Refactor config imports and add JSON report for predictions

Moved config.py to the project root and updated all imports to use the new location. Deleted the unused analyze.py script. Enhanced the prediction pipeline to save detailed model results to a JSON file, grouping predictions by event. Updated predict.main to generate a detailed report by default. Improved module import consistency in scrape modules.

src/analysis/elo.py

@@ -1,9 +1,8 @@
 import csv
 import os
 from datetime import datetime
-import sys
 
-from ..scrape.config import FIGHTS_CSV_PATH, FIGHTERS_CSV_PATH
+from ..config import FIGHTS_CSV_PATH, FIGHTERS_CSV_PATH
 
 # --- ELO Configuration ---
 INITIAL_ELO = 1500

src/analyze.py

@@ -1,15 +0,0 @@
-import pandas as pd
-
-ufc_fights = pd.read_csv('output/ufc_fights.csv')
-ufc_fighters = pd.read_csv('output/ufc_fighters.csv')
-
-print(f"Number of fighters registered in UFC: {len(ufc_fighters)}")
-unique_fighters=set()
-for fight in ufc_fights['fighter_1']:
-    unique_fighters.add(fight)
-for fight in ufc_fights['fighter_2']:
-    unique_fighters.add(fight)
-print(f"Number of fighters who have at least one fight: {len(unique_fighters)}")
-
-highest_elo_fighters=ufc_fighters.sort_values(by='elo', ascending=False).head(20)
-print(highest_elo_fighters)

src/{scrape/config.py → config.py}

@@ -1,9 +1,11 @@
 import os
 
 OUTPUT_DIR = 'output'
+FIGHTS_CSV_PATH = os.path.join(OUTPUT_DIR, 'ufc_fights.csv')
+FIGHTERS_CSV_PATH = os.path.join(OUTPUT_DIR, 'ufc_fighters.csv')
+MODEL_RESULTS_PATH = os.path.join(OUTPUT_DIR, 'model_results.json') 
 
+# JSON files (temporary)
 EVENTS_JSON_PATH = os.path.join(OUTPUT_DIR, 'ufc_fights.json')
 FIGHTERS_JSON_PATH = os.path.join(OUTPUT_DIR, 'ufc_fighters.json')
 
-FIGHTS_CSV_PATH = os.path.join(OUTPUT_DIR, 'ufc_fights.csv')
-FIGHTERS_CSV_PATH = os.path.join(OUTPUT_DIR, 'ufc_fighters.csv')

src/main.py

@@ -2,3 +2,4 @@
 
 # Run scrape.main
 # Run analysis.elo to add elo
+# Run predict.main for ML models

src/predict/main.py

@@ -24,7 +24,7 @@ def main():
     pipeline = PredictionPipeline(models=models_to_run)
     
     # Set detailed_report=False for a summary, or True for a full detailed report
-    pipeline.run(detailed_report=False)
+    pipeline.run(detailed_report=True)
 
 if __name__ == '__main__':
     main() 

src/predict/pipeline.py

@@ -3,7 +3,9 @@ import os
 import sys
 from datetime import datetime
 from collections import OrderedDict
-from ..scrape.config import FIGHTS_CSV_PATH
+import json
+
+from ..config import FIGHTS_CSV_PATH, MODEL_RESULTS_PATH
 from .models import BaseModel
 
 class PredictionPipeline:
@@ -61,6 +63,7 @@ class PredictionPipeline:
             for fight in eval_fights:
                 f1_name, f2_name = fight['fighter_1'], fight['fighter_2']
                 actual_winner = fight['winner']
+                event_name = fight.get('event_name', 'Unknown Event')
                 predicted_winner = model.predict(f1_name, f2_name)
                 
                 is_correct = (predicted_winner == actual_winner)
@@ -69,6 +72,7 @@ class PredictionPipeline:
                 
                 predictions.append({
                     'fight': f"{f1_name} vs. {f2_name}",
+                    'event': event_name,
                     'predicted_winner': predicted_winner,
                     'actual_winner': actual_winner,
                     'is_correct': is_correct
@@ -95,17 +99,38 @@ class PredictionPipeline:
             print(f"{model_name:<25} | {result['accuracy']:<9.2f}% | {result['total_fights']:<20}")
         print("-" * 65)
 
+    def _save_report_to_json(self, file_path=MODEL_RESULTS_PATH):
+        """Saves the detailed prediction results to a JSON file."""
+        print(f"\nSaving detailed report to {file_path}...")
+        try:
+            # Create a report structure that is clean and JSON-friendly
+            report = {}
+            for model_name, result in self.results.items():
+                
+                # Group predictions by event for a more organized report
+                predictions_by_event = {}
+                for p in result['predictions']:
+                    event_name = p.pop('event') # Extract event and remove it from the sub-dictionary
+                    if event_name not in predictions_by_event:
+                        predictions_by_event[event_name] = []
+                    predictions_by_event[event_name].append(p)
+
+                report[model_name] = {
+                    "overall_accuracy": f"{result['accuracy']:.2f}%",
+                    "total_fights_evaluated": result['total_fights'],
+                    "predictions_by_event": predictions_by_event
+                }
+
+            with open(file_path, 'w', encoding='utf-8') as f:
+                json.dump(report, f, indent=4)
+            print("Report saved successfully.")
+        except (IOError, TypeError) as e:
+            print(f"Error saving report to JSON file: {e}")
+
     def _report_detailed_results(self):
-        """Prints a summary and detailed report of the model evaluations."""
+        """Prints a summary and saves the detailed report to a file."""
         print("\n\n--- Prediction Pipeline Finished: Detailed Report ---")
-        for model_name, result in self.results.items():
-            print(f"\n--- Model: {model_name} ---")
-            print(f"  Overall Accuracy: {result['accuracy']:.2f}%")
-            print("  Detailed Predictions:")
-            for p in result['predictions']:
-                status = "CORRECT" if p['is_correct'] else "INCORRECT"
-                print(f"    - Fight: {p['fight']}")
-                print(f"      -> Predicted: {p['predicted_winner']}")
-                print(f"      -> Actual:    {p['actual_winner']}")
-                print(f"      -> Result: {status}")
-            print("------------------------" + "-" * len(model_name)) 
+        # A summary is printed to the console for convenience.
+        self._report_summary()
+        # The detailed report is now saved to a JSON file.
+        self._save_report_to_json() 

src/scrape/main.py

@@ -1,10 +1,10 @@
 import os
 import json
-from scrape_fights import scrape_all_events
-from scrape_fighters import scrape_all_fighters
-from to_csv import json_to_csv, fighters_json_to_csv
-from preprocess import preprocess_fighters_csv
-import config
+from .scrape_fights import scrape_all_events
+from .scrape_fighters import scrape_all_fighters
+from .to_csv import json_to_csv, fighters_json_to_csv
+from .preprocess import preprocess_fighters_csv
+from .. import config
 
 def main():
     """

src/scrape/preprocess.py

@@ -1,6 +1,6 @@
 import csv
 import os
-import config
+from .. import config
 
 def convert_height_to_cm(height_str):
     """

src/scrape/scrape_fighters.py

@@ -5,7 +5,7 @@ import time
 import string
 import concurrent.futures
 import os
-import config
+from .. import config
 
 # --- Configuration ---
 # The number of parallel threads to use for scraping fighter details.

src/scrape/scrape_fights.py

@@ -3,7 +3,7 @@ from bs4 import BeautifulSoup
 import json
 import time
 import concurrent.futures
-from config import EVENTS_JSON_PATH
+from ..config import EVENTS_JSON_PATH
 
 # --- Configuration ---
 # The number of parallel threads to use for scraping fight details.

src/scrape/to_csv.py

@@ -1,6 +1,6 @@
 import json
 import csv
-import config
+from .. import config
 
 def json_to_csv(json_file_path, csv_file_path):
     try: