pscrapy / aligned_word_embeddings

Aligned Word Embeddings

• Free software: GNU General Public License v3
• Documentation: https://aligned-word-embeddings.readthedocs.io.

Installing

• Clone the repository
• virtualenv -p python3.6 env
• source env/bin/activate
• pip install cython
• pip install git+https://github.com/valedica/gensim.git
• cd in repository
• pip install -e .

Note

• Remember: when you call the AlignedWordEmbeddings the script creates a "model/" folder

How To Use

• Train

from aligned_word_embeddings.aligned_word_embeddings import  AlignedWordEmbeddings
from aligned_word_embeddings.spatial.distances import most_similar_from_model
from gensim.models.word2vec import Word2Vec

aligner = AlignedWordEmbeddings(size=30, siter=10, diter=10, workers=4)

aligner.train_compass("/path/to/compass_text", overwrite=False) # keep an eye on the overwrite behaviour

slice_one = aligner.train_slice("/path/to/slice_one.txt", save=True)
slice_two = aligner.train_slice("/path/to/slice_two.txt", save=True)

print(most_similar_from_model("flat", silce_one, slice_two))

slice_one = Word2Vec.load("model/slice_one.model") # model loading with gensim
slice_two = Word2Vec.load("model/slice_one.model")

• Load and Visualize

from aligned_word_embeddings.utils.visualization import visualize_embeddings

model1 = Word2Vec.load("slice_one.model")
model2 = Word2Vec.load("slice_two.model")

import numpy as np
models = [model1, model2]

names = ["slice_one", "slice_two"]

key = "word"

visualize_embeddings(key, models, names, topn=2)

• Moral Embeddings

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.