search

fulifeng / Temporal_Relational_Stock_Ranking

Code for paper "Temporal Relational Ranking for Stock Prediction"
https://arxiv.org/pdf/1809.09441.pdf
GNU Affero General Public License v3.0
438 stars 164 forks source link

Creation of sequential embeddings #8

Open cchapin0927 opened 4 years ago

cchapin0927 commented 4 years ago

I am trying to repeat the experiment but using a different dataset. I was able to prepare the data in the preprocessing files, but I am having trouble creating sequential embeddings from rank_lstm.py to use in relation_rank_lstm.py. How did you save the hidden state of the LSTM in the correct format?

fulifeng commented 4 years ago

According to the released sequential embeddings and the default parameters, it should be easy to figure out the correct dimensions.

PeterNjeim commented 3 years ago

I'm lost as to how I can generate the sequential embeddings. Can anyone of you guide me or give some general tips as to how to accomplish this?

Like the OP, I've successfully preprocessed my data by modifying the eod.py file, but after that, I just don't know how to generate the sequential embedding files.