amn41

vocab_file ="/path/to/vocab_file"
vectors_file ="/path/to/vectors_file"

embed = Embedding(vocab_file,vectors_file)

cuisine_refs = ["mexican","chinese","french","british","american"]
threshold = 0.2

text = "I want to find an indian restaurant"

amn41

import sys, os
from mitie import *

trainer = text_categorizer_trainer("/path/to/total_word_feature_extractor.dat")

data = {} # same as before  - omitted for brevity

for label in training_examples.keys():
  for text in training_examples[label]["examples"]:
    tokens = tokenize(text)

amn41

import sys, os
from mitie import *
sample = ner_training_instance(["I", "am", "looking", "for", "some", "cheap", "Mexican", "food", "."])

sample.add_entity(xrange(5,6), "pricerange")
sample.add_entity(xrange(6,7), "cuisine")

# And we add another training example
sample2 = ner_training_instance(["show", "me", "indian", "restaurants", "in", "the", "centre", "."])
sample2.add_entity(xrange(2,3), "cuisine")

amn41

\emph{hello}

amn41

import numpy as np
from sklearn.svm import SVC
from sklearn.decomposition import PCA
from sklearn.cross_validation import train_test_split

from sklearn.grid_search import GridSearchCV
from sklearn.metrics import classification_report

import matplotlib.pyplot as plt
import pickle

amn41

import numpy as np

def sum_vecs(embed,text):

    tokens = text.split(' ')
    vec = np.zeros(embed.W.shape[1])

    for idx, term in enumerate(tokens):
        if term in embed.vocab:
            vec = vec + embed.W[embed.vocab[term], :]

amn41

amn41

import rinocloud as rino
import shutil, os
import subprocess
import hashlib

"""
persist = Persistor(config.rino_token,config.rino_dir)

def save_model_new(persist,model_file,score):
    temp_file="tmp_{0:06d}.txt".format(random.choice(range(10000)))                                                                                                                                                                                  

amn41

"""Implements the long-short term memory character model.
This version vectorizes over multiple examples, but each string
has a fixed length."""

from __future__ import absolute_import
from __future__ import print_function
from builtins import range
from os.path import dirname, join
import numpy as np
import numpy.random as npr

amn41

from __future__ import unicode_literals
from __future__ import print_function
from __future__ import division
from __future__ import absolute_import
from builtins import str as text

import argparse
import io
import json