#!/usr/bin/env python3
"""Bounded native WIRE-Performer run on the paper's MNIST graph benchmark."""

from __future__ import annotations

import argparse
import json
import os
import random
import sys
import time
import types
from pathlib import Path

import networkx as nx
import numpy as np
import torch
from torch import nn
from torch_geometric.datasets import GNNBenchmarkDataset
from torch_geometric.loader import DataLoader
from torch_geometric.nn import GCNConv, global_mean_pool


def import_pinned_graphrope(repo: Path):
    graphgps = types.ModuleType("graphgps")
    graphgps.__path__ = [str(repo / "graphgps")]
    sys.modules["graphgps"] = graphgps
    layer = types.ModuleType("graphgps.layer")
    layer.__path__ = [str(repo / "graphgps" / "layer")]
    sys.modules["graphgps.layer"] = layer
    from graphgps.layer.graphrope import GraphRoPE  # noqa: WPS433

    return GraphRoPE


def seed_all(seed: int):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)


def add_features(data, max_freqs: int):
    n = int(data.num_nodes)
    graph = nx.Graph()
    graph.add_nodes_from(range(n))
    graph.add_edges_from(data.edge_index.t().tolist())
    adj = nx.to_numpy_array(graph, nodelist=range(n), dtype=float)
    lap = np.diag(adj.sum(axis=1)) - adj
    _, vecs = np.linalg.eigh(lap)
    pe = vecs[:, 1 : 1 + max_freqs]
    if pe.shape[1] < max_freqs:
        pe = np.pad(pe, ((0, 0), (0, max_freqs - pe.shape[1])))
    pe = torch.tensor(pe, dtype=torch.float32)
    data.x = torch.cat([data.x.float(), pe], dim=1)
    data.t = pe
    return data


class GPSMini(nn.Module):
    def __init__(self, GraphRoPE, m: int, hidden: int = 32, layers: int = 3):
        super().__init__()
        self.m = m
        self.input = nn.Linear(9, hidden)
        self.local = nn.ModuleList([GCNConv(hidden, hidden) for _ in range(layers)])
        self.attn = nn.ModuleList([
            GraphRoPE(
                k=max(1, m), d=hidden, num_heads=4, dropout=0.0,
                enable=m > 0, init_omega="zero", attn_type="Linear",
            )
            for _ in range(layers)
        ])
        self.norm = nn.ModuleList([nn.LayerNorm(hidden) for _ in range(layers)])
        self.ff = nn.ModuleList([
            nn.Sequential(nn.Linear(hidden, hidden), nn.ReLU(), nn.Linear(hidden, hidden))
            for _ in range(layers)
        ])
        self.head = nn.Linear(hidden, 10)

    def forward(self, batch):
        h = self.input(batch.x)
        for local, attn, norm, ff in zip(self.local, self.attn, self.norm, self.ff):
            h0 = h
            h_local = local(h, batch.edge_index)
            tmp = types.SimpleNamespace(x=h, batch=batch.batch)
            if self.m > 0:
                tmp.t = batch.t[:, : self.m]
            h_attn = attn(tmp)
            h = norm(h0 + h_local + h_attn)
            h = h + ff(h)
        return self.head(global_mean_pool(h, batch.batch))


def run(GraphRoPE, root: Path, n_train: int, n_test: int, epochs: int, m: int, seed: int):
    seed_all(seed)
    train_ds = GNNBenchmarkDataset(root=str(root), name="MNIST", split="train")
    test_ds = GNNBenchmarkDataset(root=str(root), name="MNIST", split="test")
    train = [add_features(train_ds[i], 8) for i in range(n_train)]
    test = [add_features(test_ds[i], 8) for i in range(n_test)]
    train_loader = DataLoader(train, batch_size=16, shuffle=True)
    test_loader = DataLoader(test, batch_size=32, shuffle=False)
    model = GPSMini(GraphRoPE, m=m)
    opt = torch.optim.AdamW(model.parameters(), lr=1e-3, weight_decay=1e-5)
    best = 0.0
    for _ in range(epochs):
        model.train()
        for batch in train_loader:
            opt.zero_grad(set_to_none=True)
            loss = nn.functional.cross_entropy(model(batch), batch.y.view(-1))
            loss.backward()
            opt.step()
        model.eval()
        good = total = 0
        with torch.no_grad():
            for batch in test_loader:
                pred = model(batch).argmax(dim=-1)
                good += int((pred == batch.y.view(-1)).sum())
                total += len(pred)
        best = max(best, good / total)
    return {"dataset": "MNIST", "attention": "Performer", "m": m, "seed": seed,
            "train_graphs": n_train, "test_graphs": n_test, "epochs": epochs,
            "best_test_accuracy": best, "parameters": sum(p.numel() for p in model.parameters())}


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--repo", type=Path, required=True)
    ap.add_argument("--data-root", type=Path, required=True)
    ap.add_argument("--out", type=Path, required=True)
    ap.add_argument("--train-graphs", type=int, default=256)
    ap.add_argument("--test-graphs", type=int, default=256)
    ap.add_argument("--epochs", type=int, default=3)
    ap.add_argument("--seeds", type=int, nargs="+", default=[0, 1])
    args = ap.parse_args()
    torch.set_num_threads(min(4, os.cpu_count() or 1))
    GraphRoPE = import_pinned_graphrope(args.repo)
    start = time.time()
    rows = []
    for m in [0, 8]:
        for seed in args.seeds:
            print(f"running MNIST Performer m={m} seed={seed}", flush=True)
            rows.append(run(GraphRoPE, args.data_root, args.train_graphs, args.test_graphs, args.epochs, m, seed))
            print(f"  best accuracy={rows[-1]['best_test_accuracy']:.6f}", flush=True)
    out = {
        "protocol": {
            "paper": "arXiv:2509.22259v1, Section 4.3 / Table 3",
            "official_repository": "https://github.com/cederikhoefs/Graph-RoPE",
            "official_commit": "4ac067eb38272543b0cdd7591d630399ff37bce4",
            "dataset": "PyG GNNBenchmarkDataset MNIST graph classification",
            "architecture": "GCN local branch + official GraphRoPE Performer global branch, hidden=32, heads=4, layers=3",
            "budget": {"train_graphs": args.train_graphs, "test_graphs": args.test_graphs, "epochs": args.epochs, "seeds": args.seeds},
            "baseline": "m=0 with the same Laplacian features as node inputs and WIRE disabled",
            "wire": "m=8 spectral coordinates supplied to official GraphRoPE Performer",
        },
        "rows": rows,
        "runtime_seconds": time.time() - start,
    }
    args.out.parent.mkdir(parents=True, exist_ok=True)
    args.out.write_text(json.dumps(out, indent=2) + "\n", encoding="utf-8")
    print(f"wrote {args.out}")


if __name__ == "__main__":
    main()