def createDocument(self, source, docid = None, dictionary = None):
"""
source - either text as string or filename (if sourceType=='file')
docid - document id or filename
"""
if self.sourceType == 'file':
if docid == None:
docid = source
## docid = os.path.basename(source)
source = utils_dml.readfile(source)
## logging.debug("creating document %s" % str(docid))
result = Document(docid)
if self.keepTexts:
result.setText(source)
if self.keepTokens or self.keepPositions or dictionary != None:
if self.keepPositions:
tokens, pos = self.tokenizer.tokenize(source, returnPositions = self.keepPositions)
else:
tokens = self.tokenizer.tokenize(source, returnPositions = self.keepPositions)
if self.keepTokens:
result.setTokens(tokens)
if self.keepPositions:
result.setTokenPositions(pos)
if dictionary != None:
newwords = {}
result.setTokenIds(utils_dml.text2vect(tokens, dictionary, newwords))
## print 'for %s added %i (new length = %i) ' % (docid, len(newwords), len(dictionary))
return result
def createDocument(self, source, docid=None, dictionary=None):
"""
source - either text as string or filename (if sourceType=='file')
docid - document id or filename
"""
if self.sourceType == 'file':
if docid == None:
docid = source
## docid = os.path.basename(source)
source = utils_dml.readfile(source)
## logging.debug("creating document %s" % str(docid))
result = Document(docid)
if self.keepTexts:
result.setText(source)
if self.keepTokens or self.keepPositions or dictionary != None:
if self.keepPositions:
tokens, pos = self.tokenizer.tokenize(
source, returnPositions=self.keepPositions)
else:
tokens = self.tokenizer.tokenize(
source, returnPositions=self.keepPositions)
if self.keepTokens:
result.setTokens(tokens)
if self.keepPositions:
result.setTokenPositions(pos)
if dictionary != None:
newwords = {}
result.setTokenIds(
utils_dml.text2vect(tokens, dictionary, newwords))
## print 'for %s added %i (new length = %i) ' % (docid, len(newwords), len(dictionary))
return result
def createDictionary(self):
tokens = []
for doc in self.getDocs():
doctokens = doc.getTokens()
if doctokens == None:
logging.error("DocumentCollection.createDictionary called but keepTokens is False for %s" % doc.getId())
return {}
tokens.extend(doctokens)
self.dictionary = utils_dml.text2dict(tokens)
for doc in self.getDocs():
doc.setTokenIds(utils_dml.text2vect(doc.getTokens(), self.dictionary))
def createDictionary(self):
tokens = []
for doc in self.getDocs():
doctokens = doc.getTokens()
if doctokens == None:
logging.error(
"DocumentCollection.createDictionary called but keepTokens is False for %s"
% doc.getId())
return {}
tokens.extend(doctokens)
self.dictionary = utils_dml.text2dict(tokens)
for doc in self.getDocs():
doc.setTokenIds(
utils_dml.text2vect(doc.getTokens(), self.dictionary))
coll.removeDocument('m1')
coll.addDocument(df.createDocument(".", "empty_doc"))
coll.addDocument(df.createDocument("minors graph eps trees system computer survey user human time interface response.", "full_doc"))
if not coll.docExists('m1'):
coll.addDocument(df.createDocument(texts['m1'], 'brekeke'))
coll.createDictionary()
for doc in coll.getDocs():
print "dc1: %s (%i):" % (doc.getId(), len(doc.getTokenIds())), doc.getTokenIds()
print coll.getDictionary()
mat = coll.getBOWMatrix()
dfm = coll.getDocFreqMap()
stopList = ['a','and','of','the',':', 'totallyirrelevant'] # fixed stoplist
stopIds = utils_dml.text2vect(stopList, coll.getDictionary())
stopIds.extend(coll.freqRange(dfm, 0, 2)) # extend stopIds with ids that have 0 <= document frequency < 2
print 'stoplist = ', map(utils_dml.reverseMap(coll.getDictionary()).__getitem__, stopIds)
for doc in coll.getDocs():
print "before filter: %s (%i):" % (doc.getId(), len(doc.getTokenIds())), zip(doc.getTokenIds(), doc.getTokens())
coll.filterIds(stopIds) # remove unwanted tokens
for doc in coll.getDocs():
print "after filter, before rebuild: %s (%i):" % (doc.getId(), len(doc.getTokenIds())), zip(doc.getTokenIds(), doc.getTokens())
coll.rebuildDictionary()
for doc in coll.getDocs():
print "after rebuild: %s (%i):" % (doc.getId(), len(doc.getTokenIds())), zip(doc.getTokenIds(), doc.getTokens())
"full_doc"))
if not coll.docExists('m1'):
coll.addDocument(df.createDocument(texts['m1'], 'brekeke'))
coll.createDictionary()
for doc in coll.getDocs():
print "dc1: %s (%i):" % (doc.getId(), len(
doc.getTokenIds())), doc.getTokenIds()
print coll.getDictionary()
mat = coll.getBOWMatrix()
dfm = coll.getDocFreqMap()
stopList = ['a', 'and', 'of', 'the', ':',
'totallyirrelevant'] # fixed stoplist
stopIds = utils_dml.text2vect(stopList, coll.getDictionary())
stopIds.extend(coll.freqRange(
dfm, 0,
2)) # extend stopIds with ids that have 0 <= document frequency < 2
print 'stoplist = ', map(
utils_dml.reverseMap(coll.getDictionary()).__getitem__, stopIds)
for doc in coll.getDocs():
print "before filter: %s (%i):" % (doc.getId(), len(
doc.getTokenIds())), zip(doc.getTokenIds(), doc.getTokens())
coll.filterIds(stopIds) # remove unwanted tokens
for doc in coll.getDocs():
print "after filter, before rebuild: %s (%i):" % (
doc.getId(), len(doc.getTokenIds())), zip(doc.getTokenIds(),