import pandas as pd
df = pd.read_excel('肿瘤数据.xlsx')
x = df.drop(columns=['肿瘤性质'])
y = df[' 肿瘤性质']
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test
= train_test_split(x,y,test_size=0.2,random_state=1)
print('x_train: \n',x_train)
print('y_train: \n',y_train)
print('x_test: \n',x_test)
print('x_test: \n',x_test)
from sklearn.naive_bayes import GaussianNB
model = GaussianNB()
model.fit(x_train,y_train)
y_test_pred = model.predict(x_test)
print('y_test_pred:',y_test_pred)
accuracy2 = model.score(x_test,y_test)
print('accuracy2:',accuracy2)