我如何使用 t-SNE 进行降维以可视化我的 300 维词嵌入?
How can i use t-SNE for dimension reduction to visualise my 300 dimension word embeddings?
我目前正在尝试在 2d 中可视化 300 维的词向量。
我尝试了使用不同参数的 t-SNE 并阅读了 https://distill.pub/2016/misread-tsne/ 上的博客,但到目前为止我没有得到任何有用的结果。
我想要一个对应于几个选定词向量的最近邻的可视化,但是二维可视化到处都是。
我的问题不适合用TSNE吗?
from sklearn.manifold import TSNE
arr = []
for category in category_embeddings.keys():
arr.append(category_embeddings[category][0])
perplex = 30
tsne_steps = 50000
lr = 10
fig_tsne = plt.figure(figsize=(18, 18), dpi=800)
tsne = TSNE(perplexity=perplex,
n_components=2,
init='pca',
n_iter=tsne_steps,
learning_rate=lr,
method="exact")
plot_only = len(category_embeddings.keys())
low_dim_embs = tsne.fit_transform(np.asarray(arr))
for i, title in enumerate(category_embeddings.keys()):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(
title,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')
好的,解决了。
创建一个距离矩阵并用该矩阵输入 TSNE 会产生更好的二维可视化效果。
from sklearn.metrics.pairwise import cosine_distances
c1_c2_cos_dist = {}
# Create distance Matrix
for c1in category_embeddings.keys():
tmp = {}
for c2 in category_embeddings.keys():
cos_dis = cosine_distances(category_embeddings[c1],category_embeddings[
tmp[c2] = cos_dis[0][0]
c1_c2_cos_dist[c1] = copy(tmp)
# ---
from sklearn.manifold import TSNE
arr = []
for category in category_embeddings.keys():
arr.append(category_embeddings[category][0])
perplex = 30
tsne_steps = 50000
lr = 10
fig_tsne = plt.figure(figsize=(18, 18), dpi=800)
tsne = TSNE(perplexity=perplex,
n_components=2,
metric="precomputed",
n_iter=tsne_steps,
learning_rate=lr)
distMatrix = []
for col in c1_c2_cos_dist.keys():
arr =[]
for row in c1_c2_cos_dist[col]:
arr.append(c1_c2_cos_dist[col][row])
distMatrix.append(copy(arr))
distMatrix = np.asarray(distMatrix)
low_dim_embs = tsne.fit_transform(distMatrix)
plot_only = len(category_embeddings.keys())
for i, title in enumerate(category_embeddings.keys()):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(
title,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')
我目前正在尝试在 2d 中可视化 300 维的词向量。 我尝试了使用不同参数的 t-SNE 并阅读了 https://distill.pub/2016/misread-tsne/ 上的博客,但到目前为止我没有得到任何有用的结果。
我想要一个对应于几个选定词向量的最近邻的可视化,但是二维可视化到处都是。
我的问题不适合用TSNE吗?
from sklearn.manifold import TSNE
arr = []
for category in category_embeddings.keys():
arr.append(category_embeddings[category][0])
perplex = 30
tsne_steps = 50000
lr = 10
fig_tsne = plt.figure(figsize=(18, 18), dpi=800)
tsne = TSNE(perplexity=perplex,
n_components=2,
init='pca',
n_iter=tsne_steps,
learning_rate=lr,
method="exact")
plot_only = len(category_embeddings.keys())
low_dim_embs = tsne.fit_transform(np.asarray(arr))
for i, title in enumerate(category_embeddings.keys()):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(
title,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')
好的,解决了。
创建一个距离矩阵并用该矩阵输入 TSNE 会产生更好的二维可视化效果。
from sklearn.metrics.pairwise import cosine_distances
c1_c2_cos_dist = {}
# Create distance Matrix
for c1in category_embeddings.keys():
tmp = {}
for c2 in category_embeddings.keys():
cos_dis = cosine_distances(category_embeddings[c1],category_embeddings[
tmp[c2] = cos_dis[0][0]
c1_c2_cos_dist[c1] = copy(tmp)
# ---
from sklearn.manifold import TSNE
arr = []
for category in category_embeddings.keys():
arr.append(category_embeddings[category][0])
perplex = 30
tsne_steps = 50000
lr = 10
fig_tsne = plt.figure(figsize=(18, 18), dpi=800)
tsne = TSNE(perplexity=perplex,
n_components=2,
metric="precomputed",
n_iter=tsne_steps,
learning_rate=lr)
distMatrix = []
for col in c1_c2_cos_dist.keys():
arr =[]
for row in c1_c2_cos_dist[col]:
arr.append(c1_c2_cos_dist[col][row])
distMatrix.append(copy(arr))
distMatrix = np.asarray(distMatrix)
low_dim_embs = tsne.fit_transform(distMatrix)
plot_only = len(category_embeddings.keys())
for i, title in enumerate(category_embeddings.keys()):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(
title,
xy=(x, y),
xytext=(5, 2),
textcoords='offset points',
ha='right',
va='bottom')