Update preprocess.py

preprocess.py

@@ -2,6 +2,7 @@ import argparse
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MinMaxScaler
+from sklearn.preprocessing import LabelEncoder
 import os
 
 
@@ -35,6 +36,14 @@ def parse(csv_path):
     X.loc[:,"hour"] = pd.to_datetime(X['DateTime'], errors='coerce').dt.hour.values
     X = X.drop('DateTime', axis=1)
 
+    # Product label to number
+    le = LabelEncoder()
+    X.loc[:,"product"] = le.fit_transform(X["product"])
+    # Gender label to number
+    X['gender'] = X['gender'].map({'Female': 1,
+                                   'Male': 0,
+                                   'M': 0})
+    
     
     # Normalize numerical features
     scaler = MinMaxScaler()