Skip to content

updated gensim and scipy #22

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

Open
Sergiodiaz53 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

updated gensim and scipy #22

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 dna2vec/multi_k_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,20 +4,20 @@
import tempfile
import numpy as np

from gensim.models import word2vec
from gensim.models import KeyedVectors
from gensim import matutils

class SingleKModel:
def __init__(self, model):
self.model = model
self.vocab_lst = sorted(model.vocab.keys())
self.vocab_lst = sorted(model.index_to_key)

class MultiKModel:
def __init__(self, filepath):
self.aggregate = word2vec.Word2Vec.load_word2vec_format(filepath, binary=False)
self.aggregate = KeyedVectors.load_word2vec_format(filepath, binary=False)
self.logger = logbook.Logger(self.__class__.__name__)

vocab_lens = [len(vocab) for vocab in self.aggregate.vocab.keys()]
vocab_lens = [len(vocab) for vocab in self.aggregate.index_to_key]
self.k_low = min(vocab_lens)
self.k_high = max(vocab_lens)
self.vec_dim = self.aggregate.vector_size
Expand Down Expand Up @@ -45,7 +45,7 @@ def l2_norm(self, vocab):
return np.linalg.norm(self.vector(vocab))

def separate_out_model(self, k_len):
vocabs = [vocab for vocab in self.aggregate.vocab.keys() if len(vocab) == k_len]
vocabs = [vocab for vocab in self.aggregate.index_to_key if len(vocab) == k_len]
if len(vocabs) != 4 ** k_len:
self.logger.warn('Missing {}-mers: {} / {}'.format(k_len, len(vocabs), 4 ** k_len))

Expand All @@ -56,4 +56,4 @@ def separate_out_model(self, k_len):
vec_str = ' '.join("%f" % val for val in self.aggregate[vocab])
print('{} {}'.format(vocab, vec_str), file=fptr)
fptr.flush()
return SingleKModel(word2vec.Word2Vec.load_word2vec_format(fptr.name, binary=False))
return SingleKModel(KeyedVectors.load_word2vec_format(fptr.name, binary=False))
6 changes: 3 additions & 3 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,16 +3,16 @@ biopython==1.68
boto==2.46.1
bz2file==0.98
ConfigArgParse==0.11.0
gensim==0.13.2
gensim==4.1.2
Logbook==1.0.0
numpy==1.16
pep8==1.7.0
pluggy==0.4.0
py==1.4.33
pytest==3.0.7
python-dateutil==2.6.0
requests==2.20.0
scipy==0.19.0
requests==2.20
scipy==1.71
six==1.10.0
smart-open==1.5.1
tox==2.7.0
Expand Down