1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
|
# Copyright 2016 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.
"""Example of Estimator for DNN-based text classification with DBpedia data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import pandas
from sklearn import metrics
import tensorflow as tf
from tensorflow.contrib import learn
FLAGS = tf.app.flags.FLAGS
tf.app.flags.DEFINE_bool('test_with_fake_data', False,
'Test the example code with fake data.')
MAX_DOCUMENT_LENGTH = 10
EMBEDDING_SIZE = 50
n_words = 0
def bag_of_words_model(x, y):
"""A bag-of-words model. Note it disregards the word order in the text."""
target = tf.one_hot(y, 15, 1, 0)
word_vectors = learn.ops.categorical_variable(x, n_classes=n_words,
embedding_size=EMBEDDING_SIZE, name='words')
features = tf.reduce_max(word_vectors, reduction_indices=1)
prediction, loss = learn.models.logistic_regression(features, target)
train_op = tf.contrib.layers.optimize_loss(
loss, tf.contrib.framework.get_global_step(),
optimizer='Adam', learning_rate=0.01)
return {'class': tf.argmax(prediction, 1), 'prob': prediction}, loss, train_op
def rnn_model(x, y):
"""Recurrent neural network model to predict from sequence of words
to a class."""
# Convert indexes of words into embeddings.
# This creates embeddings matrix of [n_words, EMBEDDING_SIZE] and then
# maps word indexes of the sequence into [batch_size, sequence_length,
# EMBEDDING_SIZE].
word_vectors = learn.ops.categorical_variable(x, n_classes=n_words,
embedding_size=EMBEDDING_SIZE, name='words')
# Split into list of embedding per word, while removing doc length dim.
# word_list results to be a list of tensors [batch_size, EMBEDDING_SIZE].
word_list = tf.unpack(word_vectors, axis=1)
# Create a Gated Recurrent Unit cell with hidden size of EMBEDDING_SIZE.
cell = tf.nn.rnn_cell.GRUCell(EMBEDDING_SIZE)
# Create an unrolled Recurrent Neural Networks to length of
# MAX_DOCUMENT_LENGTH and passes word_list as inputs for each unit.
_, encoding = tf.nn.rnn(cell, word_list, dtype=tf.float32)
# Given encoding of RNN, take encoding of last step (e.g hidden size of the
# neural network of last step) and pass it as features for logistic
# regression over output classes.
target = tf.one_hot(y, 15, 1, 0)
prediction, loss = learn.models.logistic_regression(encoding, target)
# Create a training op.
train_op = tf.contrib.layers.optimize_loss(
loss, tf.contrib.framework.get_global_step(),
optimizer='Adam', learning_rate=0.01)
return {'class': tf.argmax(prediction, 1), 'prob': prediction}, loss, train_op
def main(unused_argv):
global n_words
# Prepare training and testing data
dbpedia = learn.datasets.load_dataset(
'dbpedia', test_with_fake_data=FLAGS.test_with_fake_data)
x_train = pandas.DataFrame(dbpedia.train.data)[1]
y_train = pandas.Series(dbpedia.train.target)
x_test = pandas.DataFrame(dbpedia.test.data)[1]
y_test = pandas.Series(dbpedia.test.target)
# Process vocabulary
vocab_processor = learn.preprocessing.VocabularyProcessor(MAX_DOCUMENT_LENGTH)
x_train = np.array(list(vocab_processor.fit_transform(x_train)))
x_test = np.array(list(vocab_processor.transform(x_test)))
n_words = len(vocab_processor.vocabulary_)
print('Total words: %d' % n_words)
# Build model
classifier = learn.Estimator(model_fn=bag_of_words_model)
# Train and predict
classifier.fit(x_train, y_train, steps=100)
y_predicted = classifier.predict(x_test)
score = metrics.accuracy_score(y_test, y_predicted['class'])
print('Accuracy: {0:f}'.format(score))
if __name__ == '__main__':
tf.app.run()
|