"""Metrics to assess performance on regression task

Functions named as ``*_score`` return a scalar value to maximize: the higher
the better

Function named as ``*_error`` or ``*_loss`` return a scalar value to minimize:
the lower the better
"""

# Authors: Alexandre Gramfort <alexandre.gramfort@inria.fr>
#          Mathieu Blondel <mathieu@mblondel.org>
#          Olivier Grisel <olivier.grisel@ensta.org>
#          Arnaud Joly <a.joly@ulg.ac.be>
#          Jochen Wersdorfer <jochen@wersdoerfer.de>
#          Lars Buitinck
#          Joel Nothman <joel.nothman@gmail.com>
#          Karan Desai <karandesai281196@gmail.com>
#          Noel Dawe <noel@dawe.me>
#          Manoj Kumar <manojkumarsivaraj334@gmail.com>
#          Michael Eickenberg <michael.eickenberg@gmail.com>
#          Konstantin Shmelkov <konstantin.shmelkov@polytechnique.edu>
#          Christian Lorentzen <lorentzen.ch@googlemail.com>
# License: BSD 3 clause

import numpy as np
import warnings

from .._loss.glm_distribution import TweedieDistribution
from ..utils.validation import (check_array, check_consistent_length,
                                _num_samples)
from ..utils.validation import column_or_1d
from ..utils.validation import _deprecate_positional_args
from ..exceptions import UndefinedMetricWarning


__ALL__ = [
    "max_error",
    "mean_absolute_error",
    "mean_squared_error",
    "mean_squared_log_error",
    "median_absolute_error",
    "r2_score",
    "explained_variance_score",
    "mean_tweedie_deviance",
    "mean_poisson_deviance",
    "mean_gamma_deviance",
]


def _check_reg_targets(y_true, y_pred, multioutput, dtype="numeric"):
    """Check that y_true and y_pred belong to the same regression task

    Parameters
    ----------
    y_true : array-like

    y_pred : array-like

    multioutput : array-like or string in ['raw_values', uniform_average',
        'variance_weighted'] or None
        None is accepted due to backward compatibility of r2_score().

    Returns
    -------
    type_true : one of {'continuous', continuous-multioutput'}
        The type of the true target data, as output by
        'utils.multiclass.type_of_target'

    y_true : array-like of shape (n_samples, n_outputs)
        Ground truth (correct) target values.

    y_pred : array-like of shape (n_samples, n_outputs)
        Estimated target values.

    multioutput : array-like of shape (n_outputs) or string in ['raw_values',
        uniform_average', 'variance_weighted'] or None
        Custom output weights if ``multioutput`` is array-like or
        just the corresponding argument if ``multioutput`` is a
        correct keyword.
    dtype: str or list, default="numeric"
        the dtype argument passed to check_array

    """
    check_consistent_length(y_true, y_pred)
    y_true = check_array(y_true, ensure_2d=False, dtype=dtype)
    y_pred = check_array(y_pred, ensure_2d=False, dtype=dtype)

    if y_true.ndim == 1:
        y_true = y_true.reshape((-1, 1))

    if y_pred.ndim == 1:
        y_pred = y_pred.reshape((-1, 1))

    if y_true.shape[1] != y_pred.shape[1]:
        raise ValueError("y_true and y_pred have different number of output "
                         "({0}!={1})".format(y_true.shape[1], y_pred.shape[1]))

    n_outputs = y_true.shape[1]
    allowed_multioutput_str = ('raw_values', 'uniform_average',
                               'variance_weighted')
    if isinstance(multioutput, str):
        if multioutput not in allowed_multioutput_str:
            raise ValueError("Allowed 'multioutput' string values are {}. "
                             "You provided multioutput={!r}".format(
                                 allowed_multioutput_str,
                                 multioutput))
    elif multioutput is not None:
        multioutput = check_array(multioutput, ensure_2d=False)
        if n_outputs == 1:
            raise ValueError("Custom weights are useful only in "
                             "multi-output cases.")
        elif n_outputs != len(multioutput):
            raise ValueError(("There must be equally many custom weights "
                              "(%d) as outputs (%d).") %
                             (len(multioutput), n_outputs))
    y_type = 'continuous' if n_outputs == 1 else 'continuous-multioutput'

    return y_type, y_true, y_pred, multioutput


@_deprecate_positional_args
def mean_absolute_error(y_true, y_pred, *,
                        sample_weight=None,
                        multioutput='uniform_average'):
    """Mean absolute error regression loss

    Read more in the :ref:`User Guide <mean_absolute_error>`.

    Parameters
    ----------
    y_true : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Ground truth (correct) target values.

    y_pred : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Estimated target values.

    sample_weight : array-like of shape (n_samples,), optional
        Sample weights.

    multioutput : string in ['raw_values', 'uniform_average'] \
                or array-like of shape (n_outputs)
        Defines aggregating of multiple output values.
        Array-like value defines weights used to average errors.

        'raw_values' :
            Returns a full set of errors in case of multioutput input.

        'uniform_average' :
            Errors of all outputs are averaged with uniform weight.


    Returns
    -------
    loss : float or ndarray of floats
        If multioutput is 'raw_values', then mean absolute error is returned
        for each output separately.
        If multioutput is 'uniform_average' or an ndarray of weights, then the
        weighted average of all output errors is returned.

        MAE output is non-negative floating point. The best value is 0.0.

    Examples
    --------
    >>> from sklearn.metrics import mean_absolute_error
    >>> y_true = [3, -0.5, 2, 7]
    >>> y_pred = [2.5, 0.0, 2, 8]
    >>> mean_absolute_error(y_true, y_pred)
    0.5
    >>> y_true = [[0.5, 1], [-1, 1], [7, -6]]
    >>> y_pred = [[0, 2], [-1, 2], [8, -5]]
    >>> mean_absolute_error(y_true, y_pred)
    0.75
    >>> mean_absolute_error(y_true, y_pred, multioutput='raw_values')
    array([0.5, 1. ])
    >>> mean_absolute_error(y_true, y_pred, multioutput=[0.3, 0.7])
    0.85...
    """
    y_type, y_true, y_pred, multioutput = _check_reg_targets(
        y_true, y_pred, multioutput)
    check_consistent_length(y_true, y_pred, sample_weight)
    output_errors = np.average(np.abs(y_pred - y_true),
                               weights=sample_weight, axis=0)
    if isinstance(multioutput, str):
        if multioutput == 'raw_values':
            return output_errors
        elif multioutput == 'uniform_average':
            # pass None as weights to np.average: uniform mean
            multioutput = None

    return np.average(output_errors, weights=multioutput)


@_deprecate_positional_args
def mean_squared_error(y_true, y_pred, *,
                       sample_weight=None,
                       multioutput='uniform_average', squared=True):
    """Mean squared error regression loss

    Read more in the :ref:`User Guide <mean_squared_error>`.

    Parameters
    ----------
    y_true : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Ground truth (correct) target values.

    y_pred : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Estimated target values.

    sample_weight : array-like of shape (n_samples,), optional
        Sample weights.

    multioutput : string in ['raw_values', 'uniform_average'] \
                or array-like of shape (n_outputs)
        Defines aggregating of multiple output values.
        Array-like value defines weights used to average errors.

        'raw_values' :
            Returns a full set of errors in case of multioutput input.

        'uniform_average' :
            Errors of all outputs are averaged with uniform weight.

    squared : boolean value, optional (default = True)
        If True returns MSE value, if False returns RMSE value.

    Returns
    -------
    loss : float or ndarray of floats
        A non-negative floating point value (the best value is 0.0), or an
        array of floating point values, one for each individual target.

    Examples
    --------
    >>> from sklearn.metrics import mean_squared_error
    >>> y_true = [3, -0.5, 2, 7]
    >>> y_pred = [2.5, 0.0, 2, 8]
    >>> mean_squared_error(y_true, y_pred)
    0.375
    >>> y_true = [3, -0.5, 2, 7]
    >>> y_pred = [2.5, 0.0, 2, 8]
    >>> mean_squared_error(y_true, y_pred, squared=False)
    0.612...
    >>> y_true = [[0.5, 1],[-1, 1],[7, -6]]
    >>> y_pred = [[0, 2],[-1, 2],[8, -5]]
    >>> mean_squared_error(y_true, y_pred)
    0.708...
    >>> mean_squared_error(y_true, y_pred, multioutput='raw_values')
    array([0.41666667, 1.        ])
    >>> mean_squared_error(y_true, y_pred, multioutput=[0.3, 0.7])
    0.825...

    """
    y_type, y_true, y_pred, multioutput = _check_reg_targets(
        y_true, y_pred, multioutput)
    check_consistent_length(y_true, y_pred, sample_weight)
    output_errors = np.average((y_true - y_pred) ** 2, axis=0,
                               weights=sample_weight)
    if isinstance(multioutput, str):
        if multioutput == 'raw_values':
            return output_errors if squared else np.sqrt(output_errors)
        elif multioutput == 'uniform_average':
            # pass None as weights to np.average: uniform mean
            multioutput = None

    mse = np.average(output_errors, weights=multioutput)
    return mse if squared else np.sqrt(mse)


@_deprecate_positional_args
def mean_squared_log_error(y_true, y_pred, *,
                           sample_weight=None,
                           multioutput='uniform_average'):
    """Mean squared logarithmic error regression loss

    Read more in the :ref:`User Guide <mean_squared_log_error>`.

    Parameters
    ----------
    y_true : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Ground truth (correct) target values.

    y_pred : array-like of shape (n_samples,) or (n_samples, n_outputs)
        Estimated target values.

    sample_weight : array-like of shape (n_samples,), optional
        Sample weights.

    multioutput : string in ['raw_values', 'uniform_average'] \
            or array-like of shape (n_outputs)

        Defines aggregating of multiple output values.
        Array-like value defines weights used to average errors.

        'raw_values' :
            Returns a full set of errors when the input is of multioutput
            format.

        'uniform_average' :
            Errors of all outputs are averaged with uniform weight.

    Returns
    -------
    loss : float or ndarray of floats
        A non-negative floating point value (the best value is 0.0), or an
        array of floating point values, one for each individual target.

    Examples
    --------
    >>> from sklearn.metrics import mean_squared_log_error
    >>> y_true = [3, 5, 2.5, 7]
    >>> y_pred = [2.5, 5, 4, 8]
    >>> mean_squared_log_error(y_true, y_pred)
    0.039...
    >>> y_true = [[0.5, 1], [1, 2], [7, 6]]
    >>> y_pred = [[0.5, 2], [1, 2.5], [8, 8]]
    >>> mean_squared_log_error(y_true, y_pred)
    0.044...
    >>> mean_squared_log_error(y_true, y_pred, multioutput='raw_values')
    array([0.00462428, 0.08377444])
    >>> mean_squared_log_error(y_true, y_pred, multioutput=[0.3, 0.7])
    0.060...

    """
    y_type, y_true, y_pred, multioutput = _check_reg_targets(
        y_true, y_pred, multioutput)
    check_consistent_length(y_true, y_pred, sample_weight)

    if (y_true < 0).any() or (y_pred < 0).any():
        raise ValueError("Mean Squared Logarithmic Error cannot be used when "
                         "targets contain negative values.")

    return mean_squared_error(np.log1p(y_true), np.log1p(y_pred),
                              sample_weight=sample_weight,
                              multioutput=multioutput)


@_deprecate_positional_args
def median_absolute_error(y_true, y_pred, *, multioutput='uniform_average'):
    """Median absolute error regression loss

    Median absolute error output is non-negative floating point. The best value
    is 0.0. Read more in the :ref:`User Guide <median_absolute_error>`.

    Parameters
    ----------