Upload folder using huggingface_hub

Dockerfile

@@ -1,16 +1,16 @@
-# Use a minimal base image with Python 3.9 installed
 FROM python:3.9-slim
 
-# Set the working directory inside the container to /app
+# Set the working directory inside the container
 WORKDIR /app
 
-# Copy all files from the current directory on the host to the container's /app directory
+# Copy all files from the current directory to the container's working directory
 COPY . .
 
-# Install Python dependencies listed in requirements.txt
-RUN pip3 install -r requirements.txt
+# 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 run the Streamlit app on port 8501 and make it accessible externally
-CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]
-
-# NOTE: Disable XSRF protection for easier external access in order to make batch predictions
+# 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:app"]

app.py

@@ -1,88 +1,96 @@
-import streamlit as st
-import requests
+# Flask API for SuperKart Product_Store_Sales_Total prediction (single JSON only)
+
+import os
+import joblib
+import numpy as np
 import pandas as pd
+from flask import Flask, request, jsonify
+
+APP_NAME = "SuperKart Sales Predictor"
+MODEL_FILENAME = "SuperKart_prediction_model_v1_0.joblib"
+
+CURRENT_YEAR = 2025
+VALID_PRODUCT_PREFIXES = {"FD", "NC", "DR"}  # allowed values for product_categories
+
+app = Flask(APP_NAME)
+
+# ---- Load model (ensure the .joblib is in the same run directory) ----
+model = joblib.load(MODEL_FILENAME)
+
+def derive_features(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    - Standardize 'Product_Sugar_Content' ('reg' -> 'Regular')
+    - Create 'Establishment_age' if 'Store_Establishment_Year' exists
+    - Ensure 'product_categories' exists and is one of ('FD','NC','DR'):
+        * If provided, clean & validate to those values
+        * Else, derive from first two chars of 'Product_Id'
+    """
+    df = df.copy()
+
+    # Fix sugar typo
+    if "Product_Sugar_Content" in df.columns:
+        df["Product_Sugar_Content"] = df["Product_Sugar_Content"].replace({"reg": "Regular"})
+
+    # Establishment_age
+    if "Establishment_age" not in df.columns and "Store_Establishment_Year" in df.columns:
+        df["Establishment_age"] = CURRENT_YEAR - pd.to_numeric(
+            df["Store_Establishment_Year"], errors="coerce"
+        )
 
-st.set_page_config(page_title="SuperKart Sales Prediction", page_icon="🛒", layout="centered")
-st.title("🛒 SuperKart Sales Prediction")
-
-# --- API base (set your HF Space URL here) ---
-api_url = st.text_input(
-    "API Base URL",
-    value="https://vinodcwanted-SuperKart.hf.space",
-    help="Your Flask API base (no trailing slash). Example: https://thiresh-rentalpricepredictionbackend.hf.space",
-)
-
-st.markdown("### Product Details")
-col1, col2 = st.columns(2)
-with col1:
-    product_weight = st.number_input("Product_Weight", min_value=0.0, value=12.5, step=0.1)
-    product_alloc_area = st.number_input("Product_Allocated_Area", min_value=0.0, value=0.05, step=0.001, format="%.3f")
-    product_mrp = st.number_input("Product_MRP", min_value=0.0, value=150.0, step=0.1)
-    product_id = st.text_input("Product_Id (optional)", value="", help="If provided, API derives product_categories from its prefix (FD/NC/DR).")
-with col2:
-    product_sugar_content = st.selectbox("Product_Sugar_Content", ["Low Sugar", "Regular", "No Sugar"])
-    product_type = st.selectbox(
-        "Product_Type",
-        [
-            "Frozen Foods","Dairy","Canned","Baking Goods","Health and Hygiene","Snack Foods","Meat",
-            "Household","Hard Drinks","Fruits and Vegetables","Breads","Soft Drinks","Breakfast",
-            "Others","Starchy Foods","Seafood"
-        ],
-    )
-    product_categories = st.selectbox(
-        "product_categories (optional)",
-        ["(leave blank)","FD","NC","DR"],
-        help="If left blank, API will derive from Product_Id (if provided)."
-    )
-
-st.markdown("### Store Details")
-col3, col4 = st.columns(2)
-with col3:
-    store_size = st.selectbox("Store_Size", ["Small", "Medium", "High"])
-    store_type = st.selectbox("Store_Type", ["Departmental Store", "Supermarket Type1", "Supermarket Type2", "Food Mart"])
-with col4:
-    store_city_type = st.selectbox("Store_Location_City_Type", ["Tier 1", "Tier 2", "Tier 3"])
-    store_est_year = st.number_input("Store_Establishment_Year", min_value=1900, max_value=2025, value=2005, step=1,
-                                     help="API will compute Establishment_age = 2025 - this year.")
-
-# Build payload (single JSON)
-payload = {
-    "Product_Weight": product_weight,
-    "Product_Sugar_Content": product_sugar_content,
-    "Product_Allocated_Area": product_alloc_area,
-    "Product_Type": product_type,
-    "Product_MRP": product_mrp,
-    "Store_Establishment_Year": int(store_est_year),
-    "Store_Size": store_size,
-    "Store_Location_City_Type": store_city_type,
-    "Store_Type": store_type,
-}
-
-# Optional fields
-if product_id.strip():
-    payload["Product_Id"] = product_id.strip()
-if product_categories != "(leave blank)":
-    payload["product_categories"] = product_categories
-
-st.markdown("---")
-if st.button("Predict"):
-    if not api_url.strip():
-        st.error("Please enter your API Base URL.")
+    # product_categories
+    if "product_categories" in df.columns:
+        df["product_categories"] = df["product_categories"].astype(str).str.upper().str.strip()
+        df.loc[~df["product_categories"].isin(VALID_PRODUCT_PREFIXES), "product_categories"] = pd.NA
+        # If you prefer "Other" instead of NA for invalid values, use:
+        # df.loc[~df["product_categories"].isin(VALID_PRODUCT_PREFIXES), "product_categories"] = "Other"
     else:
-        try:
-            endpoint = api_url.rstrip("/") + "/v1/sale"
-            with st.spinner("Contacting API..."):
-                resp = requests.post(endpoint, json=payload, timeout=30)
-            if resp.status_code == 200:
-                data = resp.json()
-                if "prediction" in data:
-                    st.success(f"Predicted Sales: **{data['prediction']}**")
-                else:
-                    st.warning(f"API responded without 'prediction' key:\n{data}")
-            else:
-                st.error(f"API error {resp.status_code}: {resp.text}")
-        except Exception as e:
-            st.error(f"Request failed: {e}")
-
-with st.expander("Show request payload"):
-    st.json(payload)
+        if "Product_Id" in df.columns:
+            prefix = df["Product_Id"].astype(str).str[:2].str.upper()
+            df["product_categories"] = np.where(prefix.isin(VALID_PRODUCT_PREFIXES), prefix, pd.NA)
+        else:
+            df["product_categories"] = pd.NA
+
+    return df
+
+def to_float(val):
+    try:
+        f = float(val)
+        return 0.0 if f == 0.0 else round(f, 2)
+    except Exception:
+        return None
+
+@app.get("/")
+def home():
+    return jsonify({
+        "message": f"Welcome to the {APP_NAME} API!",
+        "model_file": MODEL_FILENAME,
+        "product_categories_allowed_values": sorted(list(VALID_PRODUCT_PREFIXES))
+    })
+
+@app.post("/v1/sale")
+def predict_single():
+    """
+    Accepts a single JSON object and returns one prediction.
+    Example keys:
+      Product_Weight, Product_Sugar_Content, Product_Allocated_Area, Product_Type,
+      Product_MRP, Store_Establishment_Year (optional if Establishment_age passed),
+      Store_Size, Store_Location_City_Type, Store_Type, Product_Id (optional if product_categories passed)
+    """
+    try:
+        payload = request.get_json(force=True, silent=False)
+        if not isinstance(payload, dict):
+            return jsonify({"error": "Payload must be a single JSON object."}), 400
+
+        df = pd.DataFrame([payload])
+        df = derive_features(df)
+
+        pred = model.predict(df)[0]
+        return jsonify({"prediction": to_float(pred)})
+
+    except ValueError as ve:
+        return jsonify({"error": str(ve)}), 400
+    except Exception as e:
+        return jsonify({"error": f"Unexpected error: {str(e)}"}), 500
+
+if __name__ == "__main__":
+	app.run(debug=True)

requirements.txt

@@ -1,3 +1,11 @@
 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==2.32.3
+uvicorn[standard]
 streamlit==1.43.2