How to Load the pre-trained word embeddings in .npy files

Question

I'm trying to use the word embeddings pre-trained in HistWords Project by the Stanford NLP team. But when I ran the document example.py from the GitHub website, there was an error: ModuleNotFoundError: No module named 'representations.sequentialembedding'. How can I solve this problem?

I've installed the "representations" module, but it doesn't work. The pre-trained word embeddings are of ".npy" format, is there any Python-based method for uploading them?

Answer 1

To set it up you can do the following in your shell:

cd <path you want to store your project>
git clone https://github.com/williamleif/histwords.git
cd histwords

# ----- Set up Python2.7 -----
## Python2.7 via conda is quite easy
conda create -y -n <env_name> python=2.7
conda activate <env_name>

## Else install/locate a python 2 version
### Check python -V (maybe its python2.7)
### Maybe you have python2 or python2.7 executables
### On linux you could look for ls /usr/bin/python* 
python2 -m venv <env_name>
source <env_name>/bin/activate # if you use linux
bin/Scripts/activate # on Windows

# ---- Now with Python2.7 ----
pip install -r requirements.txt

# ---- Download & Move your embedding from https://nlp.stanford.edu/projects/histwords/
# to embeddings/<category> subfolders

python examples.py
# Outputs the similarities