train

run_pipeline.sh

@@ -0,0 +1,45 @@
+#!/bin/bash
+
+# Default values
+TJA_DIR="datas/tja"
+MEASURE_CSV="datas/measure.csv"
+DATASET_CSV="datas/dataset.csv"
+THRESHOLD=0.1
+TRAIN_COUNT=0 # 0 means all
+MAX_EPOCHS=5000
+MODEL_PATH="model/constant_predictor.joblib"
+
+# Parse arguments
+while [[ "$#" -gt 0 ]]; do
+    case $1 in
+        --tja_dir) TJA_DIR="$2"; shift ;;
+        --measure_csv) MEASURE_CSV="$2"; shift ;;
+        --threshold) THRESHOLD="$2"; shift ;;
+        --train_count) TRAIN_COUNT="$2"; shift ;;
+        --max_epochs) MAX_EPOCHS="$2"; shift ;;
+        *) echo "Unknown parameter passed: $1"; exit 1 ;;
+    esac
+    shift
+done
+
+ITERATIONS=${ITERATIONS:-50}
+BATCH_SIZE=${BATCH_SIZE:-200}
+
+echo "--- Step 1: TJA Factorization ---"
+bun run src/factorize.ts "$TJA_DIR" "$MEASURE_CSV" "$DATASET_CSV"
+
+echo "--- Step 2: Incremental Training ---"
+python3 model/train.py --dataset "$DATASET_CSV" --model_path "$MODEL_PATH" --batch_size "$BATCH_SIZE" --iterations "$ITERATIONS"
+
+if [ $? -ne 0 ]; then
+    echo "Training failed."
+    exit 1
+fi
+
+echo "--- Step 3: Model Validation (Sample) ---"
+# Pick a random TJA from the dir to see prediction
+SAMPLE_TJA=$(ls $TJA_DIR/*.tja | head -n 1)
+echo "Testing on $SAMPLE_TJA..."
+bun run src/predict.ts "$MODEL_PATH" "$SAMPLE_TJA" "oni"
+
+echo "--- Pipeline Complete ---"