WiV d dl Zd dlmZmZ d dlmZ d dlm Z ddej de dee dz de dee e
f d e
d
e d e d ej fd
Zy) N)ListUnion) normalizetopics_per_class 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 }t' j( }t | D ] \ }} |dk( rd }nd
}|j |j | k( ddf }|j* j, d }|j. j, }|r3t1 |j2 j, j5 dd d }n |j2 }|j7 t' j8 |j: ||| |dz d|d|D cg c]
}d| d| c} |j= d |j? d |jA |rdndd| dddd tC d d d d!||tC d"d#d$% tC 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 per class.
Arguments:
topic_model: A fitted BERTopic instance.
topics_per_class: 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 per class, simply run:
```python
topics_per_class = topic_model.topics_per_class(docs, classes)
topic_model.visualize_topics_per_class(topics_per_class)
```
Or if you want to save the resulting figure:
```python
fig = topic_model.visualize_topics_per_class(topics_per_class)
fig.write_html("path/to/file.html")
```
)z#E69F00z#56B4E9z#009E73z#F0E442z#D55E00z#0072B2z#CC79A7N_ r z...( NameT
legendonly texthz Topic z
Words: )yxvisible marker_color hoverinfoname orientation hovertext)showgridzNormalized Frequency FrequencyClassgffffff?g?centertop Black)sizecolor)r r r xanchoryanchorfont simple_whitewhite Rockwell)bgcolor font_size font_familyz Global Topic Representation)r ) xaxis_title yaxis_titler templater r
hoverlabellegend)"get_topic_freqlocTopiclistsortedto_list
isinstancestrtopic_aspects_joinlen enumerate
topic_labels_keyscustom_labels_items _outliersmapisingoFigurer valuesWordsr r% reshape add_traceBarr& update_xaxes update_yaxes
update_layoutdict) topic_modelr r r r r
r r r
colorsfreq_dfselected_topicstopic topic_nameslabelslabelindexkeyr valuedatafigr
trace_data
topic_namewordsr words o/home/sietch6/trending-topics-pipeline/venv/lib/python3.12/site-packages/bertopic/plotting/_topics_per_class.pyvisualize_topics_per_classrl 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 PD
))+C!/2
u A:G"GXXdjjE 11 45
__++A.
'' *..55==aDEaHA$$A
FF "" #EAI . PUVYug_TFCV
4 d#d#.A*{ g b0
2:N2
& JA t B^am
: Ws< #(O O
) O5 O
O O 'O#O!7O' O
)
NFFzTopics per Classi i )pandaspdtypingr r plotly.graph_objects
graph_objectsrO sklearn.preprocessingr DataFrameintboolrC rP rl rk ry s ! + # %&+*EllE E
I E
E s#
E E E
E YYErx