def embedding_fig(w2v_model,
kmeans_model,
n=500,
embed_style='tsne',
savefn=None,
show=False):
"""
Save or show a matplotlib figure, displaying word embeddings colored
according to cluster assignment. The parameter n gives the number of
words to show, in decreasing order of frequency in the dataset.
"""
freqs = {x: y.count for x, y in w2v_model.vocab.items()}
words, word_vecs = w2v_model.index2word, w2v_model.syn0
srtd_indices, srtd_words = zip(*sorted(
list(enumerate(words)), key=lambda x: freqs[x[1]], reverse=True))
srtd_vecs = np.array([word_vecs[i] for i in srtd_indices])
subset_words, subset_vecs = srtd_words[:n], srtd_vecs[:n]
# map cluster assignment to integer.
subset_clusters = np.array(
map(lambda x: int(kmeans_model.predict(x)), subset_vecs))
unique_clusters = set(subset_clusters)
print "number of unique clusters in top {} words: {}.".format(
n, len(unique_clusters))
colormap = discrete_color_scheme(len(unique_clusters))
int_to_color = {
idx: colormap[i]
for (i, idx) in enumerate(list(unique_clusters))
}
subset_colors = [int_to_color[i] for i in subset_clusters]
if embed_style == 'pca':
pca = PCA(n_components=2)
pca_embeddings = pca.fit_transform(subset_vecs)
embed_xs, embed_ys = pca_embeddings.transpose()
elif embed_style == 'tsne':
tsne_embeddings = bh_sne(np.asarray(subset_vecs, dtype=np.float64),
d=2,
perplexity=10)
embed_xs, embed_ys = tsne_embeddings.transpose()
fig = plt.figure()
fig.set_size_inches(50, 28.4)
ax = fig.add_subplot(111)
ax.scatter(embed_xs, embed_ys, color=subset_colors, s=100)
for (x, y, word) in zip(embed_xs, embed_ys, subset_words):
ax.annotate(word, xy=(x, y), textcoords='offset points', fontsize=20)
plt.title('{} 2d word embeddings'.format(embed_style))
if savefn is not None:
plt.savefig(savefn, dpi=120)
if show:
plt.show()
def plot_gpe(gpe_data, show=False, savefn=None):
terms = gpe_data.values()[0].keys()
term_serieses = {t: [] for t in terms}
scheme = discrete_color_scheme(n=len(terms))
colormap = {t: scheme[i] for i, t in enumerate(terms)}
times = []
s = sorted(gpe_data.items())
for date, per_stem_vals in s:
for stem, val in per_stem_vals.items():
term_serieses[stem].append(val)
times.append(date)
# Now for each stem, we have a list of three-tuples correspnoding to their values over time
# get a 3x1 figure, each sharing the x (time) axis..
f, (ax1, ax2, ax3) = plt.subplots(3, 1, sharex=True)
f.set_size_inches(18.5, 10.5)
for stem, serieses in term_serieses.items():
ys0 = map(lambda x: x[0], serieses)
ys1 = map(lambda x: x[1], serieses)
ys2 = map(lambda x: x[2], serieses)
ax1.plot_date(times, ys0, color=colormap[stem], label=stem, fmt='b-')
ax2.plot_date(times, ys1, color=colormap[stem], label=stem, fmt='b-')
ax3.plot_date(times, ys2, color=colormap[stem], label=stem, fmt='b-')
ax1.set_xlabel('Time')
ax2.set_xlabel('Time')
ax3.set_xlabel('Time')
ax1.set_ylabel('Differential Fecundity')
ax2.set_ylabel('Differential Mutation')
ax3.set_ylabel('Differential Convergence')
ax1.set_title('GPE Term I')
ax2.set_title('GPE Term II')
ax3.set_title('GPE Term III')
handles, labels = ax1.get_legend_handles_labels()
f.legend(handles, labels, loc='upper right')
if savefn is not None:
plt.savefig(savefn, dpi=100)
