python数据分析与应用笔记
使用sklearn构建模型
1.使用sklearn转换器处理数据
import numpy as np
from sklearn.datasets import load_breast_cancer
from sklearn.preprocessing import MinMaxScaler #该函数时对数据做标准化处理
from sklearn.decomposition import PCA #该函数时对数据进行降维处理
from sklearn.model_selection import train_test_split #该函数是对数据做训练集和测试集的划分
cancer = load_breast_cancer() #将数据集赋值给cancer变量
cancer_data = cancer['data'] #提取数据集中的数据
cancer_target = cancer['target'] #提取数据集中的标签
cancer_names = cancer['feature_names'] #查看特征数目
cancer_desc = cancer['DESCR']
#划分训练集和测试集,其中20%的作为测试集
cancer_train_data,cancer_test_data,cancer_train_target,cancer_test_target = train_test_split(cancer_data,cancer_target,test_size = 0.2,random_state = 42)
scaler = MinMaxScaler().fit(cancer_train_data) #生成规则
# 将规则应用于训练集和测试集
cancer_trainScaler = scaler.transform(cancer_train_data)
cancer_testScaler = scaler.transform(cancer_test_data)
#构建pca降维模型
pca_model = PCA(n_components = 10).fit(cancer_trainScaler)
#将降维模型应用于标准化之后的训练数据和测试数据
cancer_trainPca = pca_model.transform(cancer_trainSc