def __init__(self, root, fileids='.*'):
"""
Corpus reader designed to work with National Corpus of Polish.
See http://nkjp.pl/ for more details about NKJP.
use example:
import nltk
import nkjp
from nkjp import NKJPCorpusReader
x = NKJPCorpusReader(root='/home/USER/nltk_data/corpora/nkjp/', fileids='') # obtain the whole corpus
x.header()
x.raw()
x.words()
x.tagged_words(tags=['subst', 'comp']) #Link to find more tags: nkjp.pl/poliqarp/help/ense2.html
x.sents()
x = NKJPCorpusReader(root='/home/USER/nltk_data/corpora/nkjp/', fileids='Wilk*') # obtain particular file(s)
x.header(fileids=['WilkDom', '/home/USER/nltk_data/corpora/nkjp/WilkWilczy'])
x.tagged_words(fileids=['WilkDom', '/home/USER/nltk_data/corpora/nkjp/WilkWilczy'], tags=['subst', 'comp'])
"""
if isinstance(fileids, string_types):
XMLCorpusReader.__init__(self, root, fileids + '.*/header.xml')
else:
XMLCorpusReader.__init__(
self, root, [fileid + '/header.xml' for fileid in fileids]
)
self._paths = self.get_paths()
def feature_apply(feature_extractor, feature_vector, attribute, number_of_file):
"""
Extract features from each document
:param feature_extractor: function that extract features
:param feature_vector: contains a list of features
:param attribute: indicate if the process for gender or age feature extraction
:param number_of_file: number of document to be processed
:return:vector that contain the extracted features
"""
corpus_root = '/root/Downloads/TextMining/pan13-author-profiling-training-corpus-2013-01-09/en'
#corpus_root = '/root/Downloads/TextMining/pan13-author-profiling-training-corpus-2013-01-09/meTets'
newcorpus = XMLCorpusReader(corpus_root, '.*')
i=0
feature_set = []
doc_list = newcorpus.fileids()
print len(doc_list)
for doc in doc_list[:number_of_file]:
i+=1
if i%50==0:
print i
doc = newcorpus.xml(doc)
number_of_conversation=int(doc[0].attrib["count"])
#print(doc[0].attrib["count"])
txt = " ".join([doc[0][j].text for j in range(number_of_conversation) if doc[0][j].text is not None])
#print txt
if textstat.sentence_count(txt) != 0:
feature_set.append((feature_extractor(txt, feature_vector), doc.attrib[attribute]))
return feature_set
def __init__(self, root, fileids='.*'):
"""
Corpus reader designed to work with National Corpus of Polish.
See http://nkjp.pl/ for more details about NKJP.
use example:
import nltk
import nkjp
from nkjp import NKJPCorpusReader
x = NKJPCorpusReader(root='/home/USER/nltk_data/corpora/nkjp/', fileids='') # obtain the whole corpus
x.header()
x.raw()
x.words()
x.tagged_words(tags=['subst', 'comp']) #Link to find more tags: nkjp.pl/poliqarp/help/ense2.html
x.sents()
x = NKJPCorpusReader(root='/home/USER/nltk_data/corpora/nkjp/', fileids='Wilk*') # obtain particular file(s)
x.header(fileids=['WilkDom', '/home/USER/nltk_data/corpora/nkjp/WilkWilczy'])
x.tagged_words(fileids=['WilkDom', '/home/USER/nltk_data/corpora/nkjp/WilkWilczy'], tags=['subst', 'comp'])
"""
if isinstance(fileids, string_types):
XMLCorpusReader.__init__(self, root, fileids + '.*/header.xml')
else:
XMLCorpusReader.__init__(
self, root, [fileid + '/header.xml' for fileid in fileids]
)
self._paths = self.get_paths()
def __init__(self, *args, **kwargs):
if 'textid_file' in kwargs: self._textids = kwargs['textid_file']
else: self._textids = None
XMLCorpusReader.__init__(self, *args)
CategorizedCorpusReader.__init__(self, kwargs)
self._init_textids()
def __init__(self, *args, **kwargs): if 'textid_file' in kwargs: self._textids = kwargs['textid_file'] else: self._textids = None XMLCorpusReader.__init__(self, *args) CategorizedCorpusReader.__init__(self, kwargs) self._init_textids()
def __init__(self, root, fileids, wrap_etree=False):
XMLCorpusReader.__init__(self, root, fileids, wrap_etree)
self._lemma_to_class = defaultdict(list)
"""A dictionary mapping from verb lemma strings to lists of
verbnet class identifiers."""
self._wordnet_to_class = defaultdict(list)
"""A dictionary mapping from wordnet identifier strings to
lists of verbnet class identifiers."""
self._class_to_fileid = {}
"""A dictionary mapping from class identifiers to
corresponding file identifiers. The keys of this dictionary
provide a complete list of all classes and subclasses."""
self._shortid_to_longid = {}
# Initialize the dictionaries. Use the quick (regexp-based)
# method instead of the slow (xml-based) method, because it
# runs 2-30 times faster.
self._quick_index()
def __init__(self, root, fileids, wrap_etree=False):
XMLCorpusReader.__init__(self, root, fileids, wrap_etree)
self._lemma_to_class = defaultdict(list)
"""A dictionary mapping from verb lemma strings to lists of
verbnet class identifiers."""
self._wordnet_to_class = defaultdict(list)
"""A dictionary mapping from wordnet identifier strings to
lists of verbnet class identifiers."""
self._class_to_fileid = {}
"""A dictionary mapping from class identifiers to
corresponding file identifiers. The keys of this dictionary
provide a complete list of all classes and subclasses."""
self._shortid_to_longid = {}
# Initialize the dictionaries. Use the quick (regexp-based)
# method instead of the slow (xml-based) method, because it
# runs 2-30 times faster.
self._quick_index()
def test_set(corpus_dir, feature_extrator, vect_path, i):
"""
Read ,process the test set and extract features for each document
:param corpus_dir:path of the test set
:param feature_extrator: function that extract features
:param vect_path:
:param i:index of class in the true_pred dictionay values; if 0 it refers to the gender else it refers to the age
:return:vector that contain the extracted features
"""
vect = create_feature_vect(vect_path)
newcorpus = XMLCorpusReader(corpus_dir, '.*')
doc_list = newcorpus.fileids()
test_feature_set = []
true_pred = extract_true_pred(corpus_dir[:-2]+"truth-en.txt")
for doc in doc_list:
xml_name = doc
doc = newcorpus.xml(doc)
print(doc[0].attrib["count"])
txt = fetch_text(doc)
if (textstat.sentence_count(txt) != 0) and (txt != ""):
test_feature_set.append((feature_extrator(txt, vect), true_pred[xml_name][i]))
return test_feature_set
def xml(self, fileid=None): return XMLCorpusReader.xml(self, fileid)
def __init__(self, root, fileids='.*'):
XMLCorpusReader.__init__(self, root, fileids)
def __init__(self, root, fileids, lazy=True):
XMLCorpusReader.__init__(self, root, fileids)
self._lazy = lazy
def __init__(self, root, fileids, lazy=True):
XMLCorpusReader.__init__(self, root, fileids)
self._lazy = lazy
def __init__(self, root, fileids, wordnet, lazy=True):
XMLCorpusReader.__init__(self, root, fileids)
self._lazy = lazy
self._wordnet = wordnet
def __init__(self, root, fileids): XMLCorpusReader.__init__(self, root, fileids)
def xml(self, fileids=None, categories=None):
fileids, _ = self._resolve(fileids, categories)
if len(fileids) == 1: return XMLCorpusReader.xml(self, fileids[0])
else: raise TypeError('Expected a single file')
def xml(self, fileids=None, categories=None):
fileids, _ = self._resolve(fileids, categories)
if len(fileids) == 1: return XMLCorpusReader.xml(self, fileids[0])
else: raise TypeError('Expected a single file')
def __init__(self, root, fileid):
self.path = root + fileid
XMLCorpusReader.__init__(self, root, fileid)
def xml(self, fileid=None):
return XMLCorpusReader.xml(self, fileid)
def __init__(self, root, fileid):
XMLCorpusReader.__init__(self, root, fileid)
self._fileid = self._fileids[0]
self.elt = self.xml()
self.data = _xml_to_dict(self.elt)
def raw(self, fileids=None):
return XMLCorpusReader.raw(self, fileids)
def __init__(self, root, fileids, wordnet, lazy=True):
XMLCorpusReader.__init__(self, root, fileids)
self._lazy = lazy
self._wordnet = wordnet
def raw(self, fileids=None): return XMLCorpusReader.raw(self, fileids)
