Create app.py

app.py

@@ -0,0 +1,84 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import os
+import gdown
+import pickle
+import joblib
+
+# ---------------------- Download and Load Ensemble Model ----------------------
+# Path to save the downloaded model
+ensemble_model_path = "ensemble_model.pkl"
+
+# Download the model if it does not exist yet
+if not os.path.exists(ensemble_model_path):
+    url = "https://drive.google.com/uc?export=download&id=1jHtHOzfhtWMyYqX_pbQJ5akYAe6ZhfhU"
+    gdown.download(url, ensemble_model_path, quiet=False)
+
+# Load the ensemble model using pickle
+with open(ensemble_model_path, "rb") as f:
+    ensemble = pickle.load(f)
+
+# ---------------------- Load Preprocessing Objects ----------------------
+# Ensure that the files onehotencoder.pkl and scaler.pkl are in the same directory.
+encoder = joblib.load("onehotencoder.pkl")
+scaler = joblib.load("scaler.pkl")
+
+# ---------------------- Set up the Streamlit App ----------------------
+st.title("Customer Churn Predictor")
+st.write("""
+This app uses a trained machine learning model to predict whether a customer is likely to churn.
+Please enter the customer details below.
+""")
+
+# ---------------------- User Inputs ----------------------
+st.header("Customer Details")
+age = st.number_input("Age", min_value=18, max_value=100, value=30)
+tenure = st.number_input("Tenure (in months)", min_value=0, max_value=120, value=12)
+usage_frequency = st.number_input("Usage Frequency", min_value=0, max_value=100, value=5)
+support_calls = st.number_input("Support Calls", min_value=0, max_value=50, value=2)
+total_spend = st.number_input("Total Spend", min_value=0.0, max_value=10000.0, value=100.0, step=10.0)
+
+# Input for categorical fields (modify options as needed for your training data)
+gender = st.selectbox("Gender", options=["Male", "Female"])
+subscription_type = st.selectbox("Subscription Type", options=["Type A", "Type B", "Type C"])
+contract_length = st.selectbox("Contract Length", options=["Monthly", "Quarterly", "Yearly"])
+
+# Create a DataFrame for the input
+input_df = pd.DataFrame({
+    "Age": [age],
+    "Tenure": [tenure],
+    "Usage Frequency": [usage_frequency],
+    "Support Calls": [support_calls],
+    "Total Spend": [total_spend],
+    "Gender": [gender],
+    "Subscription Type": [subscription_type],
+    "Contract Length": [contract_length]
+})
+
+st.write("### Input Data")
+st.write(input_df)
+
+# ---------------------- Preprocessing ----------------------
+# 1. Encode categorical features using the loaded OneHotEncoder.
+categorical_cols = ["Gender", "Subscription Type", "Contract Length"]
+encoded_cat = encoder.transform(input_df[categorical_cols])
+encoded_cat_df = pd.DataFrame(encoded_cat, columns=encoder.get_feature_names_out(categorical_cols))
+
+# 2. Drop original categorical columns and concatenate encoded features.
+input_df = input_df.drop(categorical_cols, axis=1)
+input_transformed = pd.concat([input_df.reset_index(drop=True), encoded_cat_df.reset_index(drop=True)], axis=1)
+
+# 3. Standardize numerical features using the loaded StandardScaler.
+input_scaled = scaler.transform(input_transformed)
+
+# ---------------------- Run Prediction ----------------------
+if st.button("Predict Churn"):
+    prediction = ensemble.predict(input_scaled)
+    prediction_proba = ensemble.predict_proba(input_scaled)[:, 1]
+    
+    # Interpret prediction: assuming 1 = churn, 0 = not churn
+    result = "Churned" if prediction[0] == 1 else "Not Churned"
+    st.write("### Prediction Results")
+    st.write(f"**Prediction:** {result}")
+    st.write(f"**Churn Probability:** {prediction_proba[0]:.2f}")