PCA iris数据降维后分类

1. 基于iris数据 建立KNN模型实现数据分类

• 对数据进行标准环处理,选择一个维度可视化处理后效果
• 进行与元数据等维度PCA,查看各主成分的方差比例
• 保留合适的主成分,可视化降维后的数据
• 基于降维后数据建立KNN模型,与元数据表现进行对比

import pandas as pd
import numpy as np
data = pd.read_csv('iris_data.csv')
print(data.head())
X = data.drop(['target','label'],axis=1)
y = data.loc[:,'label']
print(X.shape,y.shape)#打印X，y的维度

#建立模型-预测-计算准确率
from sklearn.neighbors import KNeighborsClassifier
KNN = KNeighborsClassifier(n_neighbors=3)
KNN.fit(X,y)
y_predict = KNN.predict(X)
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y,y_predict)
print(accuracy)

0.96

#数据标准化处理
from sklearn.preprocessing import StandardScaler
X_norm = StandardScaler().fit_transform(X)
X1_mean = X.loc[:,'sepal length'].mean()
X1_norm_mean = X_norm[:,0].mean()
X1_sigma = X.loc[:,'sepal length'].std()
X1_norm_sigma = X_norm[:,0].std()
print(X1_mean,X1_norm_mean,X1_sigma,X1_norm_sigma)
#均值约等于0和标准差为1

%matplotlib inline
from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(10,5))
plt.subplot(121)
plt.hist(X.loc[:,'sepal length'],bins=100)#X有四个维度 取一个
plt.subplot(122)
plt.hist(X_norm[:,0],bins=100)
plt.show()

print(X.shape)
#4维的

from sklearn.decomposition import PCA 
pca = PCA(n_components=4)
X_pca = pca.fit_transform(X_norm)

var_ratio = pca.explained_variance_ratio_#计算比例
print(var_ratio)

#主成分
fig2 = plt.figure()
plt.bar([1,2,3,4],var_ratio)
plt.xticks([1,2,3,4],['PC1','PC2','PC3','PC4'])
plt.ylabel("variance ratio ")
plt.show()

from sklearn.decomposition import PCA 
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_norm)
print(type(X_pca))

fig3 = plt.figure()
s1= plt.scatter(X_pca[:,0][y==0],X_pca[:,1][y==0])
s2 = plt.scatter(X_pca[:,0][y==1],X_pca[:,1][y==1])
s3 = plt.scatter(X_pca[:,0][y==2],X_pca[:,1][y==2])
plt.legend((s1,s2,s3),('s1','s2','s3'))
plt.show()

#准确率
# from sklearn.neighbors import KNeighborsClassifier
KNN = KNeighborsClassifier(n_neighbors=3)
KNN.fit(X_pca,y)
y_predict_pca = KNN.predict(X_pca)
from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y,y_predict_pca)
print(accuracy)

维度下降了 信息仍然保留了