Visualize fasttext vector using tsne

word-embedding-visualization.py

import fasttext
import numpy as np
import matplotlib.pyplot as plt
from sklearn.manifold import TSNE

model = fasttext.load_model('models/cc.en.300.bin')
# static keywords
keywords = ['deeds', 'acquisitions', 'skills', 'acquirements', 'attainments', 'achievements']

keyword_vectors = []
for keyword in keywords:
  vec = model.get_word_vector(keyword)
  keyword_vectors.append(vec)

keyword_vectors = np.array(keyword_vectors)

tsne = TSNE(n_components = 2, random_state = 0, n_iter = 10000, perplexity = 2)
np.set_printoptions(suppress = True)
T = tsne.fit_transform(keyword_vectors)
labels = keywords

plt.figure(figsize = (14, 8))
plt.scatter(T[:, 0], T[:, 1], c = 'blue', edgecolors = 'r')
for label, x, y in zip(labels, T[:, 0], T[:, 1]):
  plt.annotate(label, xy = (x + 1, y + 1), xytext = (0, 0), textcoords = 'offset points')
plt.show()