从 sklearn 导入指标时出现导入错误

Question

当我尝试从 sklearn 导入指标时，出现以下错误：

from sklearn.metrics import mean_absolute_percentage_error

ImportError: cannot import name 'mean_absolute_percentage_error' from 'sklearn.metrics'

/Users/carter/opt/anaconda3/lib/python3.8/site-packages/sklearn/metrics/__init__.py)

我已经使用了 conda update all，并重新安装了 scikit-learn 无济于事。这可能发生的任何其他原因和解决方案？

Answer 1

如mean_absolute_percentage_error文档中所述，该函数是 scikit-learn 0.24 版中的新功能。

截至 2020 年 12 月，Anaconda提供的最新版本的 scikit-learn是 v0.23.2，因此您无法导入mean_absolute_percentage_error.

您可以尝试从源代码安装最新版本，或者自己实现您需要的功能。如果您想看一看，可以在此处获得源代码。

Answer 2

上面的答案是正确的。对于那些无法从源代码升级/安装的人，以下是所需的代码。

该函数本身依赖于其他函数 - 一个在同一模块中定义，其他函数来自 sklearn.utils.validation。

这是我从源代码中提取的所需代码 - 如果有人需要它（我希望我没有违反任何许可证）：

from sklearn.utils.validation import check_consistent_length, check_array

def mean_absolute_percentage_error(y_true, y_pred,
                                   sample_weight=None,
                                   multioutput='uniform_average'):
    """Mean absolute percentage error regression loss.
    Note here that we do not represent the output as a percentage in range
    [0, 100]. Instead, we represent it in range [0, 1/eps]. Read more in the
    :ref:`User Guide <mean_absolute_percentage_error>`.
    .. versionadded:: 0.24
    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,), default=None
        Sample weights.
    multioutput : {'raw_values', 'uniform_average'} or array-like
        Defines aggregating of multiple output values.
        Array-like value defines weights used to average errors.
        If input is list then the shape must be (n_outputs,).
        '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 in the range [0, 1/eps]
        If multioutput is 'raw_values', then mean absolute percentage 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.
        MAPE output is non-negative floating point. The best value is 0.0.
        But note the fact that bad predictions can lead to arbitarily large
        MAPE values, especially if some y_true values are very close to zero.
        Note that we return a large value instead of `inf` when y_true is zero.
    Examples
    --------
    >>> from sklearn.metrics import mean_absolute_percentage_error
    >>> y_true = [3, -0.5, 2, 7]
    >>> y_pred = [2.5, 0.0, 2, 8]
    >>> mean_absolute_percentage_error(y_true, y_pred)
    0.3273...
    >>> y_true = [[0.5, 1], [-1, 1], [7, -6]]
    >>> y_pred = [[0, 2], [-1, 2], [8, -5]]
    >>> mean_absolute_percentage_error(y_true, y_pred)
    0.5515...
    >>> mean_absolute_percentage_error(y_true, y_pred, multioutput=[0.3, 0.7])
    0.6198...
    """
    y_type, y_true, y_pred, multioutput = _check_reg_targets(
        y_true, y_pred, multioutput)
    check_consistent_length(y_true, y_pred, sample_weight)
    epsilon = np.finfo(np.float64).eps
    mape = np.abs(y_pred - y_true) / np.maximum(np.abs(y_true), epsilon)
    output_errors = np.average(mape,
                               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)

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