Update app.py

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 import pickle
 from sklearn.impute import SimpleImputer
 from sklearn.utils.validation import check_is_fitted
+import numpy as np
 
 # Load the trained model and preprocessing objects using pickle
 with open('random_forest_model.pkl', 'rb') as f:
@@ -83,6 +84,11 @@ def preprocess_new_data(df):
     df['state'].fillna("other", inplace=True)
     df['country'].fillna("other", inplace=True)
 
+    # Remove commas and convert numerical columns to floats
+    numerical_columns = ['Earnest Money', 'Estimated Cost', 'DocFees']
+    for col in numerical_columns:
+        df[col] = df[col].replace({',': ''}, regex=True).astype(float)
+
     df = df[['Ref No', 'Earnest Money', 'Estimated Cost', 'DocFees', 'Ownership', ' Type of Tender ', 'days_left', 'city', 'state', 'country']]
 
     imputer = SimpleImputer(strategy='median')
@@ -90,6 +96,12 @@ def preprocess_new_data(df):
 
     for column in ['Ownership', ' Type of Tender ', 'city', 'state', 'country']:
         le = label_encoders[column]
+
+        # Add 'other' to the classes if it's not already there
+        if 'other' not in le.classes_:
+            le.classes_ = np.append(le.classes_, 'other')
+
+        # Replace unseen labels with 'other'
         df[column] = df[column].apply(lambda x: x if x in le.classes_ else 'other')
         df[column] = le.transform(df[column])
 
@@ -98,6 +110,8 @@ def preprocess_new_data(df):
 
     return df
 
+
+
 def predict_new_data(new_data):
     preprocessed_data = preprocess_new_data(new_data)
     X_new = preprocessed_data.drop(columns=['Ref No'])