"""Appendix A3 — Feature-group cumulative F1 contribution (waterfall).

Each bar is the validation-F1 gain from adding that group on top of the previous
stage (incremental ablation). The gains sum to 0.0283, exactly LightGCN 0.9386 -> 0.9669.
"""
from pathlib import Path
import matplotlib.pyplot as plt
from style import apply, save, PALETTE as C, COL1  # noqa: E402

KEY = "figA3_feature_importance"
TITLE = "Appendix Figure A3. Feature-group contribution"

GROUPS = [
    ("graph / meta-path stacking", 0.0174, C[0]),
    ("7-block random-walk ensemble", 0.0028, C[1]),
    ("DeepWalk + Node2Vec", 0.0022, C[2]),
    ("higher-order propagation", 0.0020, C[3]),
    ("BPR-MF", 0.0017, C[4]),
    ("neg / topk / variant scores", 0.0011, C[5]),
    ("rich content (18-d)", 0.0006, C[6]),
    ("content mean-cos", 0.0005, C[7]),
]


def make(root, out):
    apply()
    names = [g[0] for g in GROUPS]; gains = [g[1] for g in GROUPS]; cols = [g[2] for g in GROUPS]
    total = sum(gains)
    fig, ax = plt.subplots(figsize=(COL1 * 1.5, 3.4))
    ax.barh(range(len(GROUPS)), gains, color=cols)
    ax.set_yticks(range(len(GROUPS))); ax.set_yticklabels(names, fontsize=7.5)
    ax.invert_yaxis()
    for i, g in enumerate(gains):
        ax.text(g + 0.0003, i, f"+{g:.4f}", va="center", fontsize=7)
    ax.set_xlabel("$\\Delta$F1 (cumulative, seed=202)"); ax.set_xlim(0, 0.020)
    ax.set_title(f"Feature-group contribution ($\\Sigma\\Delta$={total:.4f})", fontsize=9)
    save(fig, KEY, out)
    return dict(key=KEY, title=TITLE, status="ok", files=[f"{KEY}.pdf", f"{KEY}.png", f"{KEY}.svg"],
                sources=["post95/extra/content_rich/node2vec/randomwalk/high_order incremental ablations"],
                caption=(
        "Cumulative F1 contribution by feature group (incremental ablation on seed=202). The graph/"
        "meta-path stacking with the LightGBM stacker dominates (+0.0174); the random-walk blocks, "
        "DeepWalk/Node2Vec and higher-order propagation form the second tier. Gains sum to 0.0283, "
        "exactly the LightGCN 0.9386 -> 0.9669 improvement, confirming internal consistency."))


if __name__ == "__main__":
    from style import ensure_dirs
    r = make(Path("."), ensure_dirs(Path(".")))
    print(r["key"], r["status"])