机器学习基础

#方式1：获取小规模的数据集
import sklearn.datasets as datasets
iris = datasets.load_iris()
#提取样本数据
feature = iris[‘data‘]
target = iris[‘target‘]


feature.shape
(150, 4)

target.shape
(150,)

target
array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
       0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])


#切分样本数据
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(feature,target,test_size=0.2,random_state=2020)


x_train,y_train #训练集数据

x_test,y_test #测试集数据

#方式2：获取较大规模的数据集
datasets.fetch_20newsgroups(data_home=‘数据集保存路径‘,subset=‘all‘)