Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,23 @@
+# Use a lightweight Python base image
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements file first (for efficient Docker caching)
+COPY requirements.txt .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application files
+COPY . .
+
+# Expose port (Flask default is 5000)
+EXPOSE 5000
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Run the Flask app
+CMD ["python", "backend_files/app.py"]

app.py

@@ -0,0 +1,65 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize Flask app
+app = Flask("Sales Forecasting")
+
+# Load the trained Sales Forecasting prediction model
+model = joblib.load("sales_forecasting_model_v1_0.joblib")
+
+# Define categorical mapping dictionary
+replaceStruct = {
+    "Product_Sugar_Content": {"Low Sugar": 1, "Regular": 2, "No Sugar": 3, "reg": 4},
+    "Product_Type": {
+        "Fruits and Vegetables": 1, "Snack Foods": 2, "Frozen Foods": 3, "Dairy": 4,
+        "Household": 5, "Baking Goods": 6, "Canned": 7, "Health and Hygiene": 8,
+        "Meat": 9, "Soft Drinks": 10, "Bread": 11, "Breads": 12, "Hard Drinks": 13,
+        "Others": 14, "Starchy Foods": 15, "Breakfast": 16, "Seafood": 17
+    },
+    "Store_Id": {"OUT001": 1, "OUT002": 2, "OUT003": 3, "OUT004": 4},
+    "Store_Size": {"Medium": 1, "High": 2, "Low": 3, "Small": 4},
+    "Store_Location_City_Type": {"Tier 1": 1, "Tier 2": 2, "Tier 3": 3},
+    "Store_Type": {"Departmental Store": 1, "Supermarket Type1": 2, "Supermarket Type2": 3, "Food Mart": 4},
+}
+
+
+# Home route
+@app.get('/')
+def home():
+    return "Welcome to the Sales Forecasting API!"
+
+# Prediction endpoint
+@app.post('/v1/sales_forecast')
+def predict_sales():
+    # Get JSON data from the request
+    user_data = request.get_json()
+
+    # Extract relevant customer features from the input data
+    sample = {
+    "Product_Sugar_Content": user_data["Product_Sugar_Content"],   # e.g. "Low Sugar"
+    "Product_Type": user_data["Product_Type"],                     # e.g. "Snack Foods"
+    "Store_Id": user_data["Store_Id"],                             # e.g. "OUT002"
+    "Store_Size": user_data["Store_Size"],                         # e.g. "Medium"
+    "Store_Location_City_Type": user_data["Store_Location_City_Type"], # e.g. "Tier 2"
+    "Store_Type": user_data["Store_Type"],                         # e.g. "Supermarket Type1"
+    "Product_Weight": user_data["Product_Weight"],                 # numeric field
+    "Product_Price": user_data["Product_Price"],                   # numeric field
+    "Store_Area": user_data["Store_Area"],                         # numeric field
+    }
+   
+    # Convert to DataFrame and apply mapping
+    input_data = pd.DataFrame([sample]).replace(replaceStruct)
+
+    # Make a Sales Forecasting prediction
+    prediction = model.predict(input_data)[0]
+
+    # Prepare readable response
+    prediction_label = f"Prediction of Weekly Sales is {prediction:.2f}"
+
+    # Return JSON
+    return jsonify({'Prediction': prediction_label})
+
+# Run the Flask app in debug mode
+if __name__ == '__main__':
+    app.run(debug=True)

requirements.txt

@@ -0,0 +1,10 @@
+numpy==2.0.2
+pandas==2.2.2
+scikit-learn==1.6.1
+matplotlib==3.10.0
+seaborn==0.13.2
+joblib==1.4.2
+xgboost==2.1.4
+requests==2.32.3
+huggingface_hub==0.30.1
+flask==3.0.3

sales_forecasting_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9dbc1f0f4b0a4ca0a91845f5d0ffe7bfbff4317687c9ea2cf8ff10e61910387
+size 51054546