See data set on Wiktionary
{
"forms": [
{
"form": "data sets",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "data set (plural data sets)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"senses": [
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Computing",
"orig": "en:Computing",
"parents": [
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "29 35 37",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "30 33 37",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 41 35",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"A file of related records on a computer-readable medium such as disk, especially one on a mainframe computer."
],
"id": "en-data_set-en-noun-tidJ72Oa",
"links": [
[
"computing",
"computing#Noun"
],
[
"file",
"file"
],
[
"related",
"related"
],
[
"record",
"record"
],
[
"computer",
"computer"
],
[
"readable",
"readable"
],
[
"medium",
"medium"
],
[
"disk",
"disk"
],
[
"mainframe",
"mainframe"
]
],
"raw_glosses": [
"(computing) A file of related records on a computer-readable medium such as disk, especially one on a mainframe computer."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
],
"translations": [
{
"_dis1": "88 6 6",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "file of related records",
"word": "數據集"
},
{
"_dis1": "88 6 6",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "shùjùjí",
"sense": "file of related records",
"word": "数据集"
},
{
"_dis1": "88 6 6",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "file of related records",
"word": "資料集"
},
{
"_dis1": "88 6 6",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zīliàojí",
"sense": "file of related records",
"word": "资料集"
},
{
"_dis1": "88 6 6",
"code": "fi",
"lang": "Finnish",
"sense": "file of related records",
"word": "datasetti"
},
{
"_dis1": "88 6 6",
"code": "fi",
"lang": "Finnish",
"sense": "file of related records",
"word": "tietoaineisto"
},
{
"_dis1": "88 6 6",
"code": "fr",
"lang": "French",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "jeu de données"
},
{
"_dis1": "88 6 6",
"code": "de",
"lang": "German",
"sense": "file of related records",
"tags": [
"neuter"
],
"word": "Dataset"
},
{
"_dis1": "88 6 6",
"code": "mi",
"lang": "Maori",
"sense": "file of related records",
"word": "huinga raraunga"
},
{
"_dis1": "88 6 6",
"code": "ru",
"lang": "Russian",
"roman": "nabór dánnyx",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "набо́р да́нных"
},
{
"_dis1": "88 6 6",
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "skup podataka"
},
{
"_dis1": "88 6 6",
"code": "es",
"lang": "Spanish",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "conjunto de datos"
},
{
"_dis1": "88 6 6",
"code": "sv",
"lang": "Swedish",
"sense": "file of related records",
"tags": [
"neuter"
],
"word": "dataset"
},
{
"_dis1": "88 6 6",
"code": "tr",
"lang": "Turkish",
"sense": "file of related records",
"word": "veri grubu"
}
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Telecommunications",
"orig": "en:Telecommunications",
"parents": [
"Communication",
"Technology",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "29 35 37",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "25 42 33",
"kind": "other",
"name": "Entries with translation boxes",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "30 33 37",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 41 35",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 47 29",
"kind": "other",
"name": "Terms with Czech translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "20 55 25",
"kind": "other",
"name": "Terms with Danish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 49 28",
"kind": "other",
"name": "Terms with Finnish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 47 29",
"kind": "other",
"name": "Terms with French translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 47 29",
"kind": "other",
"name": "Terms with German translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "28 49 23",
"kind": "other",
"name": "Terms with Hungarian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 48 29",
"kind": "other",
"name": "Terms with Italian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "25 49 26",
"kind": "other",
"name": "Terms with Mandarin translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 49 28",
"kind": "other",
"name": "Terms with Maori translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 49 28",
"kind": "other",
"name": "Terms with Portuguese translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 48 29",
"kind": "other",
"name": "Terms with Russian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 49 28",
"kind": "other",
"name": "Terms with Serbo-Croatian translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "23 49 28",
"kind": "other",
"name": "Terms with Spanish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 50 28",
"kind": "other",
"name": "Terms with Swedish translations",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "22 50 28",
"kind": "other",
"name": "Terms with Turkish translations",
"parents": [],
"source": "w+disamb"
}
],
"glosses": [
"A modem that connects a device such as a teletype to an ordinary telephone."
],
"id": "en-data_set-en-noun-9cnULL2T",
"links": [
[
"telecommunications",
"telecommunications"
],
[
"modem",
"modem"
]
],
"raw_glosses": [
"(telecommunications, dated) A modem that connects a device such as a teletype to an ordinary telephone."
],
"tags": [
"dated"
],
"topics": [
"communications",
"electrical-engineering",
"engineering",
"natural-sciences",
"physical-sciences",
"telecommunications"
]
},
{
"categories": [
{
"kind": "topical",
"langcode": "en",
"name": "Statistics",
"orig": "en:Statistics",
"parents": [
"Formal sciences",
"Mathematics",
"Sciences",
"All topics",
"Fundamental"
],
"source": "w"
},
{
"_dis": "29 35 37",
"kind": "other",
"name": "English entries with incorrect language header",
"parents": [
"Entries with incorrect language header",
"Entry maintenance"
],
"source": "w+disamb"
},
{
"_dis": "30 33 37",
"kind": "other",
"name": "Pages with 1 entry",
"parents": [],
"source": "w+disamb"
},
{
"_dis": "24 41 35",
"kind": "other",
"name": "Pages with entries",
"parents": [],
"source": "w+disamb"
}
],
"derived": [
{
"_dis1": "6 0 94",
"word": "dynaset"
}
],
"glosses": [
"A set of data to be analyzed."
],
"id": "en-data_set-en-noun-LcaM80Jt",
"links": [
[
"statistics",
"statistics"
],
[
"set",
"set"
],
[
"analyze",
"analyze"
]
],
"raw_glosses": [
"(statistics) A set of data to be analyzed."
],
"related": [
{
"_dis1": "6 0 94",
"word": "database"
}
],
"synonyms": [
{
"_dis1": "6 0 94",
"word": "dataset"
}
],
"topics": [
"mathematics",
"sciences",
"statistics"
],
"translations": [
{
"_dis1": "5 6 90",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "set of data to analyze",
"word": "數據集"
},
{
"_dis1": "5 6 90",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "shùjùjí",
"sense": "set of data to analyze",
"word": "数据集"
},
{
"_dis1": "5 6 90",
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "set of data to analyze",
"word": "資料集"
},
{
"_dis1": "5 6 90",
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zīliàojí",
"sense": "set of data to analyze",
"word": "资料集"
},
{
"_dis1": "5 6 90",
"code": "cs",
"lang": "Czech",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "datový soubor"
},
{
"_dis1": "5 6 90",
"code": "da",
"lang": "Danish",
"sense": "set of data to analyze",
"tags": [
"neuter"
],
"word": "datasæt"
},
{
"_dis1": "5 6 90",
"code": "fi",
"lang": "Finnish",
"sense": "set of data to analyze",
"word": "data"
},
{
"_dis1": "5 6 90",
"code": "fr",
"lang": "French",
"sense": "set of data to analyze",
"word": "ensemble de données"
},
{
"_dis1": "5 6 90",
"code": "fr",
"lang": "French",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "jeu de données"
},
{
"_dis1": "5 6 90",
"code": "de",
"lang": "German",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "Datensatz"
},
{
"_dis1": "5 6 90",
"code": "hu",
"lang": "Hungarian",
"sense": "set of data to analyze",
"word": "adathalmaz"
},
{
"_dis1": "5 6 90",
"code": "it",
"lang": "Italian",
"sense": "set of data to analyze",
"word": "dataset"
},
{
"_dis1": "5 6 90",
"code": "pt",
"lang": "Portuguese",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "conjunto de dados"
},
{
"_dis1": "5 6 90",
"code": "ru",
"lang": "Russian",
"roman": "nabór dánnyx",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "набо́р да́нных"
},
{
"_dis1": "5 6 90",
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "skup podataka"
},
{
"_dis1": "5 6 90",
"code": "es",
"lang": "Spanish",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "conjunto de datos"
},
{
"_dis1": "5 6 90",
"code": "sv",
"lang": "Swedish",
"sense": "set of data to analyze",
"word": "datamängd"
},
{
"_dis1": "5 6 90",
"code": "tr",
"lang": "Turkish",
"sense": "set of data to analyze",
"word": "veri grubu"
}
]
}
],
"word": "data set"
}
{
"categories": [
"English countable nouns",
"English entries with incorrect language header",
"English lemmas",
"English multiword terms",
"English nouns",
"Entries with translation boxes",
"Pages with 1 entry",
"Pages with entries",
"Terms with Czech translations",
"Terms with Danish translations",
"Terms with Finnish translations",
"Terms with French translations",
"Terms with German translations",
"Terms with Hungarian translations",
"Terms with Italian translations",
"Terms with Mandarin translations",
"Terms with Maori translations",
"Terms with Portuguese translations",
"Terms with Russian translations",
"Terms with Serbo-Croatian translations",
"Terms with Spanish translations",
"Terms with Swedish translations",
"Terms with Turkish translations"
],
"derived": [
{
"word": "dynaset"
}
],
"forms": [
{
"form": "data sets",
"tags": [
"plural"
]
}
],
"head_templates": [
{
"args": {},
"expansion": "data set (plural data sets)",
"name": "en-noun"
}
],
"lang": "English",
"lang_code": "en",
"pos": "noun",
"related": [
{
"word": "database"
}
],
"senses": [
{
"categories": [
"en:Computing"
],
"glosses": [
"A file of related records on a computer-readable medium such as disk, especially one on a mainframe computer."
],
"links": [
[
"computing",
"computing#Noun"
],
[
"file",
"file"
],
[
"related",
"related"
],
[
"record",
"record"
],
[
"computer",
"computer"
],
[
"readable",
"readable"
],
[
"medium",
"medium"
],
[
"disk",
"disk"
],
[
"mainframe",
"mainframe"
]
],
"raw_glosses": [
"(computing) A file of related records on a computer-readable medium such as disk, especially one on a mainframe computer."
],
"topics": [
"computing",
"engineering",
"mathematics",
"natural-sciences",
"physical-sciences",
"sciences"
]
},
{
"categories": [
"English dated terms",
"en:Telecommunications"
],
"glosses": [
"A modem that connects a device such as a teletype to an ordinary telephone."
],
"links": [
[
"telecommunications",
"telecommunications"
],
[
"modem",
"modem"
]
],
"raw_glosses": [
"(telecommunications, dated) A modem that connects a device such as a teletype to an ordinary telephone."
],
"tags": [
"dated"
],
"topics": [
"communications",
"electrical-engineering",
"engineering",
"natural-sciences",
"physical-sciences",
"telecommunications"
]
},
{
"categories": [
"en:Statistics"
],
"glosses": [
"A set of data to be analyzed."
],
"links": [
[
"statistics",
"statistics"
],
[
"set",
"set"
],
[
"analyze",
"analyze"
]
],
"raw_glosses": [
"(statistics) A set of data to be analyzed."
],
"topics": [
"mathematics",
"sciences",
"statistics"
]
}
],
"synonyms": [
{
"word": "dataset"
}
],
"translations": [
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "file of related records",
"word": "數據集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "shùjùjí",
"sense": "file of related records",
"word": "数据集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "file of related records",
"word": "資料集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zīliàojí",
"sense": "file of related records",
"word": "资料集"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "file of related records",
"word": "datasetti"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "file of related records",
"word": "tietoaineisto"
},
{
"code": "fr",
"lang": "French",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "jeu de données"
},
{
"code": "de",
"lang": "German",
"sense": "file of related records",
"tags": [
"neuter"
],
"word": "Dataset"
},
{
"code": "mi",
"lang": "Maori",
"sense": "file of related records",
"word": "huinga raraunga"
},
{
"code": "ru",
"lang": "Russian",
"roman": "nabór dánnyx",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "набо́р да́нных"
},
{
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "skup podataka"
},
{
"code": "es",
"lang": "Spanish",
"sense": "file of related records",
"tags": [
"masculine"
],
"word": "conjunto de datos"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "file of related records",
"tags": [
"neuter"
],
"word": "dataset"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "file of related records",
"word": "veri grubu"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "set of data to analyze",
"word": "數據集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "shùjùjí",
"sense": "set of data to analyze",
"word": "数据集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"sense": "set of data to analyze",
"word": "資料集"
},
{
"code": "cmn",
"lang": "Chinese Mandarin",
"roman": "zīliàojí",
"sense": "set of data to analyze",
"word": "资料集"
},
{
"code": "cs",
"lang": "Czech",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "datový soubor"
},
{
"code": "da",
"lang": "Danish",
"sense": "set of data to analyze",
"tags": [
"neuter"
],
"word": "datasæt"
},
{
"code": "fi",
"lang": "Finnish",
"sense": "set of data to analyze",
"word": "data"
},
{
"code": "fr",
"lang": "French",
"sense": "set of data to analyze",
"word": "ensemble de données"
},
{
"code": "fr",
"lang": "French",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "jeu de données"
},
{
"code": "de",
"lang": "German",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "Datensatz"
},
{
"code": "hu",
"lang": "Hungarian",
"sense": "set of data to analyze",
"word": "adathalmaz"
},
{
"code": "it",
"lang": "Italian",
"sense": "set of data to analyze",
"word": "dataset"
},
{
"code": "pt",
"lang": "Portuguese",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "conjunto de dados"
},
{
"code": "ru",
"lang": "Russian",
"roman": "nabór dánnyx",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "набо́р да́нных"
},
{
"code": "sh",
"lang": "Serbo-Croatian",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "skup podataka"
},
{
"code": "es",
"lang": "Spanish",
"sense": "set of data to analyze",
"tags": [
"masculine"
],
"word": "conjunto de datos"
},
{
"code": "sv",
"lang": "Swedish",
"sense": "set of data to analyze",
"word": "datamängd"
},
{
"code": "tr",
"lang": "Turkish",
"sense": "set of data to analyze",
"word": "veri grubu"
}
],
"word": "data set"
}
Download raw JSONL data for data set meaning in All languages combined (6.0kB)
This page is a part of the kaikki.org machine-readable All languages combined dictionary. This dictionary is based on structured data extracted on 2024-12-15 from the enwiktionary dump dated 2024-12-04 using wiktextract (8a39820 and 4401a4c). The data shown on this site has been post-processed and various details (e.g., extra categories) removed, some information disambiguated, and additional data merged from other sources. See the raw data download page for the unprocessed wiktextract data.
If you use this data in academic research, please cite Tatu Ylonen: Wiktextract: Wiktionary as Machine-Readable Structured Data, Proceedings of the 13th Conference on Language Resources and Evaluation (LREC), pp. 1317-1325, Marseille, 20-25 June 2022. Linking to the relevant page(s) under https://kaikki.org would also be greatly appreciated.