Update predict.py

predict.py

@@ -1,14 +1,50 @@
 import argparse
+import pandas as pd
+import joblib
 
-def main():
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--model-path', type=str, required=True, help='Path to the trained model')
-    parser.add_argument('--input-data', type=str, required=True, help='Path to input data for prediction')
-    args = parser.parse_args()
 
-    print(f"Loading model from {args.model_path}")
-    print(f"Predicting on data from {args.input_data}")
-    # Add prediction logic here
+def run_prediction():
+    input_path = "data/X_test_1st.csv"
+    output_path = "results/predictions.csv"
+    model_path = "model/best_model.pkl"
 
-if __name__ == '__main__':
-    main()
+    # Load data and model
+    df = pd.read_csv(input_path)
+    model = joblib.load(model_path)
+
+    # Preprocessing
+    features = [
+        'product_category_1',
+        'product_category_2',
+        'user_depth',
+        'age_level',
+        'city_development_index',
+        'var_1',
+        'gender'
+    ]
+
+    X = df[features]
+    X = pd.get_dummies(X, columns=['gender'], drop_first=True)
+
+    # Predict
+    predictions = model.predict(X)
+
+    # Save predictions
+    df['predictions'] = predictions
+    df.to_csv(output_path, index=False)
+    print(f"Predictions saved to {output_path}")
+
+
+    
+# def main():
+#     parser = argparse.ArgumentParser()
+#     parser.add_argument('--model-path', type=str, required=True, help='Path to the trained model')
+#     parser.add_argument('--input-data', type=str, required=True, help='Path to input data for prediction')
+#     args = parser.parse_args()
+
+#     print(f"Loading model from {args.model_path}")
+#     print(f"Predicting on data from {args.input_data}")
+#     # Add prediction logic here
+
+# if __name__ == '__main__':
+#     main()