Python机器学习--降维

• 主成分分析（PCA）

• 测试

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 31 14:21:51 2017

@author: Administrator
"""

import matplotlib.pyplot as plt
from sklearn.decomposition import PCA
from sklearn.datasets import load_iris
 
data = load_iris()
y = data.target
X = data.data
pca = PCA(n_components=2)
reduced_X = pca.fit_transform(X)
 
red_x, red_y = [], []
blue_x, blue_y = [], []
green_x, green_y = [], []
 
for i in range(len(reduced_X)):
    if y[i] == 0:
        red_x.append(reduced_X[i][0])
        red_y.append(reduced_X[i][1])
    elif y[i] == 1:
        blue_x.append(reduced_X[i][0])
        blue_y.append(reduced_X[i][1])
    else:
        green_x.append(reduced_X[i][0])
        green_y.append(reduced_X[i][1])
 
plt.scatter(red_x, red_y, c='r', marker='x')
plt.scatter(blue_x, blue_y, c='b', marker='D')
plt.scatter(green_x, green_y, c='g', marker='.')
plt.show()      

• 非负矩阵分解（NMF）

# -*- coding: utf-8 -*-
"""
Created on Thu Aug 31 14:24:26 2017

@author: Administrator
"""


from numpy.random import RandomState
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_olivetti_faces
from sklearn import decomposition
 
 
n_row, n_col = 2, 3
n_components = n_row * n_col
image_shape = (64, 64)
 
 
###############################################################################
# Load faces data
dataset = fetch_olivetti_faces(shuffle=True, random_state=RandomState(0))
faces = dataset.data
 
###############################################################################
def plot_gallery(title, images, n_col=n_col, n_row=n_row):
    plt.figure(figsize=(2. * n_col, 2.26 * n_row)) 
    plt.suptitle(title, size=16)
 
    for i, comp in enumerate(images):
        plt.subplot(n_row, n_col, i + 1)
        vmax = max(comp.max(), -comp.min())
 
        plt.imshow(comp.reshape(image_shape), cmap=plt.cm.gray,
                   interpolation='nearest', vmin=-vmax, vmax=vmax)
        plt.xticks(())
        plt.yticks(())
    plt.subplots_adjust(0.01, 0.05, 0.99, 0.94, 0.04, 0.)
 
     
plot_gallery("First centered Olivetti faces", faces[:n_components])
###############################################################################
 
estimators = [
    ('Eigenfaces - PCA using randomized SVD',
         decomposition.PCA(n_components=6,whiten=True)),
 
    ('Non-negative components - NMF',
         decomposition.NMF(n_components=6, init='nndsvda', tol=5e-3))  # 设置k=6
]
 
###############################################################################
 
for name, estimator in estimators:
    print("Extracting the top %d %s..." % (n_components, name))
    print(faces.shape)
    estimator.fit(faces)
    components_ = estimator.components_
    plot_gallery(name, components_[:n_components])
 
plt.show()      

• 结果

Extracting the top 6 Eigenfaces - PCA using randomized SVD...

(400, 4096)

Extracting the top 6 Non-negative components - NMF...



C/C++基本语法学习

STL

C++ primer