amn41

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

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

\emph{hello}

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

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

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

def find_similar_words(embed,text,refs,thresh):

    C = np.zeros((len(refs),embed.W.shape[1]))

    for idx, term in enumerate(refs):
        if term in embed.vocab:
            C[idx,:] = embed.W[embed.vocab[term], :]


    tokens = text.split(' ')

amn41

class Embedding(object):
    def __init__(self,vocab_file,vectors_file):
        with open(vocab_file, 'r') as f:
            words = [x.rstrip().split(' ')[0] for x in f.readlines()]

        with open(vectors_file, 'r') as f:
            vectors = {}
            for line in f:
                vals = line.rstrip().split(' ')
                vectors[vals[0]] = [float(x) for x in vals[1:]]

amn41

while ( not formData.is_complete() ):
    questionKey = formData.first_missing_field()
    ask(questions[questionKey])