-
Notifications
You must be signed in to change notification settings - Fork 158
/
numerical_reasoning_arithmetic.py
109 lines (92 loc) · 3.24 KB
/
numerical_reasoning_arithmetic.py
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
# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# 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:https://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.
# TODO: Address all TODOs and remove all explanatory comments
"""TODO: Add a description here."""
import datasets
# TODO: Add BibTeX citation
# Find for instance the citation on arxiv or on the dataset repo/website
_CITATION = """\
"""
# TODO: Add description of the dataset here
# You can copy an official description
_DESCRIPTION = """\
Generated dataset for testing numerical reasoning
"""
# TODO: Add a link to an official homepage for the dataset here
_HOMEPAGE = ""
# TODO: Add the licence for the dataset here if you can find it
_LICENSE = ""
class NumericalReasoningArithmetic(datasets.GeneratorBasedBuilder):
"""TODO: Short description of my dataset."""
VERSION = datasets.Version("0.1.0")
BUILDER_CONFIGS = [
datasets.BuilderConfig(
name="{}".format(num),
version=datasets.Version("0.1.0"),
description="Task with {} as the first operand".format(num)) \
for num in range(0,100)
]
DEFAULT_CONFIG_NAME = None
def _info(self):
features = datasets.Features(
{
"x1": datasets.Value("int32"),
"x2": datasets.Value("int32"),
"y_mul": datasets.Value("int32"),
"y_add": datasets.Value("int32"),
}
)
return datasets.DatasetInfo(
description=_DESCRIPTION,
features=features,
homepage=_HOMEPAGE,
license=_LICENSE,
citation=_CITATION,
)
def _split_generators(self, dl_manager):
return [
datasets.SplitGenerator(
name=datasets.Split.VALIDATION,
gen_kwargs={
"split": "validation"
},
),
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"split": "test"
},
),
]
def _generate_examples(self, split):
x1 = int(self.config.name)
if split == "validation":
key = -1
for x in list(range(0,x1))+list(range(x1+1,100)):
for x2 in range(1,51):
key += 1
yield key, {
"x1": x,
"x2": x2,
"y_mul": x*x2,
"y_add": x+x2,
}
elif split == "test":
for key, x2 in enumerate(range(1,51)):
yield key, {
"x1": x1,
"x2": x2,
"y_mul": x1*x2,
"y_add": x1+x2,
}