Skip to content

Catch up the v1.1 dataset files to match the latest context in rdf.py #953

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
SujataSaurabh wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Catch up the v1.1 dataset files to match the latest context in rdf.py #953

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions datasets/1.1/audio_test/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,8 @@
"regex": "cr:regex",
"repeated": "cr:repeated",
"replace": "cr:replace",
"sc": "https://schema.org/",
"samplingRate": "cr:samplingRate",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
Expand Down Expand Up @@ -76,10 +76,10 @@
"fileSet": {
"@id": "files"
},
"samplingRate": 22050,
"extract": {
"fileProperty": "content"
},
"samplingRate": 22050
}
}
}
]
Expand Down
65 changes: 33 additions & 32 deletions datasets/1.1/huggingface-baratilab-flow3d/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,6 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"arrayShape": "cr:arrayShape",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
Expand All @@ -12,8 +11,6 @@
"@id": "cr:data",
"@type": "@json"
},
"dataBiases": "cr:dataBiases",
"dataCollection": "cr:dataCollection",
"dataType": {
"@id": "cr:dataType",
"@type": "@vocab"
Expand All @@ -30,26 +27,46 @@
"fileSet": "cr:fileSet",
"format": "cr:format",
"includes": "cr:includes",
"isArray": "cr:isArray",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "cr:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"parentField": "cr:parentField",
"path": "cr:path",
"personalSensitiveInformation": "cr:personalSensitiveInformation",
"recordSet": "cr:recordSet",
"references": "cr:references",
"regex": "cr:regex",
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
"transform": "cr:transform"
"transform": "cr:transform",
"arrayShape": "cr:arrayShape",
"dataBiases": "cr:dataBiases",
"dataCollection": "cr:dataCollection",
"isArray": "cr:isArray",
"personalSensitiveInformation": "cr:personalSensitiveInformation"
},
"@type": "sc:Dataset",
"name": "Flow3D-V0-Ti-6Al-4V_fast_test",
"description": "baratilab/Flow3D-V0-Ti-6Al-4V_fast_test dataset hosted on Hugging Face and contributed by the HF Datasets community",
"conformsTo": "http://mlcommons.org/croissant/1.1",
"keywords": [
"1K - 10K",
"parquet",
"Image",
"Tabular",
"Text",
"Datasets",
"pandas",
"Croissant",
"Polars",
"\ud83c\uddfa\ud83c\uddf8 Region: US"
],
"url": "https://huggingface.co/datasets/baratilab/Flow3D-V0-Ti-6Al-4V_fast_test",
"distribution": [
{
"@type": "cr:FileObject",
Expand All @@ -75,13 +92,13 @@
"recordSet": [
{
"@type": "cr:RecordSet",
"@id": "0_0100_01.4_1.0E-4_1.0E-2_splits",
"name": "0_0100_01.4_1.0E-4_1.0E-2_splits",
"description": "Splits for the 0_0100_01.4_1.0E-4_1.0E-2 config.",
"dataType": "cr:Split",
"key": {
"@id": "0_0100_01.4_1.0E-4_1.0E-2_splits/split_name"
},
"@id": "0_0100_01.4_1.0E-4_1.0E-2_splits",
"name": "0_0100_01.4_1.0E-4_1.0E-2_splits",
"description": "Splits for the 0_0100_01.4_1.0E-4_1.0E-2 config.",
"field": [
{
"@type": "cr:Field",
Expand All @@ -107,6 +124,11 @@
"name": "0_0100_01.4_1.0E-4_1.0E-2/split",
"description": "Split to which the example belongs to.",
"dataType": "sc:Text",
"references": {
"field": {
"@id": "0_0100_01.4_1.0E-4_1.0E-2_splits/split_name"
}
},
"source": {
"fileSet": {
"@id": "parquet-files-for-config-0_0100_01.4_1.0E-4_1.0E-2"
Expand All @@ -117,21 +139,16 @@
"transform": {
"regex": "0_0100_01\\.4_1\\.0E\\-4_1\\.0E\\-2/(?:partial-)?(simulation)/.+parquet$"
}
},
"references": {
"field": {
"@id": "0_0100_01.4_1.0E-4_1.0E-2_splits/split_name"
}
}
},
{
"@type": "cr:Field",
"@id": "0_0100_01.4_1.0E-4_1.0E-2/pressure",
"name": "0_0100_01.4_1.0E-4_1.0E-2/pressure",
"description": "Column 'pressure' from the Hugging Face parquet file.",
"arrayShape": "-1,-1,-1",
"dataType": "sc:Float",
"isArray": true,
"arrayShape": "-1,-1,-1",
Copy link
Contributor

@benjelloun benjelloun Oct 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Nit: It makes more sense to keep the arrayShape property right after isArray.

"source": {
"fileSet": {
"@id": "parquet-files-for-config-0_0100_01.4_1.0E-4_1.0E-2"
Expand Down Expand Up @@ -188,21 +205,5 @@
}
]
}
],
"conformsTo": "http://mlcommons.org/croissant/1.1",
"name": "Flow3D-V0-Ti-6Al-4V_fast_test",
"description": "baratilab/Flow3D-V0-Ti-6Al-4V_fast_test dataset hosted on Hugging Face and contributed by the HF Datasets community",
"keywords": [
"1K - 10K",
"parquet",
"Image",
"Tabular",
"Text",
"Datasets",
"pandas",
"Croissant",
"Polars",
"🇺🇸 Region: US"
],
"url": "https://huggingface.co/datasets/baratilab/Flow3D-V0-Ti-6Al-4V_fast_test"
]
}
57 changes: 31 additions & 26 deletions datasets/1.1/huggingface-manud-dfl_video_classification/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,37 +2,37 @@
"@context": {
"@language": "en",
"@vocab": "https://schema.org/",
"arrayShape": "cr:arrayShape",
"citeAs": "cr:citeAs",
"column": "cr:column",
"conformsTo": "dct:conformsTo",
"cr": "http://mlcommons.org/croissant/",
"rai": "http://mlcommons.org/croissant/RAI/",
"data": {
"@id": "cr:data",
"@type": "@json"
},
"dataBiases": "cr:dataBiases",
"dataCollection": "cr:dataCollection",
"dataType": {
"@id": "cr:dataType",
"@type": "@vocab"
},
"dct": "http://purl.org/dc/terms/",
"examples": {
"@id": "cr:examples",
"@type": "@json"
},
"extract": "cr:extract",
"field": "cr:field",
"fileProperty": "cr:fileProperty",
"fileObject": "cr:fileObject",
"fileSet": "cr:fileSet",
"format": "cr:format",
"includes": "cr:includes",
"isArray": "cr:isArray",
"isLiveDataset": "cr:isLiveDataset",
"jsonPath": "cr:jsonPath",
"key": "cr:key",
"md5": "cr:md5",
"parentField": "cr:parentField",
"path": "cr:path",
"personalSensitiveInformation": "cr:personalSensitiveInformation",
"recordSet": "cr:recordSet",
"references": "cr:references",
"regex": "cr:regex",
Expand All @@ -43,9 +43,25 @@
"separator": "cr:separator",
"source": "cr:source",
"subField": "cr:subField",
"transform": "cr:transform"
"transform": "cr:transform",
"arrayShape": "cr:arrayShape",
"dataBiases": "cr:dataBiases",
"dataCollection": "cr:dataCollection",
"isArray": "cr:isArray",
"personalSensitiveInformation": "cr:personalSensitiveInformation"
},
"@type": "sc:Dataset",
"name": "DFL_video_classification",
"description": "Simplified version for the mlcroissant repo. ManuD/DFL_video_classification dataset hosted on Hugging Face and contributed by the HF Datasets community",
"conformsTo": "http://mlcommons.org/croissant/1.1",
"keywords": [
"1K - 10K",
"Video",
"Datasets",
"Croissant",
"\ud83c\uddfa\ud83c\uddf8 Region: US"
],
"url": "https://huggingface.co/datasets/ManuD/DFL_video_classification",
"distribution": [
{
"@type": "cr:FileObject",
Expand All @@ -69,13 +85,13 @@
"recordSet": [
{
"@type": "cr:RecordSet",
"@id": "default_splits",
"name": "default_splits",
"description": "Splits for the default config.",
"dataType": "cr:Split",
"key": {
"@id": "default_splits/split_name"
},
"@id": "default_splits",
"name": "default_splits",
"description": "Splits for the default config.",
"field": [
{
"@type": "cr:Field",
Expand All @@ -96,6 +112,11 @@
"@type": "cr:Field",
"@id": "default/split",
"dataType": "sc:Text",
"references": {
"field": {
"@id": "default_splits/split_name"
}
},
"source": {
"fileSet": {
"@id": "parquet-files-for-config-default"
Expand All @@ -106,11 +127,6 @@
"transform": {
"regex": "default/(?:partial-)?(validation)/.+parquet$"
}
},
"references": {
"field": {
"@id": "default_splits/split_name"
}
}
},
{
Expand Down Expand Up @@ -141,16 +157,5 @@
}
]
}
],
"conformsTo": "http://mlcommons.org/croissant/1.1",
"name": "DFL_video_classification",
"description": "Simplified version for the mlcroissant repo. ManuD/DFL_video_classification dataset hosted on Hugging Face and contributed by the HF Datasets community",
"keywords": [
"1K - 10K",
"Video",
"Datasets",
"Croissant",
"🇺🇸 Region: US"
],
"url": "https://huggingface.co/datasets/ManuD/DFL_video_classification"
]
}
1 change: 1 addition & 0 deletions datasets/1.1/huggingface-mnist-from-main-branch/metadata.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,7 @@
"regex": "cr:regex",
"repeated": "cr:repeated",
"replace": "cr:replace",
"samplingRate": "cr:samplingRate",
"sc": "https://schema.org/",
"separator": "cr:separator",
"source": "cr:source",
Expand Down
Loading