5
3

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

gensimのPoincare Embeddingを試す

Posted at

サンプル動かすだけなのでたいしたことやってないけど、可視化でつまづいたのでメモ。

gensimのPoincare Embeddingのページ。
https://radimrehurek.com/gensim/models/poincare.html

可視化までやるならplotlyがあった方がいい。
ただし、plotlyが3.0.0以上のバージョンだとエラーが出るのでバージョン指定してインストールする必要がある

setup

gensim は既にインストール済み

pip install plotly==2.7.0

training

可視化する場合は可視化用のpoincare_2d_visualizationがsize=2にしか対応していないので、PoincareModelを実行する際にsize=2を指定する。

from gensim.models.poincare import PoincareModel, PoincareRelations
from gensim.test.utils import datapath

# Read the sample relations file and train the model
relations = PoincareRelations(file_path=datapath('poincare_hypernyms_large.tsv'))
model = PoincareModel(train_data=relations, size=2)
model.train(epochs=50)

visualization

import plotly
import gensim.viz.poincare

plotly.offline.init_notebook_mode(connected=False)
prefecutre_map = gensim.viz.poincare.poincare_2d_visualization(model=model,
                                                               tree=relations,
                                                               figure_title="tutorial",
                                                               show_node_labels=model.kv.vocab.keys())
plotly.offline.iplot(prefecutre_map)

可視化の結果
拡大とかもできるので、ごちゃごちゃしてるけど割とどうにかなる。
image.png

plotlyを3.0.0以上でインストールしていると、以下の様なエラーが出る

ValueError: 
    Invalid value of type 'builtins.str' received for the 'textposition' property of scatter
        Received value: 'bottom'

    The 'textposition' property is an enumeration that may be specified as:
      - One of the following enumeration values:
            ['top left', 'top center', 'top right', 'middle left',
            'middle center', 'middle right', 'bottom left', 'bottom
            center', 'bottom right']
      - A tuple, list, or one-dimensional numpy array of the above
5
3
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
5
3

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?