Added streamlit app, dockerfile and requirements

.github/workflows/pipeline.yml

@@ -0,0 +1,36 @@
+name: SuperKart-MLOps-Pipeline
+
+on:
+  push:
+    branches: [ main ]
+
+jobs:
+  train-and-upload:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout Repo
+        uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Install Dependencies
+        run: |
+          pip install -U pip
+          pip install pandas numpy scikit-learn xgboost joblib huggingface_hub
+
+      - name: Train Model
+        env:
+          HF_DATASET_REPO: ${{ secrets.HF_DATASET_REPO }}
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: |
+          python train.py
+
+      - name: Upload Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: model-artifacts
+          path: artifacts/

Dockerfile

@@ -1,20 +1,13 @@
-FROM python:3.13.5-slim
+FROM python:3.10-slim
 
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
 
-COPY requirements.txt ./
-COPY src/ ./src/
+COPY . .
 
-RUN pip3 install -r requirements.txt
+ENV HF_MODEL_REPO="manoj112025/SuperKartSalesModel"
+EXPOSE 7860
 
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import pandas as pd
+from predict import predict_one
+
+st.set_page_config(page_title="SuperKart Sales Predictor", page_icon="🛒", layout="centered")
+st.title("🛒 SuperKart Sales Prediction App")
+
+st.markdown("Enter product & store details to predict **Product_Store_Sales_Total**")
+
+# Input UI
+inputs = {
+    "Product_Weight": st.number_input("Product Weight", min_value=0.0, value=12.0, step=0.1),
+    "Product_Sugar_Content": st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"]),
+    "Product_Allocated_Area": st.number_input("Product Allocated Area", min_value=0.0, max_value=1.0, value=0.05),
+    "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",
+        "Breakfast", "Seafood", "Starchy Foods", "Soft Drinks", "Others",
+        "Food Mart", "Departmental Store", "Supermarket Type1", "Supermarket Type2"
+    ]),
+    "Product_MRP": st.number_input("Product MRP", min_value=0.0, value=150.0),
+    "Store_Id": st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"]),
+    "Store_Establishment_Year": st.number_input("Store Establishment Year", value=2000, step=1),
+    "Store_Size": st.selectbox("Store Size", ["Small", "Medium", "High"]),
+    "Store_Location_City_Type": st.selectbox("Store City Type", ["Tier 1", "Tier 2", "Tier 3"]),
+    "Store_Type": st.selectbox("Store Type", ["Departmental Store", "Supermarket Type1", "Supermarket Type2", "Food Mart"])
+}
+
+if st.button("Predict Sales"):
+    df = pd.DataFrame([inputs])
+    try:
+        prediction = predict_one(df)
+        st.success(f"Predicted Sales: **{float(prediction[0]):,.2f}**")
+    except Exception as e:
+        st.error(f"Prediction Failed: {e}")

deployment/app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+import pandas as pd
+from predict import predict_one
+
+st.set_page_config(page_title="SuperKart Sales Predictor", page_icon="🛒", layout="centered")
+st.title("🛒 SuperKart Sales Prediction App")
+
+st.markdown("Enter product & store details to predict **Product_Store_Sales_Total**")
+
+# Input UI
+inputs = {
+    "Product_Weight": st.number_input("Product Weight", min_value=0.0, value=12.0, step=0.1),
+    "Product_Sugar_Content": st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"]),
+    "Product_Allocated_Area": st.number_input("Product Allocated Area", min_value=0.0, max_value=1.0, value=0.05),
+    "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",
+        "Breakfast", "Seafood", "Starchy Foods", "Soft Drinks", "Others",
+        "Food Mart", "Departmental Store", "Supermarket Type1", "Supermarket Type2"
+    ]),
+    "Product_MRP": st.number_input("Product MRP", min_value=0.0, value=150.0),
+    "Store_Id": st.selectbox("Store ID", ["OUT001", "OUT002", "OUT003", "OUT004"]),
+    "Store_Establishment_Year": st.number_input("Store Establishment Year", value=2000, step=1),
+    "Store_Size": st.selectbox("Store Size", ["Small", "Medium", "High"]),
+    "Store_Location_City_Type": st.selectbox("Store City Type", ["Tier 1", "Tier 2", "Tier 3"]),
+    "Store_Type": st.selectbox("Store Type", ["Departmental Store", "Supermarket Type1", "Supermarket Type2", "Food Mart"])
+}
+
+if st.button("Predict Sales"):
+    df = pd.DataFrame([inputs])
+    try:
+        prediction = predict_one(df)
+        st.success(f"Predicted Sales: **{float(prediction[0]):,.2f}**")
+    except Exception as e:
+        st.error(f"Prediction Failed: {e}")

deployment/predict.py

@@ -0,0 +1,23 @@
+import os
+import joblib
+import pandas as pd
+from huggingface_hub import hf_hub_download
+
+MODEL_REPO = os.getenv("HF_MODEL_REPO", "manoj112025/SuperKartSalesModel")
+MODEL_FILE = "model.joblib"
+PREPROCESSOR_FILE = "preprocessor.joblib"
+
+def load_artifacts():
+    model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE, repo_type="model")
+    pre_path = hf_hub_download(repo_id=MODEL_REPO, filename=PREPROCESSOR_FILE, repo_type="model")
+
+    model = joblib.load(model_path)
+    preprocessor = joblib.load(pre_path)
+
+    return preprocessor, model
+
+def predict_one(df: pd.DataFrame):
+    preprocessor, model = load_artifacts()
+    X = preprocessor.transform(df)
+    y = model.predict(X)
+    return y

deployment/push_to_hf.py

@@ -0,0 +1,30 @@
+from huggingface_hub import HfApi
+import os
+
+
+def move_files_to_hf():
+
+    api = HfApi()
+    space_id = "manoj112025/superkart-sales-app"
+
+    files = {
+        "app.py": "app.py",
+        "predict.py": "predict.py",
+        "requirements.txt": "requirements.txt",
+        "Dockerfile": "Dockerfile"
+    }
+
+    operations = []
+
+    for src, dst in files.items():
+        with open(src, "rb") as f:
+            operations.append(("add_or_update", dst, f.read()))
+
+    api.create_commit(
+        repo_id=space_id,
+        repo_type="space",
+        commit_message="Update deployment files",
+        operations=operations
+    )
+
+    print("Files uploaded to HF Space:", space_id)

deployment/requirements.txt

@@ -0,0 +1,7 @@
+streamlit==1.31.0
+pandas
+numpy
+scikit-learn
+xgboost
+joblib
+huggingface_hub

predict.py

@@ -0,0 +1,23 @@
+import os
+import joblib
+import pandas as pd
+from huggingface_hub import hf_hub_download
+
+MODEL_REPO = os.getenv("HF_MODEL_REPO", "manoj112025/SuperKartSalesModel")
+MODEL_FILE = "model.joblib"
+PREPROCESSOR_FILE = "preprocessor.joblib"
+
+def load_artifacts():
+    model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE, repo_type="model")
+    pre_path = hf_hub_download(repo_id=MODEL_REPO, filename=PREPROCESSOR_FILE, repo_type="model")
+
+    model = joblib.load(model_path)
+    preprocessor = joblib.load(pre_path)
+
+    return preprocessor, model
+
+def predict_one(df: pd.DataFrame):
+    preprocessor, model = load_artifacts()
+    X = preprocessor.transform(df)
+    y = model.predict(X)
+    return y

requirements.txt

@@ -1,3 +1,7 @@
-altair
+streamlit==1.31.0
 pandas
-streamlit
+numpy
+scikit-learn
+xgboost
+joblib
+huggingface_hub

src/streamlit_app.py

@@ -1,40 +0,0 @@
-import altair as alt
-import numpy as np
-import pandas as pd
-import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))