# -*- coding: utf-8 -*-

import torch
import numpy as np
from typing import Union, List


class DiagonalGaussianDistribution(object):
    # Gaussian distribution
    def __init__(self, parameters: Union[torch.Tensor, List[torch.Tensor]], deterministic=False, feat_dim=1):
        self.feat_dim = feat_dim
        self.parameters = parameters

        if isinstance(parameters, list):
            self.mean = parameters[0]
            self.logvar = parameters[1]
        else:
            self.mean, self.logvar = torch.chunk(parameters, 2, dim=feat_dim)

        self.logvar = torch.clamp(self.logvar, -30.0, 20.0)
        self.deterministic = deterministic
        self.std = torch.exp(0.5 * self.logvar)
        self.var = torch.exp(self.logvar)
        if self.deterministic:
            self.var = self.std = torch.zeros_like(self.mean)

    # sample from the guassian distribution
    def sample(self):
        x = self.mean + self.std * torch.randn_like(self.mean)
        return x

    def kl(self, other=None, dims=(1, 2, 3)):
        if self.deterministic:
            return torch.Tensor([0.])
        else:
            if other is None:
                return 0.5 * torch.mean(torch.pow(self.mean, 2)
                                        + self.var - 1.0 - self.logvar,
                                        dim=dims)
            else:
                return 0.5 * torch.mean(
                    torch.pow(self.mean - other.mean, 2) / other.var
                    + self.var / other.var - 1.0 - self.logvar + other.logvar,
                    dim=dims)

    def nll(self, sample, dims=(1, 2, 3)):
        if self.deterministic:
            return torch.Tensor([0.])
        logtwopi = np.log(2.0 * np.pi)
        return 0.5 * torch.sum(
            logtwopi + self.logvar + torch.pow(sample - self.mean, 2) / self.var,
            dim=dims)

    def mode(self):
        return self.mean


def normal_kl(mean1, logvar1, mean2, logvar2):
    # Compute the KL divergence between two gaussians.
    # Shapes are automatically broadcasted, so batches can be compared to
    # scalars, among other use cases.

    tensor = None
    for obj in (mean1, logvar1, mean2, logvar2):
        if isinstance(obj, torch.Tensor):
            tensor = obj
            break
    assert tensor is not None, "at least one argument must be a Tensor"

    # Force variances to be Tensors. Broadcasting helps convert scalars to
    # Tensors, but it does not work for torch.exp().
    logvar1, logvar2 = [
        x if isinstance(x, torch.Tensor) else torch.tensor(x).to(tensor)
        for x in (logvar1, logvar2)
    ]

    return 0.5 * (
            -1.0
            + logvar2
            - logvar1
            + torch.exp(logvar1 - logvar2)
            + ((mean1 - mean2) ** 2) * torch.exp(-logvar2)
    )