二分类变量:str → int
df = pd.DataFrame({'id': [1, 2, 3],
'sex': ['female', 'female', 'male']})
df
# 输出:
# id sex
# 0 1 female
# 1 2 female
# 2 3 male
"""二分类变量:str → int"""
df['sex'] = df['sex'].replace({'female': 0,
'male': 1})
df
# 输出:
# id sex
# 0 1 0
# 1 2 0
# 2 3 1
二分类变量:bool → int
df = pd.DataFrame({'id': [1, 2, 3],
'age': [20, 25, 30],
'HBP': [False, True, False],
'T2DM': [True, True, False]})
df
# 输出:
# id age HBP T2DM
# 0 1 20 False True
# 1 2 25 True True
# 2 3 30 False False
"""二分类变量:bool → int"""
df = df.replace({False: 0,
True: 1})
df
# 输出:
# id age HBP T2DM
# 0 1 20 0 1
# 1 2 25 1 1
# 2 3 30 0 0