import os
import pickle
from typing import Any, List, Dict, Union

import numpy as np
import pytorch_lightning as pl
import torch
from pytorch_lightning.callbacks import ModelCheckpoint
from torch.optim import Optimizer
from torch.optim.lr_scheduler import LRScheduler

from navsim.agents.abstract_agent import AbstractAgent
from navsim.agents.transfuser.transfuser_callback import TransfuserCallback
from navsim.agents.vadv2.vadv2_config import Vadv2Config
from navsim.agents.vadv2.vadv2_features import (
    Vadv2FeatureBuilder,
    Vadv2TargetBuilder,
)
from navsim.agents.vadv2.vadv2_loss import vadv2_loss_pdm_wo_progress
from navsim.agents.vadv2.vadv2_pdm_model import Vadv2ModelPDM
from navsim.common.dataclasses import SensorConfig
from navsim.planning.training.abstract_feature_target_builder import (
    AbstractFeatureBuilder,
    AbstractTargetBuilder,
)

DEVKIT_ROOT = os.getenv('NAVSIM_DEVKIT_ROOT')
TRAJ_PDM_ROOT = os.getenv('NAVSIM_TRAJPDM_ROOT')

class Vadv2AgentPDM(AbstractAgent):
    def __init__(
            self,
            config: Vadv2Config,
            lr: float,
            checkpoint_path: str = None,
            pdm_split=None,
            metrics=None,
    ):
        super().__init__()
        self._config = config
        self._lr = lr
        self.metrics = metrics
        self._checkpoint_path = checkpoint_path
        self.vadv2_model = Vadv2ModelPDM(config)
        self.vocab_size = config.vocab_size
        self.vocab_pdm_score_full = pickle.load(open(f'{TRAJ_PDM_ROOT}/vocab_score_full_{self.vocab_size}/{pdm_split}.pkl', 'rb'))

    def name(self) -> str:
        """Inherited, see superclass."""

        return self.__class__.__name__

    def initialize(self) -> None:
        """Inherited, see superclass."""
        # if torch.cuda.is_available():
        #     state_dict: Dict[str, Any] = torch.load(self._checkpoint_path)["state_dict"]
        # else:
        #     state_dict: Dict[str, Any] = torch.load(self._checkpoint_path, map_location=torch.device("cpu"))[
        #         "state_dict"]
        state_dict: Dict[str, Any] = torch.load(self._checkpoint_path, map_location=torch.device("cpu"))["state_dict"]
        self.load_state_dict({k.replace("agent.", ""): v for k, v in state_dict.items()})

    def get_sensor_config(self) -> SensorConfig:
        """Inherited, see superclass."""
        return SensorConfig.build_mm_sensors()

    def get_target_builders(self) -> List[AbstractTargetBuilder]:
        return [Vadv2TargetBuilder(config=self._config)]

    def get_feature_builders(self) -> List[AbstractFeatureBuilder]:
        return [Vadv2FeatureBuilder(config=self._config)]

    def forward(self, features: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
        return self.vadv2_model(features)

    def forward_train(self, features, interpolated_traj):
        return self.vadv2_model(features, interpolated_traj)

    def compute_loss(
            self,
            features: Dict[str, torch.Tensor],
            targets: Dict[str, torch.Tensor],
            predictions: Dict[str, torch.Tensor],
            tokens=None
    ) -> Union[torch.Tensor, Dict[str, torch.Tensor]]:
        # get the pdm score by tokens
        scores = {}
        for k in self.metrics:
            tmp = [self.vocab_pdm_score_full[token][k][None] for token in tokens]
            scores[k] = (torch.from_numpy(np.concatenate(tmp, axis=0))
                         .to(predictions['trajectory'].device))
        return vadv2_loss_pdm_wo_progress(targets, predictions, self._config, scores)

    def get_optimizers(self) -> Union[Optimizer, Dict[str, Union[Optimizer, LRScheduler]]]:
        backbone_params_name = '_backbone.image_encoder.pretrained'
        img_backbone_params = list(filter(lambda kv: backbone_params_name in kv[0], self.vadv2_model.named_parameters()))
        default_params = list(filter(lambda kv: backbone_params_name not in kv[0], self.vadv2_model.named_parameters()))
        params_lr_dict = [
            {'params': [tmp[1] for tmp in default_params]},
            {'params': [tmp[1] for tmp in img_backbone_params], 'lr': self._lr * self._config.lr_mult_backbone}
        ]
        return torch.optim.Adam(params_lr_dict, lr=self._lr)

    def get_training_callbacks(self) -> List[pl.Callback]:
        return [TransfuserCallback(self._config),
                ModelCheckpoint(
                    save_top_k=30,
                    monitor="val/loss_epoch",
                    mode="min",
                    dirpath=f"{os.environ.get('NAVSIM_EXP_ROOT')}/{self._config.ckpt_path}/",
                    filename="{epoch:02d}-{step:04d}",
                )
                ]