import torch
from . import _functional as F
from .optimizer import Optimizer


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

    .. math::
       \begin{aligned}
            &\rule{110mm}{0.4pt}                                                                 \\
            &\textbf{input}      : \gamma \text{ (lr)}, \: \theta_0 \text{ (params)}, \: f(\theta)
                \text{ (objective)}, \: \lambda \text{ (weight decay)},                          \\
            &\hspace{12mm}    \tau \text{ (initial accumulator value)}, \: \eta\text{ (lr decay)}\\
            &\textbf{initialize} :  state\_sum_0 \leftarrow 0                             \\[-1.ex]
            &\rule{110mm}{0.4pt}                                                                 \\
            &\textbf{for} \: t=1 \: \textbf{to} \: \ldots \: \textbf{do}                         \\
            &\hspace{5mm}g_t           \leftarrow   \nabla_{\theta} f_t (\theta_{t-1})           \\
            &\hspace{5mm} \tilde{\gamma}    \leftarrow \gamma / (1 +(t-1) \eta)                  \\
            &\hspace{5mm} \textbf{if} \: \lambda \neq 0                                          \\
            &\hspace{10mm} g_t \leftarrow g_t + \lambda \theta_{t-1}                             \\
            &\hspace{5mm}state\_sum_t  \leftarrow  state\_sum_{t-1} + g^2_t                      \\
            &\hspace{5mm}\theta_t \leftarrow
                \theta_{t-1}- \tilde{\gamma} \frac{g_t}{\sqrt{state\_sum_t}+\epsilon}            \\
            &\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 `Adaptive Subgradient Methods for Online Learning
    and Stochastic Optimization`_.

    Args:
        params (iterable): iterable of parameters to optimize or dicts defining
            parameter groups
        lr (float, optional): learning rate (default: 1e-2)
        lr_decay (float, optional): learning rate decay (default: 0)
        weight_decay (float, optional): weight decay (L2 penalty) (default: 0)
        eps (float, optional): term added to the denominator to improve
            numerical stability (default: 1e-10)

    .. _Adaptive Subgradient Methods for Online Learning and Stochastic
        Optimization: http://jmlr.org/papers/v12/duchi11a.html
    """

    def __init__(self, params, lr=1e-2, lr_decay=0, weight_decay=0, initial_accumulator_value=0, eps=1e-10):
        if not 0.0 <= lr:
            raise ValueError("Invalid learning rate: {}".format(lr))
        if not 0.0 <= lr_decay:
            raise ValueError("Invalid lr_decay value: {}".format(lr_decay))
        if not 0.0 <= weight_decay:
            raise ValueError("Invalid weight_decay value: {}".format(weight_decay))
        if not 0.0 <= initial_accumulator_value:
            raise ValueError("Invalid initial_accumulator_value value: {}".format(initial_accumulator_value))
        if not 0.0 <= eps:
            raise ValueError("Invalid epsilon value: {}".format(eps))

        defaults = dict(lr=lr, lr_decay=lr_decay, eps=eps, weight_decay=weight_decay,
                        initial_accumulator_value=initial_accumulator_value)
        super(Adagrad, self).__init__(params, defaults)

        for group in self.param_groups:
            for p in group['params']:
                state = self.state[p]
                state['step'] = 0
                init_value = complex(initial_accumulator_value, initial_accumulator_value) if torch.is_complex(p) \
                    else initial_accumulator_value
                state['sum'] = torch.full_like(p, init_value, memory_format=torch.preserve_format)

    def share_memory(self):
        for group in self.param_groups:
            for p in group['params']:
                state = self.state[p]
                state['sum'].share_memory_()

    @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 = []
            state_sums = []
            state_steps = []

            for p in group['params']:
                if p.grad is not None:
                    params_with_grad.append(p)
                    grads.append(p.grad)
                    state = self.state[p]
                    state_sums.append(state['sum'])
                    # update the steps for each param group update
                    state['step'] += 1
                    # record the step after step update
                    state_steps.append(state['step'])

            F.adagrad(params_with_grad,
                      grads,
                      state_sums,
                      state_steps,
                      lr=group['lr'],
                      weight_decay=group['weight_decay'],
                      lr_decay=group['lr_decay'],
                      eps=group['eps'])

        return loss