Update cancer.py

cancer.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import pandas as pd
 from sklearn.pipeline import Pipeline
-from sklearn.preprocessing import StandardScaler, OrdinalEncoder, OneHotEncoder
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
 from sklearn.impute import SimpleImputer
 from sklearn.compose import ColumnTransformer
 from sklearn.model_selection import train_test_split
@@ -31,7 +31,7 @@ def preprocess_data(df):
         ]), categorical_features)
     ], remainder='passthrough')
 
-    x= df.drop('Cancer_Present', axis=1)
+    x = df.drop('Cancer_Present', axis=1)
     y = df['Cancer_Present']
     return train_test_split(x, y, test_size=0.2, random_state=23), preprocess
 
@@ -70,9 +70,9 @@ with st.sidebar:
         # Train model
         try:
             model = train_model(x_train, y_train, preprocess, model_name)
-            accuracy = model.score(x_test, y_test)
+            accuracy = model.score(X_test, y_test)
             st.session_state['trained_model'] = model
-            st.session_state['x_train'] = x_train
+            st.session_state['x_train_columns'] = x_train.columns  # Save column names for future prediction
             st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
         except ValueError as e:
             st.error(f"Error: {e}")
@@ -104,10 +104,12 @@ input_data = [[age, tumor_size, tumor_grade, symptoms_severity, smoking_history,
 if st.button("Predict Cancer Presence"):
     if 'trained_model' in st.session_state:
         model = st.session_state['trained_model']
-        x_train = st.session_state['x_train']
+        X_train_columns = st.session_state['x_train_columns']  # Get saved column names
         
         # Prepare input data for prediction
-        input_df = pd.DataFrame(input_data, columns=x_train.columns)
+        input_df = pd.DataFrame(input_data, columns=x_train_columns)
+        
+        # Align input data with the model's expected columns
         input_transformed = model.named_steps['preprocessor'].transform(input_df)
         
         # Make prediction