import torch

import numpy as np

def log_barrier(z, t=5):

    # Only one value

    if z.shape[0] == 1:

        if z <= - 1 / t ** 2:

            log_barrier_loss = - torch.log(-z) / t

        else:

            log_barrier_loss = t * z + -np.log(1 / (t ** 2)) / t + 1 / t

    # Constrain over multiple values

    else:

        log_barrier_loss = torch.tensor(0).cuda().float()

        for i in np.arange(0, z.shape[0]):

            zi = z[i, 0]

            if zi <= - 1 / t ** 2:

                log_barrier_loss += - torch.log(-zi) / t

            else:

                log_barrier_loss += t * zi + -np.log(1 / (t ** 2)) / t + 1 / t

    return log_barrier_loss

class SupConLoss(torch.nn.Module):

    """Supervised Contrastive Learning: https://arxiv.org/pdf/2004.11362.pdf.

    It also supports the unsupervised contrastive loss in SimCLR"""

    def __init__(self, temperature=0.07, contrast_mode='all',

                 base_temperature=0.07):

        super(SupConLoss, self).__init__()

        self.temperature = temperature

        self.contrast_mode = contrast_mode

        self.base_temperature = base_temperature

    def forward(self, features, labels=None, mask=None):

        """Compute loss for model. If both `labels` and `mask` are None,

        it degenerates to SimCLR unsupervised loss:

        https://arxiv.org/pdf/2002.05709.pdf

        Args:

            features: hidden vector of shape [bsz, n_views, ...].

            labels: ground truth of shape [bsz].

            mask: contrastive mask of shape [bsz, bsz], mask_{i,j}=1 if sample j

                has the same class as sample i. Can be asymmetric.

        Returns:

            A loss scalar.

        """

        device = (torch.device('cuda')

                  if features.is_cuda

                  else torch.device('cpu'))

        if len(features.shape) < 3:

            raise ValueError('`features` needs to be [bsz, n_views, ...],'

                             'at least 3 dimensions are required')

        if len(features.shape) > 3:

            features = features.view(features.shape[0], features.shape[1], -1)

        batch_size = features.shape[0]

        if labels is not None and mask is not None:

            raise ValueError('Cannot define both `labels` and `mask`')

        elif labels is None and mask is None:

            mask = torch.eye(batch_size, dtype=torch.float32).to(device)

        elif labels is not None:

            labels = labels.contiguous().view(-1, 1)

            if labels.shape[0] != batch_size:

                raise ValueError('Num of labels does not match num of features')

            mask = torch.eq(labels, labels.T).float().to(device)

        else:

            mask = mask.float().to(device)

        contrast_count = features.shape[1]

        contrast_feature = torch.cat(torch.unbind(features, dim=1), dim=0)

        if self.contrast_mode == 'one':

            anchor_feature = features[:, 0]

            anchor_count = 1

        elif self.contrast_mode == 'all':

            anchor_feature = contrast_feature

            anchor_count = contrast_count

        else:

            raise ValueError('Unknown mode: {}'.format(self.contrast_mode))

        # compute logits

        anchor_dot_contrast = torch.div(

            torch.matmul(anchor_feature, contrast_feature.T),

            self.temperature)

        # for numerical stability

        logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)

        logits = anchor_dot_contrast - logits_max.detach()

        # tile mask

        mask = mask.repeat(anchor_count, contrast_count)

        # mask-out self-contrast cases

        logits_mask = torch.scatter(

            torch.ones_like(mask),

            1,

            torch.arange(batch_size * anchor_count).view(-1, 1).to(device),

            0

        )

        mask = mask * logits_mask

        # compute log_prob

        exp_logits = torch.exp(logits) * logits_mask

        log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True) + 1e-3)

        # compute mean of log-likelihood over positive

        mean_log_prob_pos = (mask * log_prob).sum(1) / (mask.sum(1)+1e-3)

        # loss

        loss = - (self.temperature / self.base_temperature) * mean_log_prob_pos

        loss = loss.view(anchor_count, batch_size).mean()

        return loss

class SupervisedContrastiveLoss(torch.nn.Module):

    def __init__(self, temperature=0.1):

        super(SupervisedContrastiveLoss, self).__init__()

        self.temperature = temperature

    def forward(self, feature_vectors, labels):

        # Normalize feature vectors

        feature_vectors_normalized = torch.nn.functional.normalize(feature_vectors, p=2, dim=1)

        # Compute logits

        logits = torch.div(

            torch.matmul(

                feature_vectors_normalized, torch.transpose(feature_vectors_normalized, 0, 1)

            ),

            self.temperature,

        )

        return losses.NTXentLoss(temperature=0.07)(logits, torch.squeeze(labels))