def load_wv(vocabfile, wvfile):
wv = loadtxt(wvfile, dtype=float)
with open(vocabfile) as fd:
words = [line.strip() for line in fd]
num_to_word = dict(enumerate(words))
word_to_num = invert_dict(num_to_word)
return wv, word_to_num, num_to_word
def load_wv(vocabfile, wvfile):
wv = loadtxt(wvfile, dtype=float)
with open(vocabfile) as fd:
words = [line.strip() for line in fd]
num_to_word = dict(enumerate(words))
word_to_num = invert_dict(num_to_word)
return wv, word_to_num, num_to_word
#wv_dummy = random.randn(10,50)
#model = RNNLM(L0 = wv_dummy, U0 = wv_dummy,
# alpha=0.005, rseed=10, bptt=4)
#model.grad_check(array([1,2,3]), array([2,3,4]))
from data_utils import utils as du
import pandas as pd
# Load the vocabulary
vocab = pd.read_table("data/lm/vocab.ptb.txt", header=None, sep="\s+",
index_col=0, names=['count', 'freq'], )
# Choose how many top words to keep
vocabsize = 2000
num_to_word = dict(enumerate(vocab.index[:vocabsize]))
word_to_num = du.invert_dict(num_to_word)
##
# Below needed for 'adj_loss': DO NOT CHANGE
fraction_lost = float(sum([vocab['count'][word] for word in vocab.index
if (not word in word_to_num)
and (not word == "UUUNKKK")]))
fraction_lost /= sum([vocab['count'][word] for word in vocab.index
if (not word == "UUUNKKK")])
print "Retained %d words from %d (%.02f%% of all tokens)" % (vocabsize, len(vocab),
100*(1-fraction_lost))
# Load the training set
docs = du.load_dataset('data/lm/ptb-train.txt')
S_train = du.docs_to_indices(docs, word_to_num)
X_train, Y_train = du.seqs_to_lmXY(S_train)
import data_utils.utils as du
import data_utils.ner as ner
# Load the starter word vectors
wv, word_to_num, num_to_word = ner.load_wv('data/ner/vocab.txt',
'data/ner/wordVectors.txt')
tagnames = ["O", "LOC", "MISC", "ORG", "PER"]
num_to_tag = dict(enumerate(tagnames))
tag_to_num = du.invert_dict(num_to_tag)
# Set window size
windowsize = 3
# Load the training set
docs = du.load_dataset('data/ner/train')
X_train, y_train = du.docs_to_windows(docs,
word_to_num,
tag_to_num,
wsize=windowsize)
# Load the dev set (for tuning hyperparameters)
docs = du.load_dataset('data/ner/dev')
X_dev, y_dev = du.docs_to_windows(docs,
word_to_num,
tag_to_num,
wsize=windowsize)
# Load the test set (dummy labels only)
docs = du.load_dataset('data/ner/test.masked')
X_test, y_test = du.docs_to_windows(docs,
word_to_num,
if __name__ == "__main__":
# Load the vocabulary
vocab = pd.read_table(
"data/lm/vocab.ptb.txt",
header=None,
sep="\s+",
index_col=0,
names=['count', 'freq'],
)
vocabsize = 2000
num_to_word = dict(enumerate(vocab.index[:vocabsize]))
num_to_word_embedding = load_vocab_embeddings()
word_to_num = du.invert_dict(num_to_word)
# Load the training data
_, S_train = load_data_as_sentences('data/lm/ptb-train.txt', word_to_num)
in_word_index, out_word_index = convert_to_lm_dataset(S_train)
assert len(in_word_index) == len(out_word_index)
num_of_examples = len(in_word_index)
random.seed(31415)
np.random.seed(9265)
in_word_index, out_word_index = shuffle_training_data(
in_word_index, out_word_index)
startTime = time.time()
# Training should happen here
# Initialize parameters randomly
import data_utils.ner as ner
from softmax_example import SoftmaxRegression
from nerwindow import WindowMLP
import itertools
from numpy import *
from multiprocessing import Pool
import random as rdm
random.seed(10)
wv, word_to_num, num_to_word = ner.load_wv('data/ner/vocab.txt',
'data/ner/wordVectors.txt')
tagnames = ["O", "LOC", "MISC", "ORG", "PER"]
num_to_tag = dict(enumerate(tagnames))
tag_to_num = du.invert_dict(num_to_tag)
windowsize = 3
docs = du.load_dataset('data/ner/train')
X_train, y_train = du.docs_to_windows(docs, word_to_num, tag_to_num, wsize=windowsize)
docs = du.load_dataset('data/ner/dev')
X_dev, y_dev = du.docs_to_windows(docs, word_to_num, tag_to_num, wsize=windowsize)
docs = du.load_dataset('data/ner/test.masked')
X_test, y_test = du.docs_to_windows(docs, word_to_num, tag_to_num, wsize=windowsize)
nepoch = 5
N = nepoch * len(y_train)
k = 5 # minibatch size
def main():
# Load the starter word vectors
wv, word_to_num, num_to_word = ner.load_wv('data/ner/vocab.txt',
'data/ner/wordVectors.txt')
tagnames = ["O", "LOC", "MISC", "ORG", "PER"]
num_to_tag = dict(enumerate(tagnames))
tag_to_num = du.invert_dict(num_to_tag)
# Set window size
windowsize = 3
# Load the training set
docs = du.load_dataset('data/ner/train')
X_train, y_train = du.docs_to_windows(docs,
word_to_num,
tag_to_num,
wsize=windowsize)
# Load the dev set (for tuning hyperparameters)
docs = du.load_dataset('data/ner/dev')
X_dev, y_dev = du.docs_to_windows(docs,
word_to_num,
tag_to_num,
wsize=windowsize)
# Load the test set (dummy labels only)
docs = du.load_dataset('data/ner/test.masked')
X_test, y_test = du.docs_to_windows(docs,
word_to_num,
tag_to_num,
wsize=windowsize)
clf = WindowMLP(wv,
windowsize=windowsize,
dims=[None, 100, 5],
reg=0.001,
alpha=0.01)
train_size = X_train.shape[0]
"""
costs = pickle.load(open("costs.dat", "rb"))
clf = pickle.load(open("clf.dat", "rb"))
"""
nepoch = 5
N = nepoch * len(y_train)
k = 5 # minibatch size
costs = clf.train_sgd(X_train,
y_train,
idxiter=random_mini(k, N, train_size),
printevery=10000,
costevery=10000)
pickle.dump(clf, open("clf.dat", "wb"))
pickle.dump(costs, open("costs.dat", "wb"))
plot_learning_curve(clf, costs)
# Predict labels on the dev set
yp = clf.predict(X_dev)
# Save predictions to a file, one per line
ner.save_predictions(yp, "dev.predicted")
full_report(y_dev, yp, tagnames) # full report, helpful diagnostics
eval_performance(y_dev, yp, tagnames) # performance: optimize this F1
# L: V x 50
# W[:,50:100]: 100 x 50
responses = clf.sparams.L.dot(clf.params.W[:, 50:100].T) # V x 100
index = np.argsort(responses, axis=0)[::-1]
neurons = [1, 3, 4, 6, 8] # change this to your chosen neurons
for i in neurons:
print "Neuron %d" % i
top_words = [num_to_word[k] for k in index[:10, i]]
top_scores = [responses[k, i] for k in index[:10, i]]
print_scores(top_scores, top_words)
#from rnn_simple import RNN_SIMPLE
#from brnn import BRNN
#from brnn_weighted import BRNN_WEIGHTED
#from rnn_weighted import RNN_WEIGHTED
from data_utils import utils as du
import pandas as pd
from misc import *
N_ASPECTS = 5
SENT_DIM = 3
# Load the vocabulary
vocab = pd.read_table("worddic.txt",header=None,sep="\s+",index_col=0)
n2w = dict(enumerate(vocab.index))
w2n = du.invert_dict(n2w)
vocabsize = len(w2n)
num2word =dict(enumerate(w2n))
word2num = du.invert_dict(num2word)
print "Number of unique words:",len(num2word)
##############
filename_train = 'x_train.txt'#'reviews_plain.txt'
filename_dev = 'x_dev.txt'
X_train = read_data(filename_train,word2num)
X_dev = read_data(filename_dev,word2num)
# Load the vocabulary
#vocab = pd.read_table("data/lm/vocab.ptb.txt", header=None, sep="\s+",
# index_col=0, names=['count', 'freq'], )
vocab2 = pd.read_table("worddic.txt",header=None,sep="\s+",index_col=0)
# Choose how many top words to keep
#vocabsize = 2000
vocabsize2 = 58868 #remove for implemenation
#num_to_word = dict(enumerate(vocab.index[:vocabsize]))
num_to_word2 = dict(enumerate(vocab.index[:vocabsize]))
#word_to_num = du.invert_dict(num_to_word)
word_to_num2 = du.invert_dict(num_to_word2)
#print word_to_num2
##############
filename = 'reviews_plain.txt'
print "Opening the file..."
X_train = []
f = open(filename,'r')
count = 0
for line in f.readlines():
sentence = []
line = line.strip()
dropped = 0
for i in word_vocab.keys():
if word_vocab[i] < 5:
dropped += word_vocab[i]
else:
if i not in word_to_num:
word_to_num[i] = j
j = j + 1
word_to_num["<s>"] = j
word_to_num["</s>"] = j + 1
mx = j + 1
print "dropped: " + str(float(dropped)/sum(word_vocab.values()))
num_to_word = du.invert_dict(word_to_num)
vocabsize = len(num_to_word) + 2 #One for line ending and one for unknown
################################
#Prepare data for training.
################################
X_train = []
Y_train = []
for i in alltxt:
txt = ''.join(l for l in i if ord(l) < 128)
temparr = [word_to_num["<s>"]] # Start the sentence
for j in nltk.word_tokenize(txt):
if j in word_to_num:
if __name__ == "__main__":
# Load the vocabulary
vocab = pd.read_table(
"data/lm/vocab.ptb.txt",
header=None,
sep="\s+",
index_col=0,
names=['count', 'freq'],
)
vocabsize = 2000
num_to_word = dict(enumerate(vocab.index[:vocabsize]))
num_to_word_embedding = load_vocab_embeddings()
word_to_num = utils.invert_dict(num_to_word)
# Load the training data
_, S_train = load_data_as_sentences('data/lm/ptb-train.txt', word_to_num)
in_word_index, out_word_index = convert_to_lm_dataset(S_train)
assert len(in_word_index) == len(out_word_index)
num_of_examples = len(in_word_index)
random.seed(31415)
np.random.seed(9265)
in_word_index, out_word_index = shuffle_training_data(
in_word_index, out_word_index)
startTime = time.time()
# Training should happen here
# Initialize parameters randomly
dropped = 0
for i in word_vocab.keys():
if word_vocab[i] < 5:
dropped += word_vocab[i]
else:
if i not in word_to_num:
word_to_num[i] = j
j = j + 1
word_to_num["<s>"] = j
word_to_num["</s>"] = j + 1
mx = j + 1
print "dropped: " + str(float(dropped) / sum(word_vocab.values()))
num_to_word = du.invert_dict(word_to_num)
vocabsize = len(num_to_word) + 2 #One for line ending and one for unknown
################################
#Prepare data for training.
################################
X_train = []
Y_train = []
for i in alltxt:
txt = ''.join(l for l in i if ord(l) < 128)
temparr = [word_to_num["<s>"]] # Start the sentence
for j in nltk.word_tokenize(txt):
if j in word_to_num:
temparr.append(word_to_num[j])