def get_similar_words(cleaned_query_words, doc):
global expanded_query_terms
try:
command = "/home/sneha/phoenix/galago/galago-3.6-bin/bin/galago doc --index=/phoenix/ir_code/galago-index-rb4/ --id=" + doc + " --text=true --metadata=false --tokenize=true | sed -n '/Term vector:/,/<TEXT>/p'"
outl = subprocess.check_output(command, shell=True)
out = outl.split('\n')
word_array = list()
for i in range(1, len(out) - 2):
words = out[i].split()
if(len(words) > 0):
word_array.append(words[len(words)-1])
q_syn_list = list()
for q in cleaned_query_words:
q_wn = Word(q)
q_syn_list.append(q_wn.get_synsets(NOUN))
for w in word_array:
if w not in cleaned_query_words:
w_wn = Word(w)
w_syn = w_wn.get_synsets(NOUN)
for q_syn in q_syn_list:
max_syn = 0
for i in range(0, min(2, len(q_syn))):
for j in range(0, min(2, len(w_syn))):
syn = q_syn[i].path_similarity(w_syn[j])
max_syn = max(max_syn, syn)
if(max_syn > 0.3):
expanded_query_terms[w] = max_syn
except:
pass
print "Done processing " + doc
def retrieve_synset_list_for_word(word, whole_synset=True, pos_tag=None):
"""Returns the synset list for a word. Possibility to return whole synsets or just names
of synsets. Also possible to limit to specific POS tags"""
blob_word = Word(word)
if whole_synset:
return blob_word.get_synsets(pos_tag)
else:
return [name.name() for name in blob_word.get_synsets(pos_tag)]
def _get_synsets(string, pos=None):
if pos is None:
word = Word(string)
synsets = word.synsets
else:
word = Word(string)
synsets = word.get_synsets(pos)
return synsets
def sentenceToFeatures(self, sentence):
feat = []
for word in sentence:
werd = Word(word)
syns = [w.lemma_names for w in werd.get_synsets()]
for syn in syns:
try:
feat.append(self.word_to_idx[syn])
except KeyError:
continue
return list(set(feat))
def sentenceToFeatures(self, sentence): feat = [] for word in sentence: werd = Word(word) syns = [w.lemma_names for w in werd.get_synsets()] for syn in syns: try: feat.append(self.word_to_idx[syn]) except KeyError: continue return list(set(feat))
def initialize(self, sentences):
self.max_feat_len = 0
self.word_to_idx = {}
idx = self.index_offset
for sentence in sentences:
syn_count = 0
for word in sentence:
werd = Word(word)
syns = [w.lemma_names for w in werd.get_synsets()]
for syn in syns:
syn_count += 1
if syn not in self.word_to_idx:
self.word_to_idx[syn] = idx
idx += 1
self.max_feat_len = max(self.max_feat_len, syn_count)
def initialize(self, sentences):
self.max_feat_len = 0
self.word_to_idx = {}
idx = self.index_offset
for sentence in sentences:
syn_count = 0
for word in sentence:
werd = Word(word)
syns = [w.lemma_names for w in werd.get_synsets()]
for syn in syns:
syn_count += 1
if syn not in self.word_to_idx:
self.word_to_idx[syn] = idx
idx += 1
self.max_feat_len = max(self.max_feat_len, syn_count)
def synonym_finder(word, pos_tag, lch_threshold):
word = Word(word)
for words in word.get_synsets(pos=pos_tag):
print(words)
#!/usr/bin/python
from textblob import Word
from textblob.wordnet import NOUN
word = Word("plant")
print word.get_synsets(NOUN)
print("Usage: "+sys.argv[0]+" sentence target\nTranslates sentence into a (theoretically synonymous) new sentence with the same approximate sentiment as target (which may be a sentiment polarity value or a model sentence).")
sys.exit()
try:
target=float(sys.argv[2])
except:
target=TextBlob(sys.argv[2]).sentiment.polarity
sentence=sys.argv[1]
blob=TextBlob(sentence)
options=[]
optionSyns=[]
for tag in blob.tags:
word=Word(tag[0])
syns=[]
try:
syns=word.get_synsets(tagFormatConvert(tag[1]))
except:
syns=word.get_synsets()
syns_clean=[tag[0]]
singular=True
if(tag[1][0]=="N"):
singular=guessSingular(tag[0])
for syn in syns:
lemmanames=syn.lemma_names()
for name in lemmanames:
if(name.find(".")>=0):
name=name[:name.find(".")]
if(not singular):
name=Word(name).pluralize()
name=name.replace("_", " ")
syns_clean.append(name)
def get_synsets(concept_name):
word = Word(concept_name)
return word.get_synsets()
tag_to_text_dict[line.split()[0]] = " ".join(line.split()[1:])
sentence = input("Enter your sentence : ")
parts_of_speech = nltk.pos_tag(nltk.word_tokenize(sentence))
print("\nThe parts of speech in your sentence are : \n")
for tup in parts_of_speech:
if(tup[0]!='.' and tup[0]!=','):
print(tup[0] + " : " + tag_to_text_dict[tup[1]])
print("\nEnter a word you would like synonyms and antonyms for : ")
word = Word(input())
synonyms = list(set([l.name() for syn in word.get_synsets() for l in syn.lemmas()]))
antonyms = list(set([ant.name() for syn in word.get_synsets() for l in syn.lemmas() for ant in l.antonyms()]))
print(f" Synonyms : "+",".join(synonyms))
print(f" Antonyms : "+",".join(antonyms))
languages = [('ar','Arabic'),('zh-CN','Chinese'),('sk','Slovakian'),('ja','Japanese')]
lang = random.choice(languages)
sentence = TextBlob(input("\nEnter a sentence you'd like to see translated to another language : "))
print("\nYour sentence translated to " + lang[1] + " is : " + str(sentence.translate(to = lang[0])))
print("\nEnter a word you'd like definitions for : ")
word2 = Word(input())
print("\nDefinitions: ")
# In[130]:
bank3 = bank_word.synsets[2]
bank3.lemma_names()
bank1.lemma_names() == bank3.lemma_names()
# In[131]:
bank1 == bank3
# In[132]:
from textblob.wordnet import NOUN
bank_word.get_synsets(NOUN)
# In[133]:
car_word = Word("car")
car_word.get_synsets(NOUN)
# In[134]:
car1 = car_word.get_synsets(NOUN)[0]
car1.definition()
# In[135]:
