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
|
# Copyright 2015-present The Scikit Flow 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.
"""
This is an example of using recurrent neural networks over characters
for DBpedia dataset to predict class from description of an entity.
This model is similar to one described in this paper:
"Character-level Convolutional Networks for Text Classification"
http://arxiv.org/abs/1509.01626
and is somewhat alternative to the Lua code from here:
https://github.com/zhangxiangxiao/Crepe
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
from sklearn import metrics
import pandas
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 = 100
HIDDEN_SIZE = 20
def char_rnn_model(x, y):
"""Character level recurrent neural network model to predict classes."""
y = tf.one_hot(y, 15, 1, 0)
byte_list = learn.ops.one_hot_matrix(x, 256)
byte_list = tf.unpack(byte_list, axis=1)
cell = tf.nn.rnn_cell.GRUCell(HIDDEN_SIZE)
_, encoding = tf.nn.rnn(cell, byte_list, dtype=tf.float32)
prediction, loss = learn.models.logistic_regression(encoding, y)
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):
# 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
char_processor = learn.preprocessing.ByteProcessor(MAX_DOCUMENT_LENGTH)
x_train = np.array(list(char_processor.fit_transform(x_train)))
x_test = np.array(list(char_processor.transform(x_test)))
# Build model
classifier = learn.Estimator(model_fn=char_rnn_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()
|
