run_pipeline.sh

#!/bin/bash

################################################################################
# Temporal Reasoning Audio Dataset Generation Pipeline
# 
# This script orchestrates the entire dataset creation process for all tasks.
################################################################################

set -e  # Exit on error

# Default configuration
CONFIG_FILE="config.yaml"
OUTPUT_DIR=""
TASKS=""
PYTHON_CMD="python"

# Colors for output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

# Function to print colored messages
print_info() {
    echo -e "${BLUE}[INFO]${NC} $1"
}

print_success() {
    echo -e "${GREEN}[SUCCESS]${NC} $1"
}

print_warning() {
    echo -e "${YELLOW}[WARNING]${NC} $1"
}

print_error() {
    echo -e "${RED}[ERROR]${NC} $1"
}

# Function to print usage
usage() {
    cat << EOF
Usage: $0 [OPTIONS]

Temporal Reasoning Audio Dataset Generation Pipeline

OPTIONS:
    -c, --config FILE       Configuration file (default: config.yaml)
    -o, --output DIR        Output directory (overrides config)
    -t, --tasks TASKS       Specific tasks to run: count,duration,order,volume
                           (default: all enabled tasks)
    -p, --python CMD        Python command to use (default: python)
    -h, --help             Display this help message

EXAMPLES:
    # Run all tasks with default config
    $0

    # Run with custom config
    $0 --config my_config.yaml

    # Run specific tasks only
    $0 --tasks count,duration

    # Use custom output directory
    $0 --output /path/to/output

    # Combine options
    $0 --config custom.yaml --tasks count,order --output ./my_dataset

EOF
}

# Parse command line arguments
while [[ $# -gt 0 ]]; do
    case $1 in
        -c|--config)
            CONFIG_FILE="$2"
            shift 2
            ;;
        -o|--output)
            OUTPUT_DIR="$2"
            shift 2
            ;;
        -t|--tasks)
            TASKS="$2"
            shift 2
            ;;
        -p|--python)
            PYTHON_CMD="$2"
            shift 2
            ;;
        -h|--help)
            usage
            exit 0
            ;;
        *)
            print_error "Unknown option: $1"
            usage
            exit 1
            ;;
    esac
done

# Get script directory
SCRIPT_DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"

# Check if config file exists
if [ ! -f "$SCRIPT_DIR/$CONFIG_FILE" ]; then
    print_error "Config file not found: $CONFIG_FILE"
    exit 1
fi

# Print header
echo ""
echo "================================================================================"
echo "  TEMPORAL REASONING AUDIO DATASET GENERATION PIPELINE"
echo "================================================================================"
echo ""
print_info "Configuration: $CONFIG_FILE"
print_info "Python command: $PYTHON_CMD"
[ -n "$OUTPUT_DIR" ] && print_info "Output directory: $OUTPUT_DIR"
[ -n "$TASKS" ] && print_info "Tasks to run: $TASKS"
echo ""

# Check Python dependencies
print_info "Checking Python dependencies..."
$PYTHON_CMD -c "import yaml, pandas, pydub" 2>/dev/null
if [ $? -ne 0 ]; then
    print_error "Missing required Python packages. Please install:"
    echo "  pip install pyyaml pandas pydub"
    exit 1
fi
print_success "Dependencies OK"
echo ""

# Build Python command arguments
PYTHON_ARGS="$SCRIPT_DIR/main.py --config $SCRIPT_DIR/$CONFIG_FILE"
[ -n "$OUTPUT_DIR" ] && PYTHON_ARGS="$PYTHON_ARGS --output $OUTPUT_DIR"
if [ -n "$TASKS" ]; then
    # Convert comma-separated to space-separated for Python argparse
    TASKS_SPACE=$(echo $TASKS | tr ',' ' ')
    PYTHON_ARGS="$PYTHON_ARGS --tasks $TASKS_SPACE"
fi

# Run the pipeline
print_info "Starting pipeline..."
echo ""

$PYTHON_CMD $PYTHON_ARGS

if [ $? -eq 0 ]; then
    echo ""
    echo "================================================================================"
    print_success "PIPELINE COMPLETED SUCCESSFULLY!"
    echo "================================================================================"
    echo ""
else
    echo ""
    echo "================================================================================"
    print_error "PIPELINE FAILED!"
    echo "================================================================================"
    echo ""
    exit 1
fi