t-SNE是一種降維方法,是最好的降維方法之一
t-SNE是一種集降維與可視化于一體的技術,它是基于SNE可視化的改進,解決了SNE在可視化後樣本分布擁擠、邊界不明顯的特點,是目前最好的降維可視化手段。
from time import time import numpy as np import matplotlib.pyplot as plt from matplotlib import offsetbox from sklearn import manifold, datasets # ---------------------------------------------------------------------- # Scale and visualize the embedding vectors 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]): #周遊所有1083個圖 plt.text(X[i, 0], X[i, 1], str(y[i]), color=plt.cm.Set1(y[i] / 10.), #cm代表color map,即顔色映射地圖,Set1, Set2, Set3是它的三個顔色集合,可傳回顔色 fontdict={'weight': 'bold', 'size': 9}) plt.xticks([]), plt.yticks([]) if title is not None: plt.title(title) # ---------------------------------------------------------------------- digits = datasets.load_digits(n_class=6) X = digits.data #X是(1083,64) y = digits.target #y是 (1083) #即共1083張圖, X的每張圖用一個64維的矩陣表示 # t-SNE embedding of the digits dataset print("Computing t-SNE embedding") tsne = manifold.TSNE(n_components=2, init='pca', random_state=0) #把64維降到2維 X_tsne = tsne.fit_transform(X) #X_tsne是(1083,2) plot_embedding(X_tsne, "t-SNE embedding" ) plt.show()
如果沒有hasattr(offsetbox, 'AnnotationBbox') 這部分那麼結果會是這樣from time import time import numpy as np import matplotlib.pyplot as plt from matplotlib import offsetbox from sklearn import manifold, datasets digits = datasets.load_digits(n_class=6) X = digits.data #X是(1083,64) y = digits.target #y是 (1083) #即共1083張圖, X的每張圖用一個64維的矩陣表示 n_samples, n_features = X.shape n_neighbors = 30 # ---------------------------------------------------------------------- # Scale and visualize the embedding vectors 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]): #周遊所有1083個圖 plt.text(X[i, 0], X[i, 1], str(y[i]), color=plt.cm.Set1(y[i] / 10.), #cm代表color map,即顔色映射地圖,Set1, Set2, Set3是它的三個顔色集合,可傳回顔色 fontdict={'weight': 'bold', 'size': 9}) if hasattr(offsetbox, 'AnnotationBbox'): # only print thumbnails with matplotlib > 1.0 shown_images = np.array([[1., 1.]]) # just something big for i in range(X.shape[0]): dist = np.sum((X[i] - shown_images) ** 2, 1) if np.min(dist) < 4e-3: # don't show points that are too close 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) # ---------------------------------------------------------------------- # Plot images of the digits #隻取了前20*20=400個 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('A selection from the 64-dimensional digits dataset') plt.show() # ---------------------------------------------------------------------- # t-SNE embedding of the digits dataset print("Computing t-SNE embedding") tsne = manifold.TSNE(n_components=2, init='pca', random_state=0) #把64維降到2維 t0 = time() X_tsne = tsne.fit_transform(X) #X_tsne是(1083,2) plot_embedding(X_tsne, "t-SNE embedding of the digits (time %.2fs)" %(time() - t0) ) plt.show()