Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,9 @@
+FROM python:3.9-slim
+
+WORKDIR /app
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 7860
+CMD ["gunicorn", "-w", "2", "-b", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,118 @@
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# -----------------------------
+# Load pipeline (preprocessor + model)
+# -----------------------------
+MODEL_PATH = "superkart_sales_model_v1.joblib"
+model = joblib.load(MODEL_PATH)
+
+# -----------------------------
+# Helpers: map strings -> ordinal codes (if user sends strings)
+# Your training expected numeric Store_Size & City_Type
+# -----------------------------
+SIZE_MAP = {"Small": 1, "Medium": 2, "High": 3}
+CITY_MAP = {"Tier 3": 1, "Tier 2": 2, "Tier 1": 3}
+
+# Required columns in the SAME names used during training
+EXPECTED_COLUMNS = [
+    "Product_Weight",
+    "Product_Allocated_Area",
+    "Product_MRP",
+    "Store_Establishment_Year",
+    "Store_Size",                    # numeric 1/2/3 OR strings -> mapped
+    "Store_Location_City_Type",      # numeric 1/2/3 OR strings -> mapped
+    "Product_Sugar_Content",         # categorical
+    "Product_Type",                  # categorical
+    "Store_Type"                     # categorical
+]
+
+def coerce_and_validate(df: pd.DataFrame) -> pd.DataFrame:
+    # Keep only expected cols, in order
+    df = df.copy()
+    missing = [c for c in EXPECTED_COLUMNS if c not in df.columns]
+    if missing:
+        raise ValueError(f"Missing required columns: {missing}")
+
+    df = df[EXPECTED_COLUMNS]
+
+    # Map strings for ordinal columns if needed
+    if df["Store_Size"].dtype == object:
+        df["Store_Size"] = df["Store_Size"].map(SIZE_MAP)
+    if df["Store_Location_City_Type"].dtype == object:
+        df["Store_Location_City_Type"] = df["Store_Location_City_Type"].map(CITY_MAP)
+
+    # Final sanity: ensure numeric for ordinal columns
+    for col in ["Store_Size", "Store_Location_City_Type",
+                "Product_Weight", "Product_Allocated_Area", "Product_MRP", "Store_Establishment_Year"]:
+        df[col] = pd.to_numeric(df[col], errors="coerce")
+
+    # Basic NA handling (model was trained on clean data; here we drop rows with NA)
+    if df.isna().any().any():
+        # You can switch to imputation if preferred
+        df = df.dropna(axis=0).copy()
+
+    return df
+
+# -----------------------------
+# Flask app
+# -----------------------------
+app = Flask("SuperKart Sales Predictor")
+
+@app.get("/")
+def home():
+    return "SuperKart Sales Prediction API is up!"
+
+@app.post("/v1/predict")
+def predict_single():
+    """
+    JSON body example:
+    {
+      "Product_Weight": 12.5,
+      "Product_Allocated_Area": 30,
+      "Product_MRP": 199.0,
+      "Store_Establishment_Year": 2008,
+      "Store_Size": "Medium",                // or 2
+      "Store_Location_City_Type": "Tier 1",  // or 3
+      "Product_Sugar_Content": "Regular",
+      "Product_Type": "Snack Foods",
+      "Store_Type": "Supermarket Type 1"
+    }
+    """
+    try:
+        data = request.get_json(force=True)
+        df = pd.DataFrame([data])
+        df = coerce_and_validate(df)
+        if df.empty:
+            return jsonify({"error": "Input invalid or resulted in empty rows after cleaning."}), 400
+        pred = float(model.predict(df)[0])
+        return jsonify({"Predicted_Product_Store_Sales_Total": round(pred, 2)})
+    except Exception as e:
+        return jsonify({"error": str(e)}), 400
+
+@app.post("/v1/predict_batch")
+def predict_batch():
+    """
+    Form-data upload: file=CSV
+    CSV must include the EXPECTED_COLUMNS headers.
+    """
+    try:
+        if "file" not in request.files:
+            return jsonify({"error": "Please upload a CSV file with key 'file'."}), 400
+        file = request.files["file"]
+        df = pd.read_csv(file)
+        df_clean = coerce_and_validate(df)
+        if df_clean.empty:
+            return jsonify({"error": "All rows invalid or empty after cleaning."}), 400
+        preds = model.predict(df_clean)
+        out = df.copy()
+        out["Predicted_Product_Store_Sales_Total"] = preds
+        # Return top rows to avoid huge payloads
+        return out.head(50).to_json(orient="records")
+    except Exception as e:
+        return jsonify({"error": str(e)}), 400
+
+if __name__ == "__main__":
+    # For local dev (Colab), use:
+    app.run(host="0.0.0.0", port=7860, debug=True)

requirements.txt

@@ -0,0 +1,7 @@
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+flask==2.2.2
+gunicorn==20.1.0

superkart_sales_model_v1.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d2c83997bde504b399b76634a401ee47ddf63fc108cb14f250d8e47c41bea8
+size 36093786