Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+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:extraalearn_api"]

app.py

@@ -0,0 +1,64 @@
+
+# Import necessary libraries
+import numpy as np
+import joblib  # For loading the serialized model
+import pandas as pd  # For data manipulation
+from flask import Flask, request, jsonify  # For creating the Flask API
+
+# Initialize Flask app with a name reflective of the project
+extraalearn_api = Flask("ExtLearn")
+
+# Load the trained lead conversion model (ensure the file name matches your saved model)
+model = joblib.load("extlearn_model.joblib")
+
+# Define a route for the home page
+@extraalearn_api.get('/')
+def home():
+    return "Welcome to the ExtraaLearn Lead Conversion Prediction System"
+
+# Define an endpoint to predict status (converted/not converted) for a lead
+@extraalearn_api.post('/v1/predict')
+def predict_conversion():
+    # Get JSON data from the request body
+    data = request.get_json()
+
+    # Extract relevant features based on the ExtraaLearn dataset
+    # These must match the exact feature names used during model training
+    sample = {
+        'age': data['age'],
+        'current_occupation': data['current_occupation'],
+        'first_interaction': data['first_interaction'],
+        'profile_completed': data['profile_completed'],
+        'website_visits': data['website_visits'],
+        'time_spent_on_website': data['time_spent_on_website'],
+        'page_views_per_visit': data['page_views_per_visit'],
+        'last_activity': data['last_activity'],
+        'print_media_type1': data['print_media_type1'],
+        'print_media_type2': data['print_media_type2'],
+        'digital_media': data['digital_media'],
+        'educational_channels': data['educational_channels'],
+        'referral': data['referral']
+    }
+
+    # Convert the extracted data into a DataFrame for the model pipeline
+    input_data = pd.DataFrame([sample])
+    
+    # Calculate the engineered feature 'age_time_interaction'
+    input_data['age_time_interaction'] = input_data['age'] * input_data['time_spent_on_website']
+
+    # Make a prediction (1 for converted, 0 for not converted)
+    prediction = int(model.predict(input_data)[0])
+
+    # Optional: Get the probability of conversion
+    probability = model.predict_proba(input_data)[0][1]
+
+    # Return the prediction and probability as a JSON response
+    return jsonify({
+        'Status_Prediction': prediction,
+        'Conversion_Probability': round(float(probability), 4),
+        'Message': 'High Potential Lead' if prediction == 1 else 'Low Potential Lead'
+    })
+
+# Run the Flask app
+if __name__ == '__main__':
+    extraalearn_api.run(debug=True)

extlearn_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f34511ea039b78cd2ab7c73c51dc8bf750612223b90c1f2c7245cacd5718cb
+size 230374

requirements.txt

@@ -0,0 +1,13 @@
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+seaborn==0.13.2
+joblib==1.4.2
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.32.3
+uvicorn[standard]
+streamlit==1.43.2