Upload folder using huggingface_hub

Dockerfile

@@ -1,20 +1,16 @@
-FROM python:3.13.5-slim
+FROM python:3.9-slim
 
+# Set the working directory inside the container
 WORKDIR /app
 
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    git \
-    && rm -rf /var/lib/apt/lists/*
+# Copy all files from the current directory to the container's working directory
+COPY . .
 
-COPY requirements.txt ./
-COPY src/ ./src/
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir -r requirements.txt
 
-RUN pip3 install -r requirements.txt
-
-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"]
+# Define the command to start the application using Gunicorn with 4 worker processes
+# - `-w 4`: Uses 4 worker processes for handling requests
+# - `-b 0.0.0.0:7860`: Binds the server to port 7860 on all network interfaces
+# - `app:app`: Runs the Flask app (assuming `app.py` contains the Flask instance named `app`)
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "app:app"]

app.py

@@ -0,0 +1,86 @@
+
+# backend_files/app.py
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+
+# Initialize Flask app
+app = Flask("ExtraaLearn Lead Conversion Predictor")
+
+# Load the trained lead-conversion model
+model = joblib.load("my_model_v1_0.joblib")
+
+@app.get("/")
+def home():
+    return (
+        "Welcome to the ExtraaLearn Lead Conversion Prediction API - "
+        "Use POST /v1/lead for single prediction or POST /v1/leadbatch to upload CSV."
+    )
+
+@app.post("/v1/lead")
+def predict_lead():
+    """
+    Expects JSON body with the lead features only.
+    """
+    try:
+        lead_json = request.get_json(force=True)
+    except Exception as e:
+        return jsonify({"error": "Invalid or missing JSON body", "details": str(e)}), 400
+
+    # Features used during model training
+    expected_features = [
+        "age", "current_occupation", "first_interaction", "profile_completed",
+        "website_visits", "time_spent_on_website", "page_views_per_visit",
+        "last_activity", "EmailActivity", "PhoneActivity", "WebsiteActivity",
+        "print_media_type1", "print_media_type2", "digital_media",
+        "educational_channels", "referral"
+    ]
+
+    # Build sample
+    sample = {f: lead_json.get(f, None) for f in expected_features}
+    input_df = pd.DataFrame([sample])
+
+    try:
+        raw_pred = model.predict(input_df)[0]  # returns 0 or 1
+        label = "Converted" if raw_pred == 1 else "Not Converted"
+
+        return jsonify({"Prediction": label})
+    except Exception as e:
+        return jsonify({
+            "error": "Model prediction failed.",
+            "details": str(e),
+            "sample_input": sample
+        }), 500
+
+
+@app.post("/v1/leadbatch")
+def predict_lead_batch():
+    """
+    Expects a 'file' in form-data (CSV).
+    CSV must contain only model features.
+    """
+    if "file" not in request.files:
+        return jsonify({"error": "No file uploaded. Please attach a CSV with key 'file'."}), 400
+
+    file = request.files["file"]
+    if file.filename == "":
+        return jsonify({"error": "Empty filename. Please upload a valid CSV file."}), 400
+
+    try:
+        df = pd.read_csv(file)
+    except Exception as e:
+        return jsonify({"error": "Failed to read CSV file.", "details": str(e)}), 400
+
+    try:
+        raw_preds = model.predict(df).tolist()
+        results = ["Converted" if int(pred) == 1 else "Not Converted" for pred in raw_preds]
+        return jsonify({"Predictions": results})
+    except Exception as e:
+        return jsonify({
+            "error": "Batch prediction failed.",
+            "details": str(e)
+        }), 500
+
+
+if __name__ == "__main__":
+    app.run(debug=True, host="0.0.0.0", port=5000)

requirements.txt

@@ -1,3 +1,10 @@
-altair
-pandas
-streamlit
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+xgboost==2.1.4
+joblib==1.4.2
+Werkzeug==2.2.2
+flask==2.2.2
+gunicorn==20.1.0
+requests==2.28.1
+uvicorn[standard]