代码

#载入数据集到dataframe
data = pd.read_csv(r'C:\Users\Lu\Desktop\diabetes_done.csv')

Pregnancies = data.loc[:,'Pregnancies']
Glucose = data.loc[:,'Glucose']
BloodPressure = data.loc[:,'BloodPressure']
SkinThickness = data.loc[:,'SkinThickness']
Insulin = data.loc[:,'Insulin']
BMI = data.loc[:,'BMI']
DPF = data.loc[:,'DiabetesPedigreeFunction'] #DiabetesPedigreeFunction
Age = data.loc[:,'Age']
Outcome = data.loc[:,'Outcome']

X = pd.DataFrame({'Pregnancies':Pregnancies,'Glucose':Glucose,'BloodPressure':BloodPressure,'SkinThickness':SkinThickness,'Insulin':Insulin,'BMI':BMI,'DPF':DPF,'Age':Age,'Outcome':Outcome})

# define the variable types: 'c' is 'continuous'. The variables defined here
# are the ones the search is performed over -- NOT all the variables defined
# in the data frame.定义变量类型:“c”是“连续的”。这里定义的变量是执行搜索的变量，而不是数据帧中定义的所有变量。
variable_types = {'Pregnancies' : 'c', 'Glucose' : 'c', 'BloodPressure' : 'c', 'SkinThickness' : 'c', 'Insulin' : 'c','BMI' : 'c','DPF' : 'c','Age' : 'c','Outcome' : 'c'}

ic_algorithm = IC(RobustRegressionTest)
graph = ic_algorithm.search(X,variable_types)