From 50ac1e8d8b48665c2bd1304792007a17e8bf4f3c Mon Sep 17 00:00:00 2001 From: Michael Kuchnik Date: Mon, 26 Feb 2024 15:50:08 +0000 Subject: [PATCH] Revert breaking metadata changes --- datasets/1.0/bigcode-the-stack/metadata.json | 17 ++++++++++++----- .../distribution_bad_contained_in/metadata.json | 11 ++--------- .../0.8/distribution_bad_type/metadata.json | 11 ++--------- .../0.8/distribution_missing_name/metadata.json | 11 ++--------- .../metadata.json | 11 ++--------- .../graphs/0.8/metadata_bad_type/metadata.json | 11 ++--------- .../metadata.json | 11 ++--------- .../graphs/0.8/mlfield_bad_source/metadata.json | 11 ++--------- .../graphs/0.8/mlfield_bad_type/metadata.json | 11 ++--------- .../mlfield_missing_property_name/metadata.json | 11 ++--------- .../0.8/mlfield_missing_source/metadata.json | 11 ++--------- .../metadata.json | 11 ++--------- .../metadata.json | 11 ++--------- .../0.8/recordset_wrong_join/metadata.json | 11 ++--------- 14 files changed, 38 insertions(+), 122 deletions(-) diff --git a/datasets/1.0/bigcode-the-stack/metadata.json b/datasets/1.0/bigcode-the-stack/metadata.json index ece9b34bb..c690ad550 100644 --- a/datasets/1.0/bigcode-the-stack/metadata.json +++ b/datasets/1.0/bigcode-the-stack/metadata.json @@ -47,18 +47,25 @@ "name": "bigcode-the-stack", "conformsTo": "http://mlcommons.org/croissant/1.0", "description": "The Stack contains over 6TB of permissively-licensed source code files covering 358 programming languages. The dataset was created as part of the BigCode Project, an open scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs). The Stack serves as a pre-training dataset for Code LLMs, i.e., code-generating AI systems which enable the synthesis of programs from natural language descriptions as well as other from code snippets.", + "citeAs": "@article{Kocetkov2022TheStack, title={The Stack: 3 TB of permissively licensed source code}, author={Kocetkov, Denis and Li, Raymond and Ben Allal, Loubna and Li, Jia and Mou,Chenghao and Mu\u00f1oz Ferrandis, Carlos and Jernite, Yacine and Mitchell, Margaret and Hughes, Sean and Wolf, Thomas and Bahdanau, Dzmitry and von Werra, Leandro and de Vries, Harm}, journal={Preprint}, year={2022} }", "creator": [ { - "@type": "Organization", - "name": "Harm de Vries" + "@type": "Person", + "name": "Harm de Vries", + "email": "harm.devries@servicenow.com" }, { - "@type": "Organization", - "name": "Leandro von Werra" + "@type": "Person", + "name": "Leandro von Werra", + "email": "leandro@huggingface.co" } ], - "citeAs": "@article{Kocetkov2022TheStack, title={The Stack: 3 TB of permissively licensed source code}, author={Kocetkov, Denis and Li, Raymond and Ben Allal, Loubna and Li, Jia and Mou,Chenghao and Mu\u00f1oz Ferrandis, Carlos and Jernite, Yacine and Mitchell, Margaret and Hughes, Sean and Wolf, Thomas and Bahdanau, Dzmitry and von Werra, Leandro and de Vries, Harm}, journal={Preprint}, year={2022} }", + "keywords": [ + "crowdsourced", + "expert-generated" + ], "license": "other", + "sameAs": "https://www.bigcode-project.org/docs/about/the-stack/", "sdLicense": "https://www.apache.org/licenses/LICENSE-2.0", "url": "https://huggingface.co/datasets/bigcode/the-stack", "distribution": [ diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_contained_in/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_contained_in/metadata.json index 2a0d998ae..73ccc7f84 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_contained_in/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_contained_in/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_type/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_type/metadata.json index 948b0de7e..43014951a 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_type/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_bad_type/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_name/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_name/metadata.json index f969f6959..2e85d5000 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_name/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_name/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_property_content_url/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_property_content_url/metadata.json index 7b8a38dca..05c395e90 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_property_content_url/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/distribution_missing_property_content_url/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_bad_type/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_bad_type/metadata.json index 6ac1fc674..fc225b1a2 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_bad_type/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_bad_type/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:WRONG_TYPE", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_missing_property_name/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_missing_property_name/metadata.json index 803aa6d42..f6e313627 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_missing_property_name/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/metadata_missing_property_name/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "description": "This is a description.", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_source/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_source/metadata.json index 901a06504..281b26082 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_source/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_source/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_type/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_type/metadata.json index 5b0abb3b4..6e3446e8e 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_type/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_bad_type/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_property_name/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_property_name/metadata.json index 2fe884eb3..e2278e7e5 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_property_name/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_property_name/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_source/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_source/metadata.json index bdf821269..d7147662f 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_source/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/mlfield_missing_source/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -40,8 +34,7 @@ "sc": "https://schema.org/", "separator": "ml:separator", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_context_for_datatype/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_context_for_datatype/metadata.json index 50981630c..6d04dacf2 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_context_for_datatype/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_context_for_datatype/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -16,15 +14,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -37,8 +31,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_property_name/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_property_name/metadata.json index 495e02a13..caef30d72 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_property_name/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_missing_property_name/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset", diff --git a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_wrong_join/metadata.json b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_wrong_join/metadata.json index 07f48f2c4..ca3bf6639 100644 --- a/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_wrong_join/metadata.json +++ b/python/mlcroissant/mlcroissant/_src/tests/graphs/0.8/recordset_wrong_join/metadata.json @@ -2,10 +2,8 @@ "@context": { "@language": "en", "@vocab": "https://schema.org/", - "citeAs": "cr:citeAs", "column": "ml:column", "conformsTo": "dct:conformsTo", - "cr": "http://mlcommons.org/croissant/", "data": { "@id": "ml:data", "@type": "@json" @@ -20,15 +18,11 @@ "extract": "ml:extract", "field": "ml:field", "fileProperty": "ml:fileProperty", - "fileObject": "cr:fileObject", - "fileSet": "cr:fileSet", "format": "ml:format", "includes": "ml:includes", "isEnumeration": "ml:isEnumeration", - "isLiveDataset": "cr:isLiveDataset", "jsonPath": "ml:jsonPath", - "key": "cr:key", - "md5": "cr:md5", + "ml": "http://mlcommons.org/schema/", "parentField": "ml:parentField", "path": "ml:path", "personalSensitiveInformation": "ml:personalSensitiveInformation", @@ -41,8 +35,7 @@ "separator": "ml:separator", "source": "ml:source", "subField": "ml:subField", - "transform": "ml:transform", - "ml": "http://mlcommons.org/schema/" + "transform": "ml:transform" }, "@type": "sc:Dataset", "name": "mydataset",