def tsne_kmeans_clusters(tfidf, num_clusters=[3, 5, 7, 9, 11]):
'''
Vectorizer results are normalized, which makes KMeans behave as
spherical k-means for better results. Since LSA/SVD results are
not normalized, we have to redo the normalization.
'''
print(
'\nUse sklearn tSNE to visualize viability of cluster estimates to inform n topic choices: {}'
.format(num_clusters))
for k in num_clusters:
start = datetime.now()
svd = TruncatedSVD(n_components=50, n_iter=10, random_state=0)
normalizer = Normalizer(copy=False)
lsa = make_pipeline(svd, normalizer)
reduced = lsa.fit_transform(tfidf)
# next, apply kmeans to the corpus to get labels
clusters = KMeans(n_clusters=k, init='k-means++')
clusters.fit(reduced)
tsne = TSNEVisualizer(decompose=None)
tsne.fit(reduced, ["cluster {}".format(c) for c in clusters.labels_])
tsne.finalize()
filename = r'images/tsne_projections/tSNE_wKMeans_SVD_' + str(
k) + '_clusters_' + str(tfidf.shape[0]) + '_docs.png'
plt.savefig(filename)
plt.close()
end = datetime.now()
print(' ' + filename)
print(" Time taken: {}".format(end - start))
def generate_tsne(title, X, labels):
fig, (ax1) = plt.subplots(1, 1, figsize=(4, 2))
title_dic = {'fontsize': 7, 'fontweight': 'bold'}
colors = resolve_colors(11, 'Spectral_r')
colors2 = resolve_colors(10, 'BrBG_r')
tsne = TSNEVisualizer(ax1, colors=colors + colors2,decompose=None)
tsne.fit(X, labels)
tsne.finalize()
ax1 = tsne.ax
ax1.set_title(title, title_dic)
path = os.path.join(OUTPUT)
filename = title
filename = os.path.join(path, filename)
plt.savefig(filename)
def visualise_with_yellowbrick(feature_matrix, labels_tfidf):
tsne = TSNEVisualizer(title="Chat Messages Clusters", alpha = 0.7)
tsne.fit(feature_matrix, np.array(labels_tfidf))
tsne.finalize()
tsne.poof()