def test_word_similarity():
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
dog = wns.word2synset('dog')
cat = wns.word2synset('cat')
# Measuring semantic similarity between concepts using Path method
assert wns.similarity(dog[0], cat[0], 'path') is not None # 0.2
# Computing English word similarity using Li method
assert wns.word_similarity('dog', 'cat',
'li') is not None # 0.449327301063
# Computing Spanish word similarity using Lin method
assert wns.monol_word_similarity('perro', 'gato', 'spa',
'lin') is not None #0.876800984373
# Computing Chinese word similarity using Wu & Palmer method
assert wns.monol_word_similarity('狗', '猫', 'cmn',
'wup') is not None # 0.857142857143
# Computing Spanish and English word similarity using Resnik method
assert wns.crossl_word_similarity('perro', 'cat', 'spa', 'eng',
'res') is not None #7.91166650904
# Computing Spanish and Chinese word similarity using Jiang & Conrad method
assert wns.crossl_word_similarity('perro', '猫', 'spa', 'cmn',
'jcn') is not None #0.31023804699
# Computing Chinese and English word similarity using WPath method
assert wns.crossl_word_similarity('狗', 'cat', 'cmn', 'eng',
'wpath') is not None #0.593666388463
def map_subjects(subjects: list, filter_dis=0.2):
# mapping the subjects, filter the i,j in M
wns = WordNetSimilarity()
# enumerate pairing and calculate distances
# [['中国人', '安乐死'], ['太阳', '很好']]
pair = []
# return the indexes pairing
pair_idxs = []
for index, value in enumerate(subjects):
i = index + 1
while i < len(subjects):
# compare list : next list
com_value = subjects[i]
for v in value:
for cv in com_value:
pair_distance = wns.monol_word_similarity(
v, cv, 'cmn', 'wup')
# print(f'{v} -> {cv}: {pair_distance}')
if pair_distance > filter_dis:
pair.append(pair_distance)
# pairing index: (row, column)
pair_idxs.append(
([index, value.index(v)], [i,
com_value.index(cv)]))
i += 1
return pair_idxs
def controlledSetWordNetSimilarity(self, word, similarWords):
wns = WordNetSimilarity()
for similarWord in similarWords.copy():
if wns.word_similarity(
word, similarWord, 'li'
) < 0.9996: # Variable to control accuracy of controlset
similarWords.discard(similarWord)
return similarWords
def __init__(self, wsd_method='maxsim', sim_name='wpath'):
'''
wsd_methods = ['random_sense','first','frequent','maxsim', 'graph', 'lesk', 'naive']
sim_name = ['path', 'lch', 'wup', 'li', 'res', 'lin', 'jcn', 'wpath']
'''
self._method = wsd_method
self._sim_name = sim_name
self._wn_sim = WordNetSimilarity()
def test_language():
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
#check the supported languages
assert wns.languages() is not None
#find the language code
assert wns.languages('English') is not None
assert wns.languages('chinese_simplified') is not None
assert wns.languages('spanish') is not None
def __init__(self):
self.out = {}
self.keras = keras_similar()
self.classifier = Qclassifier()
self.spell=Spelling()
self.wn = WordNetSimilarity()
self.en_nlp = spacy.load("en_core_web_md")
self.stopwords_en=[]
with open(os.path.join(os.path.dirname(os.path.realpath(__file__)),
'utils', 'stopwords_en.txt')) as f:
self.stopwords_en = f.read().splitlines()
def test_classification_evaluation():
from sematch.evaluation import AspectEvaluation
from sematch.application import SimClassifier, SimSVMClassifier
from sematch.semantic.similarity import WordNetSimilarity
evaluation = AspectEvaluation()
X, y = evaluation.load_dataset()
wns = WordNetSimilarity()
word_sim = lambda x, y: wns.word_similarity(x, y)
simclassifier = SimClassifier.train(zip(X, y), word_sim)
evaluation.evaluate(X, y, simclassifier)
simSVMclassifier = SimSVMClassifier.train(X, y, word_sim)
evaluation.evaluate(X, y, simSVMclassifier)
def semantic_matching(trend_one, trend_two):
treshold = 0.3
trend_one_processed = text_processing(trend_one, keep_spaces=True)
trend_two_processed = text_processing(trend_two, keep_spaces=True)
# The options are Wordnet, YAGO and DBpedia (only the first seems usable)
wns = WordNetSimilarity()
matches = list({
x['original']
for x in trend_one_processed for y in trend_two_processed
if wns.word_similarity(x['processed'], y['processed'], 'li') > treshold
})
if len(matches) == 0: return 'No matches'
return matches
def test_sim_graph():
from sematch.semantic.graph import SimGraph
from sematch.semantic.similarity import WordNetSimilarity
from sematch.nlp import Extraction, lemmatization
from sematch.sparql import EntityFeatures
from collections import Counter
madrid = EntityFeatures().features(
'http://dbpedia.org/resource/Tom_Cruise')
words = Extraction().extract_words_sent(madrid['abstract'])
words = list(set(lemmatization(words)))
wns = WordNetSimilarity()
word_graph = SimGraph(words, wns.word_similarity)
word_scores = word_graph.page_rank()
words, scores = zip(*Counter(word_scores).most_common(10))
assert words is not None
def test_wordsim_evaluation():
from sematch.evaluation import WordSimEvaluation
from sematch.semantic.similarity import WordNetSimilarity
wordsim_eval = WordSimEvaluation()
wns = WordNetSimilarity()
#define similarity metrics
lin = lambda x, y: wns.word_similarity(x, y, 'lin')
wpath = lambda x, y: wns.word_similarity_wpath(x, y, 0.8)
#evaluate similarity metrics
assert wordsim_eval.evaluate_multiple_metrics({
'lin': lin,
'wpath': wpath
}, 'noun_simlex') is not None
#performa Steiger's Z significance Test
assert wordsim_eval.statistical_test('wpath', 'lin',
'noun_simlex') is not None
def test_wordsim_evaluation():
from sematch.evaluation import WordSimEvaluation
from sematch.semantic.similarity import WordNetSimilarity
evaluation = WordSimEvaluation()
print evaluation.dataset_names()
wns = WordNetSimilarity()
# define similarity metrics
wpath = lambda x, y: wns.word_similarity_wpath(x, y, 0.8)
# evaluate similarity metrics
print evaluation.evaluate_metric('wpath', wpath, 'noun_simlex')
# performa Steiger's Z significance Test
print evaluation.statistical_test('wpath', 'path', 'noun_simlex')
wpath_es = lambda x, y: wns.monol_word_similarity(x, y, 'spa', 'path')
wpath_en_es = lambda x, y: wns.crossl_word_similarity(
x, y, 'eng', 'spa', 'wpath')
print evaluation.evaluate_metric('wpath_es', wpath_es, 'rg65_spanish')
print evaluation.evaluate_metric('wpath_en_es', wpath_en_es, 'rg65_EN-ES')
def test_query_ned():
from sematch.nlp import FeatureExtractor
from sematch.nlp import EntityFeature
from sematch.nlp import SpaCyNLP
from sematch.utility import FileIO
from sematch.semantic.relatedness import TextRelatedness
from sematch.nel import EntityDisambiguation
import itertools
sy = SpaCyNLP()
features = EntityFeature.load(
feature_dict_file='models/query_features.json')
extractor = FeatureExtractor(features, sy.pos_tag)
ned = EntityDisambiguation(extractor)
rel = TextRelatedness()
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
#print wns.word_similarity('cooling', 'air_conditioner', 'li')
#similarity = lambda x,y : rel.text_similarity(x,y, model='lsa')
query = FileIO.read_json_file('dataset/ned/query_ned_cleaned.txt')
query = [q for q in query if extractor.context_features(q['query'])]
print len(query)
import warnings
warnings.filterwarnings("ignore")
metrics = ['path', 'wup', 'res', 'lin', 'jcn', 'wpath']
for m in metrics:
print m
similarity = lambda x, y: wns.word_similarity(x, y, m)
for k in range(1, 21):
gold = []
predict = []
for q in query:
gold.append(q['gold'])
#e = ned.text_disambiguate(q['query'], q['candidate'], similarity)
e = ned.word_disambiguate(q['query'],
q['candidate'],
similarity,
K=k)
predict.append(e)
from sklearn.metrics import precision_recall_fscore_support
#from sklearn.metrics import classification_report
#print classification_report(gold, predict)
print precision_recall_fscore_support(gold,
predict,
average='weighted')[2]
def __init__(self,
corpus,
feature_num=10,
model='onehot',
wn_method='path',
vec_file='models/GoogleNews-vectors-negative300.bin',
binary=True):
"""
:param corpus: use a corpus to train a vector representation
:param feature_num: number of dimensions
:param model: onehot or wordnet or word2vec or both
"""
self._model = model
self._wn_method = wn_method
self._features = self.extract_features(corpus, feature_num)
self._wns = WordNetSimilarity(
) if model == 'wordnet' or model == 'both' else None
self._wvs = WordVecSimilarity(
vec_file,
binary) if model == 'word2vec' or model == 'both' else None
def yhmh_nlp(url, trigger_words):
text, triggers = parse_my_url(url, trigger_words)
print("triggers2: %s" % (triggers))
if text is "" or len(triggers) == 0:
return ""
client = language.LanguageServiceClient()
if isinstance(text, six.binary_type):
text = text.decode('utf-8')
# Instantiates a plain text document.
document = types.Document(content=text,
type=enums.Document.Type.PLAIN_TEXT)
# Detects entities in the document. You can also analyze HTML with:
# document.type == enums.Document.Type.HTML
entities = client.analyze_entities(document).entities
verbose = True
counter = 0
counter2 = 0
text_output_array = pd.DataFrame(np.zeros((len(entities), 3)))
for entity in entities:
entity_type = enums.Entity.Type(entity.type)
if len(entity.name) < 25 and '.' not in entity.name:
text_output_array.iloc[counter, 0] = entity.name
text_output_array.iloc[counter, 1] = entity_type.name
text_output_array.iloc[counter, 2] = entity.salience
counter += 1
else:
counter2 += 1
celebrity_status = 0
if len(entities) > 0:
if entities[0].metadata.get(
'wikipedia_url',
'-') != '-' and text_output_array.iloc[0, 1] == 'PERSON':
celebrity_status = 1
elif entities[1].metadata.get(
'wikipedia_url',
'-') and text_output_array.iloc[1, 1] == 'PERSON':
celebrity_status = 1
else:
celebrity_status = 0
text_output_array = text_output_array.iloc[0:len(entities) - counter2, :]
# Detects the sentiment of the text
#sentiment = client.analyze_sentiment(document=document).document_sentiment
wns = WordNetSimilarity()
keywords_target = pd.Series.to_list(text_output_array[0])
#keywords_target = list(set(keywords_target))
#seen = set(keywords_target)
#keywords_target = []
#for x in keywords_target:
# if x not in seen:
# keywords_target.append(x)
# seen.add(x)
#
#keywords_target=seen
forbidden_keywords = [
'medicine', 'drug', 'fun', 'hospital', 'suicide', 'death', 'mental',
'health', 'illness', 'insta', ',man', 'woman', 'family', 'people',
'many', 'place', 'same', 'others', 'brain', 'all', 'end', 'statement',
'lot', 'condolences'
]
regex = re.compile(r'([A-Z]([a-z])+)')
selected_files = list(filter(regex.search, keywords_target))
res = list(set(keywords_target) - set(selected_files))
regex = re.compile(r'^@')
selected_files = list(filter(regex.search, res))
res = list(set(keywords_target) - set(selected_files))
regex = re.compile(r"\b[A-Z][A-Z]+\b")
selected_files = list(filter(regex.search, res))
res = list(set(res) - set(selected_files))
regex = re.compile(r'([A-Z]([a-z])+)')
selected_files = list(filter(regex.search, res))
res = list(set(res) - set(selected_files))
for key in range(len(res)):
if ' ' in res[key]:
res[key] = res[key].split(' ')[0]
for x in range(len(res)):
for y in range(len(forbidden_keywords)):
if res[x] == forbidden_keywords[y]:
res[x] = []
res = list(filter(None, res))
res_dictionary = Counter(res)
res_output = res_dictionary.most_common(10)
res_output = dict(res_output)
res_output = list(res_output.keys())
print(res_output)
res = res_output[0:num_keywords]
database = pd.read_csv(
CURATED_LIST
) #('/Users/vmutai/Projects/HMH/admin/microblog/app/yhmh_curated_articles.csv')
if celebrity_status == 1:
database = database[database.celebrity == 1]
elif celebrity_status == 0:
database = database[database.celebrity == 0]
similarity_ranks = pd.DataFrame(np.zeros(database.shape[0]))
for z in range(database.shape[0]):
newlist = []
N_rows = len(res)
keywords_source = database.iloc[z, 4:4 + num_keywords]
keywords_source = pd.Series.tolist(keywords_source)
N_cols = len(keywords_source)
#similarity_list = pd.DataFrame(np.zeros((N_rows, N_cols)))
foo = [1]
for x in range(len(res)):
for y in range(len(keywords_source)):
value = wns.word_similarity(res[x], keywords_source[y], 'lin')
#similarity_matrix.at[x,y]=value
foo.append(value)
matrix_average = sum(foo) / np.count_nonzero(foo)
similarity_ranks.at[z, 0] = matrix_average
maximum = pd.DataFrame.idxmax(similarity_ranks)
url_to_return = pd.Series.tolist(database.iloc[maximum, 0])
print(url_to_return)
title = pd.Series.tolist(database.iloc[maximum, 1])
def output(title, res_output, url_to_return):
a = {
'header': title[0],
'keywords_list': res_output,
'url_recommendation': url_to_return[0]
}
print("JSON DUMP")
print(a)
try:
return json.dumps(a)
except:
return "awesome2!"
json_output = output(title, res_output, url_to_return)
print(json_output)
return json_output
def test_synset_expand():
from sematch.semantic.similarity import WordNetSimilarity
wns = WordNetSimilarity()
cat = wns.word2synset('cat')[0]
assert wns.synset_expand(cat) is not None
from flask import Flask, json, request, render_template as template
from sematch.application import Matcher
from sematch.semantic.similarity import ConceptSimilarity, WordNetSimilarity
from sematch.semantic.similarity import YagoTypeSimilarity, EntitySimilarity
from sematch.semantic.graph import DBpediaDataTransform, Taxonomy
import os
DEBUG = True
SECRET_KEY = 'Secret_development_key'
DATA_FILE = 'data/data.txt'
app = Flask(__name__)
app.config.from_object(__name__)
wn_sim = WordNetSimilarity()
yago_sim = YagoTypeSimilarity()
matcher = Matcher()
dbpedia_sim = ConceptSimilarity(Taxonomy(DBpediaDataTransform()),
'models/dbpedia_type_ic.txt')
entity = EntitySimilarity()
from search import text_lsa, text_tfidf, data
@app.route('/api/text_search')
def text_search():
query = request.args.get('query')
result = text_tfidf.search(query)
result_data = []
from datetime import datetime
from csv import DictReader
from math import exp, log, sqrt
from random import random, shuffle
import pickle
import sys
import string
import numpy as np
from sematch.semantic.similarity import WordNetSimilarity
from config import path
wns = WordNetSimilarity()
import string
string.punctuation.__add__('!!')
string.punctuation.__add__('(')
string.punctuation.__add__(')')
string.punctuation.__add__('?')
string.punctuation.__add__('.')
string.punctuation.__add__(',')
# from gensim.models import Word2Vec
# model = Word2Vec.load_word2vec_format(path+'GoogleNews-vectors-negative300.bin', binary=True) # C binary format
# print model.vocab
model = None
def remove_punctuation(x):
new_line = [w for w in list(x) if w not in string.punctuation]
new_line = ''.join(new_line)
return new_line
import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import TfidfVectorizer
from sematch.semantic.similarity import WordNetSimilarity
WNS = WordNetSimilarity()
# NOTE: For reference see: https://pdfs.semanticscholar.org/1374/617e135eaa772e52c9a2e8253f49483676d6.pdf
def random_sentences(num_rand_sentences, df_main):
"""Select num_rand_sentences at random from the Dataframe
Args:
num_rand_sentences (int): the number of sentences to select at random
Return:
list: list of sentences
"""
size = num_rand_sentences
indices = np.random.randint(0, df_main.shape[0], size)
tokenized_subset = df_main['tokenized_sentence'].dropna()
sentence_subset = df_main['sentence'].dropna()
lecture_subset = df_main['lecture'].dropna()
start_time_subset = df_main['start_time'].dropna()
end_time_subset = df_main['end_time'].dropna()
random_tokenized_sentences = map(lambda x: tokenized_subset[x], indices)
random_normal_sentences = map(lambda x: sentence_subset[x], indices)
