Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,18 @@
+# Dockerfile — FastAPI backend for HF Spaces (Docker SDK)
+FROM python:3.10-slim
+
+# (Optional) system deps helpful for pandas/numpy wheels
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential gcc g++ && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+
+# Install Python dependencies first (better layer caching)
+COPY requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Copy app + model
+COPY app.py /app/app.py
+COPY SuperKart_prediction_model_v1_0.joblib /app/SuperKart_prediction_model_v1_0.joblib

SuperKart_prediction_model_v1_0.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33928b47148fc610cca2d689a1bef609af0dcc231f552e86342f73508e1b3c4a
+size 559087

app.py

@@ -0,0 +1,92 @@
+import io
+import json
+import joblib
+import pandas as pd
+from fastapi import FastAPI, File, UploadFile, HTTPException
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+MODEL_PATH = "SuperKart_prediction_model_v1_0.joblib"  # <-- update if your filename differs
+
+# Expected feature order/names (must match training)
+EXPECTED_COLS = [
+    "Product_Weight",
+    "Product_Allocated_Area",
+    "Product_MRP",
+    "Store_Age",  # change to Store_Age_Years or Store_Establishment_Year if that's what you trained on
+    "Product_Sugar_Content",
+    "Product_Type",
+    "Store_Type",
+    "Store_Size",
+    "Store_Location_City_Type",
+]
+
+# ---------- App ----------
+app = FastAPI(title="SuperKart Backend", version="1.0")
+
+# CORS (allow any frontend, incl. your Streamlit Space)
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # tighten for prod
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# ---------- Load model at startup ----------
+model = None
+@app.on_event("startup")
+def load_model():
+    global model
+    model = joblib.load(MODEL_PATH)
+
+# ---------- Schemas ----------
+class Payload(BaseModel):
+    Product_Weight: float
+    Product_Allocated_Area: float
+    Product_MRP: float
+    Store_Age: int         # adjust type/name if needed
+    Product_Sugar_Content: str
+    Product_Type: str
+    Store_Type: str
+    Store_Size: int        # or str, if you trained as categorical strings
+    Store_Location_City_Type: int  # or str, adjust to your training
+
+# ---------- Helpers ----------
+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()
+
+# ---------- Endpoints ----------
+@app.get("/health")
+def health():
+    return {"status": "ok"}
+
+@app.post("/v1/salesprice")
+def predict_single(payload: Payload):
+    try:
+        df = pd.DataFrame([payload.dict()])
+        X = validate_and_order(df)
+        y = model.predict(X)
+        return {"Predicted Price": float(y[0])}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.post("/v1/salespricebatch")
+def predict_batch(file: UploadFile = File(...)):
+    try:
+        # read CSV into DataFrame
+        content = file.file.read()
+        df = pd.read_csv(io.BytesIO(content))
+        X = validate_and_order(df)
+        y = model.predict(X)
+        out = df.copy()
+        out["Predicted Price"] = y
+        # return as records (JSON)
+        return json.loads(out.to_json(orient="records"))
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.111.0
+uvicorn==0.30.3
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2