train

model/train.py

@@ -1,19 +1,61 @@
-import json
+from sklearn.ensemble import GradientBoostingRegressor
+import pandas as pd
 import numpy as np
-import tensorflow as tf
+from sklearn.metrics import mean_absolute_error
+import joblib
+import argparse
+import os
+import sys
 
-with open('model/dataset.json', 'r') as f:
-    data = json.load(f)
+def train():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--dataset', type=str, default='datas/dataset.csv')
+    parser.add_argument('--model_path', type=str, default='model/constant_predictor.joblib')
+    parser.add_argument('--batch_size', type=int, default=200)
+    parser.add_argument('--iterations', type=int, default=10) # 200개씩 몇 번 반복할지
+    args = parser.parse_args()
 
-X = np.array([d['x'] for d in data])
-y = np.array([d['y'] for d in data])
+    if not os.path.exists(args.dataset):
+        sys.exit(1)
 
-model = tf.keras.Sequential([
-    tf.keras.layers.Dense(32, activation='relu', input_shape=(4,)),
-    tf.keras.layers.Dense(16, activation='relu'),
-    tf.keras.layers.Dense(1)
-])
-model.compile(optimizer='adam', loss='mse')
-model.fit(X, y, epochs=200, verbose=0)
-model.save('model/constant_model.keras')
-print("Model saved to model/constant_model.keras")
+    df = pd.read_csv(args.dataset)
+    
+    # 모델 로드 또는 생성
+    if os.path.exists(args.model_path):
+        print(f"Loading existing model from {args.model_path} for update...")
+        model = joblib.load(args.model_path)
+        # 기존 모델의 트리 개수를 늘려가며 학습하기 위해 n_estimators 증가
+        model.n_estimators += 50 
+        model.warm_start = True
+    else:
+        print("Creating new model...")
+        model = GradientBoostingRegressor(
+            n_estimators=100,
+            learning_rate=0.05,
+            max_depth=8,
+            warm_start=True,
+            random_state=42
+        )
+
+    for i in range(args.iterations):
+        # 랜덤하게 200개 샘플링
+        batch = df.sample(n=min(args.batch_size, len(df)))
+        X_batch = batch.drop('target', axis=1)
+        y_batch = batch['target']
+
+        model.fit(X_batch, y_batch)
+        
+        # 전체 데이터에 대한 성능 확인 (학습 경과 관찰용)
+        preds = model.predict(df.drop('target', axis=1))
+        mae = mean_absolute_error(df['target'], preds)
+        
+        print(f"Iteration {i+1}/{args.iterations} - Current Model Estimators: {model.n_estimators}, Dataset MAE: {mae:.4f}")
+        
+        # 매 반복마다 트리 조금씩 추가
+        model.n_estimators += 20
+
+    joblib.dump(model, args.model_path)
+    print(f"Model updated and saved to {args.model_path}")
+
+if __name__ == "__main__":
+    train()