import torch
import torch.nn as nn
import torch.nn.functional as F
from dataclasses import dataclass
import inspect
from .attention import CasualSelfAttention

class MLP(nn.Module):

    def __init__(self, config):
        super().__init__()
        self.c_fc = nn.Linear(config.n_embd, 4 * config.n_embd)
        self.gelu = nn.GELU(approximate='tanh')
        self.c_proj = nn.Linear(4 * config.n_embd, config.n_embd)
        self.c_proj.NANOGPT_SCALE_INIT = 1

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

class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd)
        self.attn = CasualSelfAttention(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


@dataclass
class GPTConfig:
    block_size: int = 1024 #max sequence length
    vocab_size: int = 50257 #number of tokens: 50000 BPE merges + 256 byte tokens +1 special token which is endoftext
    n_layer: int = 12 #number of layers
    n_head: int = 12 #number of heads
    n_embd: int = 768 #embedding dimensions


class GPT(nn.Module):
    def __init__(self, config):
        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),
            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 sharing scheme
        self.transformer.wte.weight = self.lm_head.weight

        # init params
        self.apply(self._init_weights)

    def _init_weights(self, module):
        if isinstance(module, nn.Linear):
            std = 0.02
            if hasattr(module, 'NANOGPT_SCALE_INIT'):
                std *= (2 * self.config.n_layer) ** -0.5
            torch.nn.init.normal_(module.weight, mean = 0.0, std=std)
            if module.bias is not None:
                torch.nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            torch.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"Cannot forward sequence of length {T} ,block size is only {self.config.block_size}"

        pos = torch.arange(0, T, dtype=torch.long, device=idx.device)
        pos_emb = self.transformer.wpe(pos)
        tok_emb = self.transformer.wte(idx)
        x = tok_emb + pos_emb

        for block in self.transformer.h:
            x = block(x)

        x = self.transformer.ln_f(x)
        logits = self.lm_head(x) #(B, T, vocab_size)
        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
        
        return logits, loss
    
    def configure_optimizers(self, weight_decay, learning_rate, device_type, master_process):
        param_dict = {pn:p for pn, p in self.named_parameters()}
        param_dict = {pn:p for pn, p in param_dict.items() if p.requires_grad}
        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
        optim_groups = [{'params':decay_params, ' weight_decay': weight_decay},
                       {'params':nodecay_params, 'weight_decay': 0.0}
                       ]
        num_decay_params = sum(p.numel() for p in decay_params)  
        num_nodecay_params = sum(p.numel() for p in nodecay_params) 
        if master_process:
            print(f"num decayed parameters tensors: {len(decay_params)}, with{num_decay_params}:parameters")
            print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
        use_fused = fused_available and device_type == "cuda"    
        if master_process:
            print(f"using fused AdamW: {use_fused}")
        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=(0.9,0.95), eps=1e-8, fused=use_fused)
        return optimizer