Files
foxhunt/scripts/backtest_dqn_trials_enhanced.sh
jgrusewski 8d89fe80ff chore: Second cleanup wave - organize root directory
- Archive: 85 agent .txt files → docs/archive/agents/legacy_txt/
- Scripts: Move 110 shell scripts → scripts/ (keep deploy.sh in root)
- Models: Move 18 .safetensors → ml/models/checkpoints/training_artifacts/
- Delete: 34 directories (~33GB freed) - target/, coverage_*, test artifacts
- Build: Clean 14 build artifacts (.rlib, .o, .pid, binaries)
- Tests: Move 14 .rs files → tests/standalone/
- SQL: Move 5 files → sql/ (keep init-db*.sql for Docker)
- Wave 153: Archive to docs/archive/historical/wave153/
- Docs: Archive 9 markdown files to wave_d/reports/ and historical/

Total impact: ~34GB freed (both waves), root directory cleaned from 583 to ~40 essential files
Directory count reduced from 65 to 31 (52% reduction)
All historical data preserved in organized archive structure
2025-10-30 01:26:02 +01:00

281 lines
8.0 KiB
Bash
Executable File

#!/bin/bash
# Enhanced DQN Checkpoint Backtest Script
# Agent 132 - 2025-10-14
#
# Usage:
# ./backtest_dqn_trials_enhanced.sh --quick # Test trial 35 only (10 min)
# ./backtest_dqn_trials_enhanced.sh --sample # Test 10 trials (1 hour)
# ./backtest_dqn_trials_enhanced.sh --full # Test all 36 trials (3-6 hours)
set -e
# Configuration
RESULTS_DIR="results/dqn_backtest"
RESULTS_FILE="$RESULTS_DIR/dqn_backtest_results.json"
DATA_FILE="test_data/ES.FUT.dbn"
START_DATE="2024-01-02"
SHARPE_THRESHOLD=1.5
# Sample trials (representative distribution)
SAMPLE_TRIALS=(0 4 8 12 16 20 24 28 32 35)
# Colors for output
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
RED='\033[0;31m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color
# Create results directory
mkdir -p "$RESULTS_DIR"
# Function to backtest a single checkpoint
backtest_checkpoint() {
local trial_num=$1
local checkpoint_path="ml/tuning_checkpoints/trial_${trial_num}/checkpoint_epoch_50.safetensors"
local output_file="$RESULTS_DIR/trial_${trial_num}_backtest.json"
if [ ! -f "$checkpoint_path" ]; then
echo -e "${RED}⚠️ Checkpoint not found: $checkpoint_path${NC}"
return 1
fi
echo -e "${BLUE}🔬 Testing trial ${trial_num}...${NC}"
# Check if backtest_dqn example exists
if ! cargo run -p ml --example backtest_dqn -- --help &>/dev/null; then
echo -e "${YELLOW}⚠️ backtest_dqn example not found${NC}"
echo -e "${YELLOW} Creating placeholder result...${NC}"
# Create placeholder result (for testing infrastructure)
cat > "$output_file" << EOF
{
"trial_num": ${trial_num},
"checkpoint": "${checkpoint_path}",
"sharpe_ratio": 0.0,
"total_return": 0.0,
"max_drawdown": 0.0,
"win_rate": 0.0,
"num_trades": 0,
"status": "backtest_example_not_implemented",
"note": "Requires implementation of ml/examples/backtest_dqn.rs"
}
EOF
return 0
fi
# Run actual backtest
cargo run --release -p ml --example backtest_dqn -- \
--checkpoint "$checkpoint_path" \
--data "$DATA_FILE" \
--start-date "$START_DATE" \
--output "$output_file" 2>&1 | grep -E "(Sharpe|Return|Drawdown|Win)"
# Extract Sharpe ratio
if [ -f "$output_file" ]; then
SHARPE=$(jq -r '.sharpe_ratio // 0' "$output_file")
echo -e "${GREEN} Sharpe: ${SHARPE}${NC}"
fi
}
# Function to analyze results
analyze_results() {
echo ""
echo "=" | head -c 80
echo ""
echo -e "${BLUE}📊 ANALYZING BACKTEST RESULTS${NC}"
echo "=" | head -c 80
echo ""
if [ ! -f "$RESULTS_FILE" ]; then
echo -e "${RED}❌ Results file not found: $RESULTS_FILE${NC}"
return 1
fi
# Use Python for analysis
python3 << 'EOF'
import json
import sys
results_file = sys.argv[1]
try:
with open(results_file, 'r') as f:
results = json.load(f)
except Exception as e:
print(f"❌ Error reading results: {e}")
sys.exit(1)
if not results:
print("❌ No results found")
sys.exit(1)
# Filter valid results
valid_results = [r for r in results if r.get('sharpe_ratio', 0) > 0]
if not valid_results:
print("⚠️ No valid backtest results (all Sharpe ratios are 0)")
print("\n💡 This likely means the backtest_dqn example needs to be implemented")
print(" See: ml/examples/backtest_dqn.rs")
sys.exit(0)
# Sort by Sharpe ratio
sorted_results = sorted(valid_results, key=lambda x: x.get('sharpe_ratio', 0), reverse=True)
print(f"\n✅ Analyzed {len(valid_results)} successful backtests")
print(f"\n🏆 TOP 3 PERFORMING CHECKPOINTS:\n")
for i, result in enumerate(sorted_results[:3], 1):
trial_num = result.get('trial_num', 'unknown')
sharpe = result.get('sharpe_ratio', 0)
ret = result.get('total_return', 0)
dd = result.get('max_drawdown', 0)
win = result.get('win_rate', 0)
print(f"{i}. Trial {trial_num}")
print(f" Sharpe Ratio: {sharpe:.3f}")
print(f" Total Return: {ret:.2%}")
print(f" Max Drawdown: {dd:.2%}")
print(f" Win Rate: {win:.2%}")
print()
# Best checkpoint
best = sorted_results[0]
best_trial = best.get('trial_num')
best_sharpe = best.get('sharpe_ratio')
print("=" * 80)
print(f"✅ RECOMMENDATION: Use trial_{best_trial} checkpoint")
print(f" Sharpe: {best_sharpe:.3f}")
print(f" Path: ml/tuning_checkpoints/trial_{best_trial}/checkpoint_epoch_50.safetensors")
print("=" * 80)
# Save summary
summary = {
"best_trial": best_trial,
"best_sharpe": best_sharpe,
"top_3": [
{
"trial_num": r.get('trial_num'),
"sharpe_ratio": r.get('sharpe_ratio'),
"total_return": r.get('total_return'),
"max_drawdown": r.get('max_drawdown'),
"win_rate": r.get('win_rate')
}
for r in sorted_results[:3]
]
}
import os
summary_file = os.path.join(os.path.dirname(results_file), "summary.json")
with open(summary_file, 'w') as f:
json.dump(summary, f, indent=2)
print(f"\n💾 Summary saved to: {summary_file}")
EOF
python3 - "$RESULTS_FILE"
}
# Main execution
echo "=" | head -c 80
echo ""
echo -e "${BLUE}DQN CHECKPOINT BACKTEST UTILITY${NC}"
echo "=" | head -c 80
echo ""
MODE=${1:-}
case $MODE in
--quick)
echo -e "${GREEN}Mode: QUICK TEST (trial 35 only)${NC}"
echo -e "${GREEN}Expected time: 10 minutes${NC}"
echo ""
echo "[" > "$RESULTS_FILE"
backtest_checkpoint 35
cat "$RESULTS_DIR/trial_35_backtest.json" >> "$RESULTS_FILE"
echo "]" >> "$RESULTS_FILE"
# Check if meets threshold
SHARPE=$(jq -r '.[0].sharpe_ratio // 0' "$RESULTS_FILE")
if (( $(echo "$SHARPE > $SHARPE_THRESHOLD" | bc -l 2>/dev/null || echo 0) )); then
echo ""
echo -e "${GREEN}✅ Trial 35 exceeds threshold (Sharpe=$SHARPE > $SHARPE_THRESHOLD)${NC}"
echo -e "${GREEN} Recommendation: Use trial_35 for production${NC}"
else
echo ""
echo -e "${YELLOW}⚠️ Trial 35 below threshold (Sharpe=$SHARPE < $SHARPE_THRESHOLD)${NC}"
echo -e "${YELLOW} Recommendation: Run --sample or --full backtest${NC}"
fi
;;
--sample)
echo -e "${GREEN}Mode: SAMPLE TEST (10 trials)${NC}"
echo -e "${GREEN}Expected time: 1 hour${NC}"
echo -e "${GREEN}Trials: ${SAMPLE_TRIALS[@]}${NC}"
echo ""
echo "[" > "$RESULTS_FILE"
first=true
for trial_num in "${SAMPLE_TRIALS[@]}"; do
if [ "$first" = false ]; then
echo "," >> "$RESULTS_FILE"
fi
first=false
backtest_checkpoint "$trial_num"
cat "$RESULTS_DIR/trial_${trial_num}_backtest.json" >> "$RESULTS_FILE"
done
echo "" >> "$RESULTS_FILE"
echo "]" >> "$RESULTS_FILE"
analyze_results
;;
--full)
echo -e "${GREEN}Mode: FULL TEST (all 36 trials)${NC}"
echo -e "${GREEN}Expected time: 3-6 hours${NC}"
echo ""
echo "[" > "$RESULTS_FILE"
first=true
for trial_num in {0..35}; do
if [ "$first" = false ]; then
echo "," >> "$RESULTS_FILE"
fi
first=false
backtest_checkpoint "$trial_num"
if [ -f "$RESULTS_DIR/trial_${trial_num}_backtest.json" ]; then
cat "$RESULTS_DIR/trial_${trial_num}_backtest.json" >> "$RESULTS_FILE"
fi
done
echo "" >> "$RESULTS_FILE"
echo "]" >> "$RESULTS_FILE"
analyze_results
;;
*)
echo -e "${RED}Usage:${NC}"
echo " $0 --quick # Test trial 35 only (10 min)"
echo " $0 --sample # Test 10 trials (1 hour)"
echo " $0 --full # Test all 36 trials (3-6 hours)"
echo ""
echo -e "${YELLOW}No mode specified. Defaulting to --quick${NC}"
echo ""
exec "$0" --quick
;;
esac
echo ""
echo "=" | head -c 80
echo ""
echo -e "${GREEN}✅ BACKTEST COMPLETE${NC}"
echo "=" | head -c 80
echo ""
echo -e "Results: ${RESULTS_FILE}"
echo -e "Individual results: ${RESULTS_DIR}/trial_*_backtest.json"
echo ""