Wi d dl Zd dlmZmZ d dlmZmZ d dlm Z d dl
m Z d dl m
Z d dlmZ ddee dz dedz dedz d ed
eeef d ed ed
edej* fdZy) N)ListUnion)fclusterlinkage)cosine_similarity)select_topic_representationtopics top_n_topics
n_clusters
use_ctfidf
custom_labelstitlewidthheightreturnc t | j | j | d | j d } | j }
|
j
|
j dk7 ddf }
| t | }nL|'t |
j j d| }n#t |
j j }|} |r|t t | k\ r t d t | | } t | d }
t |
|d }|D ci c] }|g }}t! || D ] \ }}|| j# | |j% D cg c] }| }}|D cg c] }|D ] }|
} }}t' j( | D cg c] }|j+ | c} }| | } t | } t- |t. r| D cg c]# }t/ | dgg| j0 | | z % }}|D cg c]' }dj3 |dd D cg c] }|d c} ) }}}|D cg c] }t | d
k r|n|dd d z }}n| j4 ,|r*| D cg c] }| j4 || j z }}n| D cg c]! }t/ | dgg| j7 | # }}|D cg c]' }dj3 |dd D cg c] }|d c} ) }}}|D cg c] }t | d
k r|n|dd d z }}t9 j: | t= d
||d }|j? | ddddt= dd d||t= ddd |j? d |j? d ! |S c c}w c c}w c c}}w c c}w c c}w c c}w c c}}w c c}w c c}w c c}w c c}w c c}}w c c}w )"a Visualize a heatmap of the topic's similarity matrix.
Based on the cosine similarity matrix between topic embeddings (either c-TF-IDF or the embeddings from the embedding
model), a heatmap is created showing the similarity between topics.
Arguments:
topic_model: A fitted BERTopic instance.
topics: A selection of topics to visualize.
top_n_topics: Only select the top n most frequent topics.
n_clusters: Create n clusters and order the similarity
matrix by those clusters.
use_ctfidf: Whether to calculate distances between topics based on c-TF-IDF embeddings. If False, the embeddings
from the embedding model are used.
custom_labels: If bool, whether to use custom topic labels that were defined using
`topic_model.set_topic_labels`.
If `str`, it uses labels from other aspects, e.g., "Aspect1".
title: Title of the plot.
width: The width of the figure.
height: The height of the figure.
Returns:
fig: A plotly figure
Examples:
To visualize the similarity matrix of
topics simply run:
```python
topic_model.visualize_heatmap()
```
Or if you want to save the resulting figure:
```python
fig = topic_model.visualize_heatmap()
fig.write_html("path/to/file.html")
```
r NzKMake sure to set `n_clusters` lower than the total number of unique topics.wardmaxclust)t criterion_ z...zSimilarity Score)colorGnBu)labelsxycolor_continuous_scalegffffff?g?centertop Black)sizer )textr r xanchoryanchorfontwhite Rockwell)bgcolor font_size font_family)r r r
hoverlabelT)
showlegendTrend)legend_title_text) r c_tf_idf_topic_embeddings_ _outliersget_topic_freqlocTopiclistsortedto_listlenset
ValueErrorr r r zipappendvaluesnparrayindex
isinstancestrtopic_aspects_joincustom_labels_ get_topicpximshowdict
update_layout) topic_modelr r
r r r
r r r
embeddingsfreq_df
sorted_topicsdistance_matrixZclustersclustermappingtopicindices
new_labelsr labelfigs f/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/plotting/_heatmap.pyvisualize_heatmapr` s f -[-B-BKDaDacmnopq J
((*Gkk'--2-q01G
f !
--/
>?
--/0 M S[) ) jk k+Jv,>? OV ,AzB /7777B;77 !&( 3 +NE7 G # #E * +*1..*:;w7;;.5K77K%KK
K hh G U+GHGG$J'
3O -%an
X]c%j$
;#=#=m#LU#S S
R\\vchhfRaj AUa AB\
\T^_5s5zBeE#2J4FF_
_ # # /M]jkTYk009N9N1NOk
kWdeeE
D)IK,A,A%,HIe
eQ[\vchhfRaj AUa AB\
\T^_5s5zBeE#2J4FF_
_
)),-
% C g b0
2:N &0 Jc 8 <K H
B\_ke A\_sf
N N$N
N
(N!<N+ N& N+/ N1##N6
&N;:O O O- O &N+ O)NNNFFzSimilarity Matrix ra )numpyrD typingr r scipy.cluster.hierarchyr r sklearn.metrics.pairwiser bertopic._utilsr plotly.expressexpressrM plotly.graph_objects
graph_objectsgointboolrH Figurer` r_ rq s 5 6 7 !
$ # ! &++} I } *} d
}
} s#
} } }
} YY}rp