File size: 9,253 Bytes
fec9168 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 |
"""
Main pipeline runner for temporal reasoning audio dataset generation.
This script orchestrates the generation of all task datasets.
"""
import argparse
import sys
import yaml
from pathlib import Path
from typing import List, Optional
# Add project root to path
sys.path.append(str(Path(__file__).parent))
from utils import setup_logger, set_random_seed
from tasks.task_count import CountTaskGenerator
from tasks.task_duration import DurationTaskGenerator
from tasks.task_order import OrderTaskGenerator
from tasks.task_volume import VolumeTaskGenerator
def load_config(config_path: str) -> dict:
"""Load configuration from YAML file."""
with open(config_path, 'r') as f:
config = yaml.safe_load(f)
return config
def run_count_task(config: dict, logger):
"""Run the count task generation."""
if not config['tasks']['count']['enabled']:
logger.info("Count task is disabled, skipping...")
return
logger.info("=" * 80)
logger.info("STARTING COUNT TASK GENERATION")
logger.info("=" * 80)
generator = CountTaskGenerator(config, logger)
generator.dataset.reset_category_usage() # Reset counter for this task
generator.generate_dataset()
# Log category usage statistics
usage_stats = generator.dataset.get_category_usage_stats()
sorted_stats = sorted(usage_stats.items(), key=lambda x: x[1], reverse=True)
logger.info("Category usage statistics (as answers):")
logger.info(f" Min usage: {sorted_stats[-1][1]} (category: {sorted_stats[-1][0]})")
logger.info(f" Max usage: {sorted_stats[0][1]} (category: {sorted_stats[0][0]})")
logger.info(f" Mean usage: {sum(usage_stats.values()) / len(usage_stats):.2f}")
logger.info("Count task completed successfully!")
def run_duration_task(config: dict, logger):
"""Run the duration task generation."""
if not config['tasks']['duration']['enabled']:
logger.info("Duration task is disabled, skipping...")
return
logger.info("=" * 80)
logger.info("STARTING DURATION TASK GENERATION")
logger.info("=" * 80)
generator = DurationTaskGenerator(config, logger)
generator.dataset.reset_category_usage() # Reset counter for this task
generator.generate_dataset()
# Log category usage statistics
usage_stats = generator.dataset.get_category_usage_stats()
sorted_stats = sorted(usage_stats.items(), key=lambda x: x[1], reverse=True)
logger.info("Category usage statistics (as longest/shortest answers):")
logger.info(f" Min usage: {sorted_stats[-1][1]} (category: {sorted_stats[-1][0]})")
logger.info(f" Max usage: {sorted_stats[0][1]} (category: {sorted_stats[0][0]})")
logger.info(f" Mean usage: {sum(usage_stats.values()) / len(usage_stats):.2f}")
logger.info("Duration task completed successfully!")
def run_order_task(config: dict, logger):
"""Run the order task generation."""
if not config['tasks']['order']['enabled']:
logger.info("Order task is disabled, skipping...")
return
logger.info("=" * 80)
logger.info("STARTING ORDER TASK GENERATION")
logger.info("=" * 80)
generator = OrderTaskGenerator(config, logger)
generator.dataset.reset_category_usage() # Reset counter for this task
generator.generate_dataset()
# Log category usage statistics
usage_stats = generator.dataset.get_category_usage_stats()
sorted_stats = sorted(usage_stats.items(), key=lambda x: x[1], reverse=True)
logger.info("Category usage statistics (as first/last/after/before answers):")
logger.info(f" Min usage: {sorted_stats[-1][1]} (category: {sorted_stats[-1][0]})")
logger.info(f" Max usage: {sorted_stats[0][1]} (category: {sorted_stats[0][0]})")
logger.info(f" Mean usage: {sum(usage_stats.values()) / len(usage_stats):.2f}")
logger.info("Order task completed successfully!")
def run_volume_task(config: dict, logger):
"""Run the volume task generation."""
if not config['tasks']['volume']['enabled']:
logger.info("Volume task is disabled, skipping...")
return
logger.info("=" * 80)
logger.info("STARTING VOLUME TASK GENERATION")
logger.info("=" * 80)
generator = VolumeTaskGenerator(config, logger)
generator.dataset.reset_category_usage() # Reset counter for this task
generator.generate_dataset()
# Log category usage statistics
usage_stats = generator.dataset.get_category_usage_stats()
sorted_stats = sorted(usage_stats.items(), key=lambda x: x[1], reverse=True)
logger.info("Category usage statistics (as loudest/softest answers):")
logger.info(f" Min usage: {sorted_stats[-1][1]} (category: {sorted_stats[-1][0]})")
logger.info(f" Max usage: {sorted_stats[0][1]} (category: {sorted_stats[0][0]})")
logger.info(f" Mean usage: {sum(usage_stats.values()) / len(usage_stats):.2f}")
logger.info("Volume task completed successfully!")
def run_pipeline(
config_path: str,
tasks: Optional[List[str]] = None,
output_path: Optional[str] = None
):
"""
Run the complete dataset generation pipeline.
Args:
config_path: Path to configuration YAML file
tasks: Optional list of specific tasks to run (default: all enabled tasks)
output_path: Optional custom output path (overrides config)
"""
# Load configuration
config = load_config(config_path)
# Override output path if provided
if output_path:
config['output']['base_path'] = output_path
# Create output directory
output_base = Path(config['output']['base_path'])
output_base.mkdir(parents=True, exist_ok=True)
# Set random seed
set_random_seed(config['random_seed'])
# Setup main logger
logger = setup_logger(
'pipeline',
log_file=str(output_base / config['logging']['log_file']),
level=config['logging']['level'],
console_output=config['logging']['console_output']
)
logger.info("=" * 80)
logger.info("TEMPORAL REASONING AUDIO DATASET GENERATION PIPELINE")
logger.info("=" * 80)
logger.info(f"Configuration: {config_path}")
logger.info(f"Output directory: {output_base}")
logger.info(f"Random seed: {config['random_seed']}")
logger.info(f"ESC-50 audio path: {config['esc50']['audio_path']}")
logger.info(f"ESC-50 metadata path: {config['esc50']['metadata_path']}")
# Determine which tasks to run
task_map = {
'count': run_count_task,
'duration': run_duration_task,
'order': run_order_task,
'volume': run_volume_task
}
if tasks:
tasks_to_run = {k: v for k, v in task_map.items() if k in tasks}
logger.info(f"Running specific tasks: {', '.join(tasks)}")
else:
tasks_to_run = task_map
logger.info("Running all enabled tasks")
# Run tasks
for task_name, task_func in tasks_to_run.items():
try:
task_func(config, logger)
except Exception as e:
logger.error(f"Error running {task_name} task: {e}", exc_info=True)
raise
logger.info("=" * 80)
logger.info("PIPELINE COMPLETED SUCCESSFULLY!")
logger.info("=" * 80)
logger.info(f"All outputs saved to: {output_base}")
def main():
"""Main entry point with argument parsing."""
parser = argparse.ArgumentParser(
description="Temporal Reasoning Audio Dataset Generation Pipeline",
formatter_class=argparse.RawDescriptionHelpFormatter,
epilog="""
Examples:
# Run all tasks with default config
python main.py
# Run with custom config
python main.py --config my_config.yaml
# Run specific tasks only
python main.py --tasks count duration
# Use custom output directory
python main.py --output /path/to/output
# Combine options
python main.py --config custom.yaml --tasks count order --output ./my_dataset
"""
)
parser.add_argument(
'--config', '-c',
type=str,
default='config.yaml',
help='Path to configuration YAML file (default: config.yaml)'
)
parser.add_argument(
'--tasks', '-t',
nargs='+',
choices=['count', 'duration', 'order', 'volume'],
help='Specific tasks to run (default: all enabled tasks)'
)
parser.add_argument(
'--output', '-o',
type=str,
help='Custom output directory (overrides config)'
)
args = parser.parse_args()
# Check if config file exists
config_path = Path(args.config)
if not config_path.exists():
# Try relative to script directory
script_dir = Path(__file__).parent
config_path = script_dir / args.config
if not config_path.exists():
print(f"Error: Config file not found: {args.config}")
sys.exit(1)
# Run pipeline
try:
run_pipeline(
config_path=str(config_path),
tasks=args.tasks,
output_path=args.output
)
except Exception as e:
print(f"Pipeline failed with error: {e}")
sys.exit(1)
if __name__ == '__main__':
main()
|