Update cancer.py

cancer.py

@@ -10,10 +10,13 @@ from sklearn.linear_model import LogisticRegression
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.ensemble import RandomForestClassifier
 from xgboost import XGBClassifier
+from sklearn.metrics import classification_report
 
 # Load dataset
 def load_data():
-    return pd.read_csv('cancer_prediction_data (2).csv')
+    df = pd.read_csv('cancer_prediction_data (2).csv')
+    st.write("Class distribution:", df['Cancer_Present'].value_counts())
+    return df
 
 # Data Preprocessing
 def preprocess_data(df):
@@ -43,11 +46,11 @@ def preprocess_data(df):
 # Train Model
 def train_model(x_train, y_train, preprocess, model_name):
     models = {
-        'Decision Tree': DecisionTreeClassifier(),
-        'Logistic Regression': LogisticRegression(),
+        'Decision Tree': DecisionTreeClassifier(class_weight='balanced'),
+        'Logistic Regression': LogisticRegression(class_weight='balanced'),
         'KNN': KNeighborsClassifier(),
-        'Random Forest': RandomForestClassifier(),
-        'XGBoost': XGBClassifier()
+        'Random Forest': RandomForestClassifier(class_weight='balanced'),
+        'XGBoost': XGBClassifier(scale_pos_weight=y_train.value_counts()[0] / y_train.value_counts()[1])
     }
     pipeline = Pipeline([
         ('preprocessor', preprocess),
@@ -66,10 +69,15 @@ with st.sidebar:
         df = load_data()
         (x_train, x_test, y_train, y_test), preprocess = preprocess_data(df)
         model = train_model(x_train, y_train, preprocess, model_name)
-        accuracy = model.score(x_test, y_test)
+        
+        # Evaluate the model
+        y_pred = model.predict(x_test)
+        report = classification_report(y_test, y_pred, output_dict=True)
+        accuracy = report['accuracy']
         st.session_state['trained_model'] = model
         st.session_state['x_train'] = x_train
         st.success(f"Model Trained Successfully! Accuracy: {accuracy:.2f}")
+        st.write("Classification Report:", report)
 
 st.title("🎗️ Cancer Prediction")
 
@@ -97,20 +105,10 @@ 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']
-
-        # Create DataFrame for input
         input_df = pd.DataFrame(input_data, columns=x_train.columns)
-
-        # Convert numeric inputs explicitly to float
-        for col in ['Age', 'Tumor_Size']:
-            input_df[col] = pd.to_numeric(input_df[col], errors='coerce')
-
-        # Apply preprocessing
         input_transformed = model.named_steps['preprocessor'].transform(input_df)
-
-        # Make prediction
         prediction = model.named_steps['classifier'].predict(input_transformed)
-
+        
         if prediction[0] == 1:
             st.markdown("<h3 style='color: red;'>Cancer Prediction: Positive 🟥</h3>", unsafe_allow_html=True)
             st.write("Unfortunately, the model predicts the presence of cancer. Please consult a doctor for further advice.")