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
|
# 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.
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 skflow
### Training data
# Downloads, unpacks and reads DBpedia dataset.
dbpedia = skflow.datasets.load_dataset('dbpedia')
X_train, y_train = pandas.DataFrame(dbpedia.train.data)[1], pandas.Series(dbpedia.train.target)
X_test, y_test = pandas.DataFrame(dbpedia.test.data)[1], pandas.Series(dbpedia.test.target)
### Process vocabulary
MAX_DOCUMENT_LENGTH = 10
vocab_processor = skflow.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)
### Models
EMBEDDING_SIZE = 50
# Customized function to transform batched X into embeddings
def input_op_fn(X):
# 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 = skflow.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 = skflow.ops.split_squeeze(1, MAX_DOCUMENT_LENGTH, word_vectors)
return word_list
# Single direction GRU with a single layer
classifier = skflow.TensorFlowRNNClassifier(rnn_size=EMBEDDING_SIZE,
n_classes=15, cell_type='gru', input_op_fn=input_op_fn,
num_layers=1, bidirectional=False, sequence_length=None,
steps=1000, optimizer='Adam', learning_rate=0.01, continue_training=True)
# Continuously train for 1000 steps & predict on test set.
while True:
classifier.fit(X_train, y_train, logdir='/tmp/tf_examples/word_rnn')
score = metrics.accuracy_score(y_test, classifier.predict(X_test))
print('Accuracy: {0:f}'.format(score))
|
