Function main

codeclash/analysis/viz/scatter_codebase_organization.py:632–682

(refresh_cache: bool = False)

def main(refresh_cache: bool = False):
    build_data_structure(refresh_cache)

    data = []
    with open(DATA_CACHE) as f:
        data = [json.loads(line) for line in f]
    print(f"Found {len(data)} player-tournament entries in cache.")

    # Analysis 1: Per player-tournament
    print("\n=== Active File Ratio Per Player-Arena ===")
    per_tournament_df = analyze_per_player_arena(data, N=5)
    print(per_tournament_df)
    per_tournament_df.to_csv(ASSETS_SUBFOLDER / "active_file_ratio_per_tournament.csv", index=False)

    # Analysis 2: Per player (aggregated)
    print("\n=== Active File Ratio Per Player ===")
    per_player_df = analyze_per_player(data, N=5)
    print(per_player_df)
    per_player_df.to_csv(ASSETS_SUBFOLDER / "active_file_ratio_per_player.csv", index=False)

    # Analysis 3: Root level file clutter per player
    print("\n=== Root Level File Clutter Per Player ===")
    root_clutter_df = analyze_root_clutter_per_player(data)
    print(root_clutter_df)
    root_clutter_df.to_csv(ASSETS_SUBFOLDER / "root_clutter_ratio_per_player.csv", index=False)

    # Analysis 4: Churn concentration per player
    print("\n=== Churn Concentration Per Player ===")
    churn_concentration_df = analyze_churn_concentration_per_player(data, use_magnitude=True)
    print(churn_concentration_df)
    churn_concentration_df.to_csv(ASSETS_SUBFOLDER / "churn_concentration_per_player.csv", index=False)

    # Analysis 5: File reuse ratio per player
    print("\n=== File Reuse Ratio Per Player ===")
    file_reuse_df = analyze_file_reuse_per_player(data)
    print(file_reuse_df)
    file_reuse_df.to_csv(ASSETS_SUBFOLDER / "file_reuse_ratio_per_player.csv", index=False)

    # Visualization: Organization metrics
    print("\n=== Plotting Organization Metrics ===")
    plot_organization_metrics(file_reuse_df, root_clutter_df)

    # Analysis 6: Filename redundancy over rounds
    print("\n=== Filename Redundancy Over Rounds Per Player-Tournament ===")
    redundancy_df = analyze_filename_redundancy_over_rounds(data)
    print(redundancy_df)
    redundancy_df.to_csv(ASSETS_SUBFOLDER / "filename_redundancy_per_player.csv", index=False)

    # Visualization: Filename redundancy over rounds
    print("\n=== Plotting Filename Redundancy Over Rounds ===")
    plot_filename_redundancy_over_rounds(redundancy_df)


if __name__ == "__main__":