aboutsummaryrefslogtreecommitdiffhomepage
path: root/tensorflow/contrib/learn/python/learn/datasets/__init__.py
blob: 80a0af5f5259510068f046403b66a29b17871f50 (plain)
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
# 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.
# ==============================================================================

"""Module includes reference datasets and utilities to load datasets."""

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

import csv
from os import path

import numpy as np

from tensorflow.contrib.learn.python.learn.datasets import base
from tensorflow.contrib.learn.python.learn.datasets import mnist
from tensorflow.contrib.learn.python.learn.datasets import text_datasets

# Export load_iris and load_boston.
load_iris = base.load_iris
load_boston = base.load_boston

# List of all available datasets.
# Note, currently they may return different types.
DATASETS = {
    # Returns base.Dataset.
    'iris': base.load_iris,
    'boston': base.load_boston,
    # Returns base.Datasets (train/validation/test sets).
    'mnist': mnist.load_mnist,
    'dbpedia': text_datasets.load_dbpedia,
}


def load_dataset(name, size='small', test_with_fake_data=False):
  """Loads dataset by name.

  Args:
    name: Name of the dataset to load.
    size: Size of the dataset to load.
    test_with_fake_data: If true, load with fake dataset.

  Returns:
    Features and labels for given dataset. Can be numpy or iterator.

  Raises:
    ValueError: if `name` is not found.
  """
  if name not in DATASETS:
    raise ValueError('Name of dataset is not found: %s' % name)
  if name == 'dbpedia':
    return DATASETS[name](size, test_with_fake_data)
  else:
    return DATASETS[name]()