python OneHotEncoder()

X = OneHotEncoder().fit_transform(X_data).todense() #one-hot编码
import numpy as np
import pandas as pd
from sklearn.preprocessing import OneHotEncoder


def oneHot(df):
    new_cols = []
    for old_col in list(df.columns):
        new_cols += sorted(['{0}_onehot_{1}'.format(old_col, str(x).lower()) for x in set(df[old_col].values)])

    ec = OneHotEncoder()
    ec.fit(df.values)
    return pd.DataFrame(ec.transform(df).toarray(),columns=new_cols)


if __name__ == '__main__':
    df = pd.DataFrame(np.arange(24).reshape(4,6))
    print(df)
    print(oneHot(df))
    0   1   2   3   4   5
0   0   1   2   3   4   5
1   6   7   8   9  10  11
2  12  13  14  15  16  17
3  18  19  20  21  22  23

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)
  
    0    1    2    3    4    5    6   ...   17   18   19   20   21   22   23
0  1.0  0.0  0.0  0.0  1.0  0.0  0.0  ...  0.0  0.0  0.0  1.0  0.0  0.0  0.0
1  0.0  1.0  0.0  0.0  0.0  1.0  0.0  ...  1.0  0.0  0.0  0.0  1.0  0.0  0.0
2  0.0  0.0  1.0  0.0  0.0  0.0  1.0  ...  0.0  1.0  0.0  0.0  0.0  1.0  0.0
3  0.0  0.0  0.0  1.0  0.0  0.0  0.0  ...  0.0  0.0  1.0  0.0  0.0  0.0  1.0
[4 rows x 24 columns]

你可能感兴趣的:(python,tip)