Add Streamlit UI

Dockerfile

@@ -2,9 +2,9 @@ FROM python:3.9
 
 WORKDIR /app
 
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+COPY requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
-COPY . .
+COPY . /app
 
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["streamlit", "run", "streamlit_app.py", "--server.port=7860", "--server.address=0.0.0.0"]

requirements.txt

@@ -5,3 +5,4 @@ joblib
 pandas
 numpy
 scikit-learn
+streamlit

streamlit_app.py

@@ -1,18 +1,41 @@
 import streamlit as st
-import requests
+import joblib
+import pandas as pd
+from huggingface_hub import hf_hub_download
 
-st.title("Supermarket Sales Forecast")
+# Load model from your HF repo
+model_file = hf_hub_download(repo_id="danialsiddiqui/task6-model", filename="model.joblib")
+model_data = joblib.load(model_file)
+model = model_data["model"]
+columns = model_data["columns"]
 
-# Input sliders or number inputs
-feature1 = st.number_input("Feature 1")
-feature2 = st.number_input("Feature 2")
-feature3 = st.number_input("Feature 3")
+st.title("Supermarket Revenue Prediction")
+
+# Input fields
+gender = st.selectbox("Gender", ["Male", "Female"])
+customer_type = st.selectbox("Customer Type", ["Member", "Normal"])
+product_line = st.selectbox("Product Line", ["Beverages", "Food", "Health and beauty", "Fashion", "Electronics", "Home and lifestyle", "Sports and travel"])
+unit_price = st.number_input("Unit Price", min_value=0.0, value=10.0)
+quantity = st.number_input("Quantity", min_value=1, value=1)
+tax_5 = st.number_input("Tax 5%", min_value=0.0, value=0.0)
 
 if st.button("Predict"):
-    data = {
-        "feature1": feature1,
-        "feature2": feature2,
-        "feature3": feature3
-    }
-    response = requests.post("https://YOUR_DEPLOYED_API_URL/predict", json=data)
-    st.write("Prediction:", response.json()["prediction"])
+    # Create dataframe
+    df = pd.DataFrame([{
+        "gender": gender,
+        "customer_type": customer_type,
+        "product_line": product_line,
+        "unit_price": unit_price,
+        "quantity": quantity,
+        "tax_5": tax_5
+    }])
+    
+    # One-hot encode same as training
+    df = pd.get_dummies(df)
+    for col in columns:
+        if col not in df.columns:
+            df[col] = 0
+    df = df[columns]
+    
+    prediction = model.predict(df)[0]
+    st.success(f"Predicted Revenue: {prediction:.2f}")