Update app.py

app.py

@@ -70,6 +70,9 @@ def preprocess_car_data(df):
         df[col] = le.fit_transform(df[col])
         label_encoders[col] = le
     
+    # Handle NaN values by filling them with a placeholder (e.g., -1 for categorical columns)
+    df.fillna(-1, inplace=True)
+    
     return df, label_encoders
 
 # Calculate similarity between the classified car and entries in the CSV
@@ -85,6 +88,9 @@ def find_closest_car(df, label_encoders, make, model, year):
     feature_columns = ['make', 'model', 'year']
     df_feature_vectors = df[feature_columns].values
     
+    # Handle NaN values before calculating similarity
+    df_feature_vectors = np.nan_to_num(df_feature_vectors)  # Converts NaN to 0
+    
     # Compute cosine similarity between the classified car and all entries in the CSV
     similarity_scores = cosine_similarity(classified_car_vector, df_feature_vectors)