Last active
June 13, 2022 10:23
-
-
Save rolisz/dfd7b6df8173d5cce4d7e2322066f6a3 to your computer and use it in GitHub Desktop.
Reproduction for PatternMatcher bug
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from typing import Union, Iterable, Optional, List | |
| import spacy | |
| from prodigy import recipe, get_stream | |
| from prodigy.models.matcher import PatternMatcher | |
| from prodigy.types import RecipeSettingsType | |
| from prodigy.util import get_labels | |
| @recipe( | |
| "textcat.manual_patterns", | |
| # fmt: off | |
| dataset=("Dataset to save annotations to", "positional", None, str), | |
| source=("Data to annotate (file path or '-' to read from standard input)", "positional", None, str), | |
| spacy_model=("Loadable spaCy pipeline or blank:lang (e.g. blank:en)", "positional", None, str), | |
| labels=("Comma-separated label(s) to annotate or text file with one label per line", "option", "l", get_labels), | |
| patterns=("Path to match patterns file", "option", "pt", str), | |
| # fmt: on | |
| ) | |
| def manual( | |
| dataset: str, | |
| source: Union[str, Iterable[dict]], | |
| spacy_model: str, | |
| labels: Optional[List[str]] = None, | |
| patterns: Optional[str] = None, | |
| ) -> RecipeSettingsType: | |
| stream = get_stream(source, rehash=True, dedup=True, input_key="text") | |
| nlp = spacy.load(spacy_model) | |
| matcher = PatternMatcher( | |
| nlp, | |
| label_span=False, | |
| label_task=True, | |
| combine_matches=True, | |
| all_examples=True | |
| ) | |
| matcher = matcher.from_disk(patterns) | |
| stream = list(matcher(stream)) | |
| return { | |
| "view_id": "choice", | |
| "dataset": dataset, | |
| "stream": stream, | |
| "config": { | |
| "labels": labels, | |
| "choice_style": "multiple", | |
| "choice_auto_accept": False, | |
| "exclude_by": "task", | |
| "auto_count_stream": True, | |
| }, | |
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"text": "no match"} | |
| {"text": "something went wrong"} | |
| {"text": "test this thing"} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| {"pattern": "test", "label": "Label1"} | |
| {"pattern": "something", "label": "Label2"} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment