def STOPWORDS(self):
result = self._stopwords
if result is None:
result = loadDataset('stopwords')
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._stopwords = result
return result
def ABSTRACTS(self):
result = self._abstracts
if result is None:
result = sliceDict(loadDataset('abstracts'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._abstracts = result
return result
def KEYWORDS(self):
result = self._keywords
if result is None:
result = sliceDict(loadDataset('keywords'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._keywords = result
return result
def CITATIONS(self):
result = self._citations
if result is None:
result = sliceDict(loadDataset('citations'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._citations = result
return result
def STOPWORDS(self):
result = self._stopwords
if result is None:
result = loadDataset('stopwords')
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._stopwords = result
return result
def KEYWORDS(self):
result = self._keywords
if result is None:
result = sliceDict(loadDataset('keywords'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._keywords = result
return result
def ABSTRACTS(self):
result = self._abstracts
if result is None:
result = sliceDict(loadDataset('abstracts'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._abstracts = result
return result
def IDS(self):
result = self._ids
if result is None:
result = [pmid for pmid in loadDataset('ids') if str(pmid).startswith(config.SUBSET)]
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._ids = result
return result
def CITATIONS(self):
result = self._citations
if result is None:
result = sliceDict(loadDataset('citations'), config.SUBSET)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._citations = result
return result
def IDS(self):
result = self._ids
if result is None:
result = [
pmid for pmid in loadDataset('ids')
if str(pmid).startswith(config.SUBSET)
]
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._ids = result
return result
def SUMMARIES(self):
result = self._summaries
if result is None:
result = sliceDict(loadDataset('summaries'), config.SUBSET)
paper = namedtuple('paper', ['title', 'authors', 'year', 'doi'])
for (pmid, paper_info) in result.iteritems():
result[pmid] = paper(*paper_info)
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._summaries = result
return result
def SUMMARIES(self):
result = self._summaries
if result is None:
result = sliceDict(loadDataset('summaries'), config.SUBSET)
paper = namedtuple('paper', ['title', 'authors', 'year', 'doi'])
for (pmid, paper_info) in result.iteritems():
result[pmid] = paper( *paper_info )
if config.CACHEUNPROCESSEDINRAM and config.CACHE:
self._summaries = result
return result