Add SuperKart Flask backend deployment files

Dockerfile

@@ -0,0 +1,20 @@
+# Lightweight Python base image
+FROM python:3.10-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy dependency file first (leverages Docker layer caching)
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the backend files (app.py, superkart_model.joblib)
+COPY . .
+
+# Expose the port Flask/gunicorn will run on
+EXPOSE 7860
+
+# Start the Flask API using gunicorn (production-ready WSGI server)
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "app:superkart_api"]

app.py

@@ -0,0 +1,59 @@
+# Flask backend that serves the trained SuperKart sales-forecasting model pipeline
+
+from flask import Flask, request, jsonify
+import pandas as pd
+import joblib
+
+# Initialize the Flask application
+superkart_api = Flask(__name__)
+
+# Load the trained pipeline (preprocessing + model) once at startup
+model = joblib.load("superkart_model.joblib")
+
+# The exact feature columns (and order) the model pipeline expects
+FEATURE_COLUMNS = [
+    "Product_Weight", "Product_Sugar_Content", "Product_Allocated_Area",
+    "Product_MRP", "Store_Size", "Store_Location_City_Type", "Store_Type",
+    "Product_Id_char", "Store_Age_Years", "Product_Type_Category",
+]
+
+
+@superkart_api.get("/")
+def home():
+    """Simple health-check route."""
+    return {"message": "SuperKart Sales Forecasting API is up and running."}
+
+
+@superkart_api.post("/v1/predict")
+def predict():
+    """Online inference: predicts sales for a single record sent as JSON."""
+    data = request.get_json()
+
+    # Build a single-row DataFrame from the incoming JSON payload, in the
+    # exact column order the pipeline was trained on
+    input_df = pd.DataFrame([data], columns=FEATURE_COLUMNS)
+
+    prediction = model.predict(input_df)[0]
+
+    return jsonify({"predicted_Product_Store_Sales_Total": round(float(prediction), 2)})
+
+
+@superkart_api.post("/v1/predictbatch")
+def predict_batch():
+    """Batch inference: predicts sales for every row in an uploaded CSV file."""
+    file = request.files["file"]
+
+    # Read the uploaded CSV into a DataFrame and align its columns
+    input_df = pd.read_csv(file)
+    input_df = input_df[FEATURE_COLUMNS]
+
+    predictions = model.predict(input_df)
+
+    # Return predictions keyed by row index, as a JSON object
+    result = {str(idx): round(float(pred), 2) for idx, pred in enumerate(predictions)}
+    return jsonify(result)
+
+
+if __name__ == "__main__":
+    # Run the Flask app on all interfaces, port 7860 (matches Codespace forwarding)
+    superkart_api.run(host="0.0.0.0", port=7860)

requirements.txt

@@ -0,0 +1,7 @@
+flask==3.0.3
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+gunicorn==22.0.0

superkart_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d38e63576bd6118f1949eacb289d86ee437f4bb28893682e339a3ba2eef2f60c
+size 16231882