def get_avg_coherence(df, n_topics):
print '{} Topics Processing...'.format(n_topics)
nmf, X, W, W_percent, labels, topic_words, feature_names, reverse_lookup = nmf_articles(df, n_topics=n_topics, n_features=10000, random_state=1, max_df=0.8, min_df=5)
print 'Factorizing Done...'
pbar = ProgressBar()
coherence = []
for words in pbar(topic_words):
coherence.append(topic_coherence(X, reverse_lookup, words))
print '\n'
return np.mean(coherence)
def get_avg_coherence(df, n_topics):
print '{} Topics Processing...'.format(n_topics)
nmf, X, W, W_percent, labels, topic_words, feature_names, reverse_lookup = nmf_articles(
df,
n_topics=n_topics,
n_features=10000,
random_state=1,
max_df=0.8,
min_df=5)
print 'Factorizing Done...'
pbar = ProgressBar()
coherence = []
for words in pbar(topic_words):
coherence.append(topic_coherence(X, reverse_lookup, words))
print '\n'
return np.mean(coherence)
fig = plt.figure(figsize=figsize)
ax = fig.add_subplot(111)
ax.imshow(wc)
ax.axis('off')
if __name__ == '__main__':
df = pd.read_pickle('election_data.pkl')
# Plot % of articles mentioning candidate accross all news sources
# plot_candidate_percentages(df, ['Clinton', 'Trump', 'Bush'])
nmf, X, W, W_percent, labels, topic_words, feature_names, reverse_lookup = nmf_articles(
df,
n_topics=90,
n_features=10000,
random_state=1,
max_df=0.8,
min_df=5)
outlets = [('nyt', 'NYT', '#4c72b0'), ('foxnews', 'FOX', '#c44e52'),
('npr', 'NPR', '#55a868'), ('guardian', 'GUA', '#8172b2'),
('wsj', 'WSJ', '#ccb974')]
# predominant_source = print_topic_summary(df, labels, outlets, topic_words)
# Create a dictionary with the topic labels for creating the plots
topic_labels = get_topic_labels()
# path = './topic_plots/'
# for idx in xrange(90):
# Create the matplotlib figure and axis if they weren't passed in
if not ax:
fig = plt.figure(figsize=figsize)
ax = fig.add_subplot(111)
ax.imshow(wc)
ax.axis('off')
if __name__=='__main__':
df = pd.read_pickle('election_data.pkl')
# Plot % of articles mentioning candidate accross all news sources
# plot_candidate_percentages(df, ['Clinton', 'Trump', 'Bush'])
nmf, X, W, W_percent, labels, topic_words, feature_names, reverse_lookup = nmf_articles(df, n_topics=90, n_features=10000, random_state=1, max_df=0.8, min_df=5)
outlets = [('nyt', 'NYT', '#4c72b0'), ('foxnews', 'FOX', '#c44e52'), ('npr', 'NPR', '#55a868'), ('guardian', 'GUA', '#8172b2'), ('wsj', 'WSJ', '#ccb974')]
# predominant_source = print_topic_summary(df, labels, outlets, topic_words)
# Create a dictionary with the topic labels for creating the plots
topic_labels = get_topic_labels()
# path = './topic_plots/'
# for idx in xrange(90):
# # If the topic is junk, skip making the plot
# if topic_labels[idx] == 'junk':
# print '\n'
# continue
# print 'Topic {}: {}'.format(str(idx), topic_labels[idx])
