train.py

#!/usr/env/bin python
# -*- coding: utf-8 -*-

import numpy as np
import random
from cs224d.data_utils import *
from utils import *
from word2vec import *
from sgd import *

# Load some data and initialize word vectors

# Reset the random seed to make sure that everyone gets the same results
random.seed(314)
dataset = StanfordSentiment()
tokens = dataset.tokens()
nWords = len(tokens)

# We are going to train 10-dimensional vectors for this assignment
dimVectors = 10

# Context size
C = 5

# Train word vectors (this could take a while!)

# Reset the random seed to make sure that everyone gets the same results
random.seed(31415)
np.random.seed(9265)
wordVectors = np.concatenate(((np.random.rand(nWords, dimVectors) - .5) / dimVectors, 
                              np.zeros((nWords, dimVectors))), axis=0)
wordVectors0 = sgd(lambda vec: word2vec_sgd_wrapper(skipgram, tokens, vec, dataset, C, negSamplingCostAndGradient), 
                   wordVectors, 0.3, 40000, None, False, PRINT_EVERY=10)
# sanity check: cost at convergence should be around or below 10

# sum the input and output word vectors
wordVectors = (wordVectors0[:nWords,:] + wordVectors0[nWords:,:])

print "\n=== For autograder ==="
checkWords = ["the", "a", "an", "movie", "ordinary", "but", "and"]
checkIdx = [tokens[word] for word in checkWords]
checkVecs = wordVectors[checkIdx, :]
print checkVecs