Created
March 15, 2020 16:44
-
-
Save ikatsov/233d2dbaf5be0b280a3b4a90ae978726 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from gensim.models.doc2vec import TaggedDocument | |
EMBEDDING_DIM = 200 # dimensionality of user representation | |
class TaggedDocumentIterator(object): | |
def __iter__(self): | |
for row in self.df.itertuples(): | |
yield TaggedDocument( | |
words=dict(row._asdict())['all_orders'].split(), | |
tags=[dict(row._asdict())['user_id']]) | |
it = TaggedDocumentIterator(orders_by_uid) | |
doc_model = gensim.models.Doc2Vec(vector_size=EMBEDDING_DIM, | |
window=5, | |
min_count=10, | |
workers=mp.cpu_count(), | |
alpha=0.055, | |
min_alpha=0.055, | |
epochs=120) | |
train_corpus = list(it) | |
doc_model.build_vocab(train_corpus) | |
for epoch in range(10): | |
doc_model.alpha -= 0.005 # decrease the learning rate | |
doc_model.min_alpha = doc_model.alpha | |
doc_model.train(train_corpus, | |
total_examples=doc_model.corpus_count, | |
epochs=doc_model.iter) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment