import torch
DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

import numpy as np
def subsequent_mask(size):
    attn_shape = (1, size, size)
    subsequent_mask = np.triu(np.ones(attn_shape),
                              k=1).astype('uint8')
    output = torch.from_numpy(subsequent_mask) == 0
    return output


def make_std_mask(tgt, pad):
    tgt_mask=(tgt != pad).unsqueeze(-2)
    output=tgt_mask & subsequent_mask(tgt.size(-1)).type_as(tgt_mask.data)
    return output 

# define the Batch class
class Batch:
    def __init__(self, src, trg=None, pad=0):
        src = torch.from_numpy(src).to(DEVICE).long()
        self.src = src
        self.src_mask = (src != pad).unsqueeze(-2)
        if trg is not None:
            trg = torch.from_numpy(trg).to(DEVICE).long()
            self.trg = trg[:, :-1]
            self.trg_y = trg[:, 1:]
            self.trg_mask = make_std_mask(self.trg, pad)
            self.ntokens = (self.trg_y != pad).data.sum()

from torch import nn
# An encoder-decoder transformer
class Transformer(nn.Module):
    def __init__(self, encoder, decoder,
                 src_embed, tgt_embed, generator):
        super().__init__()
        self.encoder = encoder
        self.decoder = decoder
        self.src_embed = src_embed
        self.tgt_embed = tgt_embed
        self.generator = generator

    def encode(self, src, src_mask):
        return self.encoder(self.src_embed(src), src_mask)

    def decode(self, memory, src_mask, tgt, tgt_mask):
        return self.decoder(self.tgt_embed(tgt), 
                            memory, src_mask, tgt_mask)

    def forward(self, src, tgt, src_mask, tgt_mask):
        memory = self.encode(src, src_mask)
        output = self.decode(memory, src_mask, tgt, tgt_mask)
        return output

# Create an encoder
from copy import deepcopy
class Encoder(nn.Module):
    def __init__(self, layer, N):
        super().__init__()
        self.layers = nn.ModuleList(
            [deepcopy(layer) for i in range(N)])
        self.norm = LayerNorm(layer.size)

    def forward(self, x, mask):
        for layer in self.layers:
            x = layer(x, mask)
            output = self.norm(x)
        return output

class EncoderLayer(nn.Module):
    def __init__(self, size, self_attn, feed_forward, dropout):
        super().__init__()
        self.self_attn = self_attn
        self.feed_forward = feed_forward
        self.sublayer = nn.ModuleList([deepcopy(
        SublayerConnection(size, dropout)) for i in range(2)])
        self.size = size  

    def forward(self, x, mask):
        x = self.sublayer[0](
            x, lambda x: self.self_attn(x, x, x, mask))
        output = self.sublayer[1](x, self.feed_forward)
        return output 
    
class SublayerConnection(nn.Module):
    def __init__(self, size, dropout):
        super().__init__()
        self.norm = LayerNorm(size)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, sublayer):
        output = x + self.dropout(sublayer(self.norm(x)))
        return output  

class LayerNorm(nn.Module):
    def __init__(self, features, eps=1e-6):
        super().__init__()
        self.a_2 = nn.Parameter(torch.ones(features))
        self.b_2 = nn.Parameter(torch.zeros(features))
        self.eps = eps

    def forward(self, x):
        mean = x.mean(-1, keepdim=True) 
        std = x.std(-1, keepdim=True)
        x_zscore = (x - mean) / torch.sqrt(std ** 2 + self.eps)
        output = self.a_2*x_zscore+self.b_2
        return output

# Create a decoder
class Decoder(nn.Module):
    def __init__(self, layer, N):
        super().__init__()
        self.layers = nn.ModuleList(
            [deepcopy(layer) for i in range(N)])
        self.norm = LayerNorm(layer.size)

    def forward(self, x, memory, src_mask, tgt_mask):
        for layer in self.layers:
            x = layer(x, memory, src_mask, tgt_mask)
        output = self.norm(x)
        return output

class DecoderLayer(nn.Module):
    def __init__(self, size, self_attn, src_attn,
                 feed_forward, dropout):
        super().__init__()
        self.size = size
        self.self_attn = self_attn
        self.src_attn = src_attn
        self.feed_forward = feed_forward
        self.sublayer = nn.ModuleList([deepcopy(
        SublayerConnection(size, dropout)) for i in range(3)])

    def forward(self, x, memory, src_mask, tgt_mask):
        x = self.sublayer[0](x, lambda x: 
                 self.self_attn(x, x, x, tgt_mask))
        x = self.sublayer[1](x, lambda x:
                 self.src_attn(x, memory, memory, src_mask))
        output = self.sublayer[2](x, self.feed_forward)
        return output 



# create the model
def create_model(src_vocab, tgt_vocab, N, d_model,
                 d_ff, h, dropout=0.1):
    attn=MultiHeadedAttention(h, d_model).to(DEVICE)
    ff=PositionwiseFeedForward(d_model, d_ff, dropout).to(DEVICE)
    pos=PositionalEncoding(d_model, dropout).to(DEVICE)
    model = Transformer(
        Encoder(EncoderLayer(d_model,deepcopy(attn),deepcopy(ff),
                             dropout).to(DEVICE),N).to(DEVICE),
        Decoder(DecoderLayer(d_model,deepcopy(attn),
             deepcopy(attn),deepcopy(ff), dropout).to(DEVICE),
                N).to(DEVICE),
        nn.Sequential(Embeddings(d_model, src_vocab).to(DEVICE),
                      deepcopy(pos)),
        nn.Sequential(Embeddings(d_model, tgt_vocab).to(DEVICE),
                      deepcopy(pos)),
        Generator(d_model, tgt_vocab)).to(DEVICE)
    for p in model.parameters():
        if p.dim() > 1:
            nn.init.xavier_uniform_(p)
    return model.to(DEVICE)

import math
class Embeddings(nn.Module):
    def __init__(self, d_model, vocab):
        super().__init__()
        self.lut = nn.Embedding(vocab, d_model)
        self.d_model = d_model

    def forward(self, x):
        out = self.lut(x) * math.sqrt(self.d_model)
        return out



class PositionalEncoding(nn.Module):
    def __init__(self, d_model, dropout, max_len=5000):
        super().__init__()
        self.dropout = nn.Dropout(p=dropout)
        pe = torch.zeros(max_len, d_model, device=DEVICE)
        position = torch.arange(0., max_len, 
                                device=DEVICE).unsqueeze(1)
        div_term = torch.exp(torch.arange(
            0., d_model, 2, device=DEVICE)
            * -(math.log(10000.0) / d_model))
        pe_pos = torch.mul(position, div_term)
        pe[:, 0::2] = torch.sin(pe_pos)
        pe[:, 1::2] = torch.cos(pe_pos)
        pe = pe.unsqueeze(0)
        self.register_buffer('pe', pe)  

    def forward(self, x):
        x = x + self.pe[:, :x.size(1)].requires_grad_(False)
        out = self.dropout(x)
        return out

def attention(query, key, value, mask=None, dropout=None):
    d_k = query.size(-1)
    scores = torch.matmul(query, 
              key.transpose(-2, -1)) / math.sqrt(d_k)
    if mask is not None:
        scores = scores.masked_fill(mask == 0, -1e9)
    p_attn = nn.functional.softmax(scores, dim=-1)
    if dropout is not None:
        p_attn = dropout(p_attn)
    return torch.matmul(p_attn, value), p_attn

class MultiHeadedAttention(nn.Module):
    def __init__(self, h, d_model, dropout=0.1):
        super().__init__()
        assert d_model % h == 0
        self.d_k = d_model // h
        self.h = h
        self.linears = nn.ModuleList([deepcopy(
            nn.Linear(d_model, d_model)) for i in range(4)])
        self.attn = None
        self.dropout = nn.Dropout(p=dropout)

    def forward(self, query, key, value, mask=None):
        if mask is not None:
            mask = mask.unsqueeze(1)
        nbatches = query.size(0)  
        query, key, value = [l(x).view(nbatches, -1, self.h,
           self.d_k).transpose(1, 2)
         for l, x in zip(self.linears, (query, key, value))]
        x, self.attn = attention(
            query, key, value, mask=mask, dropout=self.dropout)
        x = x.transpose(1, 2).contiguous().view(
            nbatches, -1, self.h * self.d_k)
        output = self.linears[-1](x)
        return output 
    
class Generator(nn.Module):
    def __init__(self, d_model, vocab):
        super().__init__()
        self.proj = nn.Linear(d_model, vocab)

    def forward(self, x):
        out = self.proj(x)
        probs = nn.functional.log_softmax(out, dim=-1)
        return probs   
    
    
class PositionwiseFeedForward(nn.Module):
    def __init__(self, d_model, d_ff, dropout=0.1):
        super().__init__()
        self.w_1 = nn.Linear(d_model, d_ff)
        self.w_2 = nn.Linear(d_ff, d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        h1 = self.w_1(x)
        h2 = self.dropout(h1)
        return self.w_2(h2)   
    
    


class LabelSmoothing(nn.Module):
    def __init__(self, size, padding_idx, smoothing=0.1):
        super().__init__()
        self.criterion = nn.KLDivLoss(reduction='sum')  
        self.padding_idx = padding_idx
        self.confidence = 1.0 - smoothing
        self.smoothing = smoothing
        self.size = size
        self.true_dist = None

    def forward(self, x, target):
        assert x.size(1) == self.size
        true_dist = x.data.clone()
        true_dist.fill_(self.smoothing / (self.size - 2))
        true_dist.scatter_(1, 
               target.data.unsqueeze(1), self.confidence)
        true_dist[:, self.padding_idx] = 0
        mask = torch.nonzero(target.data == self.padding_idx)
        if mask.dim() > 0:
            true_dist.index_fill_(0, mask.squeeze(), 0.0)
        self.true_dist = true_dist
        output = self.criterion(x, true_dist.clone().detach())
        return output

class SimpleLossCompute:
    def __init__(self, generator, criterion, opt=None):
        self.generator = generator
        self.criterion = criterion
        self.opt = opt

    def __call__(self, x, y, norm):
        x = self.generator(x)
        loss = self.criterion(x.contiguous().view(-1, x.size(-1)),
                              y.contiguous().view(-1)) / norm
        loss.backward()
        if self.opt is not None:
            self.opt.step()
            self.opt.optimizer.zero_grad()
        return loss.data.item() * norm.float()

class NoamOpt:
    def __init__(self, model_size, factor, warmup, optimizer):
        self.optimizer = optimizer
        self._step = 0
        self.warmup = warmup
        self.factor = factor
        self.model_size = model_size
        self._rate = 0

    def step(self):
        self._step += 1
        rate = self.rate()
        for p in self.optimizer.param_groups:
            p['lr'] = rate
        self._rate = rate
        self.optimizer.step()

    def rate(self, step=None):
        if step is None:
            step = self._step
        output = self.factor * (self.model_size ** (-0.5) *
        min(step ** (-0.5), step * self.warmup ** (-1.5)))
        return output