Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Copy all files from the current directory to the container's working directory
+COPY . .
+
+# Install dependencies from the requirements file without using cache to reduce image size
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# 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:shipping_return_predictor_api"]

app.py

@@ -0,0 +1,70 @@
+
+from flask import Flask, request, jsonify
+import pandas as pd
+import numpy as np
+import xgboost as xgb
+import joblib
+
+# Initialize Flask app
+app = Flask(__name__)
+
+# Load trained model and encoders
+model = joblib.load("shipment_return_predictor_model.pkl")
+target_encoder = joblib.load("target_encoder.pkl")
+feature_encoders = joblib.load("feature_encoders.pkl")  # Dictionary of encoders for categorical features
+feature_columns = joblib.load("feature_columns.pkl")    # List of feature columns used in training
+
+@app.route('/predict', methods=['POST'])
+def predict():
+    # Parse input JSON
+    input_data = request.get_json()
+    input_df = pd.DataFrame([input_data])
+
+    # Apply encoding to categorical features
+    for col, encoder in feature_encoders.items():
+        if col in input_df.columns:
+            input_df[col] = encoder.transform(input_df[col])
+
+    # Ensure all feature columns are present
+    for col in feature_columns:
+        if col not in input_df.columns:
+            input_df[col] = 0
+
+    input_df = input_df[feature_columns]
+
+    # Predict probabilities
+    probs = model.predict_proba(input_df)
+    preds = np.argmax(probs, axis=1)
+    pred_probs = probs[np.arange(len(preds)), preds]
+
+    # Get feature contributions
+    booster = model.get_booster()
+    dmatrix = xgb.DMatrix(input_df, feature_names=input_df.columns.tolist())
+    contribs = booster.predict(dmatrix, pred_contribs=True)
+
+    # Extract top contributing features
+    top_features = []
+    for i, pred_class in enumerate(preds):
+        contrib_vector = contribs[i]
+        class_contribs = contrib_vector[pred_class]
+        feature_contribs = dict(zip(input_df.columns.tolist(), class_contribs))
+        sorted_features = sorted(feature_contribs.items(), key=lambda x: abs(x[1]), reverse=True)
+        top_features.append([f[0] for f in sorted_features[:3]])
+
+    # Map predicted class to original label
+    predicted_labels = target_encoder.inverse_transform(preds)
+
+    # Prepare response
+    response = {
+        "Predicted Label": predicted_labels[0],
+        "Probability": float(pred_probs[0]),
+        "Top Contributing Features": top_features[0]
+    }
+
+    return jsonify(response)
+
+# Run the app
+if __name__ == '__main__':
+    app.run(debug=True)
+
+ 

feature_columns.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db79374159549b801f6450389ef966ab230c7181e26a8d31328511d4edfa3e10
+size 171

feature_encoders.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e6dca274d959896c9ee81ce7bd7f591ac78cc67d04a60dc4578bbaf56dfcdd
+size 639803

requirements.txt

@@ -0,0 +1,12 @@
+flask==2.2.2
+joblib==1.4.2
+shap==0.44.1
+xgboost==2.1.4
+pandas==2.2.2
+numpy==2.0.2
+scikit-learn==1.6.1
+Werkzeug==2.2.2
+gunicorn==20.1.0
+requests==2.28.1
+uvicorn[standard]
+streamlit==1.43.2

shipment_return_predictor_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123ddda2b51c8c78b57d86276fcf2b5459c59f9e6b130164a51f7d3507a6ea83
+size 2193702

target_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32de92fcab8b4762ab0b873eba004c4741c64759a59de490c6f81221c4440e9b
+size 375