mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
37c7c85a86
* Support nowrap setting in util.prints * Tidy up and fix whitespace * Simplify script and use read_jsonl helper * Add JSON schemas (see #2928) * Deprecate Doc.print_tree Will be replaced with Doc.to_json, which will produce a unified format * Add Doc.to_json() method (see #2928) Converts Doc objects to JSON using the same unified format as the training data. Method also supports serializing selected custom attributes in the doc._. space. * Remove outdated test * Add write_json and write_jsonl helpers * WIP: Update spacy train * Tidy up spacy train * WIP: Use wasabi for formatting * Add GoldParse helpers for JSON format * WIP: add debug-data command * Fix typo * Add missing import * Update wasabi pin * Add missing import * 💫 Refactor CLI (#2943) To be merged into #2932. ## Description - [x] refactor CLI To use [`wasabi`](https://github.com/ines/wasabi) - [x] use [`black`](https://github.com/ambv/black) for auto-formatting - [x] add `flake8` config - [x] move all messy UD-related scripts to `cli.ud` - [x] make converters function that take the opened file and return the converted data (instead of having them handle the IO) ### Types of change enhancement ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [x] I have submitted the spaCy Contributor Agreement. - [x] I ran the tests, and all new and existing tests passed. - [x] My changes don't require a change to the documentation, or if they do, I've added all required information. * Update wasabi pin * Delete old test * Update errors * Fix typo * Tidy up and format remaining code * Fix formatting * Improve formatting of messages * Auto-format remaining code * Add tok2vec stuff to spacy.train * Fix typo * Update wasabi pin * Fix path checks for when train() is called as function * Reformat and tidy up pretrain script * Update argument annotations * Raise error if model language doesn't match lang * Document new train command
147 lines
3.6 KiB
JSON
147 lines
3.6 KiB
JSON
{
|
|
"$schema": "http://json-schema.org/draft-06/schema",
|
|
"title": "Training data for spaCy models",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"text": {
|
|
"title": "The text of the training example",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"ents": {
|
|
"title": "Named entity spans in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"start": {
|
|
"title": "Start character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"label": {
|
|
"title": "Entity label",
|
|
"type": "string",
|
|
"minLength": 1,
|
|
"pattern": "^[A-Z0-9]*$"
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end",
|
|
"label"
|
|
]
|
|
}
|
|
},
|
|
"sents": {
|
|
"title": "Sentence spans in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"start": {
|
|
"title": "Start character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the span",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end"
|
|
]
|
|
}
|
|
},
|
|
"cats": {
|
|
"title": "Text categories for the text classifier",
|
|
"type": "object",
|
|
"patternProperties": {
|
|
"*": {
|
|
"title": "A text category",
|
|
"oneOf": [
|
|
{
|
|
"type": "boolean"
|
|
},
|
|
{
|
|
"type": "number",
|
|
"minimum": 0
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"propertyNames": {
|
|
"pattern": "^[A-Z0-9]*$",
|
|
"minLength": 1
|
|
}
|
|
},
|
|
"tokens": {
|
|
"title": "The tokens in the text",
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"minProperties": 1,
|
|
"properties": {
|
|
"id": {
|
|
"title": "Token ID, usually token index",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"start": {
|
|
"title": "Start character offset of the token",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"end": {
|
|
"title": "End character offset of the token",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
},
|
|
"pos": {
|
|
"title": "Coarse-grained part-of-speech tag",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"tag": {
|
|
"title": "Fine-grained part-of-speech tag",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"dep": {
|
|
"title": "Dependency label",
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"head": {
|
|
"title": "Index of the token's head",
|
|
"type": "integer",
|
|
"minimum": 0
|
|
}
|
|
},
|
|
"required": [
|
|
"start",
|
|
"end"
|
|
]
|
|
}
|
|
},
|
|
"_": {
|
|
"title": "Custom user space",
|
|
"type": "object"
|
|
}
|
|
},
|
|
"required": [
|
|
"text"
|
|
]
|
|
}
|
|
}
|