sklearn数值特征离散值处理2: Map

import numpy as np
import pandas as pd
poke_df = pd.read_csv('Pokemon.csv', encoding='utf-8')
poke_df.head(10)

# 随机抽样
poke_df = poke_df.sample(random_state=1, frac=1).reset_index(drop=True)
# pandas.sample()中参数frac指定抽样的百分比
np.unique(poke_df['Generation'])

array([‘Gen 1’, ‘Gen 2’, ‘Gen 3’, ‘Gen 4’, ‘Gen 5’, ‘Gen 6’], dtype=object)

gen_ord_map = {
     'Gen 1':1, 'Gen 2':2, 'Gen 3':3, 'Gen 4':4, 'Gen 5':5, 'Gen 6':6}
poke_df['GenerationLabel'] = poke_df['Generation'].map(gen_ord_map)
poke_df.head()