# Copyright The PyTorch Lightning team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import Optional, Any, Union, Tuple, List

import torch

from pytorch_lightning.metrics import Metric
from pytorch_lightning.metrics.functional.precision_recall_curve import (
    _precision_recall_curve_update,
    _precision_recall_curve_compute
)
from pytorch_lightning.utilities import rank_zero_warn


class PrecisionRecallCurve(Metric):
    """
    Computes precision-recall pairs for different thresholds. Works for both
    binary and multiclass problems. In the case of multiclass, the values will
    be calculated based on a one-vs-the-rest approach.

    Forward accepts

    - ``preds`` (float tensor): ``(N, ...)`` (binary) or ``(N, C, ...)`` (multiclass)
      where C is the number of classes

    - ``target`` (long tensor): ``(N, ...)``

    Args:
        num_classes: integer with number of classes. Not nessesary to provide
            for binary problems.
        pos_label: integer determining the positive class. Default is ``None``
            which for binary problem is translate to 1. For multiclass problems
            this argument should not be set as we iteratively change it in the
            range [0,num_classes-1]
        compute_on_step:
            Forward only calls ``update()`` and return None if this is set to False. default: True
        dist_sync_on_step:
            Synchronize metric state across processes at each ``forward()``
            before returning the value at the step. default: False
        process_group:
            Specify the process group on which synchronization is called. default: None (which selects the entire world)

    Example (binary case):

        >>> pred = torch.tensor([0, 1, 2, 3])
        >>> target = torch.tensor([0, 1, 1, 0])
        >>> pr_curve = PrecisionRecallCurve(pos_label=1)
        >>> precision, recall, thresholds = pr_curve(pred, target)
        >>> precision
        tensor([0.6667, 0.5000, 0.0000, 1.0000])
        >>> recall
        tensor([1.0000, 0.5000, 0.0000, 0.0000])
        >>> thresholds
        tensor([1, 2, 3])

    Example (multiclass case):

        >>> pred = torch.tensor([[0.75, 0.05, 0.05, 0.05, 0.05],
        ...                      [0.05, 0.75, 0.05, 0.05, 0.05],
        ...                      [0.05, 0.05, 0.75, 0.05, 0.05],
        ...                      [0.05, 0.05, 0.05, 0.75, 0.05]])
        >>> target = torch.tensor([0, 1, 3, 2])
        >>> pr_curve = PrecisionRecallCurve(num_classes=5)
        >>> precision, recall, thresholds = pr_curve(pred, target)
        >>> precision   # doctest: +NORMALIZE_WHITESPACE
        [tensor([1., 1.]), tensor([1., 1.]), tensor([0.2500, 0.0000, 1.0000]),
         tensor([0.2500, 0.0000, 1.0000]), tensor([0., 1.])]
        >>> recall
        [tensor([1., 0.]), tensor([1., 0.]), tensor([1., 0., 0.]), tensor([1., 0., 0.]), tensor([nan, 0.])]
        >>> thresholds
        [tensor([0.7500]), tensor([0.7500]), tensor([0.0500, 0.7500]), tensor([0.0500, 0.7500]), tensor([0.0500])]

    """
    def __init__(
        self,
        num_classes: Optional[int] = None,
        pos_label: Optional[int] = None,
        compute_on_step: bool = True,
        dist_sync_on_step: bool = False,
        process_group: Optional[Any] = None,
    ):
        super().__init__(
            compute_on_step=compute_on_step,
            dist_sync_on_step=dist_sync_on_step,
            process_group=process_group,
        )

        self.num_classes = num_classes
        self.pos_label = pos_label

        self.add_state("preds", default=[], dist_reduce_fx=None)
        self.add_state("target", default=[], dist_reduce_fx=None)

        rank_zero_warn(
            'Metric `PrecisionRecallCurve` will save all targets and predictions in buffer.'
            ' For large datasets this may lead to large memory footprint.'
        )

    def update(self, preds: torch.Tensor, target: torch.Tensor):
        """
        Update state with predictions and targets.

        Args:
            preds: Predictions from model
            target: Ground truth values
        """
        preds, target, num_classes, pos_label = _precision_recall_curve_update(
            preds,
            target,
            self.num_classes,
            self.pos_label
        )
        self.preds.append(preds)
        self.target.append(target)
        self.num_classes = num_classes
        self.pos_label = pos_label

    def compute(self) -> Union[Tuple[torch.Tensor, torch.Tensor, torch.Tensor],
                               Tuple[List[torch.Tensor], List[torch.Tensor], List[torch.Tensor]]]:
        """
        Compute the precision-recall curve

        Returns: 3-element tuple containing

            precision:
                tensor where element i is the precision of predictions with
                score >= thresholds[i] and the last element is 1.
                If multiclass, this is a list of such tensors, one for each class.
            recall:
                tensor where element i is the recall of predictions with
                score >= thresholds[i] and the last element is 0.
                If multiclass, this is a list of such tensors, one for each class.
            thresholds:
                Thresholds used for computing precision/recall scores

        """
        preds = torch.cat(self.preds, dim=0)
        target = torch.cat(self.target, dim=0)
        return _precision_recall_curve_compute(preds, target, self.num_classes, self.pos_label)