TypeError： unorder types： float() < str() 同时使用 LabelBinarizer 的 fit_transform

Question

我正在尝试使用scikit-learn的LabelBinarizer来处理熊猫数据帧的分类字段。

这样做时我收到错误

"TypeError： unorderable types： float(( <str((">

您可以在下面看到train_data['embarked']是一个分类字段，它只包含 3 个值。但是当我使用LabelBinarizer时，我遇到了提到的错误

train_data['embarked'].head()
train_data['embarked'].value_counts()
from sklearn.preprocessing import LabelBinarizer
labelbinarizer = LabelBinarizer()
lb_result = labelbinarizer.fit_transform(train_data["embarked"])

前两行的输出如下所示。

0    S
1    C
2    S
3    S
4    S
Name: embarked, dtype: object
S    644
C    168
Q     77
Name: embarked, dtype: int64

导致错误的最后一行。整个错误消息如下所示。

Traceback (most recent call last):
  File "<pyshell#20>", line 1, in <module>
    lb_result = labelbinarizer.fit_transform(train_data["embarked"])
  File "/usr/local/lib/python3.5/dist-packages/sklearn/preprocessing/label.py", line 307, in fit_transform
    return self.fit(y).transform(y)
  File "/usr/local/lib/python3.5/dist-packages/sklearn/preprocessing/label.py", line 276, in fit
    self.y_type_ = type_of_target(y)
  File "/usr/local/lib/python3.5/dist-packages/sklearn/utils/multiclass.py", line 284, in type_of_target
    if (len(np.unique(y)) > 2) or (y.ndim >= 2 and len(y[0]) > 1):
  File "/usr/local/lib/python3.5/dist-packages/numpy/lib/arraysetops.py", line 264, in unique
    ret = _unique1d(ar, return_index, return_inverse, return_counts)
  File "/usr/local/lib/python3.5/dist-packages/numpy/lib/arraysetops.py", line 312, in _unique1d
    ar.sort()
TypeError: unorderable types: float() < str()

这段我无法理解的代码有什么问题？

Answer 1

使用 astype('str')

lb_result = labelbinarizer.fit_transform(train_data["embarked"].astype('str'))