Wi d dl Zd dlmZmZ d dlmZ d dlm Z ddej de dz dee dz de dee e
f d e
d
e d e d ej fd
Zy) N)ListUnion) normalizetopics_over_time top_n_topicstopicsnormalize_frequency
custom_labelstitlewidthheightreturnc g d} | j }
|
j |
j dk7 ddf }
| t | } nL|'t |
j j d| } n#t |
j j } 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 d z }
}t | j j D ci c] \ }}||
|
}
}}n| j J|rH| j j D ci c]" \ }}|| j || j z $ }
}}nC| j j D ci c] \ }}|t | d
kD r|dd
d z n| }
}}|j j# |
|d < |j |j j% | ddf j' d d
g }t) j* }t |j j- D ] \ }} |j |j | k( ddf }|j. j0 d }|j2 j0 }|r3t5 |j6 j0 j9 dd d }n |j6 }|j; t) j< |j> |d| |dz d||D cg c]
}d| d| c} |jA d |jC d |jE |rdnd| dddd tG d d d d!||tG d"d#d$% tG d&' ( |S c c} w c c}w c c}}w c c}w c c}}w c c}}w c c}}w c c}w ))a Visualize topics over time.
Arguments:
topic_model: A fitted BERTopic instance.
topics_over_time: The topics you would like to be visualized with the
corresponding topic representation
top_n_topics: To visualize the most frequent topics instead of all
topics: Select which topics you would like to be visualized
normalize_frequency: Whether to normalize each topic's frequency individually
custom_labels: If bool, whether to use custom topic labels that were defined using
`topic_model.set_topic_labels`.
If `str`, it uses labels from other aspects, e.g., "Aspect1".
title: Title of the plot.
width: The width of the figure.
height: The height of the figure.
Returns:
A plotly.graph_objects.Figure including all traces
Examples:
To visualize the topics over time, simply run:
```python
topics_over_time = topic_model.topics_over_time(docs, timestamps)
topic_model.visualize_topics_over_time(topics_over_time)
```
Or if you want to save the resulting figure:
```python
fig = topic_model.visualize_topics_over_time(topics_over_time)
fig.write_html("path/to/file.html")
```
)z#E69F00z#56B4E9z#009E73z#F0E442z#D55E00z#0072B2z#CC79A7N_ r z...( NameTopic Timestamp lines textz Topic z
Words: )xymode marker_color hoverinfoname hovertextT)showgridzNormalized Frequency Frequencygffffff?g?centertop Black)sizecolor)r r r xanchoryanchorfont simple_whitewhite Rockwell)bgcolor font_size font_familyz Global Topic Representation)r ) yaxis_titler templater r
hoverlabellegend)$get_topic_freqlocr listsortedto_list
isinstancestrtopic_aspects_joinlen enumerate
topic_labels_keyscustom_labels_items _outliersmapisin sort_valuesgoFigureuniquer valuesWordsr r% reshape add_traceScatterr update_xaxes update_yaxes
update_layoutdict) topic_modelr r r r r
r r r
colorsfreq_dfselected_topicstopic topic_nameslabelslabelindexkeyr valuedatafig
trace_data
topic_namewordsr words o/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/plotting/_topics_over_time.pyvisualize_topics_over_timerk s ^F ((*Gkk'--2-q01G
v, ! !6!6!8 ,!GH !6!6!89 -%lrschUT*+k.H.H .WX].^^s sR]^sxxvbqz Beq BC^ ^U`aEE
RuU3BZ%5GGa aAJ;KdKdKiKiKkAlm:5#sK ..m m # # /MWbWpWpWvWvWx
MSSRSC++C+2G2G,GH H
U`TmTmTsTsTu
FPc5Cs5zBse#E A
0 5 5 9 9+ FV 0 6 6 ; ;O La O P \ \^egr]s tD
))+C!$**"3"3"56
uXXdjjE 11 45
__++A.
'' *..55==aDEaHA$$A
JJ && #EAI . PUVYug_TFCV
* d#d#.A*{ g b0
2:N2
$ Ju t B^am
0 Ws< #(O O') O"5 O' O- O2 'O8#O>P"O')NNFFzTopics over Timei i )pandaspdtypingr r plotly.graph_objects
graph_objectsrM sklearn.preprocessingr DataFrameintboolr@ rN rk rj rw s ! + $ # %&+*ll *
I
s#
YYrv