♥
代码语言：javascript复制from time import time
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import offsetbox
from sklearn import (manifold,datasets,decomposition,ensemble,discriminant_analysis,random_projection)
digits=datasets.load_digits(n_class=6)
X=digits.data
y=digits.target
n_samples,n_features=X.shape
n_neighbors=30
def plot_embedding(X,title=None):
x_min,x_max=np.min(X,0),np.max(X,0)
X=(X-x_min)/(x_max-x_min)
plt.figure()
ax=plt.subplot(111)
for i in range(X.shape[0]):
plt.text(X[i,0],X[i,1],str(digits.target[i]),
color=plt.cm.Set1(y[i]/10.),
fontdict={'weight':'bold','size':9})
if hasattr(offsetbox,'AnnotationBbox'):
shown_images=np.array([[1.,1.]])
for i in range(digits.data.shape[0]):
dist = np.sum((X[i]-shown_images)**2,1)
if np.min(dist)<4e-3:
continue
shown_images=np.r_[shown_images,[X[i]]]
imagebox=offsetbox.AnnotationBbox(offsetbox.OffsetImage(digits.images[i],cmap=plt.cm.gray_r),X[i])
ax.add_artist(imagebox)
plt.xticks([]),plt.yticks([])
if title is not None:
plt.title(title)
#绘制数字图像
n_img_per_row=20
img=np.zeros((10*n_img_per_row,10*n_img_per_row))
for i in range(n_img_per_row):
ix=10*i 1
for j in range(n_img_per_row):
iy=10*j 1
img[ix:ix 8,iy:iy 8]=X[i*n_img_per_row j].reshape((8,8))
plt.imshow(img,cmap=plt.cm.binary)
plt.xticks([])
plt.yticks([])
plt.title('选择64维数字数据集')
#随机树嵌入数字数据集
print("计算随机树嵌入")
hasher=ensemble.RandomTreesEmbedding(n_estimators=200,random_state=0,max_depth=5)
t0=time()
X_transformed=hasher.fit_transform(X)
pca=decomposition.TruncatedSVD(n_components=2)
X_reduced=pca.fit_transform(X_transformed)
plot_embedding(X_reduced,"随机树嵌入数字数据集 (时间 %.2fs)" %(time()-t0))
plt.show()
算法：RandomTreesEmbedding是使用高维稀疏进行无监督转换，数据点根据被分类到树的叶子节点进行编码导致了编码维度与森林中的树木同样多。
链接：https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.RandomTreesEmbedding.html
