詳細介紹在pandas中建立category型別資料的幾種方法

import pandas as pd
import numpy as np
 
contents={"name": ['Bob',    'LiSa',           'Mary',            'Alan'],
     "ID":  [1,       2,             ' ',             None],  # 輸出 NaN
     "age": [np.nan,    28,              38 ,             '' ],  # 輸出 
     "age02": [14,      26,              24 ,             6], 
    "born": [pd.NaT,   pd.Timestamp("1990-01-01"), pd.Timestamp("1980-01-01"),    ''],   # 輸出 NaT
     "sex": ['男',     '女',            '女',            None,],  # 輸出 None
     "hobbey":['打籃球',   '打羽毛球',          '打乒乓球',          '',],  # 輸出 
     "money":[200.0,        240.0,          290.0,           300.0], # 輸出
     "weight":[140.5,        120.8,         169.4,           155.6], # 輸出
     "test01":[1,  2.123456789,    3.123456781011126,  4.123456789109999],  # 輸出
     "test02":[1,  2.123456789,    3.123456781011126,  4.123456789109999],  # 輸出
     }
data_frame = pd.DataFrame(contents)
 
 
 
# T1、直接建立 category型別資料
weight_mark=pd.Categorical(['thin','medium','medium','fat'],categories=['medium','fat'])
print(weight_mark)
 
 
 
# T2、利用分箱機制(結合max、mean、min實現二分類)動態新增 category型別資料
col_age_des=pd.Series(data_frame['age02']).describe()
age_ranges=[col_age_des['min']-1,col_age_des['mean'],col_age_des['max']+1]
age_labels=['Minors','Adults']        # 高於平均值的為胖
data_frame['age02_mark']=pd.cut(data_frame['age02'],age_ranges,labels=age_labels)
print(data_frame)