---

数据预处理

1.获取数据

from sklearn.datasets import load_iris
li=load_iris()
print("获取特征值")
print(li.data)
print("目标值",li.target)#分类数据集

用于分类的大数据集

from sklearn.datasets import load_iris,fetch_20newsgroups
news=fetch_20newsgroups(subset="all")
print(news.data)
print(news.target)

from sklearn.datasets import load_boston
lb=load_boston()
print(lb.data)
print(lb.target)#回归数据集

2.处理缺失值

3.划分数据集

训练集与测试集划分：70% 30%；80% 20%；75% 25%

from sklearn.datasets import load_breast_cancer
cancer = load_breast_cancer()##将数据集赋值给cancer变量
cancer_data = cancer['data']
cancer_target = cancer['target']
from sklearn.model_selection import train_test_split
cancer_data_train, cancer_data_test,cancer_target_train, cancer_target_test = \
train_test_split(cancer_data, cancer_target,test_size=0.2, random_state=42) # test_size表示测试集在总数中的占比

4.数据预处理和PCA降维

#离差标准化
from sklearn.preprocessing import MinMaxScaler
Scaler = MinMaxScaler().fit(cancer_data_train) ##生成规则
##将规则应用于训练集
cancer_trainScaler = Scaler.transform(cancer_data_train) 
##将规则应用于测试集
cancer_testScaler = Scaler.transform(cancer_data_test)

from sklearn.decomposition import PCA
pca_model = PCA(n_components=10).fit(cancer_trainScaler) ##生成规则
cancer_trainPca = pca_model.transform(cancer_trainScaler) ##将规则应用于训练集
cancer_testPca = pca_model.transform(cancer_testScaler) ##将规则应用于测试集

5.算法实现：估计器