using_ft.py

from embeddings import FTCallback
from gensim.models.fasttext import FastText
from pprint import pprint
import matplotlib.pyplot as plt
import numpy as np


from sklearn.cluster import KMeans
from sklearn.decomposition import PCA

MODEL_FILE = ""
ft = FastText.load(MODEL_FILE)


print("SIMILARITIES OF ")
h = ft["זועבי"]
h2 = ft["דב"]
pprint(ft.similar_by_vector(h))
pprint(ft.similar_by_vector(h2))
# km = KMeans(verbose=True)
#
# reduced_data = PCA(n_components=2).fit_transform(ft.wv)
# km.fit(reduced_data)
#
#
# # Step size of the mesh. Decrease to increase the quality of the VQ.
# h = .02     # point in the mesh [x_min, x_max]x[y_min, y_max].
#
# # Plot the decision boundary. For that, we will assign a color to each
# x_min, x_max = reduced_data[:, 0].min() - 1, reduced_data[:, 0].max() + 1
# y_min, y_max = reduced_data[:, 1].min() - 1, reduced_data[:, 1].max() + 1
# xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))
#
# # Obtain labels for each point in mesh. Use last trained model.
# Z = km.predict(np.c_[xx.ravel(), yy.ravel()])
#
# # Put the result into a color plot
# Z = Z.reshape(xx.shape)
# plt.figure(1)
# plt.clf()
# plt.imshow(Z, interpolation='nearest',
#            extent=(xx.min(), xx.max(), yy.min(), yy.max()),
#            cmap=plt.cm.Paired,
#            aspect='auto', origin='lower')
#
# plt.plot(reduced_data[:, 0], reduced_data[:, 1], 'k.', markersize=2)
# # Plot the centroids as a white X
# centroids = km.cluster_centers_
# plt.scatter(centroids[:, 0], centroids[:, 1],
#             marker='x', s=169, linewidths=3,
#             color='w', zorder=10)
# plt.title('K-means clustering on the digits dataset (PCA-reduced data)\n'
#           'Centroids are marked with white cross')
# plt.xlim(x_min, x_max)
# plt.ylim(y_min, y_max)
# plt.xticks(())
# plt.yticks(())
# plt.show()

print("DONE")