1.1、获取sklearn的鸢尾花数据数据集
1.2、分隔skelarn的数据集
from sklearn.datasets import load_iris #导入鸢尾花数据集
from sklearn.model_selection import train_test_split #将数据集按比列分隔为数据集和训练集
li = load_iris()
#返回的格式,训练集 train x_train y_train 测试集 x_test y_test
x_train, x_test, y_train, y_test = train_test_split(li.data, li.target, test_size=0.25) #这里获取的顺序不能错
print("训练集的特征值和目标值:", x_train, y_train)
print("测试集的特征值和目标值:", x_test, y_test)
2.获取新闻大数据集
from sklearn.datasets import fetch_20newsgroups
from sklearn.model_selection import train_test_split #将数据集按比列分隔为数据集和训练集
news = fetch_20newsgroups('all')
print(news.data)
print(news.target)
3.获取回归数据集
目标值是连续型的数值
from sklearn.datasets import load_boston
lb = load_boston()
print(lb.data)
print(lb.target)