Update src/MonitoringModel.py

src/MonitoringModel.py

@@ -1,245 +1,245 @@
-import pandas as pd
-import numpy as np
-import joblib
-from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
-import matplotlib.pyplot as plt
-import seaborn as sns 
-import os
-
-# =========================================================
-# KONFIGURASI GLOBAL (tetap)
-# =========================================================
-DATA_FILENAME = r'C:\Dokumen\One To Many_17_10_2025\MMBTU\DASHBOARD\One To Many\disagregasi_data_spraydryer_terbaru_10_17_2025.csv'
-MODEL_FOLDER = r'C:\Dokumen\One To Many_17_10_2025\MMBTU\DASHBOARD\One To Many\MODEL CHECKPOINT FOR INVERSE MODEL'
-TARGET_COLUMN = 'GAS_MMBTU_Disaggregated'
-
-PRODUCT_LIST = [
-    'BMR BASE',
-    'CKP BASE',
-    'CKR BASE',
-    'CMR BASE',
-    'MORIGRO BASE'
-]
-
-FEATURES = [
-    'D101330TT',
-    'D102260TIC_CV',
-    'D102265TIC_PV',
-    'D102265TIC_CV',
-    'D102266TIC',
-    'D101264FTSCL'
-]
-
-PREDICTION_COLUMN = 'Prediksi_Gas'
-MODEL_FILENAME_TEMPLATE = 'model_checkpoint_xgb_{}.joblib'
-
-
-# =========================================================
-# FUNGSI UTILITAS (tetap)
-# =========================================================
-def calculate_metrics(y_true, y_pred):
-    """Menghitung R2, RMSE, dan MAE."""
-    r2 = r2_score(y_true, y_pred)
-    rmse = np.sqrt(mean_squared_error(y_true, y_pred))
-    mae = mean_absolute_error(y_true, y_pred)
-    return r2, rmse, mae
-
-
-def _load_model_for_product(model_dir, product):
-    """Load model XGBoost + poly_transformer untuk satu produk."""
-    model_path = os.path.join(model_dir, MODEL_FILENAME_TEMPLATE.format(product))
-    if not os.path.exists(model_path):
-        raise FileNotFoundError(f"File model tidak ditemukan: {model_path}")
-
-    deployment_bundle = joblib.load(model_path)
-
-    model = deployment_bundle.get('model')
-    poly_transformer = deployment_bundle.get('poly_transformer')
-    poly_feature_names = deployment_bundle.get('poly_feature_names')
-
-    if model is None or poly_transformer is None or poly_feature_names is None:
-        raise KeyError(
-            "Bundle model tidak lengkap. Pastikan berisi "
-            "'model', 'poly_transformer', dan 'poly_feature_names'."
-        )
-
-    return model, poly_transformer, poly_feature_names
-
-
-# =========================================================
-# FUNGSI UTAMA UNTUK DASHBOARD (PERBAIKAN)
-# =========================================================
-def evaluate_models_for_dashboard(
-    data_path: str = DATA_FILENAME,
-    model_dir: str = MODEL_FOLDER,
-    products: list = None,
-    features: list = None,
-    target_col: str = TARGET_COLUMN,
-    data_df=None,   # <--- NEW: bisa kirim DataFrame langsung dari Streamlit
-):
-    """
-    Fungsi utama yang melakukan evaluasi performa.
-    Mengembalikan:
-      - summary_df: DataFrame berisi [Product, R², RMSE, MAE]
-      - product_figs: dict {product_name: matplotlib.figure.Figure}
-
-    Prioritas data:
-    1) Jika data_df tidak None  -> gunakan data_df (upload dari Streamlit)
-    2) Jika data_df None        -> baca dari data_path (CSV default)
-    """
-    if products is None:
-        products = PRODUCT_LIST
-    if features is None:
-        features = FEATURES
-
-    # --- 1. Load data ---
-    if data_df is not None:
-        # Pakai dataset yang di-upload user (sudah dalam bentuk DataFrame)
-        df = data_df.copy()
-    else:
-        # Fallback: baca dari CSV path seperti sebelumnya
-        try:
-            df = pd.read_csv(data_path)
-        except FileNotFoundError:
-            print(f"[ERROR] Data file tidak ditemukan di: {data_path}")
-            return pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE']), {}
-        except Exception as e:
-            print(f"[ERROR] Gagal memuat data: {e}")
-            return pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE']), {}
-
-    # Pastikan Date_time ada dan dalam bentuk datetime (kalau mau pakai time-series)
-    if 'Date_time' in df.columns:
-        df['Date_time'] = pd.to_datetime(df['Date_time'], errors='coerce')
-
-    summary_results = []
-    plot_data_list = [] 
-    
-    # --- 2. Loop per produk ---
-    for product in products:
-        df_prod = df[df['Product'] == product].copy()
-        
-        if df_prod.empty or len(df_prod) < 2:
-            continue
-
-        missing_features = [f for f in features if f not in df_prod.columns]
-        if missing_features:
-            print(f"[WARN] Fitur hilang untuk {product}: {missing_features}")
-            continue
-
-        if 'Date_time' in df_prod.columns:
-            df_prod = df_prod.sort_values('Date_time')
-
-        X_raw = df_prod[features]
-        y_true = df_prod[target_col]
-
-        # --- 2a. Load model produk ---
-        try:
-            model, poly_transformer, poly_feature_names = _load_model_for_product(model_dir, product)
-        except Exception as e:
-            print(f"[WARN] Gagal load model untuk {product}: {e}")
-            continue
-
-        # --- 2b. Transformasi dan prediksi ---
-        try:
-            X_transformed_np = poly_transformer.transform(X_raw)
-            X_transformed_df = pd.DataFrame(
-                X_transformed_np,
-                columns=poly_feature_names,
-                index=X_raw.index
-            )
-            y_pred = model.predict(X_transformed_df)
-        except Exception as e:
-            print(f"[WARN] Gagal transform/predict untuk {product}: {e}")
-            continue
-
-        # --- 2c. Hitung metrik ---
-        r2, rmse, mae = calculate_metrics(y_true, y_pred)
-        summary_results.append({
-            'Product': product,
-            'R²': r2,
-            'RMSE': rmse,
-            'MAE': mae
-        })
-
-        # --- 2d. Siapkan data untuk plot ---
-        plot_df = pd.DataFrame({
-            'Actual': y_true.values,
-            'Predicted': y_pred,
-            'Product': product
-        })
-        plot_data_list.append(plot_df)
-
-    # --- 3. Buat summary_df ---
-    if summary_results:
-        summary_df = pd.DataFrame(summary_results)
-        summary_df['Product'] = pd.Categorical(summary_df['Product'], categories=products, ordered=True)
-        summary_df = summary_df.sort_values('Product').reset_index(drop=True)
-    else:
-        summary_df = pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE'])
-        return summary_df, {} 
-    
-    product_figs = {}
-
-    # --- 4. Generate Figures (per produk, untuk Streamlit) ---
-    if plot_data_list:
-        all_plot_data = pd.concat(plot_data_list)
-        products_evaluated = summary_df['Product'].tolist()
-
-        sns.set_style("whitegrid")
-
-        for product in products_evaluated:
-            product_data = all_plot_data[all_plot_data['Product'] == product].dropna()
-            if product_data.empty:
-                continue
-
-            metrics = summary_df[summary_df['Product'] == product].iloc[0]
-            title = (f'{product}\n'
-                     f'$R^2$: {metrics["R²"]:.3f}, '
-                     f'RMSE: {metrics["RMSE"]:.3f}, '
-                     f'MAE: {metrics["MAE"]:.3f}')
-
-            min_val = min(product_data['Actual'].min(), product_data['Predicted'].min())
-            max_val = max(product_data['Actual'].max(), product_data['Predicted'].max())
-            margin = (max_val - min_val) * 0.05
-            plot_range = [min_val - margin, max_val + margin]
-
-            # Figure tunggal per produk
-            fig_single = plt.figure(figsize=(8, 6))
-            ax_single = fig_single.add_subplot(111)
-            sns.scatterplot(
-                x='Actual',
-                y='Predicted',
-                data=product_data,
-                ax=ax_single,
-                alpha=0.6
-            )
-            ax_single.plot(plot_range, plot_range, 'r--', label='Ideal (Actual = Predicted)')
-            ax_single.set_xlim(plot_range)
-            ax_single.set_ylim(plot_range)
-            ax_single.set_title(title)
-            ax_single.set_xlabel(f'Actual {target_col}')
-            ax_single.set_ylabel(f'Predicted {target_col}')
-            ax_single.legend()
-
-            product_figs[product] = fig_single
-            plt.close(fig_single)
-
-    return summary_df, product_figs
-
-# =========================================================
-# OPSIONAL: MODE CLI (tetap)
-# =========================================================
-if __name__ == "__main__":
-    
-    print("Memulai Evaluasi Performa Model Inverse...")
-    
-    summary_df, figs = evaluate_models_for_dashboard()
-    
-    print("\n" + "="*40)
-    print("=== Ringkasan Performa Model ===")
-    print("="*40)
-    
-    if not summary_df.empty:
-        print(summary_df.to_markdown(index=False, floatfmt=".4f"))
-    else:
+import pandas as pd
+import numpy as np
+import joblib
+from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
+import matplotlib.pyplot as plt
+import seaborn as sns 
+import os
+
+# =========================================================
+# KONFIGURASI GLOBAL (tetap)
+# =========================================================
+DATA_FILENAME = r'src/disagregasi_data_spraydryer_terbaru_10_17_2025.csv'
+MODEL_FOLDER = r'src/MODEL CHECKPOINT FOR INVERSE MODEL'
+TARGET_COLUMN = 'GAS_MMBTU_Disaggregated'
+
+PRODUCT_LIST = [
+    'BMR BASE',
+    'CKP BASE',
+    'CKR BASE',
+    'CMR BASE',
+    'MORIGRO BASE'
+]
+
+FEATURES = [
+    'D101330TT',
+    'D102260TIC_CV',
+    'D102265TIC_PV',
+    'D102265TIC_CV',
+    'D102266TIC',
+    'D101264FTSCL'
+]
+
+PREDICTION_COLUMN = 'Prediksi_Gas'
+MODEL_FILENAME_TEMPLATE = 'model_checkpoint_xgb_{}.joblib'
+
+
+# =========================================================
+# FUNGSI UTILITAS (tetap)
+# =========================================================
+def calculate_metrics(y_true, y_pred):
+    """Menghitung R2, RMSE, dan MAE."""
+    r2 = r2_score(y_true, y_pred)
+    rmse = np.sqrt(mean_squared_error(y_true, y_pred))
+    mae = mean_absolute_error(y_true, y_pred)
+    return r2, rmse, mae
+
+
+def _load_model_for_product(model_dir, product):
+    """Load model XGBoost + poly_transformer untuk satu produk."""
+    model_path = os.path.join(model_dir, MODEL_FILENAME_TEMPLATE.format(product))
+    if not os.path.exists(model_path):
+        raise FileNotFoundError(f"File model tidak ditemukan: {model_path}")
+
+    deployment_bundle = joblib.load(model_path)
+
+    model = deployment_bundle.get('model')
+    poly_transformer = deployment_bundle.get('poly_transformer')
+    poly_feature_names = deployment_bundle.get('poly_feature_names')
+
+    if model is None or poly_transformer is None or poly_feature_names is None:
+        raise KeyError(
+            "Bundle model tidak lengkap. Pastikan berisi "
+            "'model', 'poly_transformer', dan 'poly_feature_names'."
+        )
+
+    return model, poly_transformer, poly_feature_names
+
+
+# =========================================================
+# FUNGSI UTAMA UNTUK DASHBOARD (PERBAIKAN)
+# =========================================================
+def evaluate_models_for_dashboard(
+    data_path: str = DATA_FILENAME,
+    model_dir: str = MODEL_FOLDER,
+    products: list = None,
+    features: list = None,
+    target_col: str = TARGET_COLUMN,
+    data_df=None,   # <--- NEW: bisa kirim DataFrame langsung dari Streamlit
+):
+    """
+    Fungsi utama yang melakukan evaluasi performa.
+    Mengembalikan:
+      - summary_df: DataFrame berisi [Product, R², RMSE, MAE]
+      - product_figs: dict {product_name: matplotlib.figure.Figure}
+
+    Prioritas data:
+    1) Jika data_df tidak None  -> gunakan data_df (upload dari Streamlit)
+    2) Jika data_df None        -> baca dari data_path (CSV default)
+    """
+    if products is None:
+        products = PRODUCT_LIST
+    if features is None:
+        features = FEATURES
+
+    # --- 1. Load data ---
+    if data_df is not None:
+        # Pakai dataset yang di-upload user (sudah dalam bentuk DataFrame)
+        df = data_df.copy()
+    else:
+        # Fallback: baca dari CSV path seperti sebelumnya
+        try:
+            df = pd.read_csv(data_path)
+        except FileNotFoundError:
+            print(f"[ERROR] Data file tidak ditemukan di: {data_path}")
+            return pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE']), {}
+        except Exception as e:
+            print(f"[ERROR] Gagal memuat data: {e}")
+            return pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE']), {}
+
+    # Pastikan Date_time ada dan dalam bentuk datetime (kalau mau pakai time-series)
+    if 'Date_time' in df.columns:
+        df['Date_time'] = pd.to_datetime(df['Date_time'], errors='coerce')
+
+    summary_results = []
+    plot_data_list = [] 
+    
+    # --- 2. Loop per produk ---
+    for product in products:
+        df_prod = df[df['Product'] == product].copy()
+        
+        if df_prod.empty or len(df_prod) < 2:
+            continue
+
+        missing_features = [f for f in features if f not in df_prod.columns]
+        if missing_features:
+            print(f"[WARN] Fitur hilang untuk {product}: {missing_features}")
+            continue
+
+        if 'Date_time' in df_prod.columns:
+            df_prod = df_prod.sort_values('Date_time')
+
+        X_raw = df_prod[features]
+        y_true = df_prod[target_col]
+
+        # --- 2a. Load model produk ---
+        try:
+            model, poly_transformer, poly_feature_names = _load_model_for_product(model_dir, product)
+        except Exception as e:
+            print(f"[WARN] Gagal load model untuk {product}: {e}")
+            continue
+
+        # --- 2b. Transformasi dan prediksi ---
+        try:
+            X_transformed_np = poly_transformer.transform(X_raw)
+            X_transformed_df = pd.DataFrame(
+                X_transformed_np,
+                columns=poly_feature_names,
+                index=X_raw.index
+            )
+            y_pred = model.predict(X_transformed_df)
+        except Exception as e:
+            print(f"[WARN] Gagal transform/predict untuk {product}: {e}")
+            continue
+
+        # --- 2c. Hitung metrik ---
+        r2, rmse, mae = calculate_metrics(y_true, y_pred)
+        summary_results.append({
+            'Product': product,
+            'R²': r2,
+            'RMSE': rmse,
+            'MAE': mae
+        })
+
+        # --- 2d. Siapkan data untuk plot ---
+        plot_df = pd.DataFrame({
+            'Actual': y_true.values,
+            'Predicted': y_pred,
+            'Product': product
+        })
+        plot_data_list.append(plot_df)
+
+    # --- 3. Buat summary_df ---
+    if summary_results:
+        summary_df = pd.DataFrame(summary_results)
+        summary_df['Product'] = pd.Categorical(summary_df['Product'], categories=products, ordered=True)
+        summary_df = summary_df.sort_values('Product').reset_index(drop=True)
+    else:
+        summary_df = pd.DataFrame(columns=['Product', 'R²', 'RMSE', 'MAE'])
+        return summary_df, {} 
+    
+    product_figs = {}
+
+    # --- 4. Generate Figures (per produk, untuk Streamlit) ---
+    if plot_data_list:
+        all_plot_data = pd.concat(plot_data_list)
+        products_evaluated = summary_df['Product'].tolist()
+
+        sns.set_style("whitegrid")
+
+        for product in products_evaluated:
+            product_data = all_plot_data[all_plot_data['Product'] == product].dropna()
+            if product_data.empty:
+                continue
+
+            metrics = summary_df[summary_df['Product'] == product].iloc[0]
+            title = (f'{product}\n'
+                     f'$R^2$: {metrics["R²"]:.3f}, '
+                     f'RMSE: {metrics["RMSE"]:.3f}, '
+                     f'MAE: {metrics["MAE"]:.3f}')
+
+            min_val = min(product_data['Actual'].min(), product_data['Predicted'].min())
+            max_val = max(product_data['Actual'].max(), product_data['Predicted'].max())
+            margin = (max_val - min_val) * 0.05
+            plot_range = [min_val - margin, max_val + margin]
+
+            # Figure tunggal per produk
+            fig_single = plt.figure(figsize=(8, 6))
+            ax_single = fig_single.add_subplot(111)
+            sns.scatterplot(
+                x='Actual',
+                y='Predicted',
+                data=product_data,
+                ax=ax_single,
+                alpha=0.6
+            )
+            ax_single.plot(plot_range, plot_range, 'r--', label='Ideal (Actual = Predicted)')
+            ax_single.set_xlim(plot_range)
+            ax_single.set_ylim(plot_range)
+            ax_single.set_title(title)
+            ax_single.set_xlabel(f'Actual {target_col}')
+            ax_single.set_ylabel(f'Predicted {target_col}')
+            ax_single.legend()
+
+            product_figs[product] = fig_single
+            plt.close(fig_single)
+
+    return summary_df, product_figs
+
+# =========================================================
+# OPSIONAL: MODE CLI (tetap)
+# =========================================================
+if __name__ == "__main__":
+    
+    print("Memulai Evaluasi Performa Model Inverse...")
+    
+    summary_df, figs = evaluate_models_for_dashboard()
+    
+    print("\n" + "="*40)
+    print("=== Ringkasan Performa Model ===")
+    print("="*40)
+    
+    if not summary_df.empty:
+        print(summary_df.to_markdown(index=False, floatfmt=".4f"))
+    else:
         print("Gagal memproses data atau model. Periksa pesan error di atas.")