python 将数据拆分为训练/测试数据集。

Posted 2021-05-09

# Save Model Using Pickle
from pandas import read_csv
from sklearn.model_selection import train_test_split

url = "https://goo.gl/vhm1eU"
names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']
dataframe = read_csv(url, names=names)
array = dataframe.values
X = array[:,0:8]
Y = array[:,8]
test_size = 0.33
seed = 7
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=test_size, random_state=seed)