Upload Streamlit frontend

README.md

@@ -1,10 +1,13 @@
 ---
-title: SuperKartBackend
-emoji: 📈
+title: SuperKartFrontend
+emoji: 🛒
 colorFrom: indigo
-colorTo: pink
-sdk: docker
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.43.2
+app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# SuperKartFrontend
+Streamlit UI for SuperKart Sales Prediction.

app.py

@@ -1,14 +1,15 @@
 import io
-import json
-import joblib
+import requests
 import pandas as pd
-from fastapi import FastAPI, File, UploadFile, HTTPException
-from fastapi.middleware.cors import CORSMiddleware
-from pydantic import BaseModel
+import streamlit as st
 
-MODEL_PATH = "SuperKart_prediction_model_v1_0.joblib"
+# ------------------ CONFIG ------------------
+DEFAULT_BACKEND_URL = "https://Amitgupta2982-SuperKartBackend.hf.space"  # <— change if needed
+SINGLE_EP = "/v1/salesprice"
+BATCH_EP  = "/v1/salespricebatch"
+TIMEOUT   = 60
 
-EXPECTED_COLS = [
+EXPECTED_KEYS = [
     "Product_Weight",
     "Product_Allocated_Area",
     "Product_MRP",
@@ -20,65 +21,92 @@ EXPECTED_COLS = [
     "Store_Location_City_Type",
 ]
 
-app = FastAPI(title="SuperKart Backend", version="1.0")
+def align_schema(df: pd.DataFrame) -> pd.DataFrame:
+    missing = [c for c in EXPECTED_KEYS if c not in df.columns]
+    if missing:
+        raise ValueError(f"Missing columns: {missing}")
+    return df[EXPECTED_KEYS].copy()
 
-app.add_middleware(
-    CORSMiddleware,
-    allow_origins=["*"],
-    allow_credentials=True,
-    allow_methods=["*"],
-    allow_headers=["*"],
-)
+st.set_page_config(page_title="SuperKart Sales Predictor", page_icon="🛒", layout="centered")
+st.title("🛒 SuperKart — Sales Prediction")
 
-model = None
+with st.expander("Backend settings", expanded=False):
+    backend_url = st.text_input("Backend URL (no trailing slash)", value=DEFAULT_BACKEND_URL)
+    st.caption(f"Will call: `{SINGLE_EP}` and `{BATCH_EP}` on the backend.")
+if not backend_url:
+    st.stop()
 
-@app.on_event("startup")
-def load_model():
-    global model
-    model = joblib.load(MODEL_PATH)
+st.subheader("Single Prediction")
 
-class Payload(BaseModel):
-    Product_Weight: float
-    Product_Allocated_Area: float
-    Product_MRP: float
-    Store_Age: int
-    Product_Sugar_Content: str
-    Product_Type: str
-    Store_Type: str
-    Store_Size: int
-    Store_Location_City_Type: int
+c1, c2 = st.columns(2)
+with c1:
+    product_weight = st.number_input("Product Weight", min_value=0.0, step=0.1, value=1.9)
+    product_allocated_area = st.number_input("Product Allocated Area", min_value=0.0, step=0.1, value=2.5)
+    product_mrp = st.number_input("Product MRP", min_value=0.0, step=0.1, value=70.0)
+    store_age = st.number_input("Store Age (years)", min_value=0, step=1, value=9)
 
-def validate_and_order(df: pd.DataFrame) -> pd.DataFrame:
-    missing = [c for c in EXPECTED_COLS if c not in df.columns]
-    if missing:
-        raise HTTPException(status_code=422, detail=f"Missing columns: {missing}")
-    return df[EXPECTED_COLS].copy()
+with c2:
+    product_sugar_content = st.selectbox("Product Sugar Content", ["Low Sugar", "Regular", "No Sugar"], index=1)
+    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"
+    ], index=8)
+    store_type = st.selectbox("Store Type", ["Supermarket Type1", "Supermarket Type2", "Supermarket Type3", "Grocery Store"], index=1)
+    store_size = st.selectbox("Store Size (1=Small, 2=Medium, 3=Large)", [1, 2, 3], index=0)
+    store_location_city_type = st.selectbox("City Tier (1, 2, 3)", [1, 2, 3], index=0)
 
-@app.get("/health")
-def health():
-    return {"status": "ok"}
+single_df = pd.DataFrame([{
+    "Product_Weight": product_weight,
+    "Product_Allocated_Area": product_allocated_area,
+    "Product_MRP": product_mrp,
+    "Store_Age": store_age,
+    "Product_Sugar_Content": product_sugar_content,
+    "Product_Type": product_type,
+    "Store_Type": store_type,
+    "Store_Size": store_size,
+    "Store_Location_City_Type": store_location_city_type,
+}])
 
-@app.post("/v1/salesprice")
-def predict_single(payload: Payload):
+if st.button("Predict"):
     try:
-        df = pd.DataFrame([payload.dict()])
-        X = validate_and_order(df)
-        y = model.predict(X)
-        return {"Predicted Price": float(y[0])}
+        payload = align_schema(single_df).to_dict(orient="records")[0]
+        with st.spinner("Predicting..."):
+            r = requests.post(backend_url.rstrip("/") + SINGLE_EP, json=payload, timeout=TIMEOUT)
+        if r.ok and r.headers.get("content-type","").startswith("application/json"):
+            st.success(f"Predicted Sales Price: {r.json().get('Predicted Price')}")
+        else:
+            st.error(f"Backend error {r.status_code}")
+            st.code(r.text[:1000])
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        st.error(f"Request failed: {e}")
+
+st.markdown("---")
 
-@app.post("/v1/salespricebatch")
-def predict_batch(file: UploadFile = File(...)):
+st.subheader("Batch Prediction")
+st.write("Upload a CSV with these exact columns:")
+st.code(", ".join(EXPECTED_KEYS))
+
+tmpl = pd.DataFrame(columns=EXPECTED_KEYS)
+buf = io.BytesIO()
+tmpl.to_csv(buf, index=False)
+buf.seek(0)
+st.download_button("Download CSV template", data=buf, file_name="superkart_template.csv", mime="text/csv")
+
+up = st.file_uploader("Upload CSV", type=["csv"])
+if up is not None and st.button("Predict Batch"):
     try:
-        content = file.file.read()
-        df = pd.read_csv(io.BytesIO(content))
-        X = validate_and_order(df)
-        y = model.predict(X)
-        df["Predicted Price"] = y
-        return json.loads(df.to_json(orient="records"))
-    except HTTPException:
-        raise
+        files = {"file": (up.name, up.getvalue(), "text/csv")}
+        with st.spinner("Uploading & predicting..."):
+            r = requests.post(backend_url.rstrip("/") + BATCH_EP, files=files, timeout=TIMEOUT)
+        if r.ok and r.headers.get("content-type","").startswith("application/json"):
+            out = pd.DataFrame(r.json())
+            st.success("Batch predictions ready:")
+            st.dataframe(out.head(50), use_container_width=True)
+            csv = out.to_csv(index=False).encode("utf-8")
+            st.download_button("Download predictions", data=csv, file_name="SuperKart_Predicted_Sales.csv", mime="text/csv")
+        else:
+            st.error(f"Backend error {r.status_code}")
+            st.code(r.text[:1000])
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
-
+        st.error(f"Batch request failed: {e}")

requirements.txt

@@ -1,7 +1,3 @@
-fastapi==0.111.0
-uvicorn==0.30.3
+streamlit==1.43.2
 pandas==2.2.2
-numpy==2.0.2
-scikit-learn==1.6.1
-xgboost==2.1.4
-joblib==1.4.2
+requests==2.32.3

runtime.txt

@@ -0,0 +1 @@
+python-3.10