import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import math
from math import sqrt

class TriangularCausalMask():
    def __init__(self, B, L, device="cpu"):
        mask_shape = [B, 1, L, L]
        with torch.no_grad():
            self._mask = torch.triu(torch.ones(mask_shape, dtype=torch.bool), diagonal=1).to(device)

    @property
    def mask(self):
        return self._mask

class PositionalEmbedding(nn.Module):
    def __init__(self, d_model, max_len=5000):
        super(PositionalEmbedding, self).__init__()
        # Compute the positional encodings once in log space.
        pe = torch.zeros(max_len, d_model).float()
        pe.require_grad = False

        position = torch.arange(0, max_len).float().unsqueeze(1)
        div_term = (torch.arange(0, d_model, 2).float()
                    * -(math.log(10000.0) / d_model)).exp()

        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)

        pe = pe.unsqueeze(0)
        self.register_buffer('pe', pe)

    def forward(self, x):
        return self.pe[:, :x.size(1)]

class FixedEmbedding(nn.Module):
    def __init__(self, c_in, d_model):
        super(FixedEmbedding, self).__init__()

        w = torch.zeros(c_in, d_model).float()
        w.require_grad = False

        position = torch.arange(0, c_in).float().unsqueeze(1)
        div_term = (torch.arange(0, d_model, 2).float()
                    * -(math.log(10000.0) / d_model)).exp()

        w[:, 0::2] = torch.sin(position * div_term)
        w[:, 1::2] = torch.cos(position * div_term)

        self.emb = nn.Embedding(c_in, d_model)
        self.emb.weight = nn.Parameter(w, requires_grad=False)

    def forward(self, x):
        return self.emb(x).detach()

class TemporalEmbedding(nn.Module):
    def __init__(self, d_model, embed_type='fixed', freq='h'):
        super(TemporalEmbedding, self).__init__()

        hour_size = 96
        weekday_size = 7

        Embed = FixedEmbedding if embed_type == 'fixed' else nn.Embedding
        self.hour_embed = Embed(hour_size, d_model)
        self.weekday_embed = Embed(weekday_size, d_model)
        
    def forward(self, x):
        x = x.long()
        hour_x = self.hour_embed(x[:, :, 0])
        weekday_x = self.weekday_embed(x[:, :, 1])

        return hour_x + weekday_x

class TokenEmbedding(nn.Module):
    def __init__(self, c_in, d_model):
        super(TokenEmbedding, self).__init__()
        padding = 1 if torch.__version__ >= '1.5.0' else 2
        self.tokenConv = nn.Conv1d(in_channels=c_in, out_channels=d_model,
                                   kernel_size=3, padding=padding, padding_mode='circular', bias=False)
        for m in self.modules():
            if isinstance(m, nn.Conv1d):
                nn.init.kaiming_normal_(
                    m.weight, mode='fan_in', nonlinearity='leaky_relu')

    def forward(self, x):
        x = self.tokenConv(x.permute(0, 2, 1)).transpose(1, 2)
        return x

class DataEmbedding(nn.Module):
    def __init__(self, c_in, d_model, embed_type='fixed', freq='h', dropout=0.1):
        super(DataEmbedding, self).__init__()

        self.value_embedding = TokenEmbedding(c_in=c_in, d_model=d_model)
        self.position_embedding = PositionalEmbedding(d_model=d_model)
        self.temporal_embedding = TemporalEmbedding(d_model=d_model, embed_type=embed_type,
                                                    freq=freq)
        self.dropout = nn.Dropout(p=dropout)

    def forward(self, x, x_mark):
        if x_mark is None:
            x = self.value_embedding(x) + self.position_embedding(x)
        else:
            x = self.value_embedding(
                x) + self.temporal_embedding(x_mark) + self.position_embedding(x)
        return self.dropout(x)

class AttentionLayer(nn.Module):
    def __init__(self, attention, d_model, n_heads, d_keys=None,
                 d_values=None):
        super(AttentionLayer, self).__init__()

        d_keys = d_keys or (d_model // n_heads)
        d_values = d_values or (d_model // n_heads)

        self.inner_attention = attention
        self.query_projection = nn.Linear(d_model, d_keys * n_heads)
        self.key_projection = nn.Linear(d_model, d_keys * n_heads)
        self.value_projection = nn.Linear(d_model, d_values * n_heads)
        self.out_projection = nn.Linear(d_values * n_heads, d_model)
        self.n_heads = n_heads

    def forward(self, queries, keys, values, attn_mask, tau=None, delta=None):
        B, L, _ = queries.shape
        _, S, _ = keys.shape
        H = self.n_heads

        queries = self.query_projection(queries).view(B, L, H, -1)
        keys = self.key_projection(keys).view(B, S, H, -1)
        values = self.value_projection(values).view(B, S, H, -1)

        out, attn = self.inner_attention(
            queries,
            keys,
            values,
            attn_mask,
            tau=tau,
            delta=delta
        )
        out = out.view(B, L, -1)

        return self.out_projection(out), attn

class FullAttention(nn.Module):
    def __init__(self, mask_flag=True, factor=5, scale=None, attention_dropout=0.1, output_attention=False):
        super(FullAttention, self).__init__()
        self.scale = scale
        self.mask_flag = mask_flag
        self.output_attention = output_attention
        self.dropout = nn.Dropout(attention_dropout)

    def forward(self, queries, keys, values, attn_mask, tau=None, delta=None):
        B, L, H, E = queries.shape
        _, S, _, D = values.shape
        scale = self.scale or 1. / sqrt(E)

        scores = torch.einsum("blhe,bshe->bhls", queries, keys)

        if self.mask_flag:
            if attn_mask is None:
                attn_mask = TriangularCausalMask(B, L, device=queries.device)

            scores.masked_fill_(attn_mask.mask, -np.inf)

        A = self.dropout(torch.softmax(scale * scores, dim=-1))
        V = torch.einsum("bhls,bshd->blhd", A, values)

        if self.output_attention:
            return V.contiguous(), A
        else:
            return V.contiguous(), None

class ConvLayer(nn.Module):
    def __init__(self, c_in):
        super(ConvLayer, self).__init__()
        self.downConv = nn.Conv1d(in_channels=c_in,
                                  out_channels=c_in,
                                  kernel_size=3,
                                  padding=2,
                                  padding_mode='circular')
        self.norm = nn.BatchNorm1d(c_in)
        self.activation = nn.ELU()
        self.maxPool = nn.MaxPool1d(kernel_size=3, stride=2, padding=1)

    def forward(self, x):
        x = self.downConv(x.permute(0, 2, 1))
        x = self.norm(x)
        x = self.activation(x)
        x = self.maxPool(x)
        x = x.transpose(1, 2)
        return x

class EncoderLayer(nn.Module):
    def __init__(self, attention, d_model, d_ff=None, dropout=0.1, activation="relu"):
        super(EncoderLayer, self).__init__()
        d_ff = d_ff or 4 * d_model
        self.attention = attention
        self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)
        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        self.activation = F.relu if activation == "relu" else F.gelu

    def forward(self, x, attn_mask=None, tau=None, delta=None):
        new_x, attn = self.attention(
            x, x, x,
            attn_mask=attn_mask,
            tau=tau, delta=delta
        )
        x = x + self.dropout(new_x)

        y = x = self.norm1(x)
        y = self.dropout(self.activation(self.conv1(y.transpose(-1, 1))))
        y = self.dropout(self.conv2(y).transpose(-1, 1))

        return self.norm2(x + y), attn


class Encoder(nn.Module):
    def __init__(self, attn_layers, conv_layers=None, norm_layer=None):
        super(Encoder, self).__init__()
        self.attn_layers = nn.ModuleList(attn_layers)
        self.conv_layers = nn.ModuleList(conv_layers) if conv_layers is not None else None
        self.norm = norm_layer

    def forward(self, x, attn_mask=None, tau=None, delta=None):
        # x [B, L, D]
        attns = []
        if self.conv_layers is not None:
            for i, (attn_layer, conv_layer) in enumerate(zip(self.attn_layers, self.conv_layers)):
                delta = delta if i == 0 else None
                x, attn = attn_layer(x, attn_mask=attn_mask, tau=tau, delta=delta)
                x = conv_layer(x)
                attns.append(attn)
            x, attn = self.attn_layers[-1](x, tau=tau, delta=None)
            attns.append(attn)
        else:
            for attn_layer in self.attn_layers:
                x, attn = attn_layer(x, attn_mask=attn_mask, tau=tau, delta=delta)
                attns.append(attn)

        if self.norm is not None:
            x = self.norm(x)

        return x, attns


class DecoderLayer(nn.Module):
    def __init__(self, self_attention, cross_attention, d_model, d_ff=None,
                 dropout=0.1, activation="relu"):
        super(DecoderLayer, self).__init__()
        d_ff = d_ff or 4 * d_model
        self.self_attention = self_attention
        self.cross_attention = cross_attention
        self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1)
        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        self.activation = F.relu if activation == "relu" else F.gelu

    def forward(self, x, cross, x_mask=None, cross_mask=None, tau=None, delta=None):
        x = x + self.dropout(self.self_attention(
            x, x, x,
            attn_mask=x_mask,
            tau=tau, delta=None
        )[0])
        x = self.norm1(x)

        x = x + self.dropout(self.cross_attention(
            x, cross, cross,
            attn_mask=cross_mask,
            tau=tau, delta=delta
        )[0])

        y = x = self.norm2(x)
        y = self.dropout(self.activation(self.conv1(y.transpose(-1, 1))))
        y = self.dropout(self.conv2(y).transpose(-1, 1))

        return self.norm3(x + y)


class Decoder(nn.Module):
    def __init__(self, layers, norm_layer=None, projection=None):
        super(Decoder, self).__init__()
        self.layers = nn.ModuleList(layers)
        self.norm = norm_layer
        self.projection = projection

    def forward(self, x, cross, x_mask=None, cross_mask=None, tau=None, delta=None):
        for layer in self.layers:
            x = layer(x, cross, x_mask=x_mask, cross_mask=cross_mask, tau=tau, delta=delta)

        if self.norm is not None:
            x = self.norm(x)

        if self.projection is not None:
            x = self.projection(x)
        return x

class Transformer(nn.Module):
    """
    Vanilla Transformer
    with O(L^2) complexity
    Paper link: https://proceedings.neurips.cc/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
    """

    def __init__(
        self,
        enc_in,
        dec_in,
        c_out,
        pred_len,
        output_attention = False,
        data_idx = [0,3,4,5,6,7],
        time_idx = [1,2],
        d_model = 16,
        factor = 3,
        n_heads = 4,
        d_ff = 512,
        d_layers = 3,
        e_layers = 3,
        activation = 'gelu',
        dropout = 0.1
    ):
        super(Transformer, self).__init__()
        self.pred_len = pred_len
        self.output_attention = output_attention
        # save indices
        self.data_idx = data_idx
        self.time_idx = time_idx
        self.dec_in = dec_in
        # Embedding
        self.enc_embedding = DataEmbedding(enc_in, d_model,'fixed', 'h',
                                           dropout)
        # Encoder
        self.encoder = Encoder(
            [
                EncoderLayer(
                    AttentionLayer(
                        FullAttention(False, factor, attention_dropout=dropout,
                                      output_attention=output_attention), d_model, n_heads),
                    d_model,
                    d_ff,
                    dropout=dropout,
                    activation=activation
                ) for l in range(e_layers)
            ],
            norm_layer=torch.nn.LayerNorm(d_model)
        )
        # Decoder
        self.dec_embedding = DataEmbedding(dec_in, d_model,'fixed', 'h',
                                            dropout)
        self.decoder = Decoder(
            [
                DecoderLayer(
                    AttentionLayer(
                        FullAttention(True, factor, attention_dropout=dropout,
                                        output_attention=False),
                        d_model, n_heads),
                    AttentionLayer(
                        FullAttention(False, factor, attention_dropout=dropout,
                                        output_attention=False),
                        d_model, n_heads),
                    d_model,
                    d_ff,
                    dropout=dropout,
                    activation=activation,
                )
                for l in range(d_layers)
            ],
            norm_layer=torch.nn.LayerNorm(d_model),
            projection=nn.Linear(d_model, c_out, bias=True)
        )

    def forecast(self, x_enc, x_mark_enc, x_dec, x_mark_dec):
        # Embedding
        enc_out = self.enc_embedding(x_enc, x_mark_enc)
        enc_out, attns = self.encoder(enc_out, attn_mask=None)

        dec_out = self.dec_embedding(x_dec, x_mark_dec)
        dec_out = self.decoder(dec_out, enc_out, x_mask=None, cross_mask=None)
        return dec_out
    
    def forward(self, x, fut_time):
        
        x_enc = x[:,:,self.data_idx]
        x_mark_enc = x[:,:,self.time_idx]
        x_dec = torch.zeros((fut_time.shape[0],fut_time.shape[1],self.dec_in),dtype=fut_time.dtype,device=fut_time.device)
        x_mark_dec = fut_time
        
        return self.forecast(x_enc,x_mark_enc,x_dec,x_mark_dec)[:,-1,[0]]