import math
import torch
from torch import Tensor
from .optimizer import Optimizer
from typing import List, Optional


class Adam(Optimizer):
    r"""Implements Adam algorithm.

    .. math::
       \begin{aligned}
            &\rule{110mm}{0.4pt}                                                                 \\
            &\textbf{input}      : \gamma \text{ (lr)}, \beta_1, \beta_2
                \text{ (betas)},\theta_0 \text{ (params)},f(\theta) \text{ (objective)}          \\
            &\hspace{13mm}      \lambda \text{ (weight decay)},  \: \textit{amsgrad},
                \:\textit{maximize}                                                              \\
            &\textbf{initialize} :  m_0 \leftarrow 0 \text{ ( first moment)},
                v_0\leftarrow 0 \text{ (second moment)},\: \widehat{v_0}^{max}\leftarrow 0\\[-1.ex]
            &\rule{110mm}{0.4pt}                                                                 \\
            &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do}                         \\

            &\hspace{5mm}\textbf{if} \: \textit{maximize}:                                       \\
            &\hspace{10mm}g_t           \leftarrow   -\nabla_{\theta} f_t (\theta_{t-1})         \\
            &\hspace{5mm}\textbf{else}                                                           \\
            &\hspace{10mm}g_t           \leftarrow   \nabla_{\theta} f_t (\theta_{t-1})          \\
            &\hspace{5mm}\textbf{if} \: \lambda \neq 0                                           \\
            &\hspace{10mm} g_t \leftarrow g_t + \lambda  \theta_{t-1}                            \\
            &\hspace{5mm}m_t           \leftarrow   \beta_1 m_{t-1} + (1 - \beta_1) g_t          \\
            &\hspace{5mm}v_t           \leftarrow   \beta_2 v_{t-1} + (1-\beta_2) g^2_t          \\
            &\hspace{5mm}\widehat{m_t} \leftarrow   m_t/\big(1-\beta_1^t \big)                   \\
            &\hspace{5mm}\widehat{v_t} \leftarrow   v_t/\big(1-\beta_2^t \big)                   \\
            &\hspace{5mm}\textbf{if} \: amsgrad                                                  \\
            &\hspace{10mm}\widehat{v_t}^{max} \leftarrow \mathrm{max}(\widehat{v_t}^{max},
                \widehat{v_t})                                                                   \\
            &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t}/
                \big(\sqrt{\widehat{v_t}^{max}} + \epsilon \big)                                 \\
            &\hspace{5mm}\textbf{else}                                                           \\
            &\hspace{10mm}\theta_t \leftarrow \theta_{t-1} - \gamma \widehat{m_t}/
                \big(\sqrt{\widehat{v_t}} + \epsilon \big)                                       \\
            &\rule{110mm}{0.4pt}                                                          \\[-1.ex]
            &\bf{return} \:  \theta_t                                                     \\[-1.ex]
            &\rule{110mm}{0.4pt}                                                          \\[-1.ex]
       \end{aligned}

    For further details regarding the algorithm we refer to `Adam: A Method for Stochastic Optimization`_.

    Args:
        params (iterable): iterable of parameters to optimize or dicts defining
            parameter groups
        lr (float, optional): learning rate (default: 1e-3)
        betas (Tuple[float, float], optional): coefficients used for computing
            running averages of gradient and its square (default: (0.9, 0.999))
        eps (float, optional): term added to the denominator to improve
            numerical stability (default: 1e-8)
        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
        amsgrad (boolean, optional): whether to use the AMSGrad variant of this
            algorithm from the paper `On the Convergence of Adam and Beyond`_
            (default: False)
        foreach (bool, optional): whether foreach implementation of optimizer
            is used (default: None)
        maximize (bool, optional): maximize the params based on the objective, instead of
            minimizing (default: False)

    .. _Adam\: A Method for Stochastic Optimization:
        https://arxiv.org/abs/1412.6980
    .. _On the Convergence of Adam and Beyond:
        https://openreview.net/forum?id=ryQu7f-RZ
    """

    def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8,
                 weight_decay=0, amsgrad=False, *, foreach: Optional[bool] = None,
                 maximize: bool = False):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))
        if not 0.0 <= betas[0] < 1.0:
            raise ValueError("Invalid beta parameter at index 0: {}".format(betas[0]))
        if not 0.0 <= betas[1] < 1.0:
            raise ValueError("Invalid beta parameter at index 1: {}".format(betas[1]))
        if not 0.0 <= weight_decay:
            raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
        defaults = dict(lr=lr, betas=betas, eps=eps,
                        weight_decay=weight_decay, amsgrad=amsgrad,
                        maximize=maximize, foreach=foreach)
        super(Adam, self).__init__(params, defaults)

    def __setstate__(self, state):
        super().__setstate__(state)
        for group in self.param_groups:
            group.setdefault('amsgrad', False)
            group.setdefault('maximize', False)
            group.setdefault('foreach', None)
        state_values = list(self.state.values())
        step_is_tensor = (len(state_values) != 0) and torch.is_tensor(state_values[0]['step'])
        if not step_is_tensor:
            for s in state_values:
                s['step'] = torch.tensor(float(s['step']))

    @torch.no_grad()
    def step(self, closure=None):
        """Performs a single optimization step.

        Args:
            closure (callable, optional): A closure that reevaluates the model
                and returns the loss.
        """
        loss = None
        if closure is not None:
            with torch.enable_grad():
                loss = closure()

        for group in self.param_groups:
            params_with_grad = []
            grads = []
            exp_avgs = []
            exp_avg_sqs = []
            max_exp_avg_sqs = []
            state_steps = []
            beta1, beta2 = group['betas']

            for p in group['params']:
                if p.grad is not None:
                    params_with_grad.append(p)
                    if p.grad.is_sparse:
                        raise RuntimeError('Adam does not support sparse gradients, please consider SparseAdam instead')
                    grads.append(p.grad)

                    state = self.state[p]
                    # Lazy state initialization
                    if len(state) == 0:
                        state['step'] = torch.tensor(0.)
                        # Exponential moving average of gradient values
                        state['exp_avg'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                        # Exponential moving average of squared gradient values
                        state['exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)
                        if group['amsgrad']:
                            # Maintains max of all exp. moving avg. of sq. grad. values
                            state['max_exp_avg_sq'] = torch.zeros_like(p, memory_format=torch.preserve_format)

                    exp_avgs.append(state['exp_avg'])
                    exp_avg_sqs.append(state['exp_avg_sq'])

                    if group['amsgrad']:
                        max_exp_avg_sqs.append(state['max_exp_avg_sq'])

                    state_steps.append(state['step'])

            adam(params_with_grad,
                 grads,
                 exp_avgs,
                 exp_avg_sqs,
                 max_exp_avg_sqs,
                 state_steps,
                 amsgrad=group['amsgrad'],
                 beta1=beta1,
                 beta2=beta2,
                 lr=group['lr'],
                 weight_decay=group['weight_decay'],
                 eps=group['eps'],
                 maximize=group['maximize'],
                 foreach=group['foreach'])

        return loss


def adam(params: List[Tensor],
         grads: List[Tensor],
         exp_avgs: List[Tensor],
         exp_avg_sqs: List[Tensor],
         max_exp_avg_sqs: List[Tensor],
         state_steps: List[Tensor],
         # kwonly args with defaults are not supported by functions compiled with torchscript issue #70627
         # setting this as kwarg for now as functional API is compiled by torch/distributed/optim
         foreach: bool = None,
         *,
         amsgrad: bool,
         beta1: float,
         beta2: float,
         lr: float,
         weight_decay: float,
         eps: float,
         maximize: bool):
    r"""Functional API that performs Adam algorithm computation.
    See :class:`~torch.optim.Adam` for details.
    """

    if not all([isinstance(t, torch.Tensor) for t in state_steps]):
        raise RuntimeError("API has changed, `state_steps` argument must contain a list of singleton tensors")

    if foreach is None:
        # Placeholder for more complex foreach logic to be added when value is not set
        foreach = False

    if foreach and torch.jit.is_scripting():
        raise RuntimeError('torch.jit.script not supported with foreach optimizers')

    if foreach and not torch.jit.is_scripting():
        func = _multi_tensor_adam
    else:
        func = _single_tensor_adam

    func(params,
         grads,
         exp_avgs,
         exp_avg_sqs,
         max_exp_avg_sqs,
         state_steps,
         amsgrad=amsgrad,
         beta1=beta1,
         beta2=beta2,
         lr=lr,
         weight_decay=weight_decay,
         eps=eps,
         maximize=maximize)


def _single_tensor_adam(params: List[Tensor],
                        grads: List[Tensor],
                        exp_avgs: List[Tensor],
                        exp_avg_sqs: List[Tensor],
                        max_exp_avg_sqs: List[Tensor],
                        state_steps: List[Tensor],
                        *,
                        amsgrad: bool,
                        beta1: float,
                        beta2: float,
                        lr: float,
                        weight_decay: float,
                        eps: float,
                        maximize: bool):

    for i, param in enumerate(params):

        grad = grads[i] if not maximize else -grads[i]
        exp_avg = exp_avgs[i]
        exp_avg_sq = exp_avg_sqs[i]
        step_t = state_steps[i]
        # update step
        step_t += 1
        step = step_t.item()

        bias_correction1 = 1 - beta1 ** step
        bias_correction2 = 1 - beta2 ** step

        if weight_decay != 0:
            grad = grad.add(param, alpha=weight_decay)

        # Decay the first and second moment running average coefficient
        exp_avg.mul_(beta1).add_(grad, alpha=1 - beta1)
        exp_avg_sq.mul_(beta2).addcmul_(grad, grad.conj(), value=1 - beta2)
        if amsgrad:
            # Maintains the maximum of all 2nd moment running avg. till now
            torch.maximum(max_exp_avg_sqs[i], exp_avg_sq, out=max_exp_avg_sqs[i])
            # Use the max. for normalizing running avg. of gradient
            denom = (max_exp_avg_sqs[i].sqrt() / math.sqrt(bias_correction2)).add_(eps)
        else:
            denom = (exp_avg_sq.sqrt() / math.sqrt(bias_correction2)).add_(eps)


        step_size = lr / bias_correction1
        param.addcdiv_(exp_avg, denom, value=-step_size)


def _multi_tensor_adam(params: List[Tensor],
                       grads: List[Tensor],
                       exp_avgs: List[Tensor],
                       exp_avg_sqs: List[Tensor],
                       max_exp_avg_sqs: List[Tensor],
                       state_steps: List[Tensor],
                       *,
                       amsgrad: bool,
                       beta1: float,
                       beta2: float,
                       lr: float,
                       weight_decay: float,
                       eps: float,
                       maximize: bool):

    if len(params) == 0:
        return

    # update steps
    torch._foreach_add_(state_steps, 1)

    if maximize:
        grads = torch._foreach_neg(tuple(grads))  # type: ignore[assignment]

    bias_correction1 = [1 - beta1 ** step.item() for step in state_steps]
    bias_correction2 = [1 - beta2 ** step.item() for step in state_steps]
    if weight_decay != 0:
        torch._foreach_add_(grads, params, alpha=weight_decay)

    torch._foreach_mul_(exp_avgs, beta1)
    torch._foreach_add_(exp_avgs, grads, alpha=1 - beta1)

    torch._foreach_mul_(exp_avg_sqs, beta2)
    torch._foreach_addcmul_(exp_avg_sqs, grads, grads, 1 - beta2)

    if amsgrad:
        # Maintains the maximum of all 2nd moment running avg. till now
        max_exp_avg_sqs = torch._foreach_maximum(max_exp_avg_sqs, exp_avg_sqs)  # type: ignore[assignment]

        # Use the max. for normalizing running avg. of gradient
        max_exp_avg_sq_sqrt = torch._foreach_sqrt(max_exp_avg_sqs)
        bias_correction_sqrt = [math.sqrt(bc) for bc in bias_correction2]
        torch._foreach_div_(max_exp_avg_sq_sqrt, bias_correction_sqrt)
        denom = torch._foreach_add(max_exp_avg_sq_sqrt, eps)
    else:
        exp_avg_sq_sqrt = torch._foreach_sqrt(exp_avg_sqs)
        bias_correction_sqrt = [math.sqrt(bc) for bc in bias_correction2]
        torch._foreach_div_(exp_avg_sq_sqrt, bias_correction_sqrt)
        denom = torch._foreach_add(exp_avg_sq_sqrt, eps)

    step_size = [(lr / bc) * -1 for bc in bias_correction1]
    torch._foreach_addcdiv_(params, exp_avgs, denom, step_size)