compact_sets/src/analyze.py

"""Analyze chord sequence outputs."""

import argparse
import json
import statistics
from pathlib import Path


def analyze_chords(
    chords: list,
    config: dict | None = None,
) -> dict:
    """Analyze chord sequence and return metrics.

    Args:
        chords: List of chords, each chord is a list of pitch dicts
        config: Optional config with target_octaves, melodic_max, max_path

    Returns:
        Dict with analysis metrics
    """
    if config is None:
        config = {}

    target_octaves = config.get("target_range_octaves", 2.0)
    melodic_max = config.get("melodic_threshold_max", 300)
    max_path = config.get("max_path", 50)

    # Basic info
    num_chords = len(chords)
    num_voices = len(chords[0]) if chords else 0

    # Melodic violations
    violations = 0
    max_violation = 0
    voice_changes = 0
    for i in range(1, num_chords):
        for v in range(num_voices):
            diff = abs(chords[i][v]["cents"] - chords[i - 1][v]["cents"])
            if diff > 0:
                voice_changes += 1
            if diff > melodic_max:
                violations += 1
                max_violation = max(max_violation, diff)

    # Target range
    target_octaves = config.get("target_range_octaves", 2.0)
    target_cents = target_octaves * 1200

    if chords:
        start_avg = sum(p["cents"] for p in chords[0]) / len(chords[0])
        end_avg = sum(p["cents"] for p in chords[-1]) / len(chords[-1])
        actual_cents = end_avg - start_avg
        target_percent = (actual_cents / target_cents) * 100 if target_cents > 0 else 0
    else:
        start_avg = end_avg = actual_cents = target_percent = 0

    return {
        "num_chords": num_chords,
        "num_voices": num_voices,
        "melodic_max": melodic_max,
        "violations": violations,
        "max_violation": max_violation,
        "voice_changes": voice_changes,
        "start_avg_cents": start_avg,
        "end_avg_cents": end_avg,
        "target_cents": target_cents,
        "actual_cents": actual_cents,
        "target_percent": target_percent,
        "target_octaves": target_octaves,
    }


def format_analysis(metrics: dict) -> str:
    """Format analysis metrics as readable output."""
    lines = [
        "=== Analysis ===",
        f"Path length: {metrics['num_chords']} chords, {metrics['num_voices']} voices",
        "",
        "--- Melodic Threshold ---",
        f"Max allowed: {metrics['melodic_max']} cents",
        f"Violations: {metrics['violations']}",
        f"Max violation: {metrics['max_violation']:.0f} cents",
        f"Voice changes: {metrics['voice_changes']}",
        "",
        "--- Target Range ---",
        f"Target: {metrics['target_octaves']} octaves ({metrics['target_cents']:.0f} cents)",
        f"Start avg: {metrics['start_avg_cents']:.0f} cents",
        f"End avg: {metrics['end_avg_cents']:.0f} cents",
        f"Achieved: {metrics['actual_cents']:.0f} cents ({metrics['target_percent']:.1f}%)",
    ]
    return "\n".join(lines)


def analyze_file(file_path: str | Path) -> dict:
    """Load and analyze a chord file."""
    with open(file_path) as f:
        chords = json.load(f)
    return analyze_chords(chords)


def main():
    parser = argparse.ArgumentParser(description="Analyze chord sequence outputs")
    parser.add_argument(
        "file",
        nargs="?",
        default="output/output_chords.json",
        help="Path to chord JSON file (default: output/output_chords.json)",
    )
    parser.add_argument(
        "--json",
        action="store_true",
        help="Output raw JSON instead of formatted text",
    )
    args = parser.parse_args()

    file_path = Path(args.file)
    if not file_path.exists():
        print(f"Error: File not found: {file_path}")
        return 1

    metrics = analyze_file(file_path)

    if args.json:
        print(json.dumps(metrics, indent=2))
    else:
        print(format_analysis(metrics))

    return 0


if __name__ == "__main__":
    exit(main())