獲取sklearn本地的數(shù)據(jù)集
from sklearn.datasets import load_iris
li = load_iris()
print("數(shù)據(jù)集描述為:")
print(li.DESCR)
print("目標(biāo)值為:")
print(li.target)
print("數(shù)據(jù)為:")
print(li.data)
print("特征描述名稱為:")
print(li.feature_names)
print("目標(biāo)描述名為:")
print(li.target_names)
從網(wǎng)絡(luò)獲取數(shù)據(jù)集
from sklearn.datasets import fetch_20newsgroups
# 從網(wǎng)絡(luò)獲取大的數(shù)據(jù)集
news = fetch_20newsgroups(subset="all")
print("打印所有獲取的數(shù)據(jù):")
print(news.data)
劃分訓(xùn)練集和測試集
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
# 加載數(shù)據(jù)集
li = load_iris()
# 將數(shù)據(jù)劃分為訓(xùn)練集特征值,訓(xùn)練集目標(biāo)值, 測試集特征值, 測試集目標(biāo)值
train_data,test_data,train_target,test_target = train_test_split(li.data, li.target, test_size = 0.25)
print("訓(xùn)練集特征值數(shù)據(jù):")
print(train_data)
print("訓(xùn)練集目標(biāo)值數(shù)據(jù):")
print(train_target)
print("測試集特征值數(shù)據(jù):")
print(test_data)
print("測試值目標(biāo)值數(shù)據(jù):")
print(test_target)
最后編輯于 ：
?著作權(quán)歸作者所有,轉(zhuǎn)載或內(nèi)容合作請聯(lián)系作者
