Deploy backend Flask app

Dockerfile

@@ -16,4 +16,4 @@ EXPOSE 7860
 # - `-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:bot_detector_api"]
+CMD ["gunicorn", "-w", "4", "-b", "0.0.0.0:7860", "bot_detector_api:app"]

bot_detector_api.py

@@ -4,17 +4,12 @@ import pandas as pd
 from flask import Flask, request, jsonify
 from urllib.parse import urlparse, parse_qs
 
-# Initialize the Flask application
-bot_detector_api = Flask("Bot detector")
+# Initialize the Flask application with standard naming for deployment
+app = Flask("Bot detector")
 
-
-# Define a route for the home page (GET request)
-@bot_detector_api.get('/')
+@app.get('/')
 def home():
-    """
-    This function handles GET requests to the root URL ('/') of the API.
-    It returns a simple welcome message.
-    """
+    """Health check or welcome route."""
     return "Welcome to the bot Prediction API!"
 
 # Load all model artifacts
@@ -33,7 +28,6 @@ def parse_url_params(url):
         return {}
 
 def prepare_features(row_dict):
-    # Start with base info
     base = {
         'region': row_dict.get('region', 'unknown'),
         'browser': row_dict.get('browser', 'unknown'),
@@ -41,19 +35,16 @@ def prepare_features(row_dict):
         'd': row_dict.get('d', '')
     }
 
-    # Extract features from URL
     query_params = parse_url_params(base['d'])
     combined = {**base, **query_params}
     combined.pop('d', None)
 
-    # Ensure all required columns exist
     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 categorical variables or convert to numeric
     for col in df.columns:
         if col in encoders:
             try:
@@ -63,7 +54,6 @@ def prepare_features(row_dict):
         else:
             df[col] = pd.to_numeric(df[col], errors='coerce').fillna(0)
 
-    # Apply scaler 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)
@@ -76,8 +66,7 @@ def prepare_features(row_dict):
 
     return df[feature_names]
 
-
-@bot_detector_api.post('/v1/predict')
+@app.post('/v1/predict')
 def predict():
     row = request.get_json()
     X = prepare_features(row)