Python 无法转换分类变量，显示类别=自动错误

python版本3.7，spyder 3.3.6。始终显示我使用不同版本python尝试过的错误：

import pandas as pa
import numpy as np

X=0
y=0
dataset = 0
#import the data set and separete the 
dataset = pa.read_csv("50_Startups.csv")
X = dataset.iloc[:,:-1].values
y = dataset.iloc[:,4].values

#categorical variable
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer(
        [('one_hot_encoder',OneHotEncoder(),[0])],
        remainder = 'passthrough'
        )
X = np.array(ct.fit_transform(X), dtype=np.float64)
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)

错误是：

C:\ProgramData\Anaconda3\lib\site-packages\sklearn\preprocessing\_encoders.py:415: FutureWarning: The handling of integer data will change in version 0.22. Currently, the categories are determined based on the range [0, max(values)], while in the future they will be determined based on the unique values.
If you want the future behaviour and silence this warning, you can specify "categories='auto'".
In case you used a LabelEncoder before this OneHotEncoder to convert the categories to integers, then you can now use the OneHotEncoder directly.
      warnings.warn(msg, FutureWarning)
Traceback (most recent call last):

 File "<ipython-input-5-139c661c06f7>", line 25, in <module>
        X = np.array(ct.fit_transform(X), dtype=np.float64)

 File "C:\ProgramData\Anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py", line 490, in fit_transform
        return self._hstack(list(Xs))

File "C:\ProgramData\Anaconda3\lib\site-packages\sklearn\compose\_column_transformer.py", line 541, in _hstack
        raise ValueError("For a sparse output, all columns should"

 ValueError: For a sparse output, all columns should be a numeric or convertible to a numeric.

---

特征矩阵作为X和dep变量作为Y将数据帧转换为numpy数组

`X = dataset.iloc[:,:-1].values`       
`Y = dataset.iloc[:,-1].values`

编码分类变量

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
en = LabelEncoder()
X[:,3] = en.fit_transform(X[:,3])
oh = OneHotEncoder(categorical_features=[3])
X = oh.fit_transform(X)  

#converting from matrix to array
X = X.toarray()
#Dummy variable trap ---- Removing one dummy variable 
X = X[:,1:]

---

在这里，您可以选择所有包含数字数据的列。您只为分类列安装编码器，然后对其进行转换。并删除虚拟变量。

不推荐使用“分类功能”关键字。我们使用上面的警告。根据我的理解，我们必须使用ColumnTransformer，因为HotEncoder应该事先转换为数字，无论如何不？