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

class AutoCorrelation(nn.Module):
    """
    AutoCorrelation Mechanism with the following two phases:
    (1) period-based dependencies discovery
    (2) time delay aggregation
    This block can replace the self-attention family mechanism seamlessly.
    """

    def __init__(self, mask_flag=True, factor=1, scale=None, attention_dropout=0.1, output_attention=False):
        super(AutoCorrelation, self).__init__()
        self.factor = factor
        self.scale = scale
        self.mask_flag = mask_flag
        self.output_attention = output_attention
        self.dropout = nn.Dropout(attention_dropout)

    def time_delay_agg_training(self, values, corr):
        """
        SpeedUp version of Autocorrelation (a batch-normalization style design)
        This is for the training phase.
        """
        head = values.shape[1]
        channel = values.shape[2]
        length = values.shape[3]
        # find top k
        top_k = int(self.factor * math.log(length))
        mean_value = torch.mean(torch.mean(corr, dim=1), dim=1)
        index = torch.topk(torch.mean(mean_value, dim=0), top_k, dim=-1)[1]
        weights = torch.stack([mean_value[:, index[i]] for i in range(top_k)], dim=-1)
        # update corr
        tmp_corr = torch.softmax(weights, dim=-1)
        # aggregation
        tmp_values = values
        delays_agg = torch.zeros_like(values).float()
        for i in range(top_k):
            pattern = torch.roll(tmp_values, -int(index[i]), -1)
            delays_agg = delays_agg + pattern * \
                         (tmp_corr[:, i].unsqueeze(1).unsqueeze(1).unsqueeze(1).repeat(1, head, channel, length))
        return delays_agg

    def time_delay_agg_inference(self, values, corr):
        """
        SpeedUp version of Autocorrelation (a batch-normalization style design)
        This is for the inference phase.
        """
        batch = values.shape[0]
        head = values.shape[1]
        channel = values.shape[2]
        length = values.shape[3]
        # index init
        init_index = torch.arange(length).unsqueeze(0).unsqueeze(0).unsqueeze(0).repeat(batch, head, channel, 1).cuda()
        # find top k
        top_k = int(self.factor * math.log(length))
        mean_value = torch.mean(torch.mean(corr, dim=1), dim=1)
        weights, delay = torch.topk(mean_value, top_k, dim=-1)
        # update corr
        tmp_corr = torch.softmax(weights, dim=-1)
        # aggregation
        tmp_values = values.repeat(1, 1, 1, 2)
        delays_agg = torch.zeros_like(values).float()
        for i in range(top_k):
            tmp_delay = init_index + delay[:, i].unsqueeze(1).unsqueeze(1).unsqueeze(1).repeat(1, head, channel, length)
            pattern = torch.gather(tmp_values, dim=-1, index=tmp_delay)
            delays_agg = delays_agg + pattern * \
                         (tmp_corr[:, i].unsqueeze(1).unsqueeze(1).unsqueeze(1).repeat(1, head, channel, length))
        return delays_agg

    def time_delay_agg_full(self, values, corr):
        """
        Standard version of Autocorrelation
        """
        batch = values.shape[0]
        head = values.shape[1]
        channel = values.shape[2]
        length = values.shape[3]
        # index init
        init_index = torch.arange(length).unsqueeze(0).unsqueeze(0).unsqueeze(0).repeat(batch, head, channel, 1).cuda()
        # find top k
        top_k = int(self.factor * math.log(length))
        weights, delay = torch.topk(corr, top_k, dim=-1)
        # update corr
        tmp_corr = torch.softmax(weights, dim=-1)
        # aggregation
        tmp_values = values.repeat(1, 1, 1, 2)
        delays_agg = torch.zeros_like(values).float()
        for i in range(top_k):
            tmp_delay = init_index + delay[..., i].unsqueeze(-1)
            pattern = torch.gather(tmp_values, dim=-1, index=tmp_delay)
            delays_agg = delays_agg + pattern * (tmp_corr[..., i].unsqueeze(-1))
        return delays_agg

    def forward(self, queries, keys, values, attn_mask):
        B, L, H, E = queries.shape
        _, S, _, D = values.shape
        if L > S:
            zeros = torch.zeros_like(queries[:, :(L - S), :]).float()
            values = torch.cat([values, zeros], dim=1)
            keys = torch.cat([keys, zeros], dim=1)
        else:
            values = values[:, :L, :, :]
            keys = keys[:, :L, :, :]

        # period-based dependencies
        q_fft = torch.fft.rfft(queries.permute(0, 2, 3, 1).contiguous(), dim=-1)
        k_fft = torch.fft.rfft(keys.permute(0, 2, 3, 1).contiguous(), dim=-1)
        res = q_fft * torch.conj(k_fft)
        corr = torch.fft.irfft(res, dim=-1)

        # time delay agg
        if self.training:
            V = self.time_delay_agg_training(values.permute(0, 2, 3, 1).contiguous(), corr).permute(0, 3, 1, 2)
        else:
            V = self.time_delay_agg_inference(values.permute(0, 2, 3, 1).contiguous(), corr).permute(0, 3, 1, 2)

        if self.output_attention:
            return (V.contiguous(), corr.permute(0, 3, 1, 2))
        else:
            return (V.contiguous(), None)


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

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

        self.inner_correlation = correlation
        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):
        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_correlation(
            queries,
            keys,
            values,
            attn_mask
        )
        out = out.view(B, L, -1)

        return self.out_projection(out), attn

class my_Layernorm(nn.Module):
    """
    Special designed layernorm for the seasonal part
    """

    def __init__(self, channels):
        super(my_Layernorm, self).__init__()
        self.layernorm = nn.LayerNorm(channels)

    def forward(self, x):
        x_hat = self.layernorm(x)
        bias = torch.mean(x_hat, dim=1).unsqueeze(1).repeat(1, x.shape[1], 1)
        return x_hat - bias


class moving_avg(nn.Module):
    """
    Moving average block to highlight the trend of time series
    """

    def __init__(self, kernel_size, stride):
        super(moving_avg, self).__init__()
        self.kernel_size = kernel_size
        self.avg = nn.AvgPool1d(kernel_size=kernel_size, stride=stride, padding=0)

    def forward(self, x):
        # padding on the both ends of time series
        front = x[:, 0:1, :].repeat(1, (self.kernel_size - 1) // 2, 1)
        end = x[:, -1:, :].repeat(1, (self.kernel_size - 1) // 2, 1)
        x = torch.cat([front, x, end], dim=1)
        x = self.avg(x.permute(0, 2, 1))
        x = x.permute(0, 2, 1)
        return x


class series_decomp(nn.Module):
    """
    Series decomposition block
    """

    def __init__(self, kernel_size):
        super(series_decomp, self).__init__()
        self.moving_avg = moving_avg(kernel_size, stride=1)

    def forward(self, x):
        moving_mean = self.moving_avg(x)
        res = x - moving_mean
        return res, moving_mean


class series_decomp_multi(nn.Module):
    """
    Multiple Series decomposition block from FEDformer
    """

    def __init__(self, kernel_size):
        super(series_decomp_multi, self).__init__()
        self.kernel_size = kernel_size
        self.series_decomp = [series_decomp(kernel) for kernel in kernel_size]

    def forward(self, x):
        moving_mean = []
        res = []
        for func in self.series_decomp:
            sea, moving_avg = func(x)
            moving_mean.append(moving_avg)
            res.append(sea)

        sea = sum(res) / len(res)
        moving_mean = sum(moving_mean) / len(moving_mean)
        return sea, moving_mean


class EncoderLayer(nn.Module):
    """
    Autoformer encoder layer with the progressive decomposition architecture
    """

    def __init__(self, attention, d_model, d_ff=None, moving_avg=25, 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, bias=False)
        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1, bias=False)
        self.decomp1 = series_decomp(moving_avg)
        self.decomp2 = series_decomp(moving_avg)
        self.dropout = nn.Dropout(dropout)
        self.activation = F.relu if activation == "relu" else F.gelu

    def forward(self, x, attn_mask=None):
        new_x, attn = self.attention(
            x, x, x,
            attn_mask=attn_mask
        )
        x = x + self.dropout(new_x)
        x, _ = self.decomp1(x)
        y = x
        y = self.dropout(self.activation(self.conv1(y.transpose(-1, 1))))
        y = self.dropout(self.conv2(y).transpose(-1, 1))
        res, _ = self.decomp2(x + y)
        return res, attn


class Encoder(nn.Module):
    """
    Autoformer encoder
    """

    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):
        attns = []
        if self.conv_layers is not None:
            for attn_layer, conv_layer in zip(self.attn_layers, self.conv_layers):
                x, attn = attn_layer(x, attn_mask=attn_mask)
                x = conv_layer(x)
                attns.append(attn)
            x, attn = self.attn_layers[-1](x)
            attns.append(attn)
        else:
            for attn_layer in self.attn_layers:
                x, attn = attn_layer(x, attn_mask=attn_mask)
                attns.append(attn)

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

        return x, attns


class DecoderLayer(nn.Module):
    """
    Autoformer decoder layer with the progressive decomposition architecture
    """

    def __init__(self, self_attention, cross_attention, d_model, c_out, d_ff=None,
                 moving_avg=25, 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, bias=False)
        self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1, bias=False)
        self.decomp1 = series_decomp(moving_avg)
        self.decomp2 = series_decomp(moving_avg)
        self.decomp3 = series_decomp(moving_avg)
        self.dropout = nn.Dropout(dropout)
        self.projection = nn.Conv1d(in_channels=d_model, out_channels=c_out, kernel_size=3, stride=1, padding=1,
                                    padding_mode='circular', bias=False)
        self.activation = F.relu if activation == "relu" else F.gelu

    def forward(self, x, cross, x_mask=None, cross_mask=None):
        x = x + self.dropout(self.self_attention(
            x, x, x,
            attn_mask=x_mask
        )[0])
        x, trend1 = self.decomp1(x)
        x = x + self.dropout(self.cross_attention(
            x, cross, cross,
            attn_mask=cross_mask
        )[0])
        x, trend2 = self.decomp2(x)
        y = x
        y = self.dropout(self.activation(self.conv1(y.transpose(-1, 1))))
        y = self.dropout(self.conv2(y).transpose(-1, 1))
        x, trend3 = self.decomp3(x + y)

        residual_trend = trend1 + trend2 + trend3
        residual_trend = self.projection(residual_trend.permute(0, 2, 1)).transpose(1, 2)
        return x, residual_trend


class Decoder(nn.Module):
    """
    Autoformer encoder
    """

    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, trend=None):
        for layer in self.layers:
            x, residual_trend = layer(x, cross, x_mask=x_mask, cross_mask=cross_mask)
            trend = trend + residual_trend

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

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

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

        self.value_embedding = TokenEmbedding(c_in=c_in, 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)
        else:
            x = self.value_embedding(x) + self.temporal_embedding(x_mark)
        return self.dropout(x)

class Autoformer(nn.Module):
    """
    Autoformer is the first method to achieve the series-wise connection,
    with inherent O(LlogL) complexity
    Paper link: https://openreview.net/pdf?id=I55UqU-M11y
    """

    def __init__(
            self,
            enc_in,
            dec_in,
            c_out,
            pred_len,
            seq_len,
            d_model = 64,
            data_idx = [0,3,4,5,6,7],
            time_idx = [1,2],
            output_attention = False,
            moving_avg_val = 25,
            factor = 3,
            n_heads = 4,
            d_ff = 512,
            d_layers = 3,
            e_layers = 3,
            activation = 'gelu',
            dropout = 0.1
    ):
        super(Autoformer, self).__init__()
        self.seq_len = seq_len
        self.pred_len = pred_len
        self.output_attention = output_attention
        self.data_idx = data_idx
        self.time_idx = time_idx
        dec_in = enc_in # encoder and decoder shapes should be the same
        self.dec_in = dec_in
        self.label_len = self.seq_len//2

        # Decomp
        kernel_size = moving_avg_val
        self.decomp = series_decomp(kernel_size)

        # Embedding
        self.enc_embedding = DataEmbedding_wo_pos(enc_in, d_model, 'fixed','h',
                                                  dropout)
        # Encoder
        self.encoder = Encoder(
            [
                EncoderLayer(
                    AutoCorrelationLayer(
                        AutoCorrelation(False, factor, attention_dropout=dropout,
                                        output_attention=output_attention),
                        d_model, n_heads),
                    d_model,
                    d_ff,
                    moving_avg=moving_avg_val,
                    dropout=dropout,
                    activation=activation
                ) for l in range(e_layers)
            ],
            norm_layer=my_Layernorm(d_model)
        )
        # Decoder
        self.dec_embedding = DataEmbedding_wo_pos(dec_in, d_model, 'fixed','h',
                                                    dropout)
        self.decoder = Decoder(
            [
                DecoderLayer(
                    AutoCorrelationLayer(
                        AutoCorrelation(True, factor, attention_dropout=dropout,
                                        output_attention=False),
                        d_model, n_heads),
                    AutoCorrelationLayer(
                        AutoCorrelation(False, factor, attention_dropout=dropout,
                                        output_attention=False),
                        d_model, n_heads),
                    d_model,
                    c_out,
                    d_ff,
                    moving_avg=moving_avg_val,
                    dropout=dropout,
                    activation=activation,
                )
                for l in range(d_layers)
            ],
            norm_layer=my_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):
        # decomp init
        mean = torch.mean(x_enc, dim=1).unsqueeze(1).repeat(1, self.pred_len, 1)
        zeros = torch.zeros([x_mark_dec.shape[0], self.pred_len,self.dec_in], device=x_enc.device)
        seasonal_init, trend_init = self.decomp(x_enc)
        # decoder input
        trend_init = torch.cat([trend_init[:, -self.label_len:, :], mean], dim=1)
        seasonal_init = torch.cat([seasonal_init[:, -self.label_len:, :], zeros], dim=1)
        # enc
        enc_out = self.enc_embedding(x_enc, x_mark_enc)
        enc_out, attns = self.encoder(enc_out, attn_mask=None)
        # dec
        x_mark_dec = torch.cat([x_mark_enc,x_mark_dec],dim=1)[:,-(self.label_len+self.pred_len):,:]
        dec_out = self.dec_embedding(seasonal_init, x_mark_dec)
        seasonal_part, trend_part = self.decoder(dec_out, enc_out, x_mask=None, cross_mask=None,
                                                 trend=trend_init)
        dec_out = trend_part + seasonal_part

        
        return dec_out[:, -self.pred_len:, :]

    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
            
        # not necessary to generate decoder input
        # return self.forecast(x_enc, x_mark_enc, x_dec, x_mark_dec)[:,-1,[0]]  # [B, 1]
        return self.forecast(x_enc, x_mark_enc, None, x_mark_dec)[:,-1,[0]]  # [B, 1]