scikit-learn labelencoder 同时处理多列

根据网络资料整理

1.

x=df.apply(LabelEncoder().fit_transform)

2.

from collections import defaultdict
d = defaultdict(LabelEncoder)

# Encoding the variable

fit = df.apply(lambda x: d[x.name].fit_transform(x))

# Inverse the encodedfit.apply(lambda x: d[x.name].inverse_transform(x))

# Using the dictionary to label future data

df.apply(lambda x: d[x.name].transform(x))

3.

import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.pipeline import Pipeline

class MultiColumnLabelEncoder:
    def __init__(self,columns = None):
        self.columns = columns # array of column names to encode

    def fit(self,X,y=None):
    &