User:Alexander Roidl/words2vec

From XPUB & Lens-Based wiki

Part of algologs workshop ~ Trained on my reader.

Graph

Screen Shot 2018-03-24 at 11.00.52.png


Code

# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import collections
import math
import os
import random
import zipfile
import codecs

import numpy as np
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf

from nltk.tokenize import word_tokenize # Algolit

# Custom Algolit addition
def export(fn, data):
	outputdir = 'output/'
	if not os.path.exists(outputdir):
			os.makedirs(outputdir)
	with open(outputdir+fn,'w+') as output:
		output.write(str(data))
		print('*exported '+fn+'*')

# Step 1: Download the data.
# url = 'http://mattmahoney.net/dc/'
# def maybe_download(filename, expected_bytes):
#   """Download a file if not present, and make sure it's the right size."""
#   if not os.path.exists(filename):
#     filename, _ = urllib.request.urlretrieve(url + filename, filename)
#   statinfo = os.stat(filename)
#   if statinfo.st_size == expected_bytes:
#     print('Found and verified', filename)
#   else:
#     print(statinfo.st_size)
#     raise Exception(
#         'Failed to verify ' + filename + '. Can you get to it with a browser?')
#   return filename

# filename = maybe_download('text8.zip', 31344016)

# # Read the data into a list of strings.
# def read_data(filename):
#   """Extract the first file enclosed in a zip file as a list of words"""
#   with zipfile.ZipFile(filename) as f:
#     data = tf.compat.as_str(f.read(f.namelist()[0])).split()
#   return data

# words = read_data(filename)
# print('Data size', len(words))

# CUSTOM Algolit addition
trainingset = 'input/text_stripped.txt'
def read_input_text(trainingset):
	words = []
	with open(trainingset, 'r') as source:
		lines = source.readlines()
		for line in lines:
			#line = line.decode('utf8')
			wordlist = word_tokenize(line)
			for word in wordlist:
				words.append(word)
	return words

words = read_input_text(trainingset)

# Algolit logging
export('wordlist-'+str(len(words))+'.txt', words)


# Step 2: Build the dictionary and replace rare words with UNK token.
vocabulary_size = 5000

def build_dataset(words):
	count = [['UNK', -1]]
	count.extend(collections.Counter(words).most_common(vocabulary_size - 1))
	dictionary = dict()
	for word, _ in count:
		dictionary[word] = len(dictionary)
	data = list()

	# Custom Algolit addition (logging disregarded words)
	disregarded = list()

	unk_count = 0
	for word in words:
		if word in dictionary:
			index = dictionary[word]
		else:
			index = 0  # dictionary['UNK']
			unk_count += 1

			# Custom Algolit addition
			disregarded.append(word)

		data.append(index)
	count[0][1] = unk_count
	reverse_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
	return data, count, dictionary, reverse_dictionary, disregarded

data, count, dictionary, reverse_dictionary, disregarded = build_dataset(words)
print('Most common words (+UNK)', count[:5])
print('Sample data', data[:10], [reverse_dictionary[i] for i in data[:10]])

# Algolit logging
export('dictionary-'+str(len(reverse_dictionary))+'.txt', reverse_dictionary)
export('counted.txt', collections.Counter(words))
export('disregarded-'+str(len(disregarded))+'.txt', disregarded)
export('data-'+str(len(data))+'.txt', data)

# Custom Algolit addition: translate the data object back to words
reversed_input = []
for index in data:
	word = reverse_dictionary[index]
	reversed_input.append(word)
reversed_input_fulltext = ' '.join(reversed_input).encode('utf-8')
export('reversed-input-'+str(len(reversed_input))+'.txt', reversed_input_fulltext)


del words  # Hint to reduce memory.
data_index = 0


# Step 3: Function to generate a training batch for the skip-gram model.
def generate_batch(batch_size, num_skips, skip_window):
	global data_index
	assert batch_size % num_skips == 0
	assert num_skips <= 2 * skip_window
	batch = np.ndarray(shape=(batch_size), dtype=np.int32)
	labels = np.ndarray(shape=(batch_size, 1), dtype=np.int32)
	span = 2 * skip_window + 1  # [ skip_window target skip_window ]
	buffer = collections.deque(maxlen=span)
	for _ in range(span):
		buffer.append(data[data_index])
		data_index = (data_index + 1) % len(data)
	for i in range(batch_size // num_skips):
		target = skip_window  # target label at the center of the buffer
		targets_to_avoid = [skip_window]
		for j in range(num_skips):
			while target in targets_to_avoid:
				target = random.randint(0, span - 1)
			targets_to_avoid.append(target)
			batch[i * num_skips + j] = buffer[skip_window]
			labels[i * num_skips + j, 0] = buffer[target]
		buffer.append(data[data_index])
		data_index = (data_index + 1) % len(data)
	return batch, labels

batch, labels = generate_batch(batch_size=8, num_skips=2, skip_window=1)

# for i in range(8):
	# print(batch[i], reverse_dictionary[batch[i]],
				# '->', labels[i, 0], reverse_dictionary[labels[i, 0]])


# Step 4: Build and train a skip-gram model.

batch_size = 128
embedding_size = 128  # Dimension of the embedding vector.
skip_window = 1       # How many words to consider left and right.
num_skips = 2         # How many times to reuse an input to generate a label.

# We pick a random validation set to sample nearest neighbors. Here we limit the
# validation samples to the words that have a low numeric ID, which by
# construction are also the most frequent.
valid_size = 16     # Random set of words to evaluate similarity on.
valid_window = 100  # Only pick dev samples in the head of the distribution.
valid_examples = np.random.choice(valid_window, valid_size, replace=False)
num_sampled = 64    # Number of negative examples to sample.

graph = tf.Graph()

with graph.as_default():

	# Input data.
	train_inputs = tf.placeholder(tf.int32, shape=[batch_size])
	train_labels = tf.placeholder(tf.int32, shape=[batch_size, 1])
	valid_dataset = tf.constant(valid_examples, dtype=tf.int32)

	# Ops and variables pinned to the CPU because of missing GPU implementation
	with tf.device('/cpu:0'):
		# Look up embeddings for inputs.
		embeddings = tf.Variable(
				tf.random_uniform([vocabulary_size, embedding_size], -1.0, 1.0))
		embed = tf.nn.embedding_lookup(embeddings, train_inputs)

		# Algolit logging
		export('big-random-matrix.txt', embeddings)

		# Construct the variables for the NCE loss
		nce_weights = tf.Variable(
				tf.truncated_normal([vocabulary_size, embedding_size],
														stddev=1.0 / math.sqrt(embedding_size)))
		nce_biases = tf.Variable(tf.zeros([vocabulary_size]))

	# Compute the average NCE loss for the batch.
	# tf.nce_loss automatically draws a new sample of the negative labels each
	# time we evaluate the loss.
	loss = tf.reduce_mean(
			tf.nn.nce_loss(weights=nce_weights,
										 biases=nce_biases,
										 labels=train_labels,
										 inputs=embed,
										 num_sampled=num_sampled,
										 num_classes=vocabulary_size))

	# Construct the SGD optimizer using a learning rate of 1.0.
	optimizer = tf.train.GradientDescentOptimizer(1.0).minimize(loss)

	# Compute the cosine similarity between minibatch examples and all embeddings.
	norm = tf.sqrt(tf.reduce_sum(tf.square(embeddings), 1, keep_dims=True))
	normalized_embeddings = embeddings / norm
	valid_embeddings = tf.nn.embedding_lookup(
			normalized_embeddings, valid_dataset)
	similarity = tf.matmul(
			valid_embeddings, normalized_embeddings, transpose_b=True)

	# Add variable initializer.
	init = tf.global_variables_initializer()

# Step 5: Begin training.
num_steps = 100001

with tf.Session(graph=graph) as session:
	# We must initialize all variables before we use them.
	init.run()
	print("Initialized")

	average_loss = 0
	for step in xrange(num_steps):
		batch_inputs, batch_labels = generate_batch(
				batch_size, num_skips, skip_window)
		feed_dict = {train_inputs: batch_inputs, train_labels: batch_labels}

		# We perform one update step by evaluating the optimizer op (including it
		# in the list of returned values for session.run()
		_, loss_val = session.run([optimizer, loss], feed_dict=feed_dict)
		average_loss += loss_val

		if step % 2000 == 0:
			if step > 0:
				average_loss /= 2000
			# The average loss is an estimate of the loss over the last 2000 batches.
			print("Average loss at step ", step, ": ", average_loss)
			average_loss = 0

		# Note that this is expensive (~20% slowdown if computed every 500 steps)
		if step % 10000 == 0:
			sim = similarity.eval()

			# CUSTOM Algolit addition
			with codecs.open('output/logfile.txt', 'a+', 'utf-8') as destination:
				destination.write('step: '+str(step)+'\n')
				destination.write('loss value: '+str(average_loss)+'\n')

				for i in xrange(valid_size):
					valid_word = reverse_dictionary[valid_examples[i]]
					top_k = 8  # number of nearest neighbors
					nearest = (-sim[i, :]).argsort()[1:top_k + 1]
					log_str = "Nearest to %s:" % valid_word
					for k in xrange(top_k):
						close_word = reverse_dictionary[nearest[k]]
						log_str = "%s %s," % (log_str, close_word)

					# CUSTOM Algolit addition
					destination.write(log_str+'\n')

					print(log_str)

				# CUSTOM Algolit addition
				destination.write('\n\n')

	final_embeddings = normalized_embeddings.eval()

	# Algolit logging
	export('final_embeddings-matrix.txt', final_embeddings)


# Step 6: Visualize the embeddings.

def plot_with_labels(low_dim_embs, labels, filename='output/graph.eps', format='eps'):
	assert low_dim_embs.shape[0] >= len(labels), "More labels than embeddings"
	plt.figure(figsize=(18, 18))  # in inches
	ax = plt.axes(frameon=False)
	ax.get_xaxis().tick_bottom()
	ax.axes.get_xaxis().set_visible(False)
	ax.axes.get_yaxis().set_visible(False)
	for i, label in enumerate(labels):
		x, y = low_dim_embs[i, :]
		plt.scatter(x, y)
		plt.annotate(label,
			xy=(x, y),
			xytext=(5, 2),
			textcoords='offset points',
			ha='right',
			va='bottom')

	plt.savefig(filename)

try:
	from sklearn.manifold import TSNE
	import matplotlib.pyplot as plt

	tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
	plot_only = 500
	low_dim_embs = tsne.fit_transform(final_embeddings[:plot_only, :])
	labels = [reverse_dictionary[i] for i in xrange(plot_only)]
	plot_with_labels(low_dim_embs, labels)

except ImportError:
	print("Please install sklearn, matplotlib, and scipy to visualize embeddings.")
Retrieved from "https://pzwiki.wdka.nl/mw-mediadesign/index.php?title=User:Alexander_Roidl/words2vec&oldid=121523"