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
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
|
# 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.
# ==============================================================================
"""Base utilities for loading datasets."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import collections
import csv
import os
from os import path
import random
import tempfile
import time
import numpy as np
from six.moves import urllib
from tensorflow.contrib.framework import deprecated
from tensorflow.python.platform import gfile
Dataset = collections.namedtuple('Dataset', ['data', 'target'])
Datasets = collections.namedtuple('Datasets', ['train', 'validation', 'test'])
def load_csv_with_header(filename,
target_dtype,
features_dtype,
target_column=-1):
"""Load dataset from CSV file with a header row."""
with gfile.Open(filename) as csv_file:
data_file = csv.reader(csv_file)
header = next(data_file)
n_samples = int(header[0])
n_features = int(header[1])
data = np.zeros((n_samples, n_features), dtype=features_dtype)
target = np.zeros((n_samples,), dtype=target_dtype)
for i, row in enumerate(data_file):
target[i] = np.asarray(row.pop(target_column), dtype=target_dtype)
data[i] = np.asarray(row, dtype=features_dtype)
return Dataset(data=data, target=target)
def load_csv_without_header(filename,
target_dtype,
features_dtype,
target_column=-1):
"""Load dataset from CSV file without a header row."""
with gfile.Open(filename) as csv_file:
data_file = csv.reader(csv_file)
data, target = [], []
for row in data_file:
target.append(row.pop(target_column))
data.append(np.asarray(row, dtype=features_dtype))
target = np.array(target, dtype=target_dtype)
data = np.array(data)
return Dataset(data=data, target=target)
def shrink_csv(filename, ratio):
"""Create a smaller dataset of only 1/ratio of original data."""
filename_small = filename.replace('.', '_small.')
with gfile.Open(filename_small, 'w') as csv_file_small:
writer = csv.writer(csv_file_small)
with gfile.Open(filename) as csv_file:
reader = csv.reader(csv_file)
i = 0
for row in reader:
if i % ratio == 0:
writer.writerow(row)
i += 1
def load_iris(data_path=None):
"""Load Iris dataset.
Args:
data_path: string, path to iris dataset (optional)
Returns:
Dataset object containing data in-memory.
"""
if data_path is None:
module_path = path.dirname(__file__)
data_path = path.join(module_path, 'data', 'iris.csv')
return load_csv_with_header(
data_path,
target_dtype=np.int,
features_dtype=np.float)
def load_boston(data_path=None):
"""Load Boston housing dataset.
Args:
data_path: string, path to boston dataset (optional)
Returns:
Dataset object containing data in-memory.
"""
if data_path is None:
module_path = path.dirname(__file__)
data_path = path.join(module_path, 'data', 'boston_house_prices.csv')
return load_csv_with_header(
data_path,
target_dtype=np.float,
features_dtype=np.float)
def retry(initial_delay,
max_delay,
factor=2.0,
jitter=0.25,
is_retriable=None):
"""Simple decorator for wrapping retriable functions.
Args:
initial_delay: the initial delay.
factor: each subsequent retry, the delay is multiplied by this value.
(must be >= 1).
jitter: to avoid lockstep, the returned delay is multiplied by a random
number between (1-jitter) and (1+jitter). To add a 20% jitter, set
jitter = 0.2. Must be < 1.
max_delay: the maximum delay allowed (actual max is
max_delay * (1 + jitter).
is_retriable: (optional) a function that takes an Exception as an argument
and returns true if retry should be applied.
"""
if factor < 1:
raise ValueError('factor must be >= 1; was %f' % (factor,))
if jitter >= 1:
raise ValueError('jitter must be < 1; was %f' % (jitter,))
# Generator to compute the individual delays
def delays():
delay = initial_delay
while delay <= max_delay:
yield delay * random.uniform(1 - jitter, 1 + jitter)
delay *= factor
def wrap(fn):
"""Wrapper function factory invoked by decorator magic."""
def wrapped_fn(*args, **kwargs):
"""The actual wrapper function that applies the retry logic."""
for delay in delays():
try:
return fn(*args, **kwargs)
except Exception as e: # pylint: disable=broad-except)
if is_retriable is None:
continue
if is_retriable(e):
time.sleep(delay)
else:
raise
return fn(*args, **kwargs)
return wrapped_fn
return wrap
_RETRIABLE_ERRNOS = {
110, # Connection timed out [socket.py]
}
def _is_retriable(e):
return isinstance(e, IOError) and e.errno in _RETRIABLE_ERRNOS
@retry(initial_delay=1.0, max_delay=16.0, is_retriable=_is_retriable)
def urlretrieve_with_retry(url, filename):
urllib.request.urlretrieve(url, filename)
def maybe_download(filename, work_directory, source_url):
"""Download the data from source url, unless it's already here.
Args:
filename: string, name of the file in the directory.
work_directory: string, path to working directory.
source_url: url to download from if file doesn't exist.
Returns:
Path to resulting file.
"""
if not gfile.Exists(work_directory):
gfile.MakeDirs(work_directory)
filepath = os.path.join(work_directory, filename)
if not gfile.Exists(filepath):
with tempfile.NamedTemporaryFile() as tmpfile:
temp_file_name = tmpfile.name
urlretrieve_with_retry(source_url, temp_file_name)
gfile.Copy(temp_file_name, filepath)
with gfile.GFile(filepath) as f:
size = f.size()
print('Successfully downloaded', filename, size, 'bytes.')
return filepath
|
