Backend API's, requirements and Dockerfile added

api_flask/Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.10-slim
+
+ENV PYTHONUNBUFFERED=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PORT=7860
+
+WORKDIR /app
+
+# Install system deps
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY api_flask/requirements.txt /app/requirements.txt
+RUN pip install --no-cache-dir -r /app/requirements.txt
+
+# Copy entire repository to container
+COPY . /app
+
+EXPOSE 7860
+
+# Use gunicorn as production server
+CMD ["bash", "-lc", "gunicorn -w 2 -b 0.0.0.0:${PORT} api_flask.app:app"]

api_flask/app.py

@@ -0,0 +1,75 @@
+import os
+import json
+import joblib
+import pandas as pd
+from pathlib import Path
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+
+app = Flask(__name__)
+CORS(app)
+
+# Model directory in HF Space (root/models/)
+MODEL_PATH = Path("models") / "best_model.joblib"
+
+if MODEL_PATH.exists():
+    PIPELINE = joblib.load(MODEL_PATH)
+else:
+    PIPELINE = None
+
+
+@app.get("/")
+def root():
+    return jsonify({
+        "status": "ok",
+        "message": "ExtraaLearn Lead Conversion API",
+        "model_loaded": PIPELINE is not None
+    })
+
+
+@app.post("/predict")
+def predict_single():
+    """Predict for a single JSON input"""
+    if PIPELINE is None:
+        return jsonify({"error": "Model not loaded"}), 503
+
+    payload = request.get_json(force=True)
+    X = pd.DataFrame([payload])
+
+    proba = float(PIPELINE.predict_proba(X)[:, 1][0])
+    pred = int(proba >= 0.5)
+
+    return jsonify({
+        "probability": proba,
+        "prediction": pred
+    })
+
+
+@app.post("/predict-batch")
+def predict_batch():
+    """Predict for multiple JSON rows"""
+    if PIPELINE is None:
+        return jsonify({"error": "Model not loaded"}), 503
+
+    payload = request.get_json(force=True)
+
+    if isinstance(payload, dict) and "records" in payload:
+        records = payload["records"]
+    elif isinstance(payload, list):
+        records = payload
+    else:
+        return jsonify({"error": "Invalid payload format"}), 400
+
+    df = pd.DataFrame(records)
+    probas = PIPELINE.predict_proba(df)[:, 1]
+    preds = (probas >= 0.5).astype(int)
+
+    df["conversion_proba"] = probas
+    df["prediction"] = preds
+
+    return df.to_json(orient="records")
+
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 7860))
+    app.run(host="0.0.0.0", port=port)

api_flask/requirements.txt

@@ -0,0 +1,8 @@
+flask
+flask-cors
+pandas
+numpy
+scikit-learn
+joblib
+gunicorn
+xgboost

api_flask/wsgi.py

@@ -0,0 +1,4 @@
+from app import app as application
+
+# Gunicorn looks for "application"
+app = application

models/best_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37ad7c789ff9745063c8a980fc28c528585eda61f68327af08ec05614c35b1f
+size 213581