scaling commit

scripts/Scaling.py

@@ -0,0 +1,29 @@
+#This function scales numerical values
+from sklearn.preprocessing import RobustScaler
+def scaler_numeric(df, target_col=''):
+
+    #separate the nutriscore and the rest of the values to do the scaling
+    X = df.drop([target_col], axis = 1)
+    y = df[target_col]
+
+    #select only the numerical variables to do the scaling
+    X_numeric = X.select_dtypes(include=['float','int'])
+    print(f": shape of df with only numeric features={X_numeric.shape}")
+
+    #scale the numerical values and put the scaled numerical data into a dataframe
+    scaler = RobustScaler()
+    X_scaled = scaler.fit_transform(X_numeric)
+    X_scaled_df = pd.DataFrame(X_scaled, columns=X_numeric.columns, index=X_numeric.index)
+
+    #combine the scaled df with the nutriscore
+    X_non_numeric = X.select_dtypes(exclude=['float','int'])
+    X_processed = pd.concat([X_scaled_df, X_non_numeric], axis=1)
+    scaled_df = pd.concat([X_processed, y], axis=1)
+
+    # Ensure the column order is the same as the original dataframe
+    scaled_df = scaled_df[df.columns]
+
+    return scaled_df
+
+scaled_df = scaler_numeric(imputed_df, target_col='nutriscore_score')  
+scaled_df.head()