使用sklearn之LabelEncoder將Label標准化

LabelEncoder可以將標簽分配一個0—n_classes-1之間的編碼 
將各種標簽分配一個可數的連續編號

將DataFrame中的每一行ID標簽分別轉換成連續編號：

 

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):
        return self # not relevant here

    def transform(self,X):
        '''
        Transforms columns of X specified in self.columns using
        LabelEncoder(). If no columns specified, transforms all
        columns in X.
        '''
        output = X.copy()
        if self.columns is not None:
            for col in self.columns:
                output[col] = LabelEncoder().fit_transform(output[col])
        else:
            for colname,col in output.iteritems():
                output[colname] = LabelEncoder().fit_transform(col)
        return output

    def fit_transform(self,X,y=None):
        return self.fit(X,y).transform(X)

fruit_data[['fruit','color']]=fruit_data[['fruit','color']].apply(LabelEncoder().fit_transform)