH/USDT', help='Trading pair symbol (e.g., ETH/USDT)')
parser.add_argument('--interval', type=float, default=1.0, help='TensorBoard update interval in seconds')
args = parser.parse_args()
# Create and run the streamer
streamer = MexcTickStreamer(symbol=args.symbol, update_interval=args.interval)
await streamer.run()
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
logger.info("Program interrupted by user")
except Exception as e:
logger.error(f"Unhandled exception: {e}")

535
mexc_visualizer.log Normal file
View File

@@ -0,0 +1,535 @@
2025-03-17 00:45:43,111 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:45:43,112 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:45:44,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf7 in position 58: invalid start byte
2025-03-17 00:45:44,578 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf5 in position 58: invalid start byte
2025-03-17 00:45:45,566 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd3 in position 58: invalid continuation byte
2025-03-17 00:45:46,573 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbb in position 58: invalid start byte
2025-03-17 00:45:46,965 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xcb in position 58: invalid continuation byte
2025-03-17 00:45:48,226 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:45:56,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8a in position 60: invalid start byte
2025-03-17 00:46:03,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xaf in position 58: invalid start byte
2025-03-17 00:46:07,079 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 60: invalid start byte
2025-03-17 00:46:07,084 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 60: invalid start byte
2025-03-17 00:46:07,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 60: invalid start byte
2025-03-17 00:46:08,074 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:46:08,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xab in position 58: invalid start byte
2025-03-17 00:46:09,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x93 in position 58: invalid start byte
2025-03-17 00:46:10,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x87 in position 58: invalid start byte
2025-03-17 00:46:10,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xfb in position 58: invalid start byte
2025-03-17 00:46:11,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:46:11,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:46:12,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 60: invalid start byte
2025-03-17 00:46:12,076 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:46:12,571 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 60: invalid start byte
2025-03-17 00:46:13,075 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbf in position 58: invalid start byte
2025-03-17 00:46:13,879 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xe9 in position 58: invalid continuation byte
2025-03-17 00:46:15,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:46:17,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xe0 in position 58: invalid continuation byte
2025-03-17 00:46:17,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd3 in position 58: invalid continuation byte
2025-03-17 00:46:18,095 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd1 in position 58: invalid continuation byte
2025-03-17 00:46:18,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbb in position 58: invalid start byte
2025-03-17 00:46:19,074 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb0 in position 58: invalid start byte
2025-03-17 00:46:20,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 58: invalid start byte
2025-03-17 00:46:21,077 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 58: invalid start byte
2025-03-17 00:46:21,307 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf0 in position 58: invalid continuation byte
2025-03-17 00:46:21,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xda in position 62: invalid continuation byte
2025-03-17 00:46:22,648 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xab in position 58: invalid start byte
2025-03-17 00:46:22,719 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xda in position 62: invalid continuation byte
2025-03-17 00:46:23,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8c in position 60: invalid start byte
2025-03-17 00:46:23,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8c in position 60: invalid start byte
2025-03-17 00:46:24,076 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc1 in position 58: invalid start byte
2025-03-17 00:46:24,577 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xab in position 58: invalid start byte
2025-03-17 00:46:25,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x9f in position 58: invalid start byte
2025-03-17 00:46:25,588 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:46:26,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x87 in position 58: invalid start byte
2025-03-17 00:46:27,767 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xab in position 58: invalid start byte
2025-03-17 00:46:29,577 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbd in position 58: invalid start byte
2025-03-17 00:46:30,076 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb1 in position 58: invalid start byte
2025-03-17 00:46:31,065 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8f in position 58: invalid start byte
2025-03-17 00:46:31,527 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdb in position 58: invalid continuation byte
2025-03-17 00:46:31,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x84 in position 58: invalid start byte
2025-03-17 00:46:31,643 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xca in position 58: invalid continuation byte
2025-03-17 00:46:32,068 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf8 in position 58: invalid start byte
2025-03-17 00:46:32,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xeb in position 58: invalid continuation byte
2025-03-17 00:46:33,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdf in position 58: invalid continuation byte
2025-03-17 00:46:33,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd4 in position 58: invalid continuation byte
2025-03-17 00:46:34,065 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc7 in position 58: invalid continuation byte
2025-03-17 00:46:35,051 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x9b in position 58: invalid start byte
2025-03-17 00:46:35,565 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa3 in position 58: invalid start byte
2025-03-17 00:46:36,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x97 in position 58: invalid start byte
2025-03-17 00:46:36,575 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x95 in position 58: invalid start byte
2025-03-17 00:46:37,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xff in position 58: invalid start byte
2025-03-17 00:46:37,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf3 in position 58: invalid continuation byte
2025-03-17 00:46:38,075 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xda in position 62: invalid continuation byte
2025-03-17 00:46:38,339 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf5 in position 58: invalid start byte
2025-03-17 00:46:39,081 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8d in position 60: invalid start byte
2025-03-17 00:46:40,072 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:46:41,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x93 in position 58: invalid start byte
2025-03-17 00:46:41,808 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:46:41,835 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa1 in position 58: invalid start byte
2025-03-17 00:46:45,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb3 in position 58: invalid start byte
2025-03-17 00:46:45,608 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8d in position 60: invalid start byte
2025-03-17 00:46:49,288 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbb in position 58: invalid start byte
2025-03-17 00:46:49,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd3 in position 58: invalid continuation byte
2025-03-17 00:46:50,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc7 in position 58: invalid continuation byte
2025-03-17 00:46:50,072 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd1 in position 58: invalid continuation byte
2025-03-17 00:46:50,227 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xe7 in position 58: invalid continuation byte
2025-03-17 00:46:56,068 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:46:57,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x93 in position 58: invalid start byte
2025-03-17 00:46:58,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x87 in position 58: invalid start byte
2025-03-17 00:46:58,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xfb in position 58: invalid start byte
2025-03-17 00:47:00,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8e in position 60: invalid start byte
2025-03-17 00:47:00,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8e in position 60: invalid start byte
2025-03-17 00:47:01,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbf in position 58: invalid start byte
2025-03-17 00:47:01,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb3 in position 58: invalid start byte
2025-03-17 00:47:02,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:47:02,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x9b in position 58: invalid start byte
2025-03-17 00:47:03,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8f in position 58: invalid start byte
2025-03-17 00:47:03,117 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc1 in position 58: invalid start byte
2025-03-17 00:47:03,566 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:47:06,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc7 in position 58: invalid continuation byte
2025-03-17 00:47:06,168 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xac in position 58: invalid start byte
2025-03-17 00:47:09,065 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x80 in position 58: invalid start byte
2025-03-17 00:47:09,426 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xe9 in position 58: invalid continuation byte
2025-03-17 00:47:12,256 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf5 in position 58: invalid start byte
2025-03-17 00:47:16,856 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:47:17,573 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb3 in position 58: invalid start byte
2025-03-17 00:47:18,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:47:19,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:47:20,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf7 in position 58: invalid start byte
2025-03-17 00:47:20,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x81 in position 58: invalid start byte
2025-03-17 00:47:23,068 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xaf in position 58: invalid start byte
2025-03-17 00:47:26,048 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd3 in position 58: invalid continuation byte
2025-03-17 00:47:28,429 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa0 in position 58: invalid start byte
2025-03-17 00:47:29,409 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xda in position 62: invalid continuation byte
2025-03-17 00:47:33,080 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x90 in position 60: invalid start byte
2025-03-17 00:47:34,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:47:35,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:47:35,576 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8d in position 58: invalid start byte
2025-03-17 00:47:36,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xeb in position 58: invalid continuation byte
2025-03-17 00:47:37,553 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbf in position 58: invalid start byte
2025-03-17 00:47:38,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc7 in position 58: invalid continuation byte
2025-03-17 00:47:39,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa3 in position 58: invalid start byte
2025-03-17 00:47:40,075 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x97 in position 58: invalid start byte
2025-03-17 00:47:42,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdc in position 58: invalid continuation byte
2025-03-17 00:47:43,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xcf in position 58: invalid continuation byte
2025-03-17 00:47:43,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x91 in position 60: invalid start byte
2025-03-17 00:47:44,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:47:45,638 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x91 in position 60: invalid start byte
2025-03-17 00:47:46,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x87 in position 58: invalid start byte
2025-03-17 00:47:46,566 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xfb in position 58: invalid start byte
2025-03-17 00:47:48,080 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:47:48,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x91 in position 60: invalid start byte
2025-03-17 00:47:49,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc0 in position 58: invalid start byte
2025-03-17 00:47:49,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb3 in position 58: invalid start byte
2025-03-17 00:47:50,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:47:50,567 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x9b in position 58: invalid start byte
2025-03-17 00:47:51,077 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x99 in position 58: invalid start byte
2025-03-17 00:47:51,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:47:52,073 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf7 in position 58: invalid start byte
2025-03-17 00:47:53,067 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdf in position 58: invalid continuation byte
2025-03-17 00:47:54,079 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc7 in position 58: invalid continuation byte
2025-03-17 00:47:54,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbb in position 58: invalid start byte
2025-03-17 00:47:55,071 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xaf in position 58: invalid start byte
2025-03-17 00:47:56,577 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x95 in position 58: invalid start byte
2025-03-17 00:47:57,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf3 in position 58: invalid continuation byte
2025-03-17 00:47:58,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdb in position 58: invalid continuation byte
2025-03-17 00:47:59,072 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xd0 in position 58: invalid continuation byte
2025-03-17 00:47:59,566 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc3 in position 58: invalid continuation byte
2025-03-17 00:48:00,069 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:48:00,578 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb5 in position 58: invalid start byte
2025-03-17 00:48:01,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa0 in position 58: invalid start byte
2025-03-17 00:48:02,073 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x87 in position 58: invalid start byte
2025-03-17 00:48:03,069 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:48:03,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:48:05,074 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbf in position 58: invalid start byte
2025-03-17 00:48:06,087 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xa7 in position 58: invalid start byte
2025-03-17 00:48:06,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x9b in position 58: invalid start byte
2025-03-17 00:48:07,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x83 in position 58: invalid start byte
2025-03-17 00:48:08,073 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf7 in position 58: invalid start byte
2025-03-17 00:48:08,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xec in position 58: invalid continuation byte
2025-03-17 00:48:09,066 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xdf in position 58: invalid continuation byte
2025-03-17 00:48:10,571 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xbb in position 58: invalid start byte
2025-03-17 00:48:12,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x8b in position 58: invalid start byte
2025-03-17 00:48:13,569 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf4 in position 58: invalid continuation byte
2025-03-17 00:48:14,589 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xf0 in position 58: invalid continuation byte
2025-03-17 00:48:15,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xc3 in position 58: invalid continuation byte
2025-03-17 00:48:16,070 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xb7 in position 58: invalid start byte
2025-03-17 00:48:16,568 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xab in position 58: invalid start byte
2025-03-17 00:48:17,570 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x93 in position 58: invalid start byte
2025-03-17 00:48:18,081 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x91 in position 58: invalid start byte
2025-03-17 00:48:18,566 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0xfb in position 58: invalid start byte
2025-03-17 00:48:19,077 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:48:19,578 - ERROR - Error processing message: 'utf-8' codec can't decode byte 0x89 in position 61: invalid start byte
2025-03-17 00:48:20,921 - INFO - Cleaned up resources
2025-03-17 00:48:20,923 - INFO - Program interrupted by user
2025-03-17 00:48:26,295 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:48:26,295 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:48:59,605 - WARNING - WebSocket connection closed
2025-03-17 00:48:59,606 - INFO - Cleaned up resources
2025-03-17 00:49:36,347 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:49:36,348 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:50:09,797 - WARNING - WebSocket connection closed
2025-03-17 00:50:09,797 - INFO - Cleaned up resources
2025-03-17 00:50:13,164 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:50:13,165 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:50:44,610 - WARNING - WebSocket connection closed
2025-03-17 00:50:44,610 - INFO - Cleaned up resources
2025-03-17 00:50:58,754 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:50:58,754 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:51:30,236 - WARNING - WebSocket connection closed
2025-03-17 00:51:30,236 - INFO - Cleaned up resources
2025-03-17 00:52:24,356 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:52:24,356 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:52:24,613 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.deals.v3.api@BTCUSDT]. Reason： Blocked!
2025-03-17 00:52:24,613 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:24,872 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:24,873 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:25,136 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:25,137 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:25,395 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:25,395 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:25,654 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:25,655 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:25,911 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:25,911 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:26,167 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:26,168 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:26,426 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:26,426 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:26,688 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:26,688 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:26,944 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:26,945 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:27,204 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:27,204 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:27,462 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:27,463 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:27,718 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:27,720 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:27,977 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:27,978 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:28,234 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:28,236 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:28,495 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:28,495 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:28,756 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:28,756 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:29,012 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:29,013 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:29,272 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:29,273 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:29,531 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:29,532 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:29,791 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:29,792 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:30,051 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:30,051 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:30,311 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:30,311 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:30,568 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:30,569 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:30,826 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:30,827 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:31,084 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:31,084 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:31,341 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:31,342 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:31,600 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:31,600 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:31,859 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:31,860 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:32,121 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:32,122 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:32,380 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:32,380 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:32,637 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:32,638 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:32,896 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:32,897 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:33,153 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:33,154 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:33,411 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:33,411 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:33,667 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:33,667 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:33,923 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:33,924 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:34,179 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:34,180 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:34,439 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:34,439 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:34,696 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:34,696 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:34,953 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:34,953 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:35,211 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:35,211 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:35,467 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:35,468 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:35,724 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:35,724 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:35,983 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:35,984 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:36,244 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:36,244 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:36,504 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:36,504 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:36,759 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:36,760 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:37,019 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:37,020 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:37,282 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:37,284 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:37,540 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:37,541 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:37,797 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:37,797 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:38,055 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:38,056 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:38,315 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:38,315 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:38,571 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:38,572 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:38,827 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:38,828 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:39,087 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:39,087 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:39,344 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:39,344 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:39,600 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:39,600 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:39,858 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:39,858 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:40,120 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:40,120 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:40,380 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:40,381 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:40,635 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:40,636 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:40,891 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:40,892 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:41,148 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:41,149 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:41,406 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:41,406 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:41,664 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:41,664 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:41,924 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:41,924 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:42,183 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:42,184 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:42,440 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:42,440 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:42,696 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:42,697 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:42,956 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:42,956 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:43,213 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:43,213 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:43,471 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:43,472 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:43,731 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:43,732 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:43,991 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:43,992 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:44,250 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:44,250 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:44,508 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:44,509 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:44,767 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:44,767 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:45,024 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:45,024 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:45,284 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:45,284 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:45,544 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:45,545 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:45,802 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:45,802 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:46,060 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:46,061 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:46,316 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:46,316 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:46,571 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:46,572 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:46,831 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:46,831 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:47,087 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:47,087 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:47,344 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:47,344 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:47,606 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:47,607 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:47,869 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:47,870 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:48,128 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:48,128 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:48,384 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:48,385 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:48,641 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:48,641 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:48,902 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:48,903 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:49,159 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:49,160 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:49,417 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:49,417 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:49,676 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:49,676 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:49,936 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:49,936 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:50,195 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:50,195 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:50,452 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:50,452 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:50,712 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:50,713 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:50,972 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:50,973 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:51,228 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:51,229 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:51,484 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:51,484 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:51,741 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:51,741 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:52,000 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:52,001 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:52,260 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:52,261 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:52,516 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:52,516 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:52:52,772 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:52:52,772 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:10,924 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 00:53:10,925 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 00:53:11,182 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.deals.v3.api@BTCUSDT]. Reason： Blocked!
2025-03-17 00:53:11,183 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:11,444 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:11,445 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:11,704 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:11,704 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:11,962 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:11,963 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:12,222 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:12,222 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:12,481 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:12,481 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:12,741 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:12,741 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:13,000 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:13,001 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:13,258 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:13,258 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:13,520 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:13,521 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:13,780 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:13,781 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:14,041 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:14,042 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:14,301 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:14,301 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:14,561 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:14,561 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:14,820 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:14,821 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:15,081 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:15,081 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:15,341 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:15,341 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:15,601 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:15,601 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:15,861 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:15,862 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:16,189 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:16,189 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:16,466 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:16,467 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:16,726 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:16,727 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:16,984 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:16,985 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:17,243 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:17,243 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:17,505 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:17,505 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:17,765 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:17,766 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:18,026 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:18,026 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:18,284 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:18,285 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:18,545 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:18,545 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:18,803 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:18,803 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:19,061 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:19,061 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:19,320 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 00:53:19,320 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 00:53:19,801 - INFO - Cleaned up resources
2025-03-17 00:53:19,803 - INFO - Program interrupted by user
2025-03-17 01:05:53,831 - INFO - Connected to MEXC WebSocket for BTCUSDT
2025-03-17 01:05:53,831 - INFO - Subscribed to BTCUSDT tick data
2025-03-17 01:05:54,105 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.deals.v3.api@BTCUSDT]. Reason： Blocked!
2025-03-17 01:05:54,106 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:54,364 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:54,365 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:54,624 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:54,624 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:54,884 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:54,885 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:55,180 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:55,180 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:55,437 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:55,438 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:55,697 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:55,697 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:55,956 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:55,956 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:56,216 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:56,217 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:56,476 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:56,476 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:56,736 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:56,737 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:56,996 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:56,997 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:57,256 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:57,257 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:57,515 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:57,515 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:57,773 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:57,774 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:58,032 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:58,033 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:58,290 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:58,291 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:58,549 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:58,549 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:58,806 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:58,806 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:59,065 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:59,065 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:59,329 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:59,329 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:59,589 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:59,589 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:05:59,849 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:05:59,850 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:00,157 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:00,157 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:00,416 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:00,417 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:00,676 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:00,677 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:00,940 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:00,940 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:01,196 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:01,197 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:01,457 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:01,457 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:01,714 - ERROR - Subscription blocked: Not Subscribed successfully! [spot@public.kline.v3.api@BTCUSDT@1m]. Reason： Blocked!
2025-03-17 01:06:01,714 - INFO - Subscribed to BTCUSDT kline data
2025-03-17 01:06:02,047 - INFO - Cleaned up resources
2025-03-17 01:06:02,048 - INFO - Program interrupted by user

BIN
models/archive/trading_agent_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-1_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-1_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-1_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-2_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-2_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-2_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-3_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-3_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-3_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-4_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-4_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-4_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-5_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-5_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-5_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-6_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-6_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-6_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-7_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-7_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Day-7_final.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Test-Day-1_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Test-Day-1_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/backtest/Test-Day-1_final.pt Normal file
View File

Binary file not shown.

BIN
models/trading_agent_best_net_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/trading_agent_best_net_pnl.pt.backup Normal file
View File

Binary file not shown.

1
models/trading_agent_best_net_pnl.pt.params.json Normal file
View File

@@ -0,0 +1 @@
{"epsilon": 1.0, "state_size": 64, "action_size": 4, "hidden_size": 384, "lstm_layers": 2, "attention_heads": 4}

BIN
models/trading_agent_best_net_pnl.pt.policy.jit Normal file
View File

Binary file not shown.

BIN
models/trading_agent_best_pnl.pt Normal file
View File

Binary file not shown.

BIN
models/trading_agent_best_pnl.pt.backup Normal file
View File

Binary file not shown.

1
models/trading_agent_best_pnl.pt.params.json Normal file
View File

@@ -0,0 +1 @@
{"epsilon": 1.0, "state_size": 64, "action_size": 4, "hidden_size": 384, "lstm_layers": 2, "attention_heads": 4}

BIN
models/trading_agent_best_reward.pt Normal file
View File

Binary file not shown.

BIN
models/trading_agent_best_reward.pt.backup Normal file
View File

Binary file not shown.

BIN
models/trading_agent_checkpoint_1650.pt.backup Normal file
View File

Binary file not shown.

BIN
models/trading_agent_checkpoint_1650.pt.minimal Normal file
View File

Binary file not shown.

1
models/trading_agent_checkpoint_1650.pt.params.json Normal file
View File

@@ -0,0 +1 @@
{"epsilon": 0.843345, "state_size": 64, "action_size": 4, "hidden_size": 384, "lstm_layers": 2, "attention_heads": 4}

BIN
models/trading_agent_final.pt Normal file
View File

Binary file not shown.

BIN
models/trading_agent_final.pt.backup Normal file
View File

Binary file not shown.

BIN
models/trading_agent_live_trained.pt Normal file
View File

Binary file not shown.

8
random.nb.txt Normal file
View File

@@ -0,0 +1,8 @@
SBIE2102 File is too large to copy into sandbox - state.vscdb [DefaultBox / 549171200]
SBIE2223 To increase the file size limit for copying files, please double-click on this message line
SBIE2102 File is too large to copy into sandbox - state.vscdb [DefaultBox / 549171200]
SBIE2223 To increase the file size limit for copying files, please double-click on this message line
SBIE2102 File is too large to copy into sandbox - state.vscdb.backup [DefaultBox / 549167104]
SBIE2223 To increase the file size limit for copying files, please double-click on this message line
SBIE2102 File is too large to copy into sandbox - state.vscdb [DefaultBox / 549171200]
SBIE2223 To increase the file size limit for copying files, please double-click on this message line

182
readme.md Normal file
View File

@@ -0,0 +1,182 @@
# Crypto Trading Bot with Reinforcement Learning
An automated cryptocurrency trading bot that uses Deep Q-Learning (DQN) to trade ETH/USDT on the MEXC exchange. The bot features a sophisticated neural network architecture with LSTM layers and attention mechanisms for better pattern recognition.
## Features
- Deep Q-Learning with experience replay
- LSTM layers for sequential data processing
- Multi-head attention mechanism
- Dueling DQN architecture
- Real-time trading capabilities
- TensorBoard integration for monitoring
- Comprehensive technical indicators
- Demo and live trading modes
- Automatic model checkpointing
## Prerequisites
- Python 3.8+
- MEXC Exchange API credentials
- GPU recommended but not required
## Installation
1. Clone the repository:
```bash
git clone https://github.com/yourusername/crypto-trading-bot.git
cd crypto-trading-bot
```
2. Create a virtual environment:
```bash
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
```
3. Install dependencies:
```bash
pip install -r requirements.txt
```
4. Create a `.env` file in the project root with your MEXC API credentials:
```bash
MEXC_API_KEY=your_api_key
MEXC_API_SECRET=your_api_secret
```
## Usage
The bot can be run in three modes:
### Training Mode
```bash
python main.py --mode train --episodes 1000
```
### Evaluation Mode
```bash
python main.py --mode eval --episodes 10
```
### Live Trading Mode
```bash
# Demo mode (simulated trading with real market data)
python main.py --mode live --demo
# Real trading (actual trades on MEXC)
python main.py --mode live
```
Demo mode simulates trading using real-time market data but does not execute actual trades. It still:
- Logs all trading decisions and performance metrics
- Updates the model based on market data (if in training mode)
- Displays real-time analytics and position information
- Calculates theoretical profits/losses
- Saves performance data to TensorBoard
This makes it perfect for testing strategies without financial risk.
## Configuration
Key parameters can be adjusted in `main.py`:
- `INITIAL_BALANCE`: Starting balance for training/demo
- `MAX_LEVERAGE`: Maximum leverage for trades
- `STOP_LOSS_PERCENT`: Stop loss percentage
- `TAKE_PROFIT_PERCENT`: Take profit percentage
- `BATCH_SIZE`: Training batch size
- `LEARNING_RATE`: Model learning rate
- `STATE_SIZE`: Size of the state representation
## Model Architecture
The DQN model includes:
- Input layer with technical indicators
- LSTM layers for temporal pattern recognition
- Multi-head attention mechanism
- Dueling architecture for better Q-value estimation
- Batch normalization for stable training
## Monitoring
Training progress can be monitored using TensorBoard:
Training progress is logged to TensorBoard:
```bash
tensorboard --logdir=logs
```
This will show:
- Training rewards
- Account balance
- Win rate
- Loss metrics
## Trading Strategy
The bot makes decisions based on:
- Price action
- Technical indicators (RSI, MACD, Bollinger Bands, etc.)
- Historical patterns through LSTM
- Risk management with stop-loss and take-profit
## Safety Features
- Demo mode for safe testing
- Automatic stop-loss
- Position size limits
- Error handling for API calls
- Logging of all actions
## Directory Structure
├── main.py # Main bot implementation
├── requirements.txt # Project dependencies
├── .env # API credentials
├── models/ # Saved model checkpoints
├── runs/ # TensorBoard logs
└── trading_bot.log # Activity logs
## Warning
Cryptocurrency trading carries significant risks. This bot is for educational purposes and should not be used with real money without thorough testing and understanding of the risks involved.
## License
[MIT License](LICENSE)
The main changes I made:
Fixed code block formatting by adding proper language identifiers
Added missing closing code blocks
Properly formatted directory structure
Added complete sections that were cut off in the original
Ensured consistent formatting throughout the document
Added proper bash syntax highlighting for command examples
The README.md now provides a complete guide for setting up and using the trading bot, with clear sections for installation, usage, configuration, and safety considerations.
# Edits/improvements
Fixes the shape mismatch by ensuring the state vector is exactly STATE_SIZE elements
Adds robust error handling in the model's forward pass to handle mismatched inputs
Adds a transformer encoder for more sophisticated pattern recognition
Provides an expand_model method to increase model capacity while preserving learned weights
Adds detailed logging about model size and shape mismatches
The model now has:
Configurable hidden layer sizes
Transformer layers for complex pattern recognition
LSTM layers for temporal patterns
Attention mechanisms for focusing on important features
Dueling architecture for better Q-value estimation
With hidden_size=256, this model has about 1-2 million parameters. By increasing hidden_size to 512 or 1024, you can easily scale to 5-20 million parameters. For even larger models (billions of parameters), you would need to implement a more distributed architecture with multiple GPUs, which would require significant changes to the training loop.

12
requirements.txt Normal file
View File

@@ -0,0 +1,12 @@
numpy>=1.21.0
pandas>=1.3.0
matplotlib>=3.4.0
mplfinance>=0.12.7
torch>=1.9.0
python-dotenv>=0.19.0
ccxt>=2.0.0
websockets>=10.0
tensorboard>=2.6.0
scikit-learn>=1.0.0
Pillow>=9.0.0
asyncio>=3.4.3

34
run_demo.py Normal file
View File

@@ -0,0 +1,34 @@
#!/usr/bin/env python
import asyncio
import logging
from main import live_trading, setup_logging
# Set up logging
setup_logging()
logger = logging.getLogger(__name__)
async def main():
"""Run a simplified demo trading session with mock data"""
logger.info("Starting simplified demo trading session")
# Run live trading in demo mode with simplified parameters
await live_trading(
symbol="ETH/USDT",
timeframe="1m",
model_path="models/trading_agent_best_pnl.pt",
demo=True,
initial_balance=1000,
update_interval=10, # Update every 10 seconds for faster feedback
max_position_size=0.1,
risk_per_trade=0.02,
stop_loss_pct=0.02,
take_profit_pct=0.04,
)
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
logger.info("Demo trading stopped by user")
except Exception as e:
logger.error(f"Error in demo trading: {e}")

40
run_live_demo.py Normal file
View File

@@ -0,0 +1,40 @@
#!/usr/bin/env python
import asyncio
import argparse
import logging
from main import live_trading, setup_logging
# Set up logging
setup_logging()
logger = logging.getLogger(__name__)
async def main():
parser = argparse.ArgumentParser(description='Run live trading in demo mode')
parser.add_argument('--symbol', type=str, default='ETH/USDT', help='Trading pair symbol')
parser.add_argument('--timeframe', type=str, default='1m', help='Timeframe for trading')
parser.add_argument('--model_path', type=str, default='data/best_model.pth', help='Path to the trained model')
parser.add_argument('--initial_balance', type=float, default=1000, help='Initial balance')
parser.add_argument('--update_interval', type=int, default=30, help='Interval to update data in seconds')
args = parser.parse_args()
logger.info(f"Starting live trading demo with {args.symbol} on {args.timeframe} timeframe")
# Run live trading in demo mode
await live_trading(
symbol=args.symbol,
timeframe=args.timeframe,
model_path=args.model_path,
demo=True, # Always use demo mode in this script
initial_balance=args.initial_balance,
update_interval=args.update_interval,
# Using default values for other parameters
)
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
logger.info("Live trading demo stopped by user")
except Exception as e:
logger.error(f"Error in live trading demo: {e}")

69
run_tensorboard.py Normal file
View File

@@ -0,0 +1,69 @@
import os
import sys
import subprocess
import webbrowser
import time
import argparse
def run_tensorboard():
"""Run TensorBoard server and open browser"""
parser = argparse.ArgumentParser(description='TensorBoard Launcher')
parser.add_argument('--port', type=int, default=6006, help='Port for TensorBoard server')
parser.add_argument('--logdir', type=str, default='runs', help='Log directory for TensorBoard')
parser.add_argument('--no-browser', action='store_true', help='Do not open browser automatically')
args = parser.parse_args()
# Create log directory if it doesn't exist
os.makedirs(args.logdir, exist_ok=True)
# Print banner
print("\n" + "="*60)
print("📊 TRADING BOT - TENSORBOARD MONITORING 📊")
print("="*60)
print(f"Starting TensorBoard server on port {args.port}")
print(f"Log directory: {args.logdir}")
print("Press Ctrl+C to stop the server")
print("="*60 + "\n")
# Start TensorBoard server
cmd = ["tensorboard", "--logdir", args.logdir, "--port", str(args.port)]
try:
# Start TensorBoard process
process = subprocess.Popen(
cmd,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT,
universal_newlines=True
)
# Wait for TensorBoard to start
time.sleep(3)
# Open browser
if not args.no_browser:
url = f"http://localhost:{args.port}"
print(f"Opening browser to {url}")
webbrowser.open(url)
# Print TensorBoard output
while True:
output = process.stdout.readline()
if output == '' and process.poll() is not None:
break
if output:
print(output.strip())
return process.poll()
except KeyboardInterrupt:
print("\nStopping TensorBoard server...")
process.terminate()
return 0
except Exception as e:
print(f"Error running TensorBoard: {str(e)}")
return 1
if __name__ == "__main__":
exit_code = run_tensorboard()
sys.exit(exit_code)

77
run_tests.py Normal file
View File

@@ -0,0 +1,77 @@
#!/usr/bin/env python
"""
Run unit tests for the trading bot.
This script runs the unit tests defined in tests.py and displays the results.
It can run a single test or all tests.
Usage:
python run_tests.py [test_name]
If test_name is provided, only that test will be run.
Otherwise, all tests will be run.
Example:
python run_tests.py TestPeriodicUpdates
python run_tests.py TestBacktesting
python run_tests.py TestBacktestingLastSevenDays
python run_tests.py TestSingleDayBacktesting
python run_tests.py
"""
import sys
import unittest
import logging
from tests import (
TestPeriodicUpdates,
TestBacktesting,
TestBacktestingLastSevenDays,
TestSingleDayBacktesting
)
if __name__ == "__main__":
# Configure logging
logging.basicConfig(level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[logging.StreamHandler()])
# Get the test name from the command line
test_name = sys.argv[1] if len(sys.argv) > 1 else None
# Run the specified test or all tests
if test_name:
logging.info(f"Running test: {test_name}")
if test_name == "TestPeriodicUpdates":
suite = unittest.TestLoader().loadTestsFromTestCase(TestPeriodicUpdates)
elif test_name == "TestBacktesting":
suite = unittest.TestLoader().loadTestsFromTestCase(TestBacktesting)
elif test_name == "TestBacktestingLastSevenDays":
suite = unittest.TestLoader().loadTestsFromTestCase(TestBacktestingLastSevenDays)
elif test_name == "TestSingleDayBacktesting":
suite = unittest.TestLoader().loadTestsFromTestCase(TestSingleDayBacktesting)
else:
logging.error(f"Unknown test: {test_name}")
logging.info("Available tests: TestPeriodicUpdates, TestBacktesting, TestBacktestingLastSevenDays, TestSingleDayBacktesting")
sys.exit(1)
else:
# Run all tests
logging.info("Running all tests")
suite = unittest.TestSuite()
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestPeriodicUpdates))
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestBacktesting))
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestBacktestingLastSevenDays))
suite.addTest(unittest.TestLoader().loadTestsFromTestCase(TestSingleDayBacktesting))
# Run the tests
runner = unittest.TextTestRunner(verbosity=2)
result = runner.run(suite)
# Print summary
print("\nTest Summary:")
print(f" Ran {result.testsRun} tests")
print(f" Errors: {len(result.errors)}")
print(f" Failures: {len(result.failures)}")
print(f" Skipped: {len(result.skipped)}")
# Exit with non-zero status if any tests failed
sys.exit(len(result.errors) + len(result.failures))

BIN
runs/LSTM_Attention_DQN_20250318_020307/events.out.tfevents.1742256187.GW-DOBRI.85560.0 Normal file
View File

Binary file not shown.

BIN
runs/LSTM_Attention_DQN_20250318_024512/events.out.tfevents.1742258712.GW-DOBRI.28200.0 Normal file
View File

Binary file not shown.

BIN
runs/LSTM_Attention_DQN_20250318_025105/events.out.tfevents.1742259065.GW-DOBRI.1444.0 Normal file
View File

Binary file not shown.

118
simplified_live_training.py Normal file
View File

@@ -0,0 +1,118 @@
#!/usr/bin/env python
import asyncio
import logging
import sys
import platform
import ccxt.async_support as ccxt
import os
import datetime
# Fix for Windows asyncio issues with aiodns
if platform.system() == 'Windows':
try:
import asyncio
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
print("Using Windows SelectorEventLoopPolicy to fix aiodns issue")
except Exception as e:
print(f"Failed to set WindowsSelectorEventLoopPolicy: {e}")
# Setup direct console logging for immediate feedback
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.StreamHandler(sys.stdout)
]
)
logger = logging.getLogger(__name__)
async def initialize_exchange():
"""Initialize the exchange with API credentials from environment variables"""
exchange_id = 'mexc'
try:
# Get API credentials from environment variables
api_key = os.getenv('MEXC_API_KEY', '')
secret_key = os.getenv('MEXC_SECRET_KEY', '')
# Initialize the exchange
exchange_class = getattr(ccxt, exchange_id)
exchange = exchange_class({
'apiKey': api_key,
'secret': secret_key,
'enableRateLimit': True,
})
logger.info(f"Exchange initialized with standard CCXT: {exchange_id}")
return exchange
except Exception as e:
logger.error(f"Error initializing exchange: {e}")
raise
async def fetch_ohlcv_data(exchange, symbol, timeframe, limit=1000):
"""Fetch OHLCV data from the exchange"""
logger.info(f"Fetching {limit} {timeframe} candles for {symbol} (attempt 1/3)")
try:
candles = await exchange.fetch_ohlcv(symbol, timeframe, limit=limit)
if not candles or len(candles) == 0:
logger.warning(f"No candles returned for {symbol} on {timeframe}")
return None
logger.info(f"Successfully fetched {len(candles)} candles")
return candles
except Exception as e:
logger.error(f"Error fetching candle data: {e}")
return None
async def main():
"""Main function to test live data fetching"""
symbol = "ETH/USDT"
timeframe = "1m"
logger.info(f"Starting simplified live training test for {symbol} on {timeframe}")
try:
# Initialize exchange
exchange = await initialize_exchange()
# Fetch data every 10 seconds
for i in range(5):
logger.info(f"Fetch attempt {i+1}/5")
candles = await fetch_ohlcv_data(exchange, symbol, timeframe)
if candles:
# Print the latest candle
latest = candles[-1]
timestamp, open_price, high, low, close, volume = latest
dt = datetime.datetime.fromtimestamp(timestamp/1000).strftime('%Y-%m-%d %H:%M:%S')
logger.info(f"Latest candle: Time={dt}, Open={open_price}, High={high}, Low={low}, Close={close}, Volume={volume}")
# Wait 10 seconds before next fetch
if i < 4: # Don't wait after the last fetch
logger.info("Waiting 10 seconds before next fetch...")
await asyncio.sleep(10)
# Close exchange connection
await exchange.close()
logger.info("Exchange connection closed")
except Exception as e:
logger.error(f"Error in simplified live training test: {e}")
import traceback
logger.error(traceback.format_exc())
finally:
try:
await exchange.close()
except:
pass
logger.info("Test completed")
if __name__ == "__main__":
try:
asyncio.run(main())
except KeyboardInterrupt:
logger.info("Test stopped by user")
except Exception as e:
logger.error(f"Error in main function: {e}")
import traceback
logger.error(traceback.format_exc())

14
start_live_trading.ps1 Normal file
View File

@@ -0,0 +1,14 @@
# PowerShell script to start live trading demo and TensorBoard
Write-Host "Starting Trading Bot Live Demo..." -ForegroundColor Green
# Create a new PowerShell window for TensorBoard
Start-Process powershell -ArgumentList "-Command python run_tensorboard.py" -WindowStyle Normal
# Wait a moment for TensorBoard to start
Write-Host "Starting TensorBoard... Please wait" -ForegroundColor Yellow
Start-Sleep -Seconds 5
# Start the live trading demo in the current window
Write-Host "Starting Live Trading Demo with mock data..." -ForegroundColor Green
python run_live_demo.py --symbol ETH/USDT --timeframe 1m --model models/trading_agent_best_pnl.pt --mock

0
test_model_save_load.log Normal file
View File

227
test_model_save_load.py Normal file
View File

@@ -0,0 +1,227 @@
#!/usr/bin/env python
import os
import logging
import torch
import argparse
import gc
import traceback
import shutil
from main import Agent, robust_save
# Set up logging
logging.basicConfig(
level=logging.INFO,
format="%(asctime)s - %(levelname)s - %(message)s",
handlers=[
logging.FileHandler("test_model_save_load.log"),
logging.StreamHandler()
]
)
logger = logging.getLogger(__name__)
def create_test_directory():
"""Create a test directory for saving models"""
test_dir = "test_models"
os.makedirs(test_dir, exist_ok=True)
return test_dir
def test_save_load_cycle(state_size=64, action_size=4, hidden_size=384):
"""Test a full cycle of saving and loading models"""
test_dir = create_test_directory()
# Create a test agent
logger.info(f"Creating test agent with state_size={state_size}, action_size={action_size}, hidden_size={hidden_size}")
agent = Agent(state_size=state_size, action_size=action_size, hidden_size=hidden_size)
# Define paths for testing
save_path = os.path.join(test_dir, "test_agent.pt")
# Test saving
logger.info(f"Testing save to {save_path}")
save_success = agent.save(save_path)
if save_success:
logger.info(f"Save successful, model size: {os.path.getsize(save_path)} bytes")
else:
logger.error("Save failed!")
return False
# Memory cleanup
del agent
if torch.cuda.is_available():
torch.cuda.empty_cache()
gc.collect()
# Test loading
logger.info(f"Testing load from {save_path}")
try:
new_agent = Agent(state_size=state_size, action_size=action_size, hidden_size=hidden_size)
new_agent.load(save_path)
logger.info("Load successful")
# Verify model architecture
logger.info(f"Verifying model architecture")
assert new_agent.state_size == state_size, f"Expected state_size={state_size}, got {new_agent.state_size}"
assert new_agent.action_size == action_size, f"Expected action_size={action_size}, got {new_agent.action_size}"
assert new_agent.hidden_size == hidden_size, f"Expected hidden_size={hidden_size}, got {new_agent.hidden_size}"
logger.info("Model architecture verified correctly")
return True
except Exception as e:
logger.error(f"Error during load or verification: {e}")
logger.error(traceback.format_exc())
return False
def test_robust_save_methods(state_size=64, action_size=4, hidden_size=384):
"""Test all the robust save methods"""
test_dir = create_test_directory()
# Create a test agent
logger.info(f"Creating test agent for robust save testing")
agent = Agent(state_size=state_size, action_size=action_size, hidden_size=hidden_size)
# Test each robust save method
methods = [
("regular", os.path.join(test_dir, "regular_save.pt")),
("backup", os.path.join(test_dir, "backup_save.pt")),
("pickle2", os.path.join(test_dir, "pickle2_save.pt")),
("no_optimizer", os.path.join(test_dir, "no_optimizer_save.pt")),
("jit", os.path.join(test_dir, "jit_save.pt"))
]
results = {}
for method_name, save_path in methods:
logger.info(f"Testing {method_name} save method to {save_path}")
try:
if method_name == "regular":
# Use regular save
success = agent.save(save_path)
elif method_name == "backup":
# Use backup method directly
backup_path = f"{save_path}.backup"
checkpoint = {
'policy_net': agent.policy_net.state_dict(),
'target_net': agent.target_net.state_dict(),
'optimizer': agent.optimizer.state_dict(),
'epsilon': agent.epsilon,
'state_size': agent.state_size,
'action_size': agent.action_size,
'hidden_size': agent.hidden_size
}
torch.save(checkpoint, backup_path)
shutil.copy(backup_path, save_path)
success = os.path.exists(save_path)
elif method_name == "pickle2":
# Use pickle protocol 2
checkpoint = {
'policy_net': agent.policy_net.state_dict(),
'target_net': agent.target_net.state_dict(),
'optimizer': agent.optimizer.state_dict(),
'epsilon': agent.epsilon,
'state_size': agent.state_size,
'action_size': agent.action_size,
'hidden_size': agent.hidden_size
}
torch.save(checkpoint, save_path, pickle_protocol=2)
success = os.path.exists(save_path)
elif method_name == "no_optimizer":
# Save without optimizer
checkpoint = {
'policy_net': agent.policy_net.state_dict(),
'target_net': agent.target_net.state_dict(),
'epsilon': agent.epsilon,
'state_size': agent.state_size,
'action_size': agent.action_size,
'hidden_size': agent.hidden_size
}
torch.save(checkpoint, save_path)
success = os.path.exists(save_path)
elif method_name == "jit":
# Use JIT save
try:
scripted_policy = torch.jit.script(agent.policy_net)
torch.jit.save(scripted_policy, f"{save_path}.policy.jit")
scripted_target = torch.jit.script(agent.target_net)
torch.jit.save(scripted_target, f"{save_path}.target.jit")
# Save parameters
with open(f"{save_path}.params.json", "w") as f:
import json
params = {
'epsilon': float(agent.epsilon),
'state_size': int(agent.state_size),
'action_size': int(agent.action_size),
'hidden_size': int(agent.hidden_size)
}
json.dump(params, f)
success = (os.path.exists(f"{save_path}.policy.jit") and
os.path.exists(f"{save_path}.target.jit") and
os.path.exists(f"{save_path}.params.json"))
except Exception as e:
logger.error(f"JIT save failed: {e}")
success = False
if success:
if method_name != "jit":
file_size = os.path.getsize(save_path)
logger.info(f"{method_name} save successful, size: {file_size} bytes")
else:
logger.info(f"{method_name} save successful")
results[method_name] = True
else:
logger.error(f"{method_name} save failed")
results[method_name] = False
except Exception as e:
logger.error(f"Error during {method_name} save: {e}")
logger.error(traceback.format_exc())
results[method_name] = False
# Test loading each saved model
for method_name, save_path in methods:
if not results[method_name]:
logger.info(f"Skipping load test for {method_name} (save failed)")
continue
if method_name == "jit":
logger.info(f"Skipping load test for {method_name} (requires special loading)")
continue
logger.info(f"Testing load from {save_path}")
try:
new_agent = Agent(state_size=state_size, action_size=action_size, hidden_size=hidden_size)
new_agent.load(save_path)
logger.info(f"Load successful for {method_name} save")
except Exception as e:
logger.error(f"Error loading from {method_name} save: {e}")
logger.error(traceback.format_exc())
results[method_name] += " (load failed)"
# Return summary of results
return results
def main():
parser = argparse.ArgumentParser(description='Test model saving and loading')
parser.add_argument('--state_size', type=int, default=64, help='State size for test model')
parser.add_argument('--action_size', type=int, default=4, help='Action size for test model')
parser.add_argument('--hidden_size', type=int, default=384, help='Hidden size for test model')
parser.add_argument('--test_robust', action='store_true', help='Test all robust save methods')
args = parser.parse_args()
logger.info("Starting model save/load test")
if args.test_robust:
results = test_robust_save_methods(args.state_size, args.action_size, args.hidden_size)
logger.info(f"Robust save method results: {results}")
else:
success = test_save_load_cycle(args.state_size, args.action_size, args.hidden_size)
logger.info(f"Save/load cycle {'successful' if success else 'failed'}")
logger.info("Test completed")
if __name__ == "__main__":
main()

BIN
test_models/backup_save.pt.backup Normal file
View File

Binary file not shown.

BIN
test_models/no_optimizer_save.pt Normal file
View File

Binary file not shown.

BIN
test_models/pickle2_save.pt Normal file
View File

Binary file not shown.

BIN
test_models/regular_save.pt Normal file
View File

Binary file not shown.

BIN
test_models/robust_save.pt Normal file
View File

Binary file not shown.

BIN
test_models/robust_save.pt.backup Normal file
View File

Binary file not shown.

12
test_save.log Normal file
View File

@@ -0,0 +1,12 @@
2025-03-17 23:32:41,968 - INFO - Testing regular save method...
2025-03-17 23:32:41,970 - INFO - Model saved to test_models\regular_save.pt
2025-03-17 23:32:41,970 - INFO - Regular save succeeded
2025-03-17 23:32:41,971 - INFO - Testing robust save method...
2025-03-17 23:32:41,971 - INFO - Saving model to test_models\robust_save.pt.backup (attempt 1)
2025-03-17 23:32:41,971 - INFO - Successfully saved to test_models\robust_save.pt.backup
2025-03-17 23:32:41,983 - INFO - Copied backup to test_models\robust_save.pt
2025-03-17 23:32:41,983 - INFO - Robust save succeeded!
2025-03-17 23:32:41,983 - INFO - Files created:
2025-03-17 23:32:41,985 - INFO - - regular_save.pt (17794 bytes)
2025-03-17 23:32:41,985 - INFO - - robust_save.pt (17826 bytes)
2025-03-17 23:32:41,985 - INFO - - robust_save.pt.backup (17826 bytes)

182
test_save.py Normal file
View File

@@ -0,0 +1,182 @@
#!/usr/bin/env python
import torch
import torch.nn as nn
import os
import logging
import sys
import platform
# Fix for Windows asyncio issues with aiodns
if platform.system() == 'Windows':
try:
import asyncio
asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
print("Using Windows SelectorEventLoopPolicy to fix aiodns issue")
except Exception as e:
print(f"Failed to set WindowsSelectorEventLoopPolicy: {e}")
# Setup logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler("test_save.log"),
logging.StreamHandler(sys.stdout)
]
)
logger = logging.getLogger(__name__)
# Define a simple model for testing
class SimpleModel(nn.Module):
def __init__(self):
super(SimpleModel, self).__init__()
self.fc1 = nn.Linear(10, 50)
self.fc2 = nn.Linear(50, 20)
self.fc3 = nn.Linear(20, 5)
def forward(self, x):
x = torch.relu(self.fc1(x))
x = torch.relu(self.fc2(x))
return self.fc3(x)
# Create a simple Agent class for testing
class TestAgent:
def __init__(self):
self.policy_net = SimpleModel()
self.target_net = SimpleModel()
self.optimizer = torch.optim.Adam(self.policy_net.parameters(), lr=0.001)
self.epsilon = 0.1
def save(self, path):
"""Standard save method that might fail"""
checkpoint = {
'policy_net': self.policy_net.state_dict(),
'target_net': self.target_net.state_dict(),
'optimizer': self.optimizer.state_dict(),
'epsilon': self.epsilon
}
torch.save(checkpoint, path)
logger.info(f"Model saved to {path}")
# Robust save function with multiple fallback approaches
def robust_save(model, path):
"""
Robust model saving with multiple fallback approaches
Args:
model: The Agent model to save
path: Path to save the model
Returns:
bool: True if successful, False otherwise
"""
# Create directory if it doesn't exist
os.makedirs(os.path.dirname(os.path.abspath(path)), exist_ok=True)
# Backup path in case the main save fails
backup_path = f"{path}.backup"
# Attempt 1: Try with default settings in a separate file first
try:
logger.info(f"Saving model to {backup_path} (attempt 1)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'optimizer': model.optimizer.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, backup_path)
logger.info(f"Successfully saved to {backup_path}")
# If backup worked, copy to the actual path
if os.path.exists(backup_path):
import shutil
shutil.copy(backup_path, path)
logger.info(f"Copied backup to {path}")
return True
except Exception as e:
logger.warning(f"First save attempt failed: {e}")
# Attempt 2: Try with pickle protocol 2 (more compatible)
try:
logger.info(f"Saving model to {path} (attempt 2 - pickle protocol 2)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'optimizer': model.optimizer.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, path, pickle_protocol=2)
logger.info(f"Successfully saved to {path} with pickle_protocol=2")
return True
except Exception as e:
logger.warning(f"Second save attempt failed: {e}")
# Attempt 3: Try without optimizer state (which can be large and cause issues)
try:
logger.info(f"Saving model to {path} (attempt 3 - without optimizer)")
checkpoint = {
'policy_net': model.policy_net.state_dict(),
'target_net': model.target_net.state_dict(),
'epsilon': model.epsilon
}
torch.save(checkpoint, path)
logger.info(f"Successfully saved to {path} without optimizer state")
return True
except Exception as e:
logger.warning(f"Third save attempt failed: {e}")
# Attempt 4: Try with torch.jit.save instead
try:
logger.info(f"Saving model to {path} (attempt 4 - with jit.save)")
# Save policy network using jit
scripted_policy = torch.jit.script(model.policy_net)
torch.jit.save(scripted_policy, f"{path}.policy.jit")
# Save target network using jit
scripted_target = torch.jit.script(model.target_net)
torch.jit.save(scripted_target, f"{path}.target.jit")
# Save epsilon value separately
with open(f"{path}.epsilon.txt", "w") as f:
f.write(str(model.epsilon))
logger.info(f"Successfully saved model components with jit.save")
return True
except Exception as e:
logger.error(f"All save attempts failed: {e}")
return False
def main():
# Create a test directory
save_dir = "test_models"
os.makedirs(save_dir, exist_ok=True)
# Create a test agent
agent = TestAgent()
# Test the regular save method (might fail)
try:
logger.info("Testing regular save method...")
save_path = os.path.join(save_dir, "regular_save.pt")
agent.save(save_path)
logger.info("Regular save succeeded")
except Exception as e:
logger.error(f"Regular save failed: {e}")
# Test our robust save method
logger.info("Testing robust save method...")
save_path = os.path.join(save_dir, "robust_save.pt")
success = robust_save(agent, save_path)
if success:
logger.info("Robust save succeeded!")
else:
logger.error("Robust save failed!")
# Check which files were created
logger.info("Files created:")
for file in os.listdir(save_dir):
file_path = os.path.join(save_dir, file)
file_size = os.path.getsize(file_path)
logger.info(f" - {file} ({file_size} bytes)")
if __name__ == "__main__":
main()

337
tests.py Normal file
View File

@@ -0,0 +1,337 @@
"""
Unit tests for the trading bot.
This file contains tests for various components of the trading bot, including:
1. Periodic candle updates
2. Backtesting on historical data
3. Training on the last 7 days of data
"""
import unittest
import asyncio
import os
import sys
import logging
import datetime
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from pathlib import Path
# Configure logging
logging.basicConfig(level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[logging.StreamHandler()])
# Import functionality from main.py
import main
from main import (
CandleCache, BacktestCandles, initialize_exchange,
TradingEnvironment, Agent, train_with_backtesting,
fetch_multi_timeframe_data, train_agent
)
class TestPeriodicUpdates(unittest.TestCase):
"""Test that candle data is periodically updated during training."""
async def async_test_periodic_updates(self):
"""Test that candle data is periodically updated during training."""
logging.info("Testing periodic candle updates...")
# Initialize exchange
exchange = await initialize_exchange()
self.assertIsNotNone(exchange, "Failed to initialize exchange")
# Create candle cache
candle_cache = CandleCache()
# Initial fetch of candle data
candle_data = await fetch_multi_timeframe_data(exchange, "ETH/USDT", candle_cache)
self.assertIsNotNone(candle_data, "Failed to fetch initial candle data")
self.assertIn('1m', candle_data, "1m candles not found in initial data")
# Check initial data timestamps
initial_1m_candles = candle_data['1m']
self.assertGreater(len(initial_1m_candles), 0, "No 1m candles found in initial data")
initial_timestamp = initial_1m_candles[-1][0]
# Wait for update interval to pass
logging.info("Waiting for update interval to pass (5 seconds for testing)...")
await asyncio.sleep(5) # Short wait for testing
# Force update by setting last_updated to None
candle_cache.last_updated['1m'] = None
# Fetch updated data
updated_data = await fetch_multi_timeframe_data(exchange, "ETH/USDT", candle_cache)
self.assertIsNotNone(updated_data, "Failed to fetch updated candle data")
# Check if data was updated
updated_1m_candles = updated_data['1m']
self.assertGreater(len(updated_1m_candles), 0, "No 1m candles found in updated data")
updated_timestamp = updated_1m_candles[-1][0]
# In a live scenario, this check should pass with real-time updates
# For testing, we just ensure data was fetched
logging.info(f"Initial timestamp: {initial_timestamp}, Updated timestamp: {updated_timestamp}")
self.assertIsNotNone(updated_timestamp, "Updated timestamp is None")
# Close exchange connection
try:
await exchange.close()
except AttributeError:
# Some exchanges don't have a close method
pass
logging.info("Periodic update test completed")
def test_periodic_updates(self):
"""Run the async test."""
asyncio.run(self.async_test_periodic_updates())
class TestBacktesting(unittest.TestCase):
"""Test backtesting on historical data."""
async def async_test_backtesting(self):
"""Test backtesting on a specific time period."""
logging.info("Testing backtesting with historical data...")
# Initialize exchange
exchange = await initialize_exchange()
self.assertIsNotNone(exchange, "Failed to initialize exchange")
# Create a timestamp for 24 hours ago
now = datetime.datetime.now()
yesterday = now - datetime.timedelta(days=1)
since_timestamp = int(yesterday.timestamp() * 1000) # Convert to milliseconds
# Create a backtesting candle cache
backtest_cache = BacktestCandles(since_timestamp=since_timestamp)
backtest_cache.period_name = "1-day-ago"
# Fetch historical data
candle_data = await backtest_cache.fetch_all_timeframes(exchange, "ETH/USDT")
self.assertIsNotNone(candle_data, "Failed to fetch historical candle data")
self.assertIn('1m', candle_data, "1m candles not found in historical data")
# Check historical data timestamps
minute_candles = candle_data['1m']
self.assertGreater(len(minute_candles), 0, "No minute candles found in historical data")
# Check if timestamps are within the requested range
first_timestamp = minute_candles[0][0]
last_timestamp = minute_candles[-1][0]
logging.info(f"Requested since: {since_timestamp}")
logging.info(f"First timestamp in data: {first_timestamp}")
logging.info(f"Last timestamp in data: {last_timestamp}")
# In real tests, this check should compare timestamps precisely
# For this test, we just ensure data was fetched
self.assertLessEqual(first_timestamp, last_timestamp, "First timestamp should be before last timestamp")
# Close exchange connection
try:
await exchange.close()
except AttributeError:
# Some exchanges don't have a close method
pass
logging.info("Backtesting fetch test completed")
def test_backtesting(self):
"""Run the async test."""
asyncio.run(self.async_test_backtesting())
class TestBacktestingLastSevenDays(unittest.TestCase):
"""Test backtesting on the last 7 days of data."""
async def async_test_seven_days_backtesting(self):
"""Test backtesting on the last 7 days."""
logging.info("Testing backtesting on the last 7 days...")
# Initialize exchange
exchange = await initialize_exchange()
self.assertIsNotNone(exchange, "Failed to initialize exchange")
# Create environment with small initial balance for testing
env = TradingEnvironment(
initial_balance=100, # Small balance for testing
leverage=10, # Lower leverage for testing
window_size=50, # Smaller window for faster testing
commission=0.0004 # Standard commission
)
# Create agent
STATE_SIZE = env.get_state().shape[0] if hasattr(env, 'get_state') else 64
ACTION_SIZE = env.action_space.n if hasattr(env.action_space, 'n') else 4
agent = Agent(state_size=STATE_SIZE, action_size=ACTION_SIZE)
# Initialize empty results dataframe
all_results = pd.DataFrame()
# Run backtesting for the last 7 days, one day at a time
now = datetime.datetime.now()
for day_offset in range(1, 8):
# Calculate time period
end_day = now - datetime.timedelta(days=day_offset-1)
start_day = end_day - datetime.timedelta(days=1)
# Convert to milliseconds
since_timestamp = int(start_day.timestamp() * 1000)
until_timestamp = int(end_day.timestamp() * 1000)
# Period name
period_name = f"Day-{day_offset}"
logging.info(f"Testing backtesting for period: {period_name}")
logging.info(f" - From: {start_day.strftime('%Y-%m-%d %H:%M:%S')}")
logging.info(f" - To: {end_day.strftime('%Y-%m-%d %H:%M:%S')}")
# Run backtesting with a small number of episodes for testing
stats = await train_with_backtesting(
agent=agent,
env=env,
symbol="ETH/USDT",
since_timestamp=since_timestamp,
until_timestamp=until_timestamp,
num_episodes=3, # Use a small number for testing
max_steps_per_episode=200, # Use a small number for testing
period_name=period_name
)
# Check if stats were returned
if stats is None:
logging.warning(f"No stats returned for period: {period_name}")
continue
# Create a dataframe from stats
if len(stats['episode_rewards']) > 0:
df = pd.DataFrame({
'Period': [period_name] * len(stats['episode_rewards']),
'Episode': list(range(1, len(stats['episode_rewards']) + 1)),
'Reward': stats['episode_rewards'],
'Balance': stats['balances'],
'PnL': stats['episode_pnls'],
'Fees': stats['fees'],
'Net_PnL': stats['net_pnl_after_fees']
})
# Append to all results
all_results = pd.concat([all_results, df], ignore_index=True)
logging.info(f"Completed backtesting for period: {period_name}")
logging.info(f" - Episodes: {len(stats['episode_rewards'])}")
logging.info(f" - Final Balance: ${stats['balances'][-1]:.2f}")
logging.info(f" - Net PnL: ${stats['net_pnl_after_fees'][-1]:.2f}")
else:
logging.warning(f"No episodes completed for period: {period_name}")
# Save all results
if not all_results.empty:
all_results.to_csv("all_backtest_results.csv", index=False)
logging.info("Saved all backtest results to all_backtest_results.csv")
# Create plot of results
plt.figure(figsize=(12, 8))
# Plot Net PnL by period
all_results.groupby('Period')['Net_PnL'].last().plot(kind='bar')
plt.title('Net PnL by Training Period (Last Episode)')
plt.ylabel('Net PnL ($)')
plt.tight_layout()
plt.savefig("backtest_results.png")
logging.info("Saved backtest results plot to backtest_results.png")
# Close exchange connection
try:
await exchange.close()
except AttributeError:
# Some exchanges don't have a close method
pass
logging.info("7-day backtesting test completed")
def test_seven_days_backtesting(self):
"""Run the async test."""
asyncio.run(self.async_test_seven_days_backtesting())
class TestSingleDayBacktesting(unittest.TestCase):
"""Test backtesting on a single day of historical data."""
async def async_test_single_day_backtesting(self):
"""Test backtesting on a single day."""
logging.info("Testing backtesting on a single day...")
# Initialize exchange
exchange = await initialize_exchange()
self.assertIsNotNone(exchange, "Failed to initialize exchange")
# Create environment with small initial balance for testing
env = TradingEnvironment(
initial_balance=100, # Small balance for testing
leverage=10, # Lower leverage for testing
window_size=50, # Smaller window for faster testing
commission=0.0004 # Standard commission
)
# Create agent
STATE_SIZE = env.get_state().shape[0] if hasattr(env, 'get_state') else 64
ACTION_SIZE = env.action_space.n if hasattr(env.action_space, 'n') else 4
agent = Agent(state_size=STATE_SIZE, action_size=ACTION_SIZE)
# Calculate time period for 1 day ago
now = datetime.datetime.now()
end_day = now
start_day = end_day - datetime.timedelta(days=1)
# Convert to milliseconds
since_timestamp = int(start_day.timestamp() * 1000)
until_timestamp = int(end_day.timestamp() * 1000)
# Period name
period_name = "Test-Day-1"
logging.info(f"Testing backtesting for period: {period_name}")
logging.info(f" - From: {start_day.strftime('%Y-%m-%d %H:%M:%S')}")
logging.info(f" - To: {end_day.strftime('%Y-%m-%d %H:%M:%S')}")
# Run backtesting with a small number of episodes for testing
stats = await train_with_backtesting(
agent=agent,
env=env,
symbol="ETH/USDT",
since_timestamp=since_timestamp,
until_timestamp=until_timestamp,
num_episodes=2, # Very small number for quick testing
max_steps_per_episode=100, # Very small number for quick testing
period_name=period_name
)
# Check if stats were returned
self.assertIsNotNone(stats, "No stats returned from backtesting")
# Check if episodes were completed
self.assertGreater(len(stats['episode_rewards']), 0, "No episodes completed")
# Log results
logging.info(f"Completed backtesting for period: {period_name}")
logging.info(f" - Episodes: {len(stats['episode_rewards'])}")
logging.info(f" - Final Balance: ${stats['balances'][-1]:.2f}")
logging.info(f" - Net PnL: ${stats['net_pnl_after_fees'][-1]:.2f}")
# Close exchange connection
try:
await exchange.close()
except AttributeError:
# Some exchanges don't have a close method
pass
logging.info("Single day backtesting test completed")
def test_single_day_backtesting(self):
"""Run the async test."""
asyncio.run(self.async_test_single_day_backtesting())
if __name__ == '__main__':
unittest.main()

45968
trading_bot.log Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
training_results.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 159 KiB

101
training_stats.csv Normal file
View File

@@ -0,0 +1,101 @@
episode_rewards,episode_lengths,balances,win_rates,episode_pnls,cumulative_pnl,drawdowns,trade_counts,loss_values,fees,net_pnl_after_fees
245.58133743041853,169,93.49705776828564,0,-6.502942231714357,-6.502942231714357,0,0,3.8250006539481025,2.3476677085473576,-8.850609940261714
832.4094761202507,499,94.04750613751911,0,-5.9524938624808925,-12.45543609419525,0,0,33.82088630806229,6.272140915345915,-12.224634777826807
255.18730411041088,185,86.56024046551762,0,-13.439759534482377,-25.895195628677627,0,0,43.29075657612569,2.4037655108544858,-15.843525045336863
119.78978677830429,72,95.3813667599062,0,-4.6186332400938,-30.513828868771427,0,0,44.92027886708578,0.9916340254343576,-5.610267265528158
122.51175362537998,85,91.31594631081882,0,-8.684053689181184,-39.19788255795261,0,0,45.3130573497099,0.9726320887358407,-9.656685777917025
305.0054315397143,210,116.87229096452045,0,16.872290964520445,-22.325591593432165,0,0,46.3667417435419,3.320549920480678,13.551741044039767
62.284146346942286,56,93.1325530556652,0,-6.867446944334802,-29.193038537766967,0,0,48.545649256025044,0.6365590497424187,-7.50400599407722
100.45460708688081,62,97.10664822082919,0,-2.893351779170814,-32.08639031693778,0,0,47.529073838264715,0.9760707887647201,-3.8694225679355343
193.931779217577,141,99.93811779543111,0,-0.06188220456888871,-32.14827252150667,0,0,41.286791862325465,2.0967969721573203,-2.158679176726209
771.3404511810347,499,107.33529119510085,0,7.335291195100851,-24.81298132640582,0,0,42.90441010805791,6.689355428199721,0.6459357669011299
343.8011302413935,223,89.58433307413128,0,-10.41566692586872,-35.22864825227454,0,0,45.18598407694043,2.692231694609321,-13.107898620478041
151.1836201290492,109,85.37179195170742,0,-14.628208048292578,-49.85685630056712,0,0,45.879525910823716,1.2460821106553646,-15.874290158947943
33.69084501639204,18,88.63060514982539,0,-11.369394850174615,-61.22625115074173,0,0,44.08014043172201,0.20209914799744422,-11.571493998172059
296.2721143348319,230,100.91907353649867,0,0.9190735364986722,-60.30717761424306,0,0,46.446043528681216,2.6593912257770924,-1.7403176892784202
310.68942047763323,220,84.12861286083523,0,-15.871387139164767,-76.17856475340783,0,0,48.09207950938832,2.7171079330637733,-18.58849507222854
102.10248003076286,67,103.2143315172572,0,3.214331517257193,-72.96423323615063,0,0,49.6177435348283,0.995181548583709,2.2191499686734844
154.7796070247227,93,99.59249081761537,0,-0.4075091823846293,-73.37174241853526,0,0,48.7942138179656,1.4840004549654364,-1.8915096373500657
142.27662985924832,78,95.94061914207992,0,-4.059380857920075,-77.43112327645534,0,0,49.389447774642555,1.046338991830505,-5.105719849750581
657.2312058095997,475,101.71161514469802,0,1.7116151446980155,-75.71950813175732,0,0,53.4358780951249,5.920061753201907,-4.208446608503891
243.75983326227475,190,92.48436829246025,0,-7.515631707539754,-83.23513983929708,0,0,54.6990302939164,2.204728192181755,-9.720359899721508
503.5407022684538,370,114.22067976639565,0,14.220679766395648,-69.01446007290143,0,0,55.37000999966183,4.947503113281474,9.273176653114174
108.76698654683082,83,92.64055941717413,0,-7.359440582825869,-76.3739006557273,0,0,57.52865586797875,1.122939491633078,-8.482380074458947
288.2645162428217,187,94.16572074286584,0,-5.834279257134156,-82.20817991286145,0,0,56.778801188749426,2.7596873757719163,-8.593966632906072
694.574834347051,500,124.38194363244577,0,24.38194363244577,-57.826236280415685,0,0,57.476991076268746,7.616086957167,16.76585667527877
61.77139917751085,52,89.62592956541371,0,-10.374070434586287,-68.20030671500197,0,0,57.153403942401596,0.6360214924844756,-11.010091927070762
136.34512859980074,100,83.33171493389538,0,-16.668285066104616,-84.86859178110659,0,0,57.55507698059082,1.224767956811129,-17.893053022915744
347.25837922642773,227,130.79210001851564,0,30.79210001851564,-54.07649176259095,0,0,58.05349503576228,3.5340462836874016,27.258053734828238
103.3965622283485,81,97.68386910781076,0,-2.3161308921892356,-56.39262265478018,0,0,56.30076151718328,0.9164887013369737,-3.232619593526209
265.88097276940334,160,83.93754552617912,0,-16.06245447382088,-72.45507712860106,0,0,59.35555845536526,1.868667523542714,-17.931121997363594
607.726473225615,377,98.84259170578743,0,-1.1574082942125727,-73.61248542281363,0,0,56.93259246298607,5.303576699105105,-6.460984993317678
171.76355735461715,119,82.1398069210588,0,-17.860193078941194,-91.47267850175483,0,0,56.68230017969164,1.560211436232409,-19.4204045151736
57.17447366096833,37,102.2353597779798,0,2.235359777979795,-89.23731872377503,0,0,58.93467372172588,0.5267973679750108,1.7085624100047845
526.6853167557408,351,91.57796429201413,0,-8.42203570798587,-97.6593544317609,0,0,57.39789538792201,4.603868898733577,-13.025904606719447
533.4621095416652,388,100.18443251293645,0,0.18443251293645346,-97.47492191882445,0,0,57.32353478854464,5.269862515807407,-5.085430002870954
767.6384516972751,501,106.53994742273046,0,6.539947422730464,-90.93497449609399,0,0,56.075344276810455,6.941744377571792,-0.4017969548413287
268.39207803314275,164,74.02426074441962,0,-25.97573925558038,-116.91071375167436,0,0,54.65164536786226,1.8040949631519818,-27.77983421873236
486.74971964904495,355,94.81814783250175,0,-5.181852167498249,-122.09256591917261,0,0,52.54617132343584,4.639298254087809,-9.821150421586058
48.19990337118416,35,89.86047892582286,0,-10.13952107417714,-132.23208699334975,0,0,52.4935922895159,0.3724969825147257,-10.512018056691865
317.14688938741654,198,77.27582678036522,0,-22.72417321963478,-154.95626021298455,0,0,53.14049422138869,2.3104186094919625,-25.03459182912674
55.68057868456839,43,94.36343793141816,0,-5.6365620685818385,-160.59282228156638,0,0,52.18246051877044,0.5009234143139363,-6.137485482895775
108.98178163481917,65,88.84191178095307,0,-11.158088219046931,-171.75091050061332,0,0,54.54355762188251,0.8988542687329729,-12.056942487779905
195.06535418367304,129,80.37638841826704,0,-19.62361158173296,-191.37452208234626,0,0,54.25914459819941,1.5279752537717612,-21.15158683550472
263.85742805154445,192,87.31804171564818,0,-12.681958284351822,-204.05648036669808,0,0,53.566342590977904,2.252679163105727,-14.934637447457549
42.08812691754652,37,96.23102669642205,0,-3.768973303577951,-207.82545367027603,0,0,54.52740478515625,0.41129305958705703,-4.180266363165008
255.0337738896274,185,80.82253926915493,0,-19.17746073084507,-227.0029144011211,0,0,57.01246037690536,2.2844205421478603,-21.46188127299293
473.3238767813625,304,76.490800770486,0,-23.509199229513996,-250.5121136306351,0,0,55.752617271322954,3.672135650508411,-27.18133488002241
124.48339751068255,96,82.37275938190088,0,-17.627240618099123,-268.1393542487342,0,0,55.1293203830719,1.0139912257072856,-18.64123184380641
177.0372058503859,102,120.75183228650069,0,20.751832286500687,-247.38752196223354,0,0,55.58330300275017,1.6177940342162778,19.13403825228441
668.9726066324473,464,106.60954141921921,0,6.609541419219212,-240.77798054301434,0,0,53.35351522215481,6.574125868937176,0.03541555028203636
235.6822691679875,173,101.02730460913321,0,1.0273046091332105,-239.7506759338811,0,0,51.442252506410455,2.3720098584207254,-1.344705249287515
29.393838454091096,23,102.48855123922196,0,2.4885512392219624,-237.26212469465915,0,0,50.64632133815599,0.3449140455084859,2.1436371937134764
314.404350268341,206,132.17502316477743,0,32.17502316477743,-205.08710152988172,0,0,49.86209524950935,3.4187221697492065,28.756300995028223
449.80273436874546,294,85.86708282041911,0,-14.132917179580886,-219.2200187094626,0,0,50.660906629497504,3.327512218325091,-17.460429397905976
43.78295364860909,23,93.32998305543147,0,-6.6700169445685304,-225.89003565403112,0,0,48.14624272222104,0.30225939171808053,-6.972276336286611
100.47935066911198,82,85.43625012639903,0,-14.563749873600969,-240.4537855276321,0,0,50.21175172593858,0.8687399948089715,-15.43248986840994
245.04877800524088,149,94.92578814324827,0,-5.074211856751731,-245.52799738438384,0,0,48.87210794397303,1.9491516870782084,-7.023363543829939
448.1745373852734,275,92.79970655436605,0,-7.200293445633946,-252.72829083001778,0,0,50.84040899346345,3.2999356705654224,-10.500229116199367
604.3083327451844,410,171.36341223774605,0,71.36341223774605,-181.36487859227174,0,0,47.38697471805647,8.044634836766896,63.31877740097915
445.735162940227,347,115.79447252348977,0,15.794472523489773,-165.57040606878195,0,0,46.95305928467326,5.463746469325774,10.330726054164
188.26423842058716,130,85.67123642235606,0,-14.32876357764394,-179.8991696464259,0,0,47.85700696013694,1.4459890509690823,-15.774752628613022
249.95700058828476,176,100.63418773527684,0,0.6341877352768392,-179.26498191114905,0,0,47.09227745099501,2.2905264292731857,-1.6563386939963465
291.7787084045001,200,92.41764950116612,0,-7.5823504988338755,-186.84733240998293,0,0,46.07237024307251,2.3878948481416247,-9.9702453469755
39.49455231726071,34,105.17297715381125,0,5.172977153811246,-181.67435525617168,0,0,45.147511201746326,0.43200232970373437,4.740974824107512
270.4231929424243,184,93.76079758961349,0,-6.239202410386511,-187.9135576665582,0,0,46.36682858674423,2.5813276818104973,-8.820530092197009
465.2307230663394,345,142.31403796186228,0,42.31403796186228,-145.59951970469592,0,0,47.12680500989769,4.934661849269876,37.37937611259241
354.0709138887967,253,102.3923564837438,0,2.3923564837437965,-143.2071632209521,0,0,44.706567900521414,3.626792580607198,-1.2344360968634014
72.87629503513513,53,94.2158680822552,0,-5.784131917744801,-148.99129513869693,0,0,42.83745182685132,0.6630920708528815,-6.447223988597683
64.6807928869498,45,93.66580566705527,0,-6.334194332944733,-155.32548947164167,0,0,45.26956371731228,0.5287071091187852,-6.862901442063518
508.66036280979847,297,86.47061479834193,0,-13.529385201658073,-168.85487467329972,0,0,41.576025184319946,3.7591471424850886,-17.28853234414316
92.36510982811035,66,91.33419627440843,0,-8.665803725591573,-177.5206783988913,0,0,40.11061216501089,0.9116306354437804,-9.577434361035353
318.1738390997916,208,130.73147464777986,0,30.731474647779862,-146.78920375111144,0,0,39.614786673283234,3.2278138137724106,27.50366083400745
47.49064937763736,34,90.31843168727164,0,-9.68156831272836,-156.4707720638398,0,0,38.943554386948094,0.30301102389683343,-9.984579336625192
747.7323524200937,502,88.00297441445022,0,-11.997025585549778,-168.46779764938958,0,0,37.31163117785253,5.4236005627262305,-17.420626148276007
197.95639730277807,139,79.95413897621663,0,-20.045861023783374,-188.51365867317296,0,0,34.041194929493415,1.5609323757928528,-21.606793399576226
278.8283885528506,210,97.16879460202368,0,-2.831205397976319,-191.3448640711493,0,0,33.00566090070284,2.5672068646263684,-5.398412262602688
648.7793299316244,409,108.86023988510733,0,8.860239885107333,-182.48462418604194,0,0,28.99119337867288,5.416512290229198,3.443727594878135
111.58999686248235,67,93.34461894707614,0,-6.6553810529238575,-189.14000523896578,0,0,26.240258621447015,0.9292218629873201,-7.584602915911177
79.36649990440858,50,95.74834856466987,0,-4.251651435330132,-193.39165667429592,0,0,24.562227363586427,0.7537257543525197,-5.005377189682651
102.77658053248489,84,76.43085079701073,0,-23.569149202989266,-216.9608058772852,0,0,23.018385875655945,0.9143137963689831,-24.48346299935825
738.0525604642081,500,110.82078134730637,0,10.820781347306365,-206.14002452997883,0,0,20.300480945793566,7.125179360202941,3.695601987103424
484.428102172877,342,104.16844064037448,0,4.1684406403744845,-201.97158388960435,0,0,10.086975039103452,4.768527585194042,-0.6000869448195578
65.67162922969268,36,101.91490114791101,0,1.91490114791101,-200.05668274169335,0,0,1.9290405147605472,0.6267909715787242,1.2881101763322858
254.92615266892506,163,84.70688630578415,0,-15.293113694215847,-215.34979643590918,0,0,2.197029543892006,2.18487588123249,-17.477989575448337
386.0688480519854,291,84.23048553641095,0,-15.769514463589047,-231.11931089949823,0,0,2.647557835185176,3.6125445725924594,-19.382059036181506
163.58304242380865,127,93.24454429873177,0,-6.755455701268232,-237.87476660076646,0,0,2.5592061410406752,1.5203821076964832,-8.275837808964715
360.1105692649448,237,108.46964096170034,0,8.469640961700335,-229.4051256390661,0,0,3.2837834234196173,3.348683113346831,5.1209578483535045
166.5936314582434,111,93.25853727674894,0,-6.741462723251061,-236.14658836231717,0,0,2.3705001306124367,1.558288007515565,-8.299750730766625
31.79062848778471,14,94.54125091016239,0,-5.45874908983761,-241.6053374521548,0,0,3.663335899689368,0.18502029875836917,-5.643769388595979
766.2602327804954,507,79.53704062494181,0,-20.46295937505819,-262.068296827213,0,0,2.2676825669233898,5.746946187937156,-26.209905562995345
808.0987615884774,506,96.55036833755842,0,-3.4496316624415755,-265.51792848965454,0,0,2.3812816971726343,7.178936220281195,-10.62856788272277
526.72560429803,346,87.27581844234555,0,-12.724181557654447,-278.242110047309,0,0,2.0199785625572932,4.05454691115033,-16.778728468804776
742.0860299994148,493,79.38149296059294,0,-20.618507039407064,-298.86061708671605,0,0,2.3157294217623328,6.331309914949699,-26.949816954356763
122.8700996125919,71,100.50025170255012,0,0.5002517025501163,-298.36036538416596,0,0,1.5784865789641829,1.0850045415492369,-0.5847528389991206
365.36747369636174,241,103.93399590295836,0,3.933995902958358,-294.4263694812076,0,0,1.9304202096809528,3.271458391489611,0.6625375114687473
137.56042070549447,70,86.2184807577603,0,-13.781519242239696,-308.2078887234473,0,0,2.041805549710989,0.9463594611124042,-14.7278787033521
70.67448352065381,66,94.98203690081301,0,-5.017963099186986,-313.2258518226343,0,0,1.7464851798828354,0.7227296911232824,-5.740692790310268
100.67381032735967,67,93.38307644153083,0,-6.616923558469168,-319.8427753811035,0,0,1.5876922868121641,0.9068664170112423,-7.52378997548041
175.3187964581547,111,93.2227229868474,0,-6.777277013152599,-326.62005239425605,0,0,1.956010960012572,1.3353482564018333,-8.112625269554432
144.56778676791527,96,111.82402197115043,0,11.82402197115043,-314.7960304231056,0,0,2.1400070753928864,1.5718585971130639,10.252163374037366
341.84158515939083,228,115.97533737071987,0,15.97533737071987,-298.82069305238576,0,0,1.9551628017531388,3.337288446997239,12.638048923722632
1 episode_rewards episode_lengths balances win_rates episode_pnls cumulative_pnl drawdowns trade_counts loss_values fees net_pnl_after_fees
2 245.58133743041853 169 93.49705776828564 0 -6.502942231714357 -6.502942231714357 0 0 3.8250006539481025 2.3476677085473576 -8.850609940261714
3 832.4094761202507 499 94.04750613751911 0 -5.9524938624808925 -12.45543609419525 0 0 33.82088630806229 6.272140915345915 -12.224634777826807
4 255.18730411041088 185 86.56024046551762 0 -13.439759534482377 -25.895195628677627 0 0 43.29075657612569 2.4037655108544858 -15.843525045336863
5 119.78978677830429 72 95.3813667599062 0 -4.6186332400938 -30.513828868771427 0 0 44.92027886708578 0.9916340254343576 -5.610267265528158
6 122.51175362537998 85 91.31594631081882 0 -8.684053689181184 -39.19788255795261 0 0 45.3130573497099 0.9726320887358407 -9.656685777917025
7 305.0054315397143 210 116.87229096452045 0 16.872290964520445 -22.325591593432165 0 0 46.3667417435419 3.320549920480678 13.551741044039767
8 62.284146346942286 56 93.1325530556652 0 -6.867446944334802 -29.193038537766967 0 0 48.545649256025044 0.6365590497424187 -7.50400599407722
9 100.45460708688081 62 97.10664822082919 0 -2.893351779170814 -32.08639031693778 0 0 47.529073838264715 0.9760707887647201 -3.8694225679355343
10 193.931779217577 141 99.93811779543111 0 -0.06188220456888871 -32.14827252150667 0 0 41.286791862325465 2.0967969721573203 -2.158679176726209
11 771.3404511810347 499 107.33529119510085 0 7.335291195100851 -24.81298132640582 0 0 42.90441010805791 6.689355428199721 0.6459357669011299
12 343.8011302413935 223 89.58433307413128 0 -10.41566692586872 -35.22864825227454 0 0 45.18598407694043 2.692231694609321 -13.107898620478041
13 151.1836201290492 109 85.37179195170742 0 -14.628208048292578 -49.85685630056712 0 0 45.879525910823716 1.2460821106553646 -15.874290158947943
14 33.69084501639204 18 88.63060514982539 0 -11.369394850174615 -61.22625115074173 0 0 44.08014043172201 0.20209914799744422 -11.571493998172059
15 296.2721143348319 230 100.91907353649867 0 0.9190735364986722 -60.30717761424306 0 0 46.446043528681216 2.6593912257770924 -1.7403176892784202
16 310.68942047763323 220 84.12861286083523 0 -15.871387139164767 -76.17856475340783 0 0 48.09207950938832 2.7171079330637733 -18.58849507222854
17 102.10248003076286 67 103.2143315172572 0 3.214331517257193 -72.96423323615063 0 0 49.6177435348283 0.995181548583709 2.2191499686734844
18 154.7796070247227 93 99.59249081761537 0 -0.4075091823846293 -73.37174241853526 0 0 48.7942138179656 1.4840004549654364 -1.8915096373500657
19 142.27662985924832 78 95.94061914207992 0 -4.059380857920075 -77.43112327645534 0 0 49.389447774642555 1.046338991830505 -5.105719849750581
20 657.2312058095997 475 101.71161514469802 0 1.7116151446980155 -75.71950813175732 0 0 53.4358780951249 5.920061753201907 -4.208446608503891
21 243.75983326227475 190 92.48436829246025 0 -7.515631707539754 -83.23513983929708 0 0 54.6990302939164 2.204728192181755 -9.720359899721508
22 503.5407022684538 370 114.22067976639565 0 14.220679766395648 -69.01446007290143 0 0 55.37000999966183 4.947503113281474 9.273176653114174
23 108.76698654683082 83 92.64055941717413 0 -7.359440582825869 -76.3739006557273 0 0 57.52865586797875 1.122939491633078 -8.482380074458947
24 288.2645162428217 187 94.16572074286584 0 -5.834279257134156 -82.20817991286145 0 0 56.778801188749426 2.7596873757719163 -8.593966632906072
25 694.574834347051 500 124.38194363244577 0 24.38194363244577 -57.826236280415685 0 0 57.476991076268746 7.616086957167 16.76585667527877
26 61.77139917751085 52 89.62592956541371 0 -10.374070434586287 -68.20030671500197 0 0 57.153403942401596 0.6360214924844756 -11.010091927070762
27 136.34512859980074 100 83.33171493389538 0 -16.668285066104616 -84.86859178110659 0 0 57.55507698059082 1.224767956811129 -17.893053022915744
28 347.25837922642773 227 130.79210001851564 0 30.79210001851564 -54.07649176259095 0 0 58.05349503576228 3.5340462836874016 27.258053734828238
29 103.3965622283485 81 97.68386910781076 0 -2.3161308921892356 -56.39262265478018 0 0 56.30076151718328 0.9164887013369737 -3.232619593526209
30 265.88097276940334 160 83.93754552617912 0 -16.06245447382088 -72.45507712860106 0 0 59.35555845536526 1.868667523542714 -17.931121997363594
31 607.726473225615 377 98.84259170578743 0 -1.1574082942125727 -73.61248542281363 0 0 56.93259246298607 5.303576699105105 -6.460984993317678
32 171.76355735461715 119 82.1398069210588 0 -17.860193078941194 -91.47267850175483 0 0 56.68230017969164 1.560211436232409 -19.4204045151736
33 57.17447366096833 37 102.2353597779798 0 2.235359777979795 -89.23731872377503 0 0 58.93467372172588 0.5267973679750108 1.7085624100047845
34 526.6853167557408 351 91.57796429201413 0 -8.42203570798587 -97.6593544317609 0 0 57.39789538792201 4.603868898733577 -13.025904606719447
35 533.4621095416652 388 100.18443251293645 0 0.18443251293645346 -97.47492191882445 0 0 57.32353478854464 5.269862515807407 -5.085430002870954
36 767.6384516972751 501 106.53994742273046 0 6.539947422730464 -90.93497449609399 0 0 56.075344276810455 6.941744377571792 -0.4017969548413287
37 268.39207803314275 164 74.02426074441962 0 -25.97573925558038 -116.91071375167436 0 0 54.65164536786226 1.8040949631519818 -27.77983421873236
38 486.74971964904495 355 94.81814783250175 0 -5.181852167498249 -122.09256591917261 0 0 52.54617132343584 4.639298254087809 -9.821150421586058
39 48.19990337118416 35 89.86047892582286 0 -10.13952107417714 -132.23208699334975 0 0 52.4935922895159 0.3724969825147257 -10.512018056691865
40 317.14688938741654 198 77.27582678036522 0 -22.72417321963478 -154.95626021298455 0 0 53.14049422138869 2.3104186094919625 -25.03459182912674
41 55.68057868456839 43 94.36343793141816 0 -5.6365620685818385 -160.59282228156638 0 0 52.18246051877044 0.5009234143139363 -6.137485482895775
42 108.98178163481917 65 88.84191178095307 0 -11.158088219046931 -171.75091050061332 0 0 54.54355762188251 0.8988542687329729 -12.056942487779905
43 195.06535418367304 129 80.37638841826704 0 -19.62361158173296 -191.37452208234626 0 0 54.25914459819941 1.5279752537717612 -21.15158683550472
44 263.85742805154445 192 87.31804171564818 0 -12.681958284351822 -204.05648036669808 0 0 53.566342590977904 2.252679163105727 -14.934637447457549
45 42.08812691754652 37 96.23102669642205 0 -3.768973303577951 -207.82545367027603 0 0 54.52740478515625 0.41129305958705703 -4.180266363165008
46 255.0337738896274 185 80.82253926915493 0 -19.17746073084507 -227.0029144011211 0 0 57.01246037690536 2.2844205421478603 -21.46188127299293
47 473.3238767813625 304 76.490800770486 0 -23.509199229513996 -250.5121136306351 0 0 55.752617271322954 3.672135650508411 -27.18133488002241
48 124.48339751068255 96 82.37275938190088 0 -17.627240618099123 -268.1393542487342 0 0 55.1293203830719 1.0139912257072856 -18.64123184380641
49 177.0372058503859 102 120.75183228650069 0 20.751832286500687 -247.38752196223354 0 0 55.58330300275017 1.6177940342162778 19.13403825228441
50 668.9726066324473 464 106.60954141921921 0 6.609541419219212 -240.77798054301434 0 0 53.35351522215481 6.574125868937176 0.03541555028203636
51 235.6822691679875 173 101.02730460913321 0 1.0273046091332105 -239.7506759338811 0 0 51.442252506410455 2.3720098584207254 -1.344705249287515
52 29.393838454091096 23 102.48855123922196 0 2.4885512392219624 -237.26212469465915 0 0 50.64632133815599 0.3449140455084859 2.1436371937134764
53 314.404350268341 206 132.17502316477743 0 32.17502316477743 -205.08710152988172 0 0 49.86209524950935 3.4187221697492065 28.756300995028223
54 449.80273436874546 294 85.86708282041911 0 -14.132917179580886 -219.2200187094626 0 0 50.660906629497504 3.327512218325091 -17.460429397905976
55 43.78295364860909 23 93.32998305543147 0 -6.6700169445685304 -225.89003565403112 0 0 48.14624272222104 0.30225939171808053 -6.972276336286611
56 100.47935066911198 82 85.43625012639903 0 -14.563749873600969 -240.4537855276321 0 0 50.21175172593858 0.8687399948089715 -15.43248986840994
57 245.04877800524088 149 94.92578814324827 0 -5.074211856751731 -245.52799738438384 0 0 48.87210794397303 1.9491516870782084 -7.023363543829939
58 448.1745373852734 275 92.79970655436605 0 -7.200293445633946 -252.72829083001778 0 0 50.84040899346345 3.2999356705654224 -10.500229116199367
59 604.3083327451844 410 171.36341223774605 0 71.36341223774605 -181.36487859227174 0 0 47.38697471805647 8.044634836766896 63.31877740097915
60 445.735162940227 347 115.79447252348977 0 15.794472523489773 -165.57040606878195 0 0 46.95305928467326 5.463746469325774 10.330726054164
61 188.26423842058716 130 85.67123642235606 0 -14.32876357764394 -179.8991696464259 0 0 47.85700696013694 1.4459890509690823 -15.774752628613022
62 249.95700058828476 176 100.63418773527684 0 0.6341877352768392 -179.26498191114905 0 0 47.09227745099501 2.2905264292731857 -1.6563386939963465
63 291.7787084045001 200 92.41764950116612 0 -7.5823504988338755 -186.84733240998293 0 0 46.07237024307251 2.3878948481416247 -9.9702453469755
64 39.49455231726071 34 105.17297715381125 0 5.172977153811246 -181.67435525617168 0 0 45.147511201746326 0.43200232970373437 4.740974824107512
65 270.4231929424243 184 93.76079758961349 0 -6.239202410386511 -187.9135576665582 0 0 46.36682858674423 2.5813276818104973 -8.820530092197009
66 465.2307230663394 345 142.31403796186228 0 42.31403796186228 -145.59951970469592 0 0 47.12680500989769 4.934661849269876 37.37937611259241
67 354.0709138887967 253 102.3923564837438 0 2.3923564837437965 -143.2071632209521 0 0 44.706567900521414 3.626792580607198 -1.2344360968634014
68 72.87629503513513 53 94.2158680822552 0 -5.784131917744801 -148.99129513869693 0 0 42.83745182685132 0.6630920708528815 -6.447223988597683
69 64.6807928869498 45 93.66580566705527 0 -6.334194332944733 -155.32548947164167 0 0 45.26956371731228 0.5287071091187852 -6.862901442063518
70 508.66036280979847 297 86.47061479834193 0 -13.529385201658073 -168.85487467329972 0 0 41.576025184319946 3.7591471424850886 -17.28853234414316
71 92.36510982811035 66 91.33419627440843 0 -8.665803725591573 -177.5206783988913 0 0 40.11061216501089 0.9116306354437804 -9.577434361035353
72 318.1738390997916 208 130.73147464777986 0 30.731474647779862 -146.78920375111144 0 0 39.614786673283234 3.2278138137724106 27.50366083400745
73 47.49064937763736 34 90.31843168727164 0 -9.68156831272836 -156.4707720638398 0 0 38.943554386948094 0.30301102389683343 -9.984579336625192
74 747.7323524200937 502 88.00297441445022 0 -11.997025585549778 -168.46779764938958 0 0 37.31163117785253 5.4236005627262305 -17.420626148276007
75 197.95639730277807 139 79.95413897621663 0 -20.045861023783374 -188.51365867317296 0 0 34.041194929493415 1.5609323757928528 -21.606793399576226
76 278.8283885528506 210 97.16879460202368 0 -2.831205397976319 -191.3448640711493 0 0 33.00566090070284 2.5672068646263684 -5.398412262602688
77 648.7793299316244 409 108.86023988510733 0 8.860239885107333 -182.48462418604194 0 0 28.99119337867288 5.416512290229198 3.443727594878135
78 111.58999686248235 67 93.34461894707614 0 -6.6553810529238575 -189.14000523896578 0 0 26.240258621447015 0.9292218629873201 -7.584602915911177
79 79.36649990440858 50 95.74834856466987 0 -4.251651435330132 -193.39165667429592 0 0 24.562227363586427 0.7537257543525197 -5.005377189682651
80 102.77658053248489 84 76.43085079701073 0 -23.569149202989266 -216.9608058772852 0 0 23.018385875655945 0.9143137963689831 -24.48346299935825
81 738.0525604642081 500 110.82078134730637 0 10.820781347306365 -206.14002452997883 0 0 20.300480945793566 7.125179360202941 3.695601987103424
82 484.428102172877 342 104.16844064037448 0 4.1684406403744845 -201.97158388960435 0 0 10.086975039103452 4.768527585194042 -0.6000869448195578
83 65.67162922969268 36 101.91490114791101 0 1.91490114791101 -200.05668274169335 0 0 1.9290405147605472 0.6267909715787242 1.2881101763322858
84 254.92615266892506 163 84.70688630578415 0 -15.293113694215847 -215.34979643590918 0 0 2.197029543892006 2.18487588123249 -17.477989575448337
85 386.0688480519854 291 84.23048553641095 0 -15.769514463589047 -231.11931089949823 0 0 2.647557835185176 3.6125445725924594 -19.382059036181506
86 163.58304242380865 127 93.24454429873177 0 -6.755455701268232 -237.87476660076646 0 0 2.5592061410406752 1.5203821076964832 -8.275837808964715
87 360.1105692649448 237 108.46964096170034 0 8.469640961700335 -229.4051256390661 0 0 3.2837834234196173 3.348683113346831 5.1209578483535045
88 166.5936314582434 111 93.25853727674894 0 -6.741462723251061 -236.14658836231717 0 0 2.3705001306124367 1.558288007515565 -8.299750730766625
89 31.79062848778471 14 94.54125091016239 0 -5.45874908983761 -241.6053374521548 0 0 3.663335899689368 0.18502029875836917 -5.643769388595979
90 766.2602327804954 507 79.53704062494181 0 -20.46295937505819 -262.068296827213 0 0 2.2676825669233898 5.746946187937156 -26.209905562995345
91 808.0987615884774 506 96.55036833755842 0 -3.4496316624415755 -265.51792848965454 0 0 2.3812816971726343 7.178936220281195 -10.62856788272277
92 526.72560429803 346 87.27581844234555 0 -12.724181557654447 -278.242110047309 0 0 2.0199785625572932 4.05454691115033 -16.778728468804776
93 742.0860299994148 493 79.38149296059294 0 -20.618507039407064 -298.86061708671605 0 0 2.3157294217623328 6.331309914949699 -26.949816954356763
94 122.8700996125919 71 100.50025170255012 0 0.5002517025501163 -298.36036538416596 0 0 1.5784865789641829 1.0850045415492369 -0.5847528389991206
95 365.36747369636174 241 103.93399590295836 0 3.933995902958358 -294.4263694812076 0 0 1.9304202096809528 3.271458391489611 0.6625375114687473
96 137.56042070549447 70 86.2184807577603 0 -13.781519242239696 -308.2078887234473 0 0 2.041805549710989 0.9463594611124042 -14.7278787033521
97 70.67448352065381 66 94.98203690081301 0 -5.017963099186986 -313.2258518226343 0 0 1.7464851798828354 0.7227296911232824 -5.740692790310268
98 100.67381032735967 67 93.38307644153083 0 -6.616923558469168 -319.8427753811035 0 0 1.5876922868121641 0.9068664170112423 -7.52378997548041
99 175.3187964581547 111 93.2227229868474 0 -6.777277013152599 -326.62005239425605 0 0 1.956010960012572 1.3353482564018333 -8.112625269554432
100 144.56778676791527 96 111.82402197115043 0 11.82402197115043 -314.7960304231056 0 0 2.1400070753928864 1.5718585971130639 10.252163374037366
101 341.84158515939083 228 115.97533737071987 0 15.97533737071987 -298.82069305238576 0 0 1.9551628017531388 3.337288446997239 12.638048923722632