pandas

Series

apply

pandas的s.apply§相当于s中的数据使用p函数：

drop

Return Series with specified index labels removed.

axis

axis=0表示跨行，axis=1表示跨列

dropna

Remove missing values.

Remove missing values.

transformer

import pandas as pd
import numpy as np

from sklearn.base import TransformerMixin

class DataFrameImputer(TransformerMixin):

    def __init__(self):
        """Impute missing values.

        Columns of dtype object are imputed with the most frequent value 
        in column.

        Columns of other types are imputed with mean of column.

        """
    def fit(self, X, y=None):

        self.fill = pd.Series([X[c].value_counts().index[0]
            if X[c].dtype == np.dtype('O') else X[c].mean() for c in X],
            index=X.columns)

        return self

    def transform(self, X, y=None):
        return X.fillna(self.fill)

data = [
    ['a', 1, 2],
    ['b', 1, 1],
    ['b', 2, 2],
    [np.nan, np.nan, np.nan]
]

X = pd.DataFrame(data)
xt = DataFrameImputer().fit_transform(X)

print('before...')
print(X)
print('after...')
print(xt)

concat

连接 Concatenate Series.

drop

notnull

enumerate

loc

根据列提取行

get_dummies

1. https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.Series.apply.html
2. https://blog.csdn.net/nuaadot/article/details/78304642