__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()
def __init__(self):
self.chunker = NPChunker()
self.chunker.train()
