"""
nanoWeatherGPT — a tiny character-level GPT trained on weather text.
Architecture: GPT with causal self-attention (Karpathy-style nanoGPT).
"""

import math
import torch
import torch.nn as nn
from torch.nn import functional as F
from dataclasses import dataclass


@dataclass
class GPTConfig:
    block_size: int = 128   # context length (characters)
    vocab_size: int = 65    # set after building vocab
    n_layer: int = 4
    n_head: int = 4
    n_embd: int = 128
    dropout: float = 0.1


class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        self.c_attn  = nn.Linear(config.n_embd, 3 * config.n_embd, bias=False)
        self.c_proj  = nn.Linear(config.n_embd, config.n_embd, bias=False)
        self.attn_drop  = nn.Dropout(config.dropout)
        self.resid_drop = nn.Dropout(config.dropout)
        self.n_head  = config.n_head
        self.n_embd  = config.n_embd
        self.register_buffer(
            "bias",
            torch.tril(torch.ones(config.block_size, config.block_size))
            .view(1, 1, config.block_size, config.block_size),
        )

    def forward(self, x):
        B, T, C = x.size()
        q, k, v = self.c_attn(x).split(self.n_embd, dim=2)
        nh, hs = self.n_head, C // self.n_head
        q = q.view(B, T, nh, hs).transpose(1, 2)
        k = k.view(B, T, nh, hs).transpose(1, 2)
        v = v.view(B, T, nh, hs).transpose(1, 2)
        att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(hs))
        att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float("-inf"))
        att = F.softmax(att, dim=-1)
        att = self.attn_drop(att)
        y = att @ v
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.resid_drop(self.c_proj(y))


class MLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.c_fc   = nn.Linear(config.n_embd, 4 * config.n_embd, bias=False)
        self.gelu   = nn.GELU()
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd, bias=False)
        self.drop   = nn.Dropout(config.dropout)

    def forward(self, x):
        return self.drop(self.c_proj(self.gelu(self.c_fc(x))))


class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.n_embd)
        self.mlp  = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln_1(x))
        x = x + self.mlp(self.ln_2(x))
        return x


class GPT(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        self.config = config
        self.transformer = nn.ModuleDict(dict(
            wte  = nn.Embedding(config.vocab_size, config.n_embd),
            wpe  = nn.Embedding(config.block_size, config.n_embd),
            drop = nn.Dropout(config.dropout),
            h    = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f = nn.LayerNorm(config.n_embd),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        # weight tying
        self.transformer.wte.weight = self.lm_head.weight
        self.apply(self._init_weights)

    def _init_weights(self, module):
        if isinstance(module, (nn.Linear, nn.Embedding)):
            nn.init.normal_(module.weight, mean=0.0, std=0.02)

    def forward(self, idx, targets=None):
        B, T = idx.size()
        assert T <= self.config.block_size, f"Sequence {T} > block_size {self.config.block_size}"
        pos = torch.arange(T, dtype=torch.long, device=idx.device)
        x = self.transformer.drop(self.transformer.wte(idx) + self.transformer.wpe(pos))
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)
        logits = self.lm_head(x)
        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
        return logits, loss

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=0.8, top_k=40):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.config.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / temperature
            if top_k is not None:
                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
                logits[logits < v[:, [-1]]] = float("-inf")
            probs = F.softmax(logits, dim=-1)
            next_tok = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, next_tok), dim=1)
        return idx