Create app.py

app.py

@@ -0,0 +1,130 @@
+import streamlit as st
+import joblib
+import numpy as np
+import pandas as pd
+
+# --- 1. Load Model and Dataset for Feature Information ---
+
+@st.cache_data
+def load_data_and_model():
+    """
+    Loads the saved model and the dataset from the Excel file.
+    Using st.cache_data to avoid reloading on every interaction.
+    """
+    try:
+        # Load the pre-trained Voting Classifier model
+        model = joblib.load('voting_classifier_model.joblib')
+    except FileNotFoundError:
+        st.error("The model file 'voting_classifier_model.joblib' was not found.")
+        st.info("Please ensure the model file is in the same directory as this script.")
+        st.stop()
+
+    try:
+        # Load your specific dataset to get feature names and default values
+        df = pd.read_excel('breast-cancer.xls')
+        # Assuming the first column is 'id' and the second is 'diagnosis' (the target)
+        # The rest are the features.
+        feature_names = df.columns[2:].tolist()
+        
+        # Store the dataframe for calculating min/max/mean values for sliders
+        feature_data = df[feature_names]
+
+    except FileNotFoundError:
+        st.error("The dataset file 'breast-cancer.xls' was not found.")
+        st.info("Please ensure your Excel file is in the same directory as this script.")
+        st.stop()
+    except Exception as e:
+        st.error(f"Could not load or process the dataset file. Error: {e}")
+        st.stop()
+        
+    return model, feature_names, feature_data
+
+model, feature_names, feature_data = load_data_and_model()
+
+
+# --- 2. Streamlit App Interface ---
+
+st.set_page_config(page_title="Breast Cancer Predictor", layout="wide")
+
+# Main Title
+st.title("🔬 Breast Cancer Prediction Interface")
+st.markdown("""
+This application uses your pre-trained model to predict whether a breast tumor is **Malignant** or **Benign**. 
+The input fields below are based on the columns from your `breast-cancer.xls` file.
+""")
+
+st.write("---")
+
+
+# --- 3. User Input via Sliders ---
+
+st.sidebar.header("Input Tumor Features")
+st.sidebar.markdown("Use the sliders to provide the feature values.")
+
+# Dictionary to hold the user's input
+input_features = {}
+
+# Create sliders for all features based on your Excel file
+for feature in feature_names:
+    # Set min/max/default values from the actual data for better usability
+    min_val = float(feature_data[feature].min())
+    max_val = float(feature_data[feature].max())
+    mean_val = float(feature_data[feature].mean())
+
+    # Create a slider for each feature
+    input_features[feature] = st.sidebar.slider(
+        label=f"{feature.replace('_', ' ').title()}",
+        min_value=min_val,
+        max_value=max_val,
+        value=mean_val,
+        key=f"slider_{feature}"
+    )
+
+st.sidebar.write("---")
+
+
+# --- 4. Prediction Logic ---
+
+# Convert the dictionary of input features into a NumPy array
+# The order of features must match the order in the feature_names list
+input_data = np.array([list(input_features.values())])
+
+# Main section for displaying inputs and results
+st.header("Prediction Results")
+col1, col2 = st.columns([2, 1])
+
+with col1:
+    st.subheader("Current Input Values")
+    st.json(input_features)
+
+# "Predict" button
+if st.button("✨ Predict Diagnosis", key="predict_button"):
+    try:
+        # Make prediction. This returns the string label directly (e.g., 'M' or 'B').
+        prediction_label = model.predict(input_data)[0]
+
+        # Get prediction probabilities. The order corresponds to model.classes_
+        prediction_proba = model.predict_proba(input_data)[0]
+
+        with col2:
+            st.subheader("Diagnosis")
+            # Display the predicted label directly
+            # We check for 'M' or 'B' as is common in this dataset
+            if prediction_label.upper() == 'M':
+                st.error("Predicted Diagnosis: **Malignant**")
+            else:
+                st.success("Predicted Diagnosis: **Benign**")
+
+            st.subheader("Prediction Confidence")
+            # Get the class labels from the model itself to ensure correct order
+            class_labels = list(model.classes_)
+            
+            # Display probabilities for each class using the model's class order
+            for i, label in enumerate(class_labels):
+                display_label = "Malignant" if label.upper() == 'M' else "Benign"
+                st.write(f"Confidence for **{display_label}**: `{prediction_proba[i]:.2%}`")
+
+    except Exception as e:
+        st.error(f"An error occurred during prediction: {e}")
+
+st.write("---")