Upload folder using huggingface_hub

app.py

@@ -3,33 +3,34 @@ import pandas as pd
 from flask import Flask, request, jsonify
 
 # Initialize Flask app with a name
-churn_predictor_api = Flask("Customer Churn Predictor")
+app = Flask("Telecom Customer Churn Predictor")
 
 # Load the trained churn prediction model
 model = joblib.load("churn_prediction_model_v1_0.joblib")
 
 # Define a route for the home page
-@churn_predictor_api.get('/')
+@app.get('/')
 def home():
-    return "Welcome to the Customer Churn Prediction API!"
+    return "Welcome to the Telecom Customer Churn Prediction API"
 
 # Define an endpoint to predict churn for a single customer
-@churn_predictor_api.post('/v1/customer')
+@app.post('/v1/customer')
 def predict_churn():
     # Get JSON data from the request
     customer_data = request.get_json()
 
     # Extract relevant customer features from the input data
     sample = {
-        'CreditScore': customer_data['CreditScore'],
-        'Geography': customer_data['Geography'],
-        'Age': customer_data['Age'],
-        'Tenure': customer_data['Tenure'],
-        'Balance': customer_data['Balance'],
-        'NumOfProducts': customer_data['NumOfProducts'],
-        'HasCrCard': customer_data['HasCrCard'],
-        'IsActiveMember': customer_data['IsActiveMember'],
-        'EstimatedSalary': customer_data['EstimatedSalary']
+        'SeniorCitizen': customer_data['SeniorCitizen'],
+        'Partner': customer_data['Partner'],
+        'Dependents': customer_data['Dependents'],
+        'tenure': customer_data['tenure'],
+        'PhoneService': customer_data['PhoneService'],
+        'InternetService': customer_data['InternetService'],
+        'Contract': customer_data['Contract'],
+        'PaymentMethod': customer_data['PaymentMethod'],
+        'MonthlyCharges': customer_data['MonthlyCharges'],
+        'TotalCharges': customer_data['TotalCharges']
     }
 
     # Convert the extracted data into a DataFrame
@@ -45,7 +46,7 @@ def predict_churn():
     return jsonify({'Prediction': prediction_label})
 
 # Define an endpoint to predict churn for a batch of customers
-@churn_predictor_api.post('/v1/customerbatch')
+@app.post('/v1/customerbatch')
 def predict_churn_batch():
     # Get the uploaded CSV file from the request
     file = request.files['file']
@@ -57,10 +58,10 @@ def predict_churn_batch():
     predictions = [
         'Churn' if x == 1
         else "Not Churn"
-        for x in model.predict(input_data.drop("CustomerId",axis=1)).tolist()
+        for x in model.predict(input_data.drop("customerID",axis=1)).tolist()
     ]
 
-    cust_id_list = input_data.CustomerId.values.tolist()
+    cust_id_list = input_data.customerID.values.tolist()
     output_dict = dict(zip(cust_id_list, predictions))
 
     return output_dict

requirements.txt

@@ -8,4 +8,3 @@ flask==2.2.2
 gunicorn==20.1.0
 requests==2.28.1
 uvicorn[standard]
-streamlit==1.43.2