Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,19 @@
+# Use Python base image
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy all files into the container
+COPY . /app
+
+# Install dependencies
+RUN pip install --upgrade pip && \
+    pip install -r requirements.txt
+
+# Expose port for Streamlit
+EXPOSE 7860
+
+
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,82 @@
+import numpy as np
+import joblib
+import pandas as pd
+from flask import Flask, request, jsonify
+from urllib.parse import urlparse, parse_qs
+
+# Load model artifacts
+model = joblib.load("model.joblib")
+encoders = joblib.load("encoders.joblib")
+scaler = joblib.load("scaler.joblib")
+if_model = joblib.load("best_if_model.joblib")
+svm_model = joblib.load("best_svm_model.joblib")
+feature_names = joblib.load("feature_names.joblib")
+
+# Initialize the Flask app
+app = Flask("Bot Detection API")
+
+def parse_url_params(url):
+    try:
+        query = urlparse(url).query
+        return {k: v[0] if isinstance(v, list) else v for k, v in parse_qs(query).items()}
+    except Exception:
+        return {}
+
+def prepare_features(row_dict):
+    base = {
+        'region': row_dict.get('region', 'unknown'),
+        'browser': row_dict.get('browser', 'unknown'),
+        'device': row_dict.get('device', 'unknown'),
+        'd': row_dict.get('d', '')
+    }
+    query_params = parse_url_params(base['d'])
+    combined = {**base, **query_params}
+    combined.pop('d', None)
+
+    # Fill any missing expected features
+    for col in feature_names:
+        if col not in combined and col not in ["iso_anomaly_prob", "svm_anomaly_prob"]:
+            combined[col] = "unknown"
+
+    df = pd.DataFrame([combined])
+
+    # Encode categoricals
+    for col in df.columns:
+        if col in encoders:
+            try:
+                df[col] = encoders[col].transform(df[col].astype(str))
+            except:
+                df[col] = encoders[col].transform(["unknown"])[0]
+        else:
+            df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0)
+
+    # Scale and compute anomaly scores
+    df_scaled = scaler.transform(df)
+    iso_score = if_model.decision_function(df_scaled)
+    svm_score = svm_model.decision_function(df_scaled)
+    iso_anomaly_prob = 1 - float(np.clip((iso_score - iso_score.min()) / (iso_score.max() - iso_score.min() + 1e-9), 0, 1))
+    svm_anomaly_prob = 1 - float(np.clip((svm_score - svm_score.min()) / (svm_score.max() - svm_score.min() + 1e-9), 0, 1))
+
+    df['iso_anomaly_prob'] = iso_anomaly_prob
+    df['svm_anomaly_prob'] = svm_anomaly_prob
+
+    return df[feature_names]
+
+@app.get('/')
+def home():
+    return "✅ Bot Detection API is live."
+
+@app.post('/v1/predict')
+def predict():
+    row = request.get_json()
+    X = prepare_features(row)
+    pred_prob = model.predict_proba(X)[0][1]
+    pred_label = int(pred_prob >= 0.5)
+
+    return jsonify({
+        "Prediction": "Bot Attack" if pred_label else "Legitimate",
+        "Bot Probability": round(float(pred_prob), 4)
+    })
+
+if __name__ == '__main__':
+    app.run(debug=True)

requirements.txt

@@ -0,0 +1,11 @@
+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
+streamlit==1.43.2
+uvicorn[standard]