WiQ 8 d dl Zd dlZd dlmZmZ d dlmZ d dl Z d dl
m Z dddddd dd
d dddi i fd ee dz d
ee dz dej dej deeef dedeedf dededededededede f dZy# e $ r ed G d de
Z Y vw xY w) N)ListUnion)warn)FigurezAData map plotting is unavailable unless datamapplot is installed.c e Zd Zy)r N)__name__
__module__ __qualname__ f/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/plotting/_datamap.pyr r
s r r FzDocuments and Topicsi i docstopics
embeddingsreduced_embeddings
custom_labelstitle sub_titlewidthheight interactive
enable_search topic_prefix datamap_kwdsint_datamap_kwdsreturnc T | j }t j dt j | i }||d< ||d< |.|,| j |j j d }n|}|/ ddlm } |dd d
d j | }|j }n|}t | }t |t r|D cg c]# }t! | dgg| j" | | z % }}|D cg c]' }dj% |dd D cg c] }|d c} ) }}}|D cg c] }t' | dk r|n|dd dz }}n| j( ,|r*|D cg c] }| j( || j* z }}n| rO|D cg c]? }d| ddj% | j- | D cg c] \ }}| c}}dd z A }}}}nG|D cg c]8 }dj% | j- | D cg c] \ }}| c}}dd : }}}}t/ || D ci c] \ } } | |
} } } d| d< | t | } | D ] } | | vsd| | < t j0 | j3 | j4 } |
r t7 j8 || f|| || d|}!|!S t7 j: || f|dz | dz fd||d|
\ }!}"|!S # t t f$ r t d
w xY wc 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 documents and their topics in 2D as a static plot for publication using
DataMapPlot.
Arguments:
topic_model: A fitted BERTopic instance.
docs: The documents you used when calling either `fit` or `fit_transform`.
topics: A selection of topics to visualize.
Not to be confused with the topics that you get from `.fit_transform`.
For example, if you want to visualize only topics 1 through 5:
`topics = [1, 2, 3, 4, 5]`. Documents not in these topics will be shown
as noise points.
embeddings: The embeddings of all documents in `docs`.
reduced_embeddings: The 2D reduced embeddings of all documents in `docs`.
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.
sub_title: Sub-title of the plot.
width: The width of the figure.
height: The height of the figure.
interactive: Whether to create an interactive plot using DataMapPlot's `create_interactive_plot`.
enable_search: Whether to enable search in the interactive plot. Only works if `interactive=True`.
topic_prefix: Prefix to add to the topic number when displaying the topic name.
datamap_kwds: Keyword args be passed on to DataMapPlot's `create_plot` function
if you are not using the interactive version.
See the DataMapPlot documentation for more details.
int_datamap_kwds: Keyword args be passed on to DataMapPlot's `create_interactive_plot` function
if you are using the interactive version.
See the DataMapPlot documentation for more details.
Returns:
figure: A Matplotlib Figure object.
Examples:
To visualize the topics simply run:
```python
topic_model.visualize_document_datamap(docs)
```
Do note that this re-calculates the embeddings and reduces them to 2D.
The advised and preferred pipeline for using this function is as follows:
```python
from sklearn.datasets import fetch_20newsgroups
from sentence_transformers import SentenceTransformer
from bertopic import BERTopic
from umap import UMAP
# Prepare embeddings
docs = fetch_20newsgroups(subset='all', remove=('headers', 'footers', 'quotes'))['data']
sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
embeddings = sentence_model.encode(docs, show_progress_bar=False)
# Train BERTopic
topic_model = BERTopic().fit(docs, embeddings)
# Reduce dimensionality of embeddings, this step is optional
# reduced_embeddings = UMAP(n_neighbors=10, n_components=2, min_dist=0.0, metric='cosine').fit_transform(embeddings)
# Run the visualization with the original embeddings
topic_model.visualize_document_datamap(docs, embeddings=embeddings)
# Or, if you have reduced the original embeddings already:
topic_model.visualize_document_datamap(docs, reduced_embeddings=reduced_embeddings)
```
Or if you want to save the resulting figure:
```python
fig = topic_model.visualize_document_datamap(docs, reduced_embeddings=reduced_embeddings)
fig.savefig("path/to/file.png", bbox_inches="tight")
```
topicdocNdocument)methodr )UMAP g333333?cosine) n_neighbors n_componentsmin_distmetricz{UMAP is required if the embeddings are not yet reduced in dimensionality. Please install it using `pip install umap-learn`. z...zTopic-z:
Unlabelled)
hover_textr r r d )figsizedpir r ) topics_pd DataFramenparray_extract_embeddingsr to_listumapr" fit
embedding_ ImportErrorModuleNotFoundErrorset
isinstancestrtopic_aspects_joinlencustom_labels_ _outliers get_topiczipSeriesmapvalues datamapplotcreate_interactive_plot create_plot)# topic_modelr r r r r r r r r r r r r r
topic_per_docdfembeddings_to_reducer"
umap_model
embeddings_2d
unique_topicsr nameslabelslabelwordvalue topic_num
topic_nametopic_name_mappingselected_topicsnamed_topic_per_docfigure_s# r
visualize_document_datamaprd s z ''M w 78 9BBuI BwK 0 8 * > >rvv~~?OXb > c ) ! ! "1tT\]aabvwJ & 1 1M +
&M -%fst]b3u:t$% (B(B=(QRW(XXttLQR&<58<=RROTUe#e*r/uSbzE/AAUU # # /MXefu++EK4I4I,IJff + r"SXX{G\G\]bGc.d et.degfg.h%iiE
huuu^cSXX{7L7LU7S T et TUWVW XYuEuMPQ^`eMfg4IIz)Z/gg )r f++ =I/0<"9- =
))M2667IJQQ 44
'
( M ++
S[&3,/
Mw 01 % N
u<RUf /e
Uugsl 6-K (K04K: K5 K:' L #L )L2 L
>L$L < L
L (
L$K-5K:
LL )numpyr8 pandasr6 typingr r warningsr rN matplotlib.figurer r? objectrC intndarraybooldictrd r r r
ro sC
( " # !%)&+'"& k
s)d
k
I k
k
k s#
k k S$Y k k
k k k k k k !k
LM
s
A> >BB