Upload 6 files

app.py

@@ -0,0 +1,74 @@
+import streamlit as st
+import numpy as np
+import tensorflow as tf
+from sklearn.preprocessing import StandardScaler, LabelEncoder, OneHotEncoder
+import pandas as pd
+import pickle
+
+# Load the trained model
+model = tf.keras.models.load_model('model.h5')
+
+# Load the encoders and scaler
+with open('label_encoder_gender.pkl', 'rb') as file:
+    label_encoder_gender = pickle.load(file)
+
+with open('onehot_encoder_geo.pkl', 'rb') as file:
+    onehot_encoder_geo = pickle.load(file)
+
+with open('scaler.pkl', 'rb') as file:
+    scaler = pickle.load(file)
+
+
+## Streamlit app
+st.title('Customer Churn Prediction')
+
+# User input
+geography = st.selectbox('Geography', onehot_encoder_geo.categories_[0])
+gender = st.selectbox('Gender', label_encoder_gender.classes_)
+age = st.slider('Age', 18, 92)
+balance = st.number_input('Balance')
+credit_score = st.number_input('Credit Score')
+estimated_salary = st.number_input('Estimated Salary')
+tenure = st.slider('Tenure', 0, 10)
+num_of_products = st.slider('Number of Products', 1, 4)
+has_cr_card = st.selectbox('Has Credit Card', [0, 1])
+is_active_member = st.selectbox('Is Active Member', [0, 1])
+
+# Prepare the input data
+input_data = pd.DataFrame({
+    'CreditScore': [credit_score],
+    'Gender': [label_encoder_gender.transform([gender])[0]],
+    'Age': [age],
+    'Tenure': [tenure],
+    'Balance': [balance],
+    'NumOfProducts': [num_of_products],
+    'HasCrCard': [has_cr_card],
+    'IsActiveMember': [is_active_member],
+    'EstimatedSalary': [estimated_salary]
+})
+
+# One-hot encode 'Geography'
+geo_encoded = onehot_encoder_geo.transform([[geography]]).toarray()
+
+# Manually create column names for the one-hot encoded geography
+geo_columns = [f'Geography_{category}' for category in onehot_encoder_geo.categories_[0]]
+
+geo_encoded_df = pd.DataFrame(geo_encoded, columns=geo_columns)
+
+# Combine one-hot encoded columns with input data
+input_data = pd.concat([input_data.reset_index(drop=True), geo_encoded_df], axis=1)
+
+# Scale the input data
+input_data_scaled = scaler.transform(input_data)
+
+# Predict churn
+prediction = model.predict(input_data_scaled)
+prediction_proba = prediction[0][0]
+
+# Display the prediction result
+st.write(f'Churn Probability: {prediction_proba:.2f}')
+
+if prediction_proba > 0.5:
+    st.write('The customer is likely to churn.')
+else:
+    st.write('The customer is not likely to churn.')

label_encoder_gender.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:360bd57973ec93035a912994862bffe697c19e212fddcd4f966fb030af35522a
+size 258

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9746b8918c0f16928c2797c35815fefd713d6f00c637b28dd8497e6f04fae782
+size 62832

onehot_encoder_geo.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f046f4d2e0236095bbec4afacb7bfa1bcde581696e52a72b8d4dc31fbf0b75a
+size 597

scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0cba24ccc97524d4e79423685898630de704289622df2aaa849e786b1bed44
+size 992