Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,86 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import joblib
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report, accuracy_score
+
+MODEL_FILENAME = "insurance_churn_model.pkl"
+
+st.title("Insurance Churn Prediction App")
+
+menu = st.sidebar.radio("Navigation", ["Train Model", "Predict Churn"])
+
+if menu == "Train Model":
+    st.header("Upload Dataset and Train Model")
+    uploaded_file = st.file_uploader("Upload Insurance Churn Dataset (CSV)", type=["csv"])
+
+    if uploaded_file is not None:
+        data = pd.read_csv(uploaded_file)
+        st.subheader("Dataset Preview")
+        st.dataframe(data.head())
+
+        st.subheader("Summary Statistics")
+        st.write(data.describe())
+
+        if 'churn' in data.columns:
+            st.subheader("Churn Distribution")
+            fig, ax = plt.subplots()
+            sns.countplot(x='churn', data=data, ax=ax)
+            st.pyplot(fig)
+
+        st.subheader("Model Training")
+        target_column = st.selectbox("Select Target Column", options=data.columns, index=data.columns.get_loc('churn') if 'churn' in data.columns else 0)
+        feature_columns = st.multiselect("Select Feature Columns", options=[col for col in data.columns if col != target_column])
+
+        if feature_columns and target_column:
+            X = pd.get_dummies(data[feature_columns])
+            y = data[target_column]
+
+            X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+            model = RandomForestClassifier()
+            model.fit(X_train, y_train)
+
+            y_pred = model.predict(X_test)
+            st.subheader("Model Performance")
+            st.write("Accuracy:", accuracy_score(y_test, y_pred))
+            st.text("Classification Report:")
+            st.text(classification_report(y_test, y_pred))
+
+            joblib.dump((model, X.columns.tolist()), MODEL_FILENAME)
+            st.success(f"Model trained and saved as {MODEL_FILENAME}")
+
+elif menu == "Predict Churn":
+    st.header("Insurance Churn Predictor")
+
+    try:
+        model, feature_names = joblib.load(MODEL_FILENAME)
+        st.success("Model loaded successfully.")
+    except:
+        st.error("Model not found. Please train the model first.")
+        st.stop()
+
+    st.subheader("Enter Customer Details")
+    input_data = {}
+    for feature in feature_names:
+        input_data[feature] = st.text_input(f"{feature}", "")
+
+    if st.button("Predict Churn"):
+        try:
+            input_df = pd.DataFrame([input_data])
+            input_df = pd.get_dummies(input_df)
+
+            for col in feature_names:
+                if col not in input_df.columns:
+                    input_df[col] = 0
+            input_df = input_df[feature_names]
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+            prediction = model.predict(input_df)[0]
+            st.subheader("Prediction Result")
+            st.write(f"Churn: {'Yes' if prediction == 1 else 'No'}")
+        except Exception as e:
+            st.error(f"Error in prediction: {e}")