Updating DNA2Vec to work with Python 3.7, and to work on Windows 10.

.gitignore

@@ -1,5 +1,6 @@
 inputs/hg38/
 results/
+tmp/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
@@ -90,3 +91,7 @@ ENV/
 
 # Rope project settings
 .ropeproject
+
+test.py
+
+data/

attic_util/util.py

@@ -1,11 +1,18 @@
 import random
 import string
-import resource
 import logbook
 import arrow
 import numpy as np
 import os
 
+importedResource = False
+
+try:
+    import resource
+    importedResource = True
+except ImportError:
+    pass
+
 def split_Xy(df, y_colname='label'):
     X = df.drop([y_colname], axis=1)
     y = df[y_colname]
@@ -26,7 +33,10 @@ def random_str(N):
     return ''.join(random.SystemRandom().choice(string.ascii_lowercase + string.ascii_uppercase + string.digits) for _ in range(N))
 
 def memory_usage():
-    return resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1E6
+    if(importedResource):
+        return resource.getrusage(resource.RUSAGE_SELF).ru_maxrss / 1E6
+    else:
+        return 0
 
 def estimate_bytes(filenames):
     return sum([os.stat(f).st_size for f in filenames])

dna2vec/multi_k_model.py

@@ -4,17 +4,19 @@
 import tempfile
 import numpy as np
 
-from gensim.models import word2vec
+# from gensim.models import word2vec
 from gensim import matutils
 
+import gensim
+
 class SingleKModel:
     def __init__(self, model):
         self.model = model
         self.vocab_lst = sorted(model.vocab.keys())
 
 class MultiKModel:
     def __init__(self, filepath):
-        self.aggregate = word2vec.Word2Vec.load_word2vec_format(filepath, binary=False)
+        self.aggregate = gensim.models.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()]
@@ -25,6 +27,7 @@ def __init__(self, filepath):
         self.data = {}
         for k in range(self.k_low, self.k_high + 1):
             self.data[k] = self.separate_out_model(k)
+        print(len(self.data))
 
     def model(self, k_len):
         """
@@ -50,10 +53,11 @@ def separate_out_model(self, k_len):
             self.logger.warn('Missing {}-mers: {} / {}'.format(k_len, len(vocabs), 4 ** k_len))
 
         header_str = '{} {}'.format(len(vocabs), self.vec_dim)
-        with tempfile.NamedTemporaryFile(mode='w') as fptr:
+        with tempfile.NamedTemporaryFile(mode='w', delete=False) as fptr:
             print(header_str, file=fptr)
             for vocab in vocabs:
                 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))
+            open(fptr.name, "rb")
+            return SingleKModel(gensim.models.KeyedVectors.load_word2vec_format(fptr.name, binary=False))

requirements.txt

@@ -1,20 +1,18 @@
-arrow==0.8.0
-biopython==1.68
-boto==2.46.1
+arrow==0.15.6
+biopython==1.76
 bz2file==0.98
-ConfigArgParse==0.11.0
-gensim==0.13.2
-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
-six==1.10.0
-smart-open==1.5.1
-tox==2.7.0
-tox-pyenv==1.0.3
-virtualenv==15.1.0
+ConfigArgParse==1.2.3
+gensim==3.8.3
+Logbook==1.5.3
+numpy==1.18.1
+pep8==1.7.1
+pluggy==0.13.1
+py==1.8.1
+pytest==5.4.2
+python-dateutil==2.8.1
+requests==2.23.0
+six==1.14.0
+smart-open==2.0.0
+tox==3.15.0
+tox-pyenv==1.1.0
+virtualenv==20.0.20

scripts/train_dna2vec.py

@@ -132,7 +132,7 @@ def main():
             args.kmer_fragmenter))
 
     out_txt_filename = '{}.txt'.format(out_fileroot)
-    with open(out_txt_filename, 'w') as summary_fptr:
+    with open(out_txt_filename, 'w+') as summary_fptr:
         with Tee(summary_fptr):
             logbook.StreamHandler(sys.stdout, level=log_level).push_application()
             redirect_logging()