Upload folder using huggingface_hub

app.py

@@ -1,8 +1,59 @@
 
 import joblib
 import pandas as pd
+import numpy as np
 from flask import Flask, request, jsonify
 
+from sklearn.pipeline import Pipeline
+from sklearn.compose import ColumnTransformer
+from sklearn.base import BaseEstimator, TransformerMixin
+from sklearn.preprocessing import OneHotEncoder, StandardScaler, LabelEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.ensemble import RandomForestRegressor
+from xgboost import XGBRegressor # Included for compatibility if you switch models
+
+class FeatureEngineer(BaseEstimator, TransformerMixin):
+    def __init__(self):
+        self.le_prod = LabelEncoder()
+        self.le_store = LabelEncoder()
+
+    def fit(self, X, y=None):
+        X_copy = X.copy()
+        X_copy['Product_Id_Cd'] = X_copy['Product_Id'].apply(lambda x: x[:2])
+        X_copy['Product_Sugar_Content_Corr'] = X_copy['Product_Sugar_Content'].str.replace('reg', 'Regular', regex=True)
+        X_copy['Operation_Years'] = 2025 - X_copy['Store_Establishment_Year']
+        
+        self.le_prod.fit(X_copy['Product_Id_Cd'])
+        le_feat=['Product_Sugar_Content_Corr','Store_Size','Store_Location_City_Type','Store_Type','Product_Id_Cd']
+        for i in le_feat:
+            self.le_prod.fit(X_copy[i])
+        
+        self.le_store.fit(X_copy['Store_Id'])
+        return self
+
+    def transform(self, X):
+        X_copy = X.copy()
+        X_copy['Product_Id_Cd'] = X_copy['Product_Id'].apply(lambda x: x[:2])
+        X_copy['Product_Sugar_Content_Corr'] = X_copy['Product_Sugar_Content'].str.replace('reg', 'Regular', regex=True)
+        X_copy['Operation_Years'] = 2013 - X_copy['Store_Establishment_Year']
+        
+        try:
+            le_feat=['Product_Sugar_Content_Corr','Store_Size','Store_Location_City_Type','Store_Type','Product_Id_Cd']
+            for i in le_feat:
+                X_copy[i] = self.le_prod.transform(X_copy[i])
+        except ValueError:
+            X_copy['Product_Id_Cd'] = -1
+        
+        try:
+            X_copy['Store'] = self.le_store.transform(X_copy['Store_Id'])
+        except ValueError:
+            X_copy['Store'] = -1
+        
+        rem_feat=['Product_Id','Store_Id','Product_Sugar_Content','Product_Type', 'Store_Establishment_Year']
+        X_copy.drop(rem_feat, axis=1, inplace=True)
+        
+        return X_copy
+
 # Initialize Flask app with a name
 app = Flask("SuperKart Sales Predictor")