Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy dependency file first (better layer caching)
+COPY requirements.txt .
+
+# Install dependencies without cache
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Copy the rest of the code
+COPY . .
+
+# Environment variable for Hugging Face Spaces (or Docker run)
+ENV PORT=7860
+
+# Expose the port
+EXPOSE $PORT
+
+# Start the Flask app using Gunicorn with 4 worker processes
+# - "app:sales_revenue_predictor_api" → app.py has Flask instance named sales_revenue_predictor_api
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:sales_revenue_predictor_api"]

app.py

@@ -0,0 +1,124 @@
+# 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 the Flask application
+extraaLearn_predictor_api = Flask("ExtraaLearn paid customers Predictor")
+
+# Load the trained machine learning model
+model = joblib.load("extraaLearn_model_prediction_model_v1_0.joblib")
+
+# -----------------------------
+# Feature mapping (incoming JSON -> model column names)
+# -----------------------------
+feature_mapping = {
+    "id": "ID",
+    "age": "age",
+    "currentOccupation": "current_occupation",
+    "firstInteraction": "first_interaction",
+    "profileCompleted": "profile_completed",
+    "websiteVisits": "website_visits",
+    "timeSpentOnWebsite": "time_spent_on_website",
+    "pageViewsPerVisit": "page_views_per_visit",
+    "lastActivity": "last_activity",
+    "printMediaType1": "print_media_type1",
+    "printMediaType2": "print_media_type2",
+    "digitalMedia": "digital_media",
+    "educationalChannels": "educational_channels",
+    "referral": "referral",
+    "status": "status"   # (target) include if present in input; otherwise leave out at inference
+}
+
+
+# -----------------------------
+# Routes
+# -----------------------------
+
+# Health check
+@extraaLearn_predictor_api.get("/ping")
+def ping():
+    """Simple health check endpoint."""
+    return jsonify({"status": "ok"})
+
+
+# Home route
+@extraaLearn_predictor_api.get("/")
+def home():
+    """Welcome message for the API."""
+    return "Welcome to the ExtraaLearn customers Prediction API!"
+
+
+# Single prediction
+@extraaLearn_predictor_api.post("/v1/customers")
+def predict_sales_revenue():
+    """
+    Handles POST requests to predict sales revenue for a single product/store.
+    Expects a JSON payload with features.
+    """
+    # try:
+        # Get the JSON data from the request body
+    property_data = request.get_json()
+
+    # Map input keys to model feature names
+    sample = {}
+    for api_key, model_key in feature_mapping.items():
+        if api_key not in property_data:
+            return jsonify({"error": f"Missing required field: {api_key}"}), 400
+        sample[model_key] = property_data[api_key]
+
+    # Convert the extracted data into a Pandas DataFrame
+    input_data = pd.DataFrame([sample])
+
+    # Make prediction (log-transformed sales total)
+    predicted_customer = model.predict(input_data)[0]
+
+
+
+    return jsonify({"Predicted_Sales": predicted_customer})
+
+    # except Exception as e:
+    #     return jsonify({"error": str(e)}), 500
+
+
+# Batch prediction
+@extraaLearn_predictor_api.post("/v1/customersbatch")
+def predict_sales_batch():
+    """
+    Handles POST requests for batch prediction.
+    Expects a CSV file with multiple records.
+    """
+    try:
+        # Get the uploaded CSV file
+        file = request.files.get("file")
+        if file is None:
+            return jsonify({"error": "CSV file is required"}), 400
+
+        # Read the CSV file into a Pandas DataFrame
+        input_data = pd.read_csv(file)
+
+        # Make predictions
+        predicted_extraaLearn_customers_totals = model.predict(input_data).tolist()
+
+        # Convert predictions back from log scale
+        predicted_customers = [
+            round(float(np.exp(p)), 2) for p in predicted_extraaLearn_customers_totals
+        ]
+
+        # If an "id" column exists, return mapping {id: prediction}
+        if "id" in input_data.columns:
+            property_ids = input_data["id"].tolist()
+            output_dict = dict(zip(property_ids, predicted_customers))
+        else:
+            output_dict = {"predictions": predicted_customers}
+
+        return jsonify(output_dict)
+
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+# Run the Flask application in debug mode if this script is executed directly
+if __name__ == "__main__":
+    extraaLearn_predictor_api.run(host="0.0.0.0", port=7860, debug=True)

extraaLearn_model_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0180b83fd6065d069fc94df4b2b954846d086d14e9f116f7f431898ad745472a
+size 89891

requirements.txt

@@ -0,0 +1,12 @@
+gunicorn
+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
+uvicorn[standard]
+streamlit==1.43.2