marvinscham/masterthesis-playground
1
0
Fork 0
mirror of https://github.com/marvinscham/masterthesis-playground.git synced 2026-03-22 08:22:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

22.02.

Browse Source
This commit is contained in:
Marvin Scham
2026-02-22 23:52:26 +01:00
parent 61edb35f70
commit a7efed86f9
16 changed files with 1994 additions and 6420 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
bertopic/nb_bertopic_lowprep.py
View File

@@ -360,7 +360,6 @@ vis = topic_model.visualize_documents(
custom_labels=True,
hide_annotations=True,
)
# vis.write_html("output/visualization.html")
vis
# %%
@@ -497,7 +496,12 @@ if CALCULATE_TOKEN_DISTRIBUTIONS:
#
# %%
topic_model.visualize_hierarchy(custom_labels=True)
topic_model.visualize_hierarchy(custom_labels=True, color_threshold=0.98)
# %%
hierarchical_topics = topic_model.hierarchical_topics(reviews)
tree = topic_model.get_topic_tree(hier_topics=hierarchical_topics)
print(tree)
# %% [markdown]
# ### Intertopic Distance Map
@@ -512,3 +516,20 @@ topic_model.visualize_topics(use_ctfidf=True)
# %%
topic_model.visualize_barchart(top_n_topics=12, custom_labels=True, n_words=10)
# %%
from wordcloud import WordCloud
import matplotlib.pyplot as plt
def create_wordcloud(model, topic):
text = {word: value for word, value in model.get_topic(topic)}
wc = WordCloud(background_color="white", max_words=1000)
wc.generate_from_frequencies(text)
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.show()
# Show wordcloud
create_wordcloud(topic_model, topic=1)