def generate_bokeh_umap(self, media_type):
output_notebook()
topics = []
labels = []
for key, value in self.top_words_map.items():
topics.append(value)
labels.append(key)
if len(labels) >= 20000:
reducer = umap.UMAP(n_neighbors=100, metric='hellinger')
if len(labels) >= 5000:
reducer = umap.UMAP(n_neighbors=50, metric='hellinger')
else:
reducer = umap.UMAP(metric='hellinger')
X = self.vectorized_out.copy()
X_embedded = reducer.fit_transform(X)
# tsne = TSNE(verbose=1, perplexity=100, random_state=42)
# X = self.vectorized_out
# X_embedded = tsne.fit_transform(X.toarray())
df_tmp = pd.DataFrame(self.doc_topic_dists)
df_tmp['topic'] = df_tmp.idxmax(axis=1)
y_labels = df_tmp['topic'].values
y_labels_new = []
for i in y_labels:
y_labels_new.append(labels[i])
df = self.original_df.copy()
# data sources
if media_type == 'videos':
source = ColumnDataSource(
data=dict(x=X_embedded[:, 0],
y=X_embedded[:, 1],
x_backup=X_embedded[:, 0],
y_backup=X_embedded[:, 1],
desc=y_labels,
ids=df['id'],
titles=df['title'],
published_times=df['first_airing'],
text=df['text'],
publication_end_times=df['publication_end_time'],
media_availables=df['media_available'],
duration_minutes=df['duration_minutes'],
finnpanel_genres=df['finnpanel_genre'],
labels=["Topic " + str(x) for x in y_labels_new],
links=df['link']))
# hover over information
hover = HoverTool(
tooltips=[
("Id", "@ids{safe}"),
("Title", "@titles{safe}"),
("Published", "@published_times{safe}"),
# ("Text", "@texts{safe}"),
("Publication ends", "@publication_end_times{safe}"),
("Currently available", "@media_availables{safe}"),
("Duration (minutes)", "@duration_minutes{safe}"),
("Finnpanel genres", "@finnpanel_genres{safe}"),
("Link", "@links")
],
point_policy="follow_mouse")
elif media_type == 'articles':
source = ColumnDataSource(
data=dict(x=X_embedded[:, 0],
y=X_embedded[:, 1],
x_backup=X_embedded[:, 0],
y_backup=X_embedded[:, 1],
desc=y_labels,
ids=df.index,
titles=df['title'],
published_times=df['published_time'].dt.strftime(
'%Y-%m-%d %H:%M'),
text=df['text'],
labels=["Topic " + str(x) for x in y_labels_new],
links=df['link']))
# hover over information
hover = HoverTool(
tooltips=[
("Id", "@ids{safe}"),
("Title", "@titles{safe}"),
("Published", "@published_times{safe}"),
# ("Text", "@texts{safe}"),
("Link", "@links")
],
point_policy="follow_mouse")
# map colors
mapper = linear_cmap(field_name='desc',
palette=Category20[20],
low=min(y_labels),
high=max(y_labels))
# prepare the figure
plot = figure(plot_width=1200,
plot_height=850,
tools=[
hover, 'pan', 'wheel_zoom', 'box_zoom', 'reset',
'save', 'tap'
],
title="Clustering of the content with UMAP and NMF",
toolbar_location="above")
# plot settings
plot.scatter('x',
'y',
size=5,
source=source,
fill_color=mapper,
line_alpha=0.3,
line_color="black",
legend='labels')
plot.legend.background_fill_alpha = 0.6
# Keywords
text_banner = Paragraph(
text='Keywords: Slide to specific cluster to see the keywords.',
height=45)
input_callback_1 = input_callback(plot, source, text_banner, topics,
self.nr_of_topics)
# currently selected article
div_curr = Div(
text="""Click on a plot to see the link to the article.""",
height=150)
if media_type == 'videos':
callback_selected = CustomJS(args=dict(source=source,
current_selection=div_curr),
code=selected_code_videos())
elif media_type == 'articles':
callback_selected = CustomJS(args=dict(source=source,
current_selection=div_curr),
code=selected_code_articles())
taptool = plot.select(type=TapTool)
taptool.callback = callback_selected
# WIDGETS
slider = Slider(
start=0,
end=self.nr_of_topics,
value=self.nr_of_topics,
step=1,
title="Topic #") #, js_event_callbacks=input_callback_1)
slider.js_on_change("value", input_callback_1)
keyword = TextInput(
title="Search:") #, js_event_callbacks=input_callback_1)
keyword.js_on_change("value", input_callback_1)
# pass call back arguments
input_callback_1.args["text"] = keyword
input_callback_1.args["slider"] = slider
# STYLE
slider.sizing_mode = "stretch_width"
slider.margin = 15
keyword.sizing_mode = "scale_both"
keyword.margin = 15
div_curr.style = {
'color': '#BF0A30',
'font-family': 'Helvetica Neue, Helvetica, Arial, sans-serif;',
'font-size': '1.1em'
}
div_curr.sizing_mode = "scale_both"
div_curr.margin = 20
text_banner.style = {
'color': '#0269A4',
'font-family': 'Helvetica Neue, Helvetica, Arial, sans-serif;',
'font-size': '1.1em'
}
text_banner.sizing_mode = "scale_both"
text_banner.margin = 20
plot.sizing_mode = "scale_both"
plot.margin = 5
r = row(div_curr, text_banner)
r.sizing_mode = "stretch_width"
# LAYOUT OF THE PAGE
l = layout([
[slider, keyword],
[text_banner],
[div_curr],
[plot],
])
l.sizing_mode = "scale_both"
# show
output_file('t-sne_interactive_streamlit.html')
show(l)
return (l)
taptool.callback = callback_selected
# WIDGETS
slider = Slider(start=0, end=20, value=20, step=1, title="Cluster #", callback=input_callback_1)
keyword = TextInput(title="Search:", callback=input_callback_1)
# pass call back arguments
input_callback_1.args["text"] = keyword
input_callback_1.args["slider"] = slider
# STYLE
slider.sizing_mode = "stretch_width"
slider.margin=15
keyword.sizing_mode = "scale_both"
keyword.margin=15
div_curr.style={'color': '#BF0A30', 'font-family': 'Helvetica Neue, Helvetica, Arial, sans-serif;', 'font-size': '1.1em'}
div_curr.sizing_mode = "scale_both"
div_curr.margin = 20
text_banner.style={'color': '#0269A4', 'font-family': 'Helvetica Neue, Helvetica, Arial, sans-serif;', 'font-size': '1.1em'}
text_banner.sizing_mode = "scale_both"
text_banner.margin = 20
plot.sizing_mode = "scale_both"
plot.margin = 5
r = row(div_curr,text_banner)
r.sizing_mode = "stretch_width"
