深度学习-回归问题的评估指标：MAE, MAPE, MSE, R

回归问题常用的评估指标

回归问题常用的评估指标包括：MAE, MAPE, MSE, RMSE, R2_Score等。

这些评价指标基本都在 sklearn 包中都封装好了，可直接调用。

安装 sklearn, 完整的名字是 scikit-learn。

pip install -U scikit-learn
# 现在最新版是 V0.22.2.post1

metric	formula	method
MAE		sklearn.metrics.mean_absolute_error
MAPE		sklearn.metrics.mean_absolute_percentage_error
MSE		sklearn.metrics.mean_squared_error
RMSE		sklearn.metrics.mean_squared_error
R2 Score		sklearn.metrics.r2_score

注：

• MAPE 在V0.22.2中还不能直接调用，预计会在V0.23中发布；
  • 参见 github #15007
• RMSE 可以调用 mean_squared_error 方法实现, 设置 squared=False 即可;
  • rmse_score = mean_squared_error(y_test, y_pred, squared=False)

示例

from sklearn.metrics import mean_absolute_error
from sklearn.metrics import mean_absolute_percentage_error
from sklearn.metrics import mean_squared_error
from sklearn.metrics import r2_score

x_true = xxx
y_true = yyy
y_pred = model.predict(x_true)

# 评估标准： mae, mape, mse, rmse, r2_score
mae_score = mean_absolute_error(y_true, y_pred)
mape_score = mean_absolute_percentage_error(y_true, y_pred)

mse_score = mean_squared_error(y_true, y_pred)
rmse_score = mean_squared_error(y_true, y_pred, squared=False)

r_2_score = r2_score(y_true, y_pred)

---

PS： 修改 sklearn(0.22.2) 源码， 直接调用 mean_absolute_percentage_error

需要修改两个文件： sklearn/metrics/__init__.py, sklearn/metrics/_regression.py

• sklearn/metrics/__init__.py, 修改两处。

## 第 63 行左右
from ._regression import explained_variance_score
from ._regression import max_error
from ._regression import mean_absolute_error
from ._regression import mean_absolute_percentage_error  # +++ add MAPE +++
from ._regression import mean_squared_error
from ._regression import mean_squared_log_error
from ._regression import median_absolute_error

# 第 126 行左右
    'matthews_corrcoef',
    'max_error',
    'mean_absolute_error',
    'mean_absolute_percentage_error',  # +++ add MAPE +++
    'mean_squared_error',
    'mean_squared_log_error',
    'mean_poisson_deviance',

• sklearn/metrics/_regression.py, 修改两处

# 第 36 行左右
    "max_error",
    "mean_absolute_error",
    "mean_absolute_percentage_error",  # +++ add MAPE +++
    "mean_squared_error",
    "mean_squared_log_error",
    "median_absolute_error",

# 第 190 行左右
    return np.average(output_errors, weights=multioutput)

# +++ add MAPE +++
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>`.
    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.
    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)
# +++ add MAPE +++


def mean_squared_error(y_true, y_pred,
                       sample_weight=None,

参考 github：#15007

sklearn-mape-1.png sklearn-mape-2.png