FSSCoding
53174a34eb
Project Reorganization: - Created docs/ directory and moved all documentation - Created scripts/ directory for shell scripts - Created scripts/experimental/ for research scripts - Updated .gitignore for new structure - Updated README.md with MVP status and new structure New Features: - Category verification system (verify_model_categories) - --verify-categories flag for mailbox compatibility check - --no-llm-fallback flag for pure ML classification - Trained model saved in src/models/calibrated/ Threshold Optimization: - Reduced default threshold from 0.75 to 0.55 - Updated all category thresholds to 0.55 - Reduces LLM fallback rate by 40% (35% -> 21%) Documentation: - SYSTEM_FLOW.html - Complete system architecture - VERIFY_CATEGORIES_FEATURE.html - Feature documentation - LABEL_TRAINING_PHASE_DETAIL.html - Calibration breakdown - FAST_ML_ONLY_WORKFLOW.html - Pure ML guide - PROJECT_STATUS_AND_NEXT_STEPS.html - Roadmap - ROOT_CAUSE_ANALYSIS.md - Bug fixes MVP Status: - 10k emails in 4 minutes, 72.7% accuracy, 0 LLM calls - LLM-driven category discovery working - Embedding-based transfer learning confirmed - All model paths verified and working
52 lines
1.5 KiB
Bash
Executable File
52 lines
1.5 KiB
Bash
Executable File
#!/bin/bash
|
|
# Train final production model with 10k emails and 0.55 thresholds
|
|
|
|
set -e
|
|
|
|
echo "=========================================="
|
|
echo "TRAINING FINAL MODEL"
|
|
echo "=========================================="
|
|
echo ""
|
|
echo "Config: 0.55 thresholds across all categories"
|
|
echo "Training set: 10,000 Enron emails"
|
|
echo "Calibration: 300 samples (3%)"
|
|
echo "Validation: 100 samples (1%)"
|
|
echo ""
|
|
|
|
# Backup existing model if it exists
|
|
if [ -f src/models/calibrated/classifier.pkl ]; then
|
|
BACKUP_FILE="src/models/calibrated/classifier.pkl.backup-$(date +%Y%m%d-%H%M%S)"
|
|
cp src/models/calibrated/classifier.pkl "$BACKUP_FILE"
|
|
echo "Backed up existing model to: $BACKUP_FILE"
|
|
fi
|
|
|
|
# Clean old results
|
|
rm -rf results_final/ final_training.log
|
|
|
|
# Activate venv
|
|
if [ -z "$VIRTUAL_ENV" ]; then
|
|
source venv/bin/activate
|
|
fi
|
|
|
|
# Train model
|
|
python -m src.cli run \
|
|
--source enron \
|
|
--limit 10000 \
|
|
--output results_final/ \
|
|
2>&1 | tee final_training.log
|
|
|
|
# Create timestamped backup of trained model
|
|
if [ -f src/models/calibrated/classifier.pkl ]; then
|
|
TRAINED_BACKUP="src/models/calibrated/classifier.pkl.backup-trained-$(date +%Y%m%d-%H%M%S)"
|
|
cp src/models/calibrated/classifier.pkl "$TRAINED_BACKUP"
|
|
echo "Created backup of trained model: $TRAINED_BACKUP"
|
|
fi
|
|
|
|
echo ""
|
|
echo "=========================================="
|
|
echo "Training complete!"
|
|
echo "Model saved to: src/models/calibrated/classifier.pkl"
|
|
echo "Backup created with timestamp"
|
|
echo "Log: final_training.log"
|
|
echo "=========================================="
|