e0830d7736bb620f926545078bea5620a8b4a19c,src/gensim/utils.py,,isCorpus,#Any#,199
Before Change
**NOTE**: When called on an empty corpus (no documents), will return False.
try:
if hasattr(obj, "next"):
return False // iterators are not allowed to be corpora (need an iterable)
doc1 = iter(obj).next() // obj supports iteration and is not empty
if len(doc1) == 0: // the first document is empty
return True
id1, val1 = iter(doc1).next() // or the first document is a 2-tuple
id1, val1 = int(id1), float(val1) // id must be an integer, weight a float
After Change
result is forcefully defined as `is_corpus=False`.
try:
if hasattr(obj, "next"):
if hasattr(obj, "__iter__"):
logger.warning("corpus-testing objects that are both iterators and iterables is ambiguous; assuming iterator (one-pass).")
// the input is an iterator (not iterable), meaning once we call next()
// that element is gone forever. we must be careful to put whatever we
// retrieve back again
doc1 = obj.next()
obj = itertools.chain([doc1], obj)
else:
doc1 = iter(obj).next()
if not list(doc1):
return True, obj // the first document is empty, assume this is a corpus
id1, val1 = iter(doc1).next()
id1, val1 = int(id1), float(val1) // must be a 2-tuple (integer, float)
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 7
Instances
Project Name: RaRe-Technologies/gensim
Commit Name: e0830d7736bb620f926545078bea5620a8b4a19c
Time: 2010-09-06
Author: piskvorky@92d0401f-a546-4972-9173-107b360ed7e5
File Name: src/gensim/utils.py
Class Name:
Method Name: isCorpus
Project Name: RaRe-Technologies/gensim
Commit Name: f96837d570ed738baa0f47924cfa09f40787cdbe
Time: 2010-09-06
Author: radimrehurek@seznam.cz
File Name: src/gensim/utils.py
Class Name:
Method Name: isCorpus
Project Name: dmlc/gluon-nlp
Commit Name: 03b0e7061cf477fbeccb9c128ee76603df582d86
Time: 2018-09-04
Author: leonard@lausen.nl
File Name: scripts/word_embeddings/evaluate_pretrained.py
Class Name:
Method Name: