small changes

routes/predictions.py

@@ -242,87 +242,8 @@ def predict_fertilizer(request: FertilizerPredictionRequest):
 
 
 
-@router.get("/api/predict/{commodity}")
-def predict_commodity_price(commodity: str):
-    if DF_FULL is None:
-        raise HTTPException(status_code=500, detail="Server Error: Dataset not loaded.")
-        
-    # 2. Check if Model exists (Normalize to Upper Case)
-    target_commodity = commodity.upper()
-    
-    if target_commodity not in models:
-        raise HTTPException(status_code=404, detail=f"Model for '{commodity}' not found.")
-
-    model = models[target_commodity]
-
-    # 3. Check if we have history for this commodity
-    df_commodity = DF_FULL[DF_FULL['commodity'].str.upper() == target_commodity]
-    if df_commodity.empty:
-         raise HTTPException(status_code=404, detail="No historical data found for commodity")
-
-    # 4. Get the last known date
-    df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
-    last_known_date = df_daily.index.max()
-
-    # 5. Generate Recent History (for comparison chart)
-    start_context_date = last_known_date - pd.Timedelta(days=90)
-    df_featured = _create_features(df_daily)
-    test_df = df_featured.loc[df_featured.index >= start_context_date]
-    
-    recent_data = []
-    if not test_df.empty:
-        FEATURES = [col for col in test_df.columns if col != 'modal_price']
-        try:
-            # We try to disable feature check here too just in case
-            try:
-                model.get_booster().feature_names = None
-            except: 
-                pass
-                
-            # Use values here as well to be safe
-            input_values = test_df[FEATURES].values
-            predictions = model.predict(input_values)
-            
-            for date, actual, pred in zip(test_df.index, test_df['modal_price'], predictions):
-                recent_data.append({
-                    "date": date.strftime('%Y-%m-%d'),
-                    "actual_price": float(actual),
-                    "predicted_price": float(pred)
-                })
-        except Exception as e:
-            print(f"Warning: Could not generate history validation: {e}")
-
-    # 6. Generate Future Forecast
-    try:
-        # Calls the helper which now correctly returns a DataFrame
-        daily_forecast_df = get_market_prediction(model, DF_FULL, target_commodity, last_known_date)
-        
-        future_data = []
-        # YOUR ORIGINAL LOOP NOW WORKS BECAUSE IT'S A DATAFRAME AGAIN
-        for date, row in daily_forecast_df.iterrows():
-            future_data.append({
-                "date": date.strftime('%Y-%m-%d'),
-                "forecast_price": float(row['forecast'])
-            })
-            
-    except Exception as e:
-        print(f"Forecast Error: {e}")
-        raise HTTPException(status_code=500, detail=f"Prediction failed: {str(e)}")
-
-    # Returns the exact structure your frontend expects
-    return {
-        "commodity": commodity,
-        "recent_data": recent_data,
-        "forecast_data": future_data
-    }
-    
 # @router.get("/api/predict/{commodity}")
 # def predict_commodity_price(commodity: str):
-#     # result = get_market_prediction(commodity)
-#     # if "error" in result:
-#     #     raise HTTPException(status_code=404, detail=result["error"])
-#     # return result
-
 #     if DF_FULL is None:
 #         raise HTTPException(status_code=500, detail="Server Error: Dataset not loaded.")
         
@@ -344,7 +265,6 @@ def predict_commodity_price(commodity: str):
 #     last_known_date = df_daily.index.max()
 
 #     # 5. Generate Recent History (for comparison chart)
-#     # Get last 90 days of actual data
 #     start_context_date = last_known_date - pd.Timedelta(days=90)
 #     df_featured = _create_features(df_daily)
 #     test_df = df_featured.loc[df_featured.index >= start_context_date]
@@ -353,7 +273,16 @@ def predict_commodity_price(commodity: str):
 #     if not test_df.empty:
 #         FEATURES = [col for col in test_df.columns if col != 'modal_price']
 #         try:
-#             predictions = model.predict(test_df[FEATURES])
+#             # We try to disable feature check here too just in case
+#             try:
+#                 model.get_booster().feature_names = None
+#             except: 
+#                 pass
+                
+#             # Use values here as well to be safe
+#             input_values = test_df[FEATURES].values
+#             predictions = model.predict(input_values)
+            
 #             for date, actual, pred in zip(test_df.index, test_df['modal_price'], predictions):
 #                 recent_data.append({
 #                     "date": date.strftime('%Y-%m-%d'),
@@ -363,13 +292,13 @@ def predict_commodity_price(commodity: str):
 #         except Exception as e:
 #             print(f"Warning: Could not generate history validation: {e}")
 
-#     # 6. Generate Future Forecast (Calling the helper function correctly!)
+#     # 6. Generate Future Forecast
 #     try:
-#         # HERE IS THE FIX: We pass all 4 arguments required by the helper
-#         print(model, DF_FULL, target_commodity, last_known_date)
+#         # Calls the helper which now correctly returns a DataFrame
 #         daily_forecast_df = get_market_prediction(model, DF_FULL, target_commodity, last_known_date)
-#         print(daily_forecast_df)
+        
 #         future_data = []
+#         # YOUR ORIGINAL LOOP NOW WORKS BECAUSE IT'S A DATAFRAME AGAIN
 #         for date, row in daily_forecast_df.iterrows():
 #             future_data.append({
 #                 "date": date.strftime('%Y-%m-%d'),
@@ -380,11 +309,82 @@ def predict_commodity_price(commodity: str):
 #         print(f"Forecast Error: {e}")
 #         raise HTTPException(status_code=500, detail=f"Prediction failed: {str(e)}")
 
+#     # Returns the exact structure your frontend expects
 #     return {
 #         "commodity": commodity,
 #         "recent_data": recent_data,
 #         "forecast_data": future_data
 #     }
+    
+@router.get("/api/predict/{commodity}")
+def predict_commodity_price(commodity: str):
+    # result = get_market_prediction(commodity)
+    # if "error" in result:
+    #     raise HTTPException(status_code=404, detail=result["error"])
+    # return result
+
+    if DF_FULL is None:
+        raise HTTPException(status_code=500, detail="Server Error: Dataset not loaded.")
+        
+    # 2. Check if Model exists (Normalize to Upper Case)
+    target_commodity = commodity.upper()
+    
+    if target_commodity not in models:
+        raise HTTPException(status_code=404, detail=f"Model for '{commodity}' not found.")
+
+    model = models[target_commodity]
+
+    # 3. Check if we have history for this commodity
+    df_commodity = DF_FULL[DF_FULL['commodity'].str.upper() == target_commodity]
+    if df_commodity.empty:
+         raise HTTPException(status_code=404, detail="No historical data found for commodity")
+
+    # 4. Get the last known date
+    df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
+    last_known_date = df_daily.index.max()
+
+    # 5. Generate Recent History (for comparison chart)
+    # Get last 90 days of actual data
+    start_context_date = last_known_date - pd.Timedelta(days=90)
+    df_featured = _create_features(df_daily)
+    test_df = df_featured.loc[df_featured.index >= start_context_date]
+    
+    recent_data = []
+    if not test_df.empty:
+        FEATURES = [col for col in test_df.columns if col != 'modal_price']
+        try:
+            predictions = model.predict(test_df[FEATURES])
+            for date, actual, pred in zip(test_df.index, test_df['modal_price'], predictions):
+                recent_data.append({
+                    "date": date.strftime('%Y-%m-%d'),
+                    "actual_price": float(actual),
+                    "predicted_price": float(pred)
+                })
+        except Exception as e:
+            print(f"Warning: Could not generate history validation: {e}")
+
+    # 6. Generate Future Forecast (Calling the helper function correctly!)
+    try:
+        # HERE IS THE FIX: We pass all 4 arguments required by the helper
+        print(model, DF_FULL, target_commodity, last_known_date)
+        daily_forecast_df = get_market_prediction(model, DF_FULL, target_commodity, last_known_date)
+        print(daily_forecast_df)
+        future_data = []
+        for date, row in daily_forecast_df.iterrows():
+            future_data.append({
+                "date": date.strftime('%Y-%m-%d'),
+                "forecast_price": float(row['forecast'])
+            })
+            
+    except Exception as e:
+        print(f"Forecast Error: {e}")
+        raise HTTPException(status_code=500, detail=f"Prediction failed: {str(e)}")
+
+    return {
+        "commodity": commodity,
+        "recent_data": recent_data,
+        "forecast_data": future_data
+    }
 
 @router.post(
     "/api/marketPrice",

services/market_services.py

@@ -1,132 +1,9 @@
-# import pandas as pd
-# import numpy as np
-# import joblib
-# import os
-# from fastapi import APIRouter, HTTPException
-# from pydantic import BaseModel
-# from typing import List, Dict, Optional
-
-# # --- Load Models & Data ---
-# MODELS_DIR = 'models'
-# models = {}
-
-# feature_names = [
-#     'dayofweek', 'dayofyear', 'month', 'year', 'quarter', 'weekofyear',
-#     'price_lag_7', 'price_lag_14', 'price_lag_30', 'rolling_mean_30', 'rolling_std_30'
-# ]
-
-# # Ensure models dir exists
-# if os.path.exists(MODELS_DIR):
-#     for model_file in os.listdir(MODELS_DIR):
-#         if model_file.endswith('.pkl'):
-#             commodity_name = model_file.replace('.pkl', '').replace('_', '/')
-#             models[commodity_name] = joblib.load(os.path.join(MODELS_DIR, model_file))
-#             print(f"✅ Model loaded for: {commodity_name}")
-
-# try:
-#     # Ensure your CSV is accessible
-#     DF_FULL = pd.read_csv('final_output.csv', parse_dates=['created_at'], index_col='created_at')
-#     print("✅ Dataset loaded.")
-# except FileNotFoundError:
-#     print("❌ 'final_output.csv' not found. Predictions will fail.")
-#     DF_FULL = None 
-
-# # --- Helper Functions ---
-
-# # def _create_features(df):
-# #     df = df.copy()
-# #     df['dayofweek'] = df.index.dayofweek
-# #     df['dayofyear'] = df.index.dayofyear
-# #     df['month'] = df.index.month
-# #     df['year'] = df.index.year
-# #     df['quarter'] = df.index.quarter
-# #     df['weekofyear'] = df.index.isocalendar().week.astype(int)
-# #     # Lags and Rolling features
-# #     df['price_lag_7'] = df['modal_price'].shift(7)
-# #     df['price_lag_14'] = df['modal_price'].shift(14)
-# #     df['price_lag_30'] = df['modal_price'].shift(30)
-# #     df['rolling_mean_30'] = df['modal_price'].shift(1).rolling(window=30).mean()
-# #     df['rolling_std_30'] = df['modal_price'].shift(1).rolling(window=30).std()
-# #     return df.dropna()
-
-
-# def _create_features(df):
-#     df = df.copy()
-#     df['dayofweek'] = df.index.dayofweek
-#     df['dayofyear'] = df.index.dayofyear
-#     df['month'] = df.index.month
-#     df['year'] = df.index.year
-#     df['quarter'] = df.index.quarter
-#     df['weekofyear'] = df.index.isocalendar().week.astype(int)
-    
-#     # Lags and Rolling features
-#     df['price_lag_7'] = df['modal_price'].shift(7)
-#     df['price_lag_14'] = df['modal_price'].shift(14)
-#     df['price_lag_30'] = df['modal_price'].shift(30)
-#     df['rolling_mean_30'] = df['modal_price'].shift(1).rolling(window=30).mean()
-#     df['rolling_std_30'] = df['modal_price'].shift(1).rolling(window=30).std()
-    
-#     # REMOVE .dropna() here! We need the last row even if modal_price is NaN.
-#     return df
-
-# def get_market_prediction(model, df_full, commodity, last_known_date):
-#     """
-#     Iteratively predicts the next 180 days.
-#     """
-#     print(f"--- PREDICTION STARTED FOR {commodity} ---")
-    
-#     # --- FIX START: DISABLE FEATURE NAME CHECK ---
-#     # This tells XGBoost: "Don't check column names, just trust the order of numbers I give you"
-#     try:
-#         booster = model.get_booster()
-#         booster.feature_names = None
-#     except Exception:
-#         pass # If it fails, we proceed anyway
-#     # --- FIX END ---
-
-#     df_commodity = df_full[df_full['commodity'] == commodity]
-#     df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
-    
-#     future_dates = pd.date_range(start=last_known_date + pd.Timedelta(days=1), periods=180, freq='D')
-    
-#     future_df = pd.DataFrame(index=future_dates)
-#     future_df['modal_price'] = np.nan
-    
-#     df_extended = pd.concat([df_daily, future_df])
-    
-#     for date in future_dates:
-#         subset = df_extended.loc[:date]
-#         if len(subset) < 30: continue 
-        
-#         featured_subset = _create_features(subset)
-#         target_row = featured_subset.iloc[-1]
-        
-#         if target_row[feature_names].isna().any():
-#             continue
-
-#         # 1. Extract values as a plain Numpy Array
-#         # Reshape to (1, 11) -> 1 row, 11 features
-#         input_values = target_row[feature_names].values.reshape(1, -1)
-        
-#         # 2. Predict using the Numpy Array directly (Faster & Safer now)
-#         # Since we disabled feature_names check, this will now work.
-#         prediction = model.predict(input_values)[0]
-        
-#         df_extended.loc[date, 'modal_price'] = prediction
-    
-#     daily_forecast_df = df_extended.loc[future_dates].copy()
-#     daily_forecast_df.rename(columns={'modal_price': 'forecast'}, inplace=True)
-    
-#     print("--- PREDICTION SUCCESS ---")
-#     return daily_forecast_df
-
-
-
 import pandas as pd
 import numpy as np
 import joblib
 import os
 from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
 from typing import List, Dict, Optional
 
 # --- Load Models & Data ---
@@ -156,6 +33,23 @@ except FileNotFoundError:
 
 # --- Helper Functions ---
 
+# def _create_features(df):
+#     df = df.copy()
+#     df['dayofweek'] = df.index.dayofweek
+#     df['dayofyear'] = df.index.dayofyear
+#     df['month'] = df.index.month
+#     df['year'] = df.index.year
+#     df['quarter'] = df.index.quarter
+#     df['weekofyear'] = df.index.isocalendar().week.astype(int)
+#     # Lags and Rolling features
+#     df['price_lag_7'] = df['modal_price'].shift(7)
+#     df['price_lag_14'] = df['modal_price'].shift(14)
+#     df['price_lag_30'] = df['modal_price'].shift(30)
+#     df['rolling_mean_30'] = df['modal_price'].shift(1).rolling(window=30).mean()
+#     df['rolling_std_30'] = df['modal_price'].shift(1).rolling(window=30).std()
+#     return df.dropna()
+
+
 def _create_features(df):
     df = df.copy()
     df['dayofweek'] = df.index.dayofweek
@@ -172,24 +66,23 @@ def _create_features(df):
     df['rolling_mean_30'] = df['modal_price'].shift(1).rolling(window=30).mean()
     df['rolling_std_30'] = df['modal_price'].shift(1).rolling(window=30).std()
     
-    # CRITICAL: Do NOT dropna() here, or we lose the row we are trying to predict
+    # REMOVE .dropna() here! We need the last row even if modal_price is NaN.
     return df
 
 def get_market_prediction(model, df_full, commodity, last_known_date):
     """
     Iteratively predicts the next 180 days.
-    Returns a DataFrame so the route can iterate over it.
     """
     print(f"--- PREDICTION STARTED FOR {commodity} ---")
     
-    # --- FIX 1: DISABLE FEATURE NAME CHECK ---
-    # This prevents the "X does not have valid feature names" error
+    # --- FIX START: DISABLE FEATURE NAME CHECK ---
+    # This tells XGBoost: "Don't check column names, just trust the order of numbers I give you"
     try:
         booster = model.get_booster()
         booster.feature_names = None
     except Exception:
-        pass 
-    # -----------------------------------------
+        pass # If it fails, we proceed anyway
+    # --- FIX END ---
 
     df_commodity = df_full[df_full['commodity'] == commodity]
     df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
@@ -208,24 +101,131 @@ def get_market_prediction(model, df_full, commodity, last_known_date):
         featured_subset = _create_features(subset)
         target_row = featured_subset.iloc[-1]
         
-        # Only check if features are NaN (modal_price is allowed to be NaN)
         if target_row[feature_names].isna().any():
             continue
 
-        # --- FIX 2: Pass Pure Values ---
+        # 1. Extract values as a plain Numpy Array
         # Reshape to (1, 11) -> 1 row, 11 features
         input_values = target_row[feature_names].values.reshape(1, -1)
         
-        # Predict using the values (bypassing column name check)
+        # 2. Predict using the Numpy Array directly (Faster & Safer now)
+        # Since we disabled feature_names check, this will now work.
         prediction = model.predict(input_values)[0]
         
         df_extended.loc[date, 'modal_price'] = prediction
     
-    # Extract just the future part
     daily_forecast_df = df_extended.loc[future_dates].copy()
     daily_forecast_df.rename(columns={'modal_price': 'forecast'}, inplace=True)
     
     print("--- PREDICTION SUCCESS ---")
-    
-    # Returns DataFrame (Matches your route code)
     return daily_forecast_df
+
+
+
+# import pandas as pd
+# import numpy as np
+# import joblib
+# import os
+# from fastapi import APIRouter, HTTPException
+# from typing import List, Dict, Optional
+
+# # --- Load Models & Data ---
+# MODELS_DIR = 'models'
+# models = {}
+
+# feature_names = [
+#     'dayofweek', 'dayofyear', 'month', 'year', 'quarter', 'weekofyear',
+#     'price_lag_7', 'price_lag_14', 'price_lag_30', 'rolling_mean_30', 'rolling_std_30'
+# ]
+
+# # Ensure models dir exists
+# if os.path.exists(MODELS_DIR):
+#     for model_file in os.listdir(MODELS_DIR):
+#         if model_file.endswith('.pkl'):
+#             commodity_name = model_file.replace('.pkl', '').replace('_', '/')
+#             models[commodity_name] = joblib.load(os.path.join(MODELS_DIR, model_file))
+#             print(f"✅ Model loaded for: {commodity_name}")
+
+# try:
+#     # Ensure your CSV is accessible
+#     DF_FULL = pd.read_csv('final_output.csv', parse_dates=['created_at'], index_col='created_at')
+#     print("✅ Dataset loaded.")
+# except FileNotFoundError:
+#     print("❌ 'final_output.csv' not found. Predictions will fail.")
+#     DF_FULL = None 
+
+# # --- Helper Functions ---
+
+# def _create_features(df):
+#     df = df.copy()
+#     df['dayofweek'] = df.index.dayofweek
+#     df['dayofyear'] = df.index.dayofyear
+#     df['month'] = df.index.month
+#     df['year'] = df.index.year
+#     df['quarter'] = df.index.quarter
+#     df['weekofyear'] = df.index.isocalendar().week.astype(int)
+    
+#     # Lags and Rolling features
+#     df['price_lag_7'] = df['modal_price'].shift(7)
+#     df['price_lag_14'] = df['modal_price'].shift(14)
+#     df['price_lag_30'] = df['modal_price'].shift(30)
+#     df['rolling_mean_30'] = df['modal_price'].shift(1).rolling(window=30).mean()
+#     df['rolling_std_30'] = df['modal_price'].shift(1).rolling(window=30).std()
+    
+#     # CRITICAL: Do NOT dropna() here, or we lose the row we are trying to predict
+#     return df
+
+# def get_market_prediction(model, df_full, commodity, last_known_date):
+#     """
+#     Iteratively predicts the next 180 days.
+#     Returns a DataFrame so the route can iterate over it.
+#     """
+#     print(f"--- PREDICTION STARTED FOR {commodity} ---")
+    
+#     # --- FIX 1: DISABLE FEATURE NAME CHECK ---
+#     # This prevents the "X does not have valid feature names" error
+#     try:
+#         booster = model.get_booster()
+#         booster.feature_names = None
+#     except Exception:
+#         pass 
+#     # -----------------------------------------
+
+#     df_commodity = df_full[df_full['commodity'] == commodity]
+#     df_daily = df_commodity.groupby(df_commodity.index).agg({'modal_price': 'mean'})
+    
+#     future_dates = pd.date_range(start=last_known_date + pd.Timedelta(days=1), periods=180, freq='D')
+    
+#     future_df = pd.DataFrame(index=future_dates)
+#     future_df['modal_price'] = np.nan
+    
+#     df_extended = pd.concat([df_daily, future_df])
+    
+#     for date in future_dates:
+#         subset = df_extended.loc[:date]
+#         if len(subset) < 30: continue 
+        
+#         featured_subset = _create_features(subset)
+#         target_row = featured_subset.iloc[-1]
+        
+#         # Only check if features are NaN (modal_price is allowed to be NaN)
+#         if target_row[feature_names].isna().any():
+#             continue
+
+#         # --- FIX 2: Pass Pure Values ---
+#         # Reshape to (1, 11) -> 1 row, 11 features
+#         input_values = target_row[feature_names].values.reshape(1, -1)
+        
+#         # Predict using the values (bypassing column name check)
+#         prediction = model.predict(input_values)[0]
+        
+#         df_extended.loc[date, 'modal_price'] = prediction
+    
+#     # Extract just the future part
+#     daily_forecast_df = df_extended.loc[future_dates].copy()
+#     daily_forecast_df.rename(columns={'modal_price': 'forecast'}, inplace=True)
+    
+#     print("--- PREDICTION SUCCESS ---")
+    
+#     # Returns DataFrame (Matches your route code)
+#     return daily_forecast_df