__author__ = 'daksh'
import time
from dishingOut.Database.database import MongoOperator as mongo
from dishingOut.NPChunking.NPChunker import NPChunker
import csv
import json
chunker = NPChunker()
chunker.train()
''' Get all test adjectives : Unfiltered. Around 1 lakh adjectives. Contains a lot of non adjectives'''
# database = mongo('DishingOut')
# database.setUpConnection()
# database.setUpCollection('reviews')
# restaurants = database.getAll()
restaurants = None
with open('../data/restaurants.json') as data_file:
restaurants = json.load(data_file)
restaurants = restaurants[2000:]
start = time.time()
# for restaurant in restaurants:
# for review in restaurant['userReviews']:
# text = review['reviewText']
# sentences = chunker.split(text)
# for sent in sentences:
# tree,terms = chunker.extractChunk(sent)
# print(tree)
vocabulary = list()
import nltk
import csv
import json
from dishingOut.NPChunking.NPChunker import NPChunker
nltk.data.path.append("/home/daksh/Documents/Softwares/nltk_data")
from nltk.corpus import sentiwordnet as wn
from textblob import Word
pos_words = list()
neg_words = list()
chunker = NPChunker()
chunker.train()
with open('../data/posAdj.csv', 'r') as csvfile:
spamwriter = csv.reader(csvfile)
pos_words = list(spamwriter)
with open('../data/negAdj.csv', 'r') as csvfile:
spamwriter = csv.reader(csvfile)
neg_words = list(spamwriter)
pos_words = [word[0] for word in pos_words]
neg_words = [word[0] for word in neg_words]
posSeed_list = {key:True for key in pos_words}
__author__ = 'daksh'
from dishingOut.NPChunking.NPChunker import NPChunker
chunker = NPChunker()
chunker.train()
# tree,terms = chunker.extractChunk("Dosa was good")
# text = 'An institution in south indian offerings with Benne Masala Dosa at its best along with rava upma,kesari bath and mangalore bhajji with same level of excellence.Masala Dosa- You cant eat just one,will crave for more for sure.It tastes heavenly with the chutney CTR offers,its own kind.'
# text = 'Biryani was aromatic and superb'
# text = "Brilliant Idli Vada but Kara Bhath is not good!"
# text = "Amritsari fish were my favorites of the day"
# text = "Rasgulla and jamun were good"
# text = "Idli Vada and Kara Bhath are good!"
# text= "We had a crispy dosa and the coffee was not hot but the paneer was pathetic"
# text = "crispy dosa and coffee not hot"
# text = "Double masala chicken biryani served here is the best biryani I have tried till date"
# text = "Other starters that I have ordered like lemon chicken chicken kebab paneer Manchurian are okayish but the taste of biryani covers it all for me"
# text = "paneer was tasty"
# text = "I did not expect palak paneer to be so good but to my wonder it was excellent."
text = "Paneer tikka - Soft and tasty."
tree, terms = chunker.extractChunk(text)
tree.draw()
# tree.draw()
print(terms)
# sentences = chunker.getSentences(text)
# print(type(sentences[0]))
#for sent in sentences:
# print(chunker.getAdjetives(sent))
class AntonymReplacer(object):
def __init__(self):
self.chunker = NPChunker()
self.chunker.train()
def replace(self, adj, pos=None):
'''antonyms = set()
for syn in wordnet.synsets(adj, pos=pos):
for lemma in syn.lemmas():
for antonym in lemma.antonyms():
antonyms.add(antonym.name())
if len(antonyms) >= 1:
return antonyms.pop()
else:
return None'''
antonyms = []
synonyms = []
# word = Word(adj)
# for syn in word.synsets[:]:
for syn in list(wn.senti_synsets(adj)):
# for l in syn.lemmas():
for l in syn.synset.lemmas():
synonyms.append(l.name())
if l.antonyms():
antonyms.append(l.antonyms()[0].name())
if len(antonyms) > 0:
return antonyms[0]
else:
return None
def replace_negations(self, sent):
i, l = 0, len(sent)
words = []
flag = False
while i < l:
word = sent[i]
if word == 'not' and i + 1 < l:
ant = self.replace(sent[i + 1])
if ant:
words.append(ant)
i += 2
flag = True
continue
words.append(word)
i += 1
return flag, words
def checkNegationWords(self, words):
if 'not' in words:
return True
elif 'nothing' in words:
return True
else:
return False
def NegationCheck(self, sentence):
words = self.chunker.getWords(sentence)
flag, new_sent = self.replace_negations(words)
if flag:
return False, new_sent
else:
check = self.checkNegationWords(words)
if check:
return check, words
else:
return False, words
# a = AntonymReplacer()
# print(a.NegationCheck('The dosa was good'))
def __init__(self):
self.chunker = NPChunker()
self.chunker.train()
class AntonymReplacer(object):
def __init__(self):
self.chunker = NPChunker()
self.chunker.train()
def replace(self, adj, pos=None):
'''antonyms = set()
for syn in wordnet.synsets(adj, pos=pos):
for lemma in syn.lemmas():
for antonym in lemma.antonyms():
antonyms.add(antonym.name())
if len(antonyms) >= 1:
return antonyms.pop()
else:
return None'''
antonyms=[]
synonyms = []
# word = Word(adj)
# for syn in word.synsets[:]:
for syn in list(wn.senti_synsets(adj)):
# for l in syn.lemmas():
for l in syn.synset.lemmas():
synonyms.append(l.name())
if l.antonyms():
antonyms.append(l.antonyms()[0].name())
if len(antonyms) > 0:
return antonyms[0]
else:
return None
def replace_negations(self, sent):
i, l = 0, len(sent)
words = []
flag = False
while i < l:
word = sent[i]
if word == 'not' and i+1 < l:
ant = self.replace(sent[i+1])
if ant:
words.append(ant)
i += 2
flag = True
continue
words.append(word)
i += 1
return flag,words
def checkNegationWords(self,words):
if 'not' in words:
return True
elif 'nothing' in words:
return True
else:
return False
def NegationCheck(self,sentence):
words = self.chunker.getWords(sentence)
flag,new_sent = self.replace_negations(words)
if flag:
return False,new_sent
else:
check = self.checkNegationWords(words)
if check:
return check,words
else:
return False,words
# a = AntonymReplacer()
# print(a.NegationCheck('The dosa was good'))
def __init__(self):
self.chunker = NPChunker()
self.chunker.train()
__author__ = "Daksh"
import nltk
import csv
import json
from dishingOut.NPChunking.NPChunker import NPChunker
nltk.data.path.append("/home/daksh/Documents/Softwares/nltk_data")
from nltk.corpus import sentiwordnet as wn
from textblob import Word
pos_words = list()
neg_words = list()
chunker = NPChunker()
chunker.train()
with open('../data/posAdj.csv', 'r') as csvfile:
spamwriter = csv.reader(csvfile)
pos_words = list(spamwriter)
with open('../data/negAdj.csv', 'r') as csvfile:
spamwriter = csv.reader(csvfile)
neg_words = list(spamwriter)
pos_words = [word[0] for word in pos_words]
neg_words = [word[0] for word in neg_words]
posSeed_list = {key: True for key in pos_words}
negSeed_list = {key: False for key in neg_words}
import json
from dishingOut.NPChunking.NPChunker import NPChunker
from dishingOut.SentimentAnalysis.antonymReplacer import AntonymReplacer
import pickle
import time
with open('../data/final_data.json','r') as f:
data = json.load(f)
chunker = NPChunker()
chunker.train()
replacer = AntonymReplacer()
f = open('../SentimentAnalysis/nb_classifier.pickle', 'rb')
classifier = pickle.load(f)
f.close()
print("Done pre-processing")
def word_feats(words):
return dict([word,True] for word in words)
start = time.time()
restaurants = data
for restaurant in restaurants:
dishes = restaurant['dishes']
restaurant['dishRatings'] = dict()
print(dishes.keys())
allChunks = dict()
for dish in dishes.keys():
# print(dish)
__author__ = 'daksh'
from dishingOut.NPChunking.NPChunker import NPChunker
chunker = NPChunker()
chunker.train()
# tree,terms = chunker.extractChunk("Dosa was good")
# text = 'An institution in south indian offerings with Benne Masala Dosa at its best along with rava upma,kesari bath and mangalore bhajji with same level of excellence.Masala Dosa- You cant eat just one,will crave for more for sure.It tastes heavenly with the chutney CTR offers,its own kind.'
# text = 'Biryani was aromatic and superb'
# text = "Brilliant Idli Vada but Kara Bhath is not good!"
# text = "Amritsari fish were my favorites of the day"
# text = "Rasgulla and jamun were good"
# text = "Idli Vada and Kara Bhath are good!"
# text= "We had a crispy dosa and the coffee was not hot but the paneer was pathetic"
# text = "crispy dosa and coffee not hot"
# text = "Double masala chicken biryani served here is the best biryani I have tried till date"
# text = "Other starters that I have ordered like lemon chicken chicken kebab paneer Manchurian are okayish but the taste of biryani covers it all for me"
# text = "paneer was tasty"
# text = "I did not expect palak paneer to be so good but to my wonder it was excellent."
text = "Paneer tikka - Soft and tasty."
tree,terms = chunker.extractChunk(text)
tree.draw()
# tree.draw()
print(terms)
# sentences = chunker.getSentences(text)
# print(type(sentences[0]))
#for sent in sentences:
# print(chunker.getAdjetives(sent))
