移除所有无限值:

(并替换为该列的min或Max)

import numpy as np

# generate example matrix
matrix = np.random.rand(5,5)
matrix[0,:] = np.inf
matrix[2,:] = -np.inf
>>> matrix
array([[       inf,        inf,        inf,        inf,        inf],
       [0.87362809, 0.28321499, 0.7427659 , 0.37570528, 0.35783064],
       [      -inf,       -inf,       -inf,       -inf,       -inf],
       [0.72877665, 0.06580068, 0.95222639, 0.00833664, 0.68779902],
       [0.90272002, 0.37357483, 0.92952479, 0.072105  , 0.20837798]])

# find min and max values for each column, ignoring nan, -inf, and inf
mins = [np.nanmin(matrix[:, i][matrix[:, i] != -np.inf]) for i in range(matrix.shape[1])]
maxs = [np.nanmax(matrix[:, i][matrix[:, i] != np.inf]) for i in range(matrix.shape[1])]

# go through matrix one column at a time and replace  + and -infinity 
# with the max or min for that column
for i in range(matrix.shape[1]):
    matrix[:, i][matrix[:, i] == -np.inf] = mins[i]
    matrix[:, i][matrix[:, i] == np.inf] = maxs[i]

>>> matrix
array([[0.90272002, 0.37357483, 0.95222639, 0.37570528, 0.68779902],
       [0.87362809, 0.28321499, 0.7427659 , 0.37570528, 0.35783064],
       [0.72877665, 0.06580068, 0.7427659 , 0.00833664, 0.20837798],
       [0.72877665, 0.06580068, 0.95222639, 0.00833664, 0.68779902],
       [0.90272002, 0.37357483, 0.92952479, 0.072105  , 0.20837798]])

使用isneginf可能会有所帮助。 http://docs.scipy.org/doc/numpy/reference/generated/numpy.isneginf.html#numpy.isneginf

x[numpy.isneginf(x)] = 0 #0 is the value you want to replace with

try

mat.sum()

如果你的数据和是无穷大(大于最大浮点值3.402823e+38)，你会得到这个错误。

请参阅scikit源代码中的validation.py中的_assert_all_finite函数:

if is_float and np.isfinite(X.sum()):
    pass
elif is_float:
    msg_err = "Input contains {} or a value too large for {!r}."
    if (allow_nan and np.isinf(X).any() or
            not allow_nan and not np.isfinite(X).all()):
        type_err = 'infinity' if allow_nan else 'NaN, infinity'
        # print(X.sum())
        raise ValueError(msg_err.format(type_err, X.dtype))

我有同样的错误，在我的情况下，X和y是数据帧，所以我必须先将它们转换为矩阵:

X = X.values.astype(np.float)
y = y.values.astype(np.float)

编辑:最初建议的X.as_matrix()已弃用

问题似乎发生在DecisionTreeClassifier输入检查，尝试

X_train = X_train.replace((np.inf, -np.inf, np.nan), 0).reset_index(drop=True)

这是它失败的检查:

https://github.com/scikit-learn/scikit-learn/blob/0.17.X/sklearn/utils/validation.py#L51

说

def _assert_all_finite(X):
    """Like assert_all_finite, but only for ndarray."""
    X = np.asanyarray(X)
    # First try an O(n) time, O(1) space solution for the common case that
    # everything is finite; fall back to O(n) space np.isfinite to prevent
    # false positives from overflow in sum method.
    if (X.dtype.char in np.typecodes['AllFloat'] and not np.isfinite(X.sum())
            and not np.isfinite(X).all()):
        raise ValueError("Input contains NaN, infinity"
                         " or a value too large for %r." % X.dtype)

所以确保你的输入中有非NaN值。所有这些值实际上都是浮点值。这些值也不应该是Inf。