Spaces:
Runtime error
Runtime error
File size: 4,052 Bytes
e4f9cbe |
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 |
"""Tests for the pandas source."""
import os
import pathlib
# mypy: disable-error-code="attr-defined"
from datasets import Dataset, Features, Sequence, Value
from ...schema import schema
from .huggingface_source import HF_SPLIT_COLUMN, HuggingFaceDataset
from .source import SourceSchema
def test_hf(tmp_path: pathlib.Path) -> None:
dataset = Dataset.from_list([{'x': 1, 'y': 'ten'}, {'x': 2, 'y': 'twenty'}])
dataset_name = os.path.join(tmp_path, 'hf-test-dataset')
dataset.save_to_disk(dataset_name)
source = HuggingFaceDataset(dataset_name=dataset_name, load_from_disk=True)
items = source.process()
source.setup()
source_schema = source.source_schema()
assert source_schema == SourceSchema(
fields=schema({
HF_SPLIT_COLUMN: 'string',
'x': 'int64',
'y': 'string'
}).fields, num_items=2)
items = list(source.process())
assert items == [{
HF_SPLIT_COLUMN: 'default',
'x': 1,
'y': 'ten'
}, {
HF_SPLIT_COLUMN: 'default',
'x': 2,
'y': 'twenty'
}]
def test_hf_sequence(tmp_path: pathlib.Path) -> None:
dataset = Dataset.from_list([{
'scalar': 1,
'seq': [1, 0],
'seq_dict': {
'x': [1, 2, 3],
'y': ['four', 'five', 'six']
}
}, {
'scalar': 2,
'seq': [2, 0],
'seq_dict': {
'x': [10, 20, 30],
'y': ['forty', 'fifty', 'sixty']
}
}],
features=Features({
'scalar': Value(dtype='int64'),
'seq': Sequence(feature=Value(dtype='int64')),
'seq_dict': Sequence(feature={
'x': Value(dtype='int64'),
'y': Value(dtype='string')
})
}))
dataset_name = os.path.join(tmp_path, 'hf-test-dataset')
dataset.save_to_disk(dataset_name)
source = HuggingFaceDataset(dataset_name=dataset_name, load_from_disk=True)
items = source.process()
source.setup()
source_schema = source.source_schema()
assert source_schema == SourceSchema(
fields=schema({
HF_SPLIT_COLUMN: 'string',
'scalar': 'int64',
'seq': ['int64'],
'seq_dict': {
'x': ['int64'],
'y': ['string'],
},
}).fields,
num_items=2)
items = list(source.process())
assert items == [{
HF_SPLIT_COLUMN: 'default',
'scalar': 1,
'seq': [1, 0],
'seq_dict': {
'x': [1, 2, 3],
'y': ['four', 'five', 'six']
}
}, {
HF_SPLIT_COLUMN: 'default',
'scalar': 2,
'seq': [2, 0],
'seq_dict': {
'x': [10, 20, 30],
'y': ['forty', 'fifty', 'sixty']
}
}]
def test_hf_list(tmp_path: pathlib.Path) -> None:
dataset = Dataset.from_list([{
'scalar': 1,
'list': [{
'x': 1,
'y': 'two'
}]
}, {
'scalar': 2,
'list': [{
'x': 3,
'y': 'four'
}]
}],
features=Features({
'scalar': Value(dtype='int64'),
'list': [{
'x': Value(dtype='int64'),
'y': Value(dtype='string')
}]
}))
dataset_name = os.path.join(tmp_path, 'hf-test-dataset')
dataset.save_to_disk(dataset_name)
source = HuggingFaceDataset(dataset_name=dataset_name, load_from_disk=True)
items = source.process()
source.setup()
source_schema = source.source_schema()
assert source_schema == SourceSchema(
fields=schema({
HF_SPLIT_COLUMN: 'string',
'scalar': 'int64',
'list': [{
'x': 'int64',
'y': 'string',
}],
}).fields,
num_items=2)
items = list(source.process())
assert items == [{
HF_SPLIT_COLUMN: 'default',
'scalar': 1,
'list': [{
'x': 1,
'y': 'two'
}]
}, {
HF_SPLIT_COLUMN: 'default',
'scalar': 2,
'list': [{
'x': 3,
'y': 'four'
}]
}]
|