diff --git a/scripts/Imputing.py b/scripts/Imputing.py
index e69de29..4b6bbda 100644
--- a/scripts/Imputing.py
+++ b/scripts/Imputing.py
@@ -0,0 +1,29 @@
+
+import pandas as pd
+import numpy as np
+from sklearn.impute import KNNImputer
+#this function imputes missing values from any df with KNNImputer
+def knn_impute_numeric(df, n_neighbors=5):
+  
+  #select only the numerical variables to do the imputer
+  numeric_cols = df.select_dtypes(include=['float','int'])
+  print(f": shape of df with only numeric features={numeric_cols.shape}")
+
+  #Impute the numerical variables
+  imputer = KNNImputer(missing_values=np.nan, n_neighbors=n_neighbors, keep_empty_features=True)
+  imputed_numeric_data = imputer.fit_transform(numeric_cols)
+
+  # Create a new DataFrame with the imputed numeric data
+  imputed_numeric_df = pd.DataFrame(imputed_numeric_data, columns=numeric_cols.columns, index=df.index)
+
+  # Combine the imputed numeric columns with the non-numeric columns to ensure that we keep them 
+  non_numeric_cols = df.select_dtypes(exclude=['float','int'])
+  imputed_df = pd.concat([imputed_numeric_df, non_numeric_cols], axis=1)
+
+  # Ensure the column order is the same as the original dataframe
+  imputed_df = imputed_df[df.columns]
+
+  return imputed_df
+
+#imputed_df = knn_impute_numeric(filtered_df, n_neighbors=5)
+#imputed_df.head()  
diff --git a/scripts/Scaling.py b/scripts/Scaling.py
index e69de29..6e15393 100644
--- a/scripts/Scaling.py
+++ b/scripts/Scaling.py
@@ -0,0 +1,31 @@
+
+#This function scales numerical values
+from sklearn.preprocessing import RobustScaler
+import pandas as pd
+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()