Spaces:
Sleeping
Sleeping
File size: 3,530 Bytes
ffd453e 5271c2e 7fcaffe ffd453e 7fcaffe ffd453e 5271c2e ffd453e 3994c21 ffd453e 5271c2e ffd453e 5271c2e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
import argparse
import sys
import os
def main():
"""
Main entry point for the UFC data pipeline.
Supports scraping, analysis, and prediction workflows.
"""
parser = argparse.ArgumentParser(description="UFC Data Pipeline")
parser.add_argument(
'--pipeline',
type=str,
default='scrape',
choices=['scrape', 'analysis', 'predict', 'update', 'all'],
help="Pipeline to run: 'scrape', 'analysis', 'predict', 'update', or 'all'"
)
parser.add_argument(
'--scrape-mode',
type=str,
default='full',
choices=['full', 'update'],
help="Scraping mode: 'full' (complete scraping) or 'update' (latest events only)"
)
parser.add_argument(
'--num-events',
type=int,
default=5,
help="Number of latest events to scrape in update mode (default: 5)"
)
# Model management arguments for prediction pipeline
parser.add_argument(
'--use-existing-models',
action='store_true',
default=True,
help="Use existing saved models if available and no new data (default: True)."
)
parser.add_argument(
'--no-use-existing-models',
action='store_true',
default=False,
help="Force retrain all models from scratch, ignoring existing saved models."
)
parser.add_argument(
'--force-retrain',
action='store_true',
default=False,
help="Force retrain all models even if no new data is available."
)
args = parser.parse_args()
if args.pipeline in ['scrape', 'all']:
print("=== Running Scraping Pipeline ===")
from src.scrape.main import main as scrape_main
# Override sys.argv to pass arguments to scrape.main
original_argv = sys.argv
sys.argv = ['scrape_main', '--mode', args.scrape_mode, '--num-events', str(args.num_events)]
try:
scrape_main()
finally:
sys.argv = original_argv
if args.pipeline in ['analysis', 'all']:
print("\n=== Running ELO Analysis ===")
from src.analysis.elo import main as elo_main
elo_main()
if args.pipeline == 'update':
print("\n=== Running Model Update Pipeline ===")
try:
from src.predict.main import MODELS_TO_RUN
from src.predict.pipeline import PredictionPipeline
except ImportError:
print("Fatal: Could not import prediction modules.")
print("Please ensure your project structure and python path are correct.")
return
pipeline = PredictionPipeline(models=MODELS_TO_RUN)
pipeline.update_models_if_new_data()
if args.pipeline in ['predict', 'all']:
print("\n=== Running Prediction Pipeline ===")
from src.predict.main import main as predict_main
# Override sys.argv to pass model management arguments to predict.main
original_argv = sys.argv
predict_args = ['predict_main']
if args.no_use_existing_models:
predict_args.append('--no-use-existing-models')
elif args.use_existing_models:
predict_args.append('--use-existing-models')
if args.force_retrain:
predict_args.append('--force-retrain')
sys.argv = predict_args
try:
predict_main()
finally:
sys.argv = original_argv
if __name__ == '__main__':
main()
|