sklearn数据集的获取与划分

from sklearn.datasets import load_iris
li = load_iris()

print("数据集描述为:")
print(li.DESCR)
print("目标值为:")
print(li.target)
print("数据为:")
print(li.data)
print("特征描述名称为:")
print(li.feature_names)
print("目标描述名为:")
print(li.target_names)

from sklearn.datasets import fetch_20newsgroups

# 从网络获取大的数据集
news = fetch_20newsgroups(subset="all")
print("打印所有获取的数据:")
print(news.data) 

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
# 加载数据集
li = load_iris()

# 将数据划分为训练集特征值,训练集目标值, 测试集特征值, 测试集目标值
train_data,test_data,train_target,test_target = train_test_split(li.data, li.target, test_size = 0.25)

print("训练集特征值数据:")
print(train_data)
print("训练集目标值数据:")
print(train_target)
print("测试集特征值数据:")
print(test_data)
print("测试值目标值数据:")
print(test_target)