Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Eliminate obsolete step parameter from doc2vec infer_vector and similarity_unseen_docs #3176

Merged
merged 3 commits into from
Jun 29, 2021
Merged

Eliminate obsolete step parameter from doc2vec infer_vector and similarity_unseen_docs #3176

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
84b7b18
Fix: eliminate step params
rock420 Jun 18, 2021
c0668fd
Fix: typo in doc2vec.infer_vector() documentation
rock420 Jun 18, 2021
2157afa
Update CHANGELOG.md
mpenkov Jun 29, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions gensim/models/doc2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -581,13 +581,13 @@ def estimated_lookup_memory(self):
"""
return 60 * len(self.dv) + 140 * len(self.dv)

def infer_vector(self, doc_words, alpha=None, min_alpha=None, epochs=None, steps=None):
def infer_vector(self, doc_words, alpha=None, min_alpha=None, epochs=None):
"""Infer a vector for given post-bulk training document.

Notes
-----
Subsequent calls to this function may infer different representations for the same document.
For a more stable representation, increase the number of steps to assert a stricket convergence.
For a more stable representation, increase the number of epochs to assert a stricter convergence.

Parameters
----------
Expand Down Expand Up @@ -1047,7 +1047,7 @@ def scan_vocab(self, corpus_iterable=None, corpus_file=None, progress_per=10000,

return total_words, corpus_count

def similarity_unseen_docs(self, doc_words1, doc_words2, alpha=None, min_alpha=None, steps=None):
def similarity_unseen_docs(self, doc_words1, doc_words2, alpha=None, min_alpha=None, epochs=None):
"""Compute cosine similarity between two post-bulk out of training documents.

Parameters
Expand All @@ -1062,7 +1062,7 @@ def similarity_unseen_docs(self, doc_words1, doc_words2, alpha=None, min_alpha=N
The initial learning rate.
min_alpha : float, optional
Learning rate will linearly drop to `min_alpha` as training progresses.
steps : int, optional
epochs : int, optional
Number of epoch to train the new document.

Returns
Expand All @@ -1071,8 +1071,8 @@ def similarity_unseen_docs(self, doc_words1, doc_words2, alpha=None, min_alpha=N
The cosine similarity between `doc_words1` and `doc_words2`.

"""
d1 = self.infer_vector(doc_words=doc_words1, alpha=alpha, min_alpha=min_alpha, steps=steps)
d2 = self.infer_vector(doc_words=doc_words2, alpha=alpha, min_alpha=min_alpha, steps=steps)
d1 = self.infer_vector(doc_words=doc_words1, alpha=alpha, min_alpha=min_alpha, epochs=epochs)
d2 = self.infer_vector(doc_words=doc_words2, alpha=alpha, min_alpha=min_alpha, epochs=epochs)
return np.dot(matutils.unitvec(d1), matutils.unitvec(d2))


Expand Down
4 changes: 2 additions & 2 deletions gensim/test/test_doc2vec.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -718,8 +718,8 @@ def __str__(self):
def epochs(self):
return self.models[0].epochs

def infer_vector(self, document, alpha=None, min_alpha=None, epochs=None, steps=None):
return np.concatenate([model.infer_vector(document, alpha, min_alpha, epochs, steps) for model in self.models])
def infer_vector(self, document, alpha=None, min_alpha=None, epochs=None):
return np.concatenate([model.infer_vector(document, alpha, min_alpha, epochs) for model in self.models])

def train(self, *ignore_args, **ignore_kwargs):
pass # train subcomponents individually
Expand Down