import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler import streamlit as st from src.model import LogisticRegression st.title("Customer Chrun Classifier") st.divider() file_path = r"telco_customer_churn.csv" # 1. Load CSV df = pd.read_csv(file_path) df["TotalCharges"] = pd.to_numeric(df["TotalCharges"], errors="coerce") df = df.dropna() df["target"] = (df["Churn"] == "Yes").astype(int) # 2. Feature selection UI numeric_cols = ["tenure", "MonthlyCharges", "TotalCharges", "SeniorCitizen"] selected = st.multiselect( "Select Numeric Features:", options=numeric_cols, default=numeric_cols ) if selected: X = df[selected].values y = df["target"].values X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.2, random_state=42 ) scaler = StandardScaler() X_train_scaled = scaler.fit_transform(X_train) X_test_scaled = scaler.transform(X_test) # 3. Train using YOUR class m, n = X_train_scaled.shape model = LogisticRegression(X_train_scaled, y_train, m, n) model.gradient_descent(alpha=0.1, epochs=500) # 4. Predict probs = model.predict(X_test_scaled) preds = (probs >= 0.5).astype(int) acc = np.mean(preds == y_test) # 5. Display st.metric("Model Test Accuracy", f"{acc * 100:.2f}%") st.write( "**Learned Weights:**", pd.DataFrame({"Feature": selected, "Weight": model.w}), )