opener-kaf-naf-parser 1.0.1 → 1.0.2

data/core/site-packages/pre_build/VUA_pylib/io_utils/feature_file.py

@@ -1,121 +0,0 @@
-from operator import itemgetter
-import sys
-import cPickle
-
-
-
-class Cexample:
-    def __init__(self,str_line=None):
-        self.label = ''
-        self.features = []
-        if str_line is not None:
-            self.load_from_line(str_line)
-        
-    def load_from_line(self,str_line):
-        fields = str_line.strip().split('\t')
-        self.label = fields[0]
-        for feat in fields[1:]:
-            first_equal = feat.find('=')
-            if first_equal != -1:
-                name = feat[:first_equal]
-                value = feat[first_equal+1:]
-                self.features.append((name,value))
-
-    def __str__(self):
-        s  = 'Label: '+self.label+'\n'
-        s += 'Feats: '+str(self.features) 
-        return s
-    
-    def get_label(self):
-        return self.label
-    
-    def get_features(self):
-        for name,value in self.features:
-            yield name,value
-            
-    def get_all_features(self):
-        return self.features
-    
-    
-class Cfeature_index:
-    def __init__(self):
-        self.idx = {}
-    
-    def get_number_feat(self,feat):
-        return self.idx.get(feat,None)
-    
-    def add_feat(self,feat):
-        num_feat = len(self.idx)+1
-        self.idx[feat] = num_feat
-        return num_feat
-        
-        
-    def compose_feat(self,name,value):
-        return name+'###'+value
-    
-    
-    def __encode_features(self,feats,modify_index=True):
-        feats_for_example = {}
-        clean_feats = ''
-        for name, value in feats:
-            my_feat = self.compose_feat(name, value)
-            clean_feats+=my_feat+' '
-            num_feat = self.get_number_feat(my_feat)
-            if num_feat is None:
-                if modify_index:
-                    num_feat = self.add_feat(my_feat)
-            
-            if num_feat is not None:
-                if num_feat in feats_for_example:
-                    feats_for_example[num_feat] += 1
-                else:
-                    feats_for_example[num_feat] = 1
-        return sorted(feats_for_example.items(),key=itemgetter(0)),clean_feats
-         
-            
-    def encode_feature_file_to_svm(self,feat_file_obj,out_fic=sys.stdout):
-        for example in feat_file_obj:
-            class_label = example.get_label()
-            out_fic.write(class_label)
-            feats_for_example, clean_feats =self.__encode_features(example.get_all_features())
-                                                                   
-            for feat,freq_feat in feats_for_example:
-                value = freq_feat
-                out_fic.write(' %d:%d' % (feat,value))
-            out_fic.write(' #'+clean_feats+'\n')
-            
-    def encode_example_for_classification(self, feats,out_fic,my_class='0'):
-        feats_for_example, clean_feats =self.__encode_features(feats,modify_index=False)
-        out_fic.write(my_class)
-        for feat,freq_feat in feats_for_example:
-                value = freq_feat
-                out_fic.write(' %d:%d' % (feat,value))
-        out_fic.write(' #'+clean_feats.encode('utf-8')+'\n')        
-    
-    def save_to_file(self,filename):
-        fic = open(filename,'wb')
-        cPickle.dump(self.idx, fic, protocol=0)
-        fic.close()
-        
-    def load_from_file(self,filename):
-        fic = open(filename,'rb')
-        self.idx = cPickle.load(fic)
-        fic.close()
-
-                
-    
-class Cfeature_file:
-    def __init__(self,filename=None):
-        self.filename = filename
-
-    def __iter__(self):
-        if self.filename is not None:
-            fic = open(self.filename,'r')
-            for line in fic:
-                if line[0] != '#':
-                    yield Cexample(line)
-            fic.close()
-    
-   
-              
-            

data/core/site-packages/pre_build/VUA_pylib/lexicon/__init__.py

@@ -1 +0,0 @@
-from lexicon import *

data/core/site-packages/pre_build/VUA_pylib/lexicon/lexicon.py

@@ -1,72 +0,0 @@
-#!/usr/bin/env python
-
-import os
-import re
-from VUA_pylib.common import normalize_pos
-
-__this_folder__ = os.path.dirname(os.path.realpath(__file__))
-
-class MPQA_subjectivity_lexicon:
-    def __init__(self):
-        self.__filename=os.path.join(__this_folder__,'data','subjclueslen1-HLTEMNLP05.tff')
-        self.stemmed = {}
-        self.stemmed_anypos = {}
-        self.no_stemmed = {}
-        self.no_stemmed_anypos = {}
-
-        self.__load()
-        
-    def __load(self):
-        # Format of lines: 
-        # type=weaksubj len=1 word1=abandoned pos1=adj stemmed1=n priorpolarity=negative
-        fic = open(self.__filename)
-        for line in fic:
-            line=line.strip()+' '
-            this_type = re.findall('type=([^ ]+)', line)[0]
-            word = re.findall('word1=([^ ]+)', line)[0]
-            pos = re.findall('pos1=([^ ]+)', line)[0]
-            stemmed = re.findall('stemmed1=([^ ]+)', line)[0]
-            prior_polarity = re.findall('priorpolarity=([^ ]+)', line)[0]
-            pos = normalize_pos(pos)
-            if stemmed == 'y':
-                self.stemmed[(word,pos)] = (this_type,prior_polarity)
-                if True or pos == '*':  #anypos
-                    self.stemmed_anypos[word] = (this_type,prior_polarity)
-
-            elif stemmed == 'n':  
-                self.no_stemmed[(word,pos)] = (this_type,prior_polarity) 
-                if True or pos == '*':
-                    self.no_stemmed_anypos[word] = (this_type,prior_polarity)
-
-        fic.close()
-        
-    def get_type_and_polarity(self,word,pos=None):
-        res = None
-        if pos is not None:
-            pos = normalize_pos(pos)
-            
-            # Try no stemmed with the given pos
-            res = self.no_stemmed.get((word,pos))
-            
-            # Try stemmed with the given pos
-            if res is None:
-                res = self.stemmed.get((word,pos))
-            
-        # Try no stemmed with any pos    
-        if res is None:
-            res = self.no_stemmed_anypos.get(word)
-
-        # Try stemm with any pos
-        if res is None:
-            res = self.stemmed_anypos.get(word)
-            
-            
-        
-        return res
-            
-            
-if __name__ == '__main__':
-    o = MPQA_subjectivity_lexicon()
-    print o.get_type_and_polarity('abidance','adj')
-    
-    

data/core/site-packages/pre_build/VUA_pylib-1.3-py2.7.egg-info/PKG-INFO

@@ -1,10 +0,0 @@
-Metadata-Version: 1.0
-Name: VUA-pylib
-Version: 1.3
-Summary: Various KAF / NAF python helpers
-Home-page: https://github.com/cltl/VUA_pylib
-Author: Ruben Izquierdo
-Author-email: r.izquierdobevia@vu.nl
-License: UNKNOWN
-Description: UNKNOWN
-Platform: UNKNOWN

data/core/site-packages/pre_build/VUA_pylib-1.3-py2.7.egg-info/SOURCES.txt

@@ -1,14 +0,0 @@
-README
-VUA_pylib/__init__.py
-VUA_pylib.egg-info/PKG-INFO
-VUA_pylib.egg-info/SOURCES.txt
-VUA_pylib.egg-info/dependency_links.txt
-VUA_pylib.egg-info/top_level.txt
-VUA_pylib/common/__init__.py
-VUA_pylib/common/common.py
-VUA_pylib/corpus_reader/__init__.py
-VUA_pylib/corpus_reader/google_web_nl.py
-VUA_pylib/io_utils/__init__.py
-VUA_pylib/io_utils/feature_file.py
-VUA_pylib/lexicon/__init__.py
-VUA_pylib/lexicon/lexicon.py

data/core/site-packages/pre_build/VUA_pylib-1.3-py2.7.egg-info/dependency_links.txt

@@ -1 +0,0 @@
-

data/core/site-packages/pre_build/VUA_pylib-1.3-py2.7.egg-info/installed-files.txt

@@ -1,23 +0,0 @@
-../VUA_pylib/__init__.py
-../VUA_pylib/lexicon/lexicon.py
-../VUA_pylib/lexicon/__init__.py
-../VUA_pylib/common/common.py
-../VUA_pylib/common/__init__.py
-../VUA_pylib/io_utils/feature_file.py
-../VUA_pylib/io_utils/__init__.py
-../VUA_pylib/corpus_reader/google_web_nl.py
-../VUA_pylib/corpus_reader/__init__.py
-../VUA_pylib/__init__.pyc
-../VUA_pylib/lexicon/lexicon.pyc
-../VUA_pylib/lexicon/__init__.pyc
-../VUA_pylib/common/common.pyc
-../VUA_pylib/common/__init__.pyc
-../VUA_pylib/io_utils/feature_file.pyc
-../VUA_pylib/io_utils/__init__.pyc
-../VUA_pylib/corpus_reader/google_web_nl.pyc
-../VUA_pylib/corpus_reader/__init__.pyc
-./
-SOURCES.txt
-dependency_links.txt
-top_level.txt
-PKG-INFO

data/core/site-packages/pre_build/VUA_pylib-1.3-py2.7.egg-info/top_level.txt

@@ -1 +0,0 @@
-VUA_pylib

data/core/site-packages/pre_build/VUKafParserPy/KafDataObjectsMod.py

@@ -1,165 +0,0 @@
-class KafTermSentiment:
-  def __init__(self):
-    self.resource=None
-    self.polarity=None
-    self.strength=None
-    self.subjectivity=None
-    
-  def simpleInit(self,r,p,st,su,sm=None):
-    self.resource=r
-    self.polarity=p
-    self.strength=st
-    self.subjectivity=su
-    self.sentiment_modifier = sm
-    
-  def getPolarity(self):
-    return self.polarity
-  
-  def getSentimentModifier(self):
-    return self.sentiment_modifier
-    
-    
-class KafToken:
-  def __init__(self,wid, value, sent=None, para=None):
-    self.token_id = wid
-    self.value = value
-    self.sent = sent
-    self.para = para
-  
-
-class KafOpinionExpression:
-  def __init__(self,polarity,strength,targets):
-    self.polarity = polarity
-    self.strength = strength
-    self.targets = targets
-    
-  def __str__(self):
-    return 'Op_exp==> pol:'+self.polarity+' Str:'+self.strength+' ids:'+'-'.join(self.targets)
-    
-class KafOpinion:
-  def __init__(self,id,holders, targets, opi_exp):
-    self.id = id
-    self.holders = holders
-    self.targets = targets
-    self.opi_exp = opi_exp
-    
-  def __str__(self):
-    c='Opinion id'+self.id+'\n'
-    c+='  Holders: '+'-'.join(self.holders)+'\n'
-    c+='  Targets: '+'-'.join(self.targets)+'\n'
-    c+=str(self.opi_exp)
-    return c
-    
-    
-
-class KafSingleProperty:
-  def __init__(self,id,type,targets):
-    self.id = id
-    self.type = type
-    self.targets = targets
-    
-    
-  def get_id(self):
-    return self.id
-    
-  def get_type(self):
-    return self.type
-  
-  def get_span(self):
-    return self.targets
-  
-  def __str__(self):
-    return 'Id: '+self.id+' Type: '+self.type+' ids:'+' '.join(self.targets)
-
-
-class KafSingleEntity:
-  def __init__(self,id,type,targets):
-    self.id = id
-    self.type = type
-    self.targets = targets
-    
-  def get_id(self):
-    return self.id
-    
-  def get_type(self):
-    return self.type
-  
-  def get_span(self):
-    return self.targets
-  
-  def __str__(self):
-    return 'Id: '+self.id+' Type: '+self.type+' ids:'+' '.join(self.targets)
-
-class KafTerm:
-  def __init__(self):
-    self.tid = None
-    self.lemma = None
-    self.pos = None
-    self.morphofeat = None
-    self.sentiment = None
-    self.list_span_id = []
-    
-  def get_morphofeat(self):
-    return self.morphofeat
-    
-  def set_list_span_id(self, L):
-    self.list_span_id = L
-    
-  def get_list_span(self):
-    return self.list_span_id
-    
-  def get_polarity(self):
-    if self.sentiment != None:
-      return self.sentiment.getPolarity()
-    else:
-      return None
-      
-  def get_sentiment_modifier(self):
-    if self.sentiment != None:
-      return self.sentiment.getSentimentModifier()
-    else:
-      return None
-    
-    
-  def setSentiment(self,my_sent):
-    self.sentiment = my_sent
-    
-  def getSentiment(self):
-    return self.sentiment
-    
-  def getLemma(self): 
-      return self.lemma
-    
-  def setLemma(self,lemma):
-      self.lemma = lemma
-    
-  def getPos(self):
-      return self.pos
-    
-  def setPos(self,pos):
-      self.pos = pos
-      
-  def getId(self):
-      return self.tid
-      
-  def setId(self,id):
-      self.tid = id
-
-  def getShortPos(self):
-    if self.pos==None:
-      return None
-    auxpos=self.pos.lower()[0]
-    if auxpos == 'g': auxpos='a'
-    elif auxpos == 'a': auxpos='r'
-    return auxpos
-    
-  def __str__(self):
-    if self.tid and self.lemma and self.pos:
-        return self.tid+'\n\t'+self.lemma.encode('utf-8')+'\n\t'+self.pos
-    else:
-        return 'None'
-      
-    
-    
-    
-