Upload folder using huggingface_hub

Churn_model_v1.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a10e003ff70d9caf8dcd74ac5eed30883909e24a19afea6feaa8300194f9df
+size 6361812

DockerFile

@@ -0,0 +1,19 @@
+
+%%writefile backend_files/Dockerfile
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:ChurnPredictionAPI"]
+

app.py

@@ -0,0 +1,56 @@
+import pandas as pd
+import numpy as np
+import joblib
+from flask import Flask,request,jsonify
+
+ChurnPredictionAPI=Flask("Churn Prediction API")
+
+model=joblib.load('Churn_model_v1.joblib')
+
+# let us create endpoint for home
+
+@ChurnPredictionAPI.get('/')
+def home():
+  return "Welcome to the Backend API for Customer Churn Prediction"
+
+# let us create endpoint for predict data record
+
+@ChurnPredictionAPI.post('/Predict/Data')
+def predict_data():
+  data=request.get_json()
+      
+  user_input={ 'CreditScore':data['CreditScore'],
+               'Geography':data['Geography'],
+               'Age':data['Age'],
+               'Tenure':data['Tenure'],
+               'Balance':data['Balance'],
+               'NumOfProducts':data['NumOfProducts'],
+               'HasCrCard':data['HasCrCard'],
+               'IsActiveMember':data['IsActiveMember'],
+               'EstimatedSalary':data['EstimatedSalary']      
+                }
+    
+  df_user_input=pd.DataFrame([user_input])
+  prediction=model.predict_proba(df_user_input)[:,1]>0.21.tolist()[0]
+  predict_label='Churn' if prediction==1 else 'Not Churn'
+
+  return jsonify({'predict_label':predict_label})
+
+
+# let us create endpoint for predicting batch data
+
+@ChurnPredictionAPI.post('/Predict/Batch')
+def predict_batch():
+
+  file1=request.files['file']
+  df_file=pd.read_csv(file1)
+  prediction=model.predict_proba(df_file.drop(['CustomerId','Surname']),axis=1)[:,1]>0.21.tolist()
+  predictionlist=['Churn' if x==1 else 'Not Churn' for x in prediction]
+  listofids=df_file.CustomerId.values.tolist()
+  dictionary1=dict(zip(listofids,predictionlist))
+  return dictionary1
+
+if __name__=='__main__':
+  app.run(debug=True)
+
+

requirements.txt

@@ -0,0 +1,10 @@
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.28.1
+imblearn==0.13.0