diff --git a/spacy/cli/find_threshold.py b/spacy/cli/find_threshold.py index 48077fa51..3e86495e7 100644 --- a/spacy/cli/find_threshold.py +++ b/spacy/cli/find_threshold.py @@ -39,7 +39,7 @@ def find_threshold_cli( # fmt: on ): """ - Runs prediction trials for a trained model with varying tresholds to maximize + Runs prediction trials for a trained model with varying thresholds to maximize the specified metric. The search space for the threshold is traversed linearly from 0 to 1 in `n_trials` steps. Results are displayed in a table on `stdout` (the corresponding API call to `spacy.cli.find_threshold.find_threshold()` @@ -81,7 +81,7 @@ def find_threshold( silent: bool = True, ) -> Tuple[float, float, Dict[float, float]]: """ - Runs prediction trials for models with varying tresholds to maximize the specified metric. + Runs prediction trials for models with varying thresholds to maximize the specified metric. model (Union[str, Path]): Pipeline to evaluate. Can be a package or a path to a data directory. data_path (Path): Path to file with DocBin with docs to use for threshold search. pipe_name (str): Name of pipe to examine thresholds for. diff --git a/spacy/tests/test_language.py b/spacy/tests/test_language.py index d229739e1..ee707f793 100644 --- a/spacy/tests/test_language.py +++ b/spacy/tests/test_language.py @@ -329,7 +329,7 @@ def test_language_pipe_error_handler(n_process): nlp.set_error_handler(raise_error) with pytest.raises(ValueError): list(nlp.pipe(texts, n_process=n_process)) - # set explicitely to ignoring + # set explicitly to ignoring nlp.set_error_handler(ignore_error) docs = list(nlp.pipe(texts, n_process=n_process)) assert len(docs) == 0 diff --git a/website/docs/api/attributes.mdx b/website/docs/api/attributes.mdx index 3142b741d..9cb76ac58 100644 --- a/website/docs/api/attributes.mdx +++ b/website/docs/api/attributes.mdx @@ -45,33 +45,33 @@ For attributes that represent string values, the internal integer ID is accessed as `Token.attr`, e.g. `token.dep`, while the string value can be retrieved by appending `_` as in `token.dep_`. -| Attribute | Description | -| ------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `DEP` | The token's dependency label. ~~str~~ | -| `ENT_ID` | The token's entity ID (`ent_id`). ~~str~~ | -| `ENT_IOB` | The IOB part of the token's entity tag. Uses custom integer vaues rather than the string store: unset is `0`, `I` is `1`, `O` is `2`, and `B` is `3`. ~~str~~ | -| `ENT_KB_ID` | The token's entity knowledge base ID. ~~str~~ | -| `ENT_TYPE` | The token's entity label. ~~str~~ | -| `IS_ALPHA` | Token text consists of alphabetic characters. ~~bool~~ | -| `IS_ASCII` | Token text consists of ASCII characters. ~~bool~~ | -| `IS_DIGIT` | Token text consists of digits. ~~bool~~ | -| `IS_LOWER` | Token text is in lowercase. ~~bool~~ | -| `IS_PUNCT` | Token is punctuation. ~~bool~~ | -| `IS_SPACE` | Token is whitespace. ~~bool~~ | -| `IS_STOP` | Token is a stop word. ~~bool~~ | -| `IS_TITLE` | Token text is in titlecase. ~~bool~~ | -| `IS_UPPER` | Token text is in uppercase. ~~bool~~ | -| `LEMMA` | The token's lemma. ~~str~~ | -| `LENGTH` | The length of the token text. ~~int~~ | -| `LIKE_EMAIL` | Token text resembles an email address. ~~bool~~ | -| `LIKE_NUM` | Token text resembles a number. ~~bool~~ | -| `LIKE_URL` | Token text resembles a URL. ~~bool~~ | -| `LOWER` | The lowercase form of the token text. ~~str~~ | -| `MORPH` | The token's morphological analysis. ~~MorphAnalysis~~ | -| `NORM` | The normalized form of the token text. ~~str~~ | -| `ORTH` | The exact verbatim text of a token. ~~str~~ | -| `POS` | The token's universal part of speech (UPOS). ~~str~~ | -| `SENT_START` | Token is start of sentence. ~~bool~~ | -| `SHAPE` | The token's shape. ~~str~~ | -| `SPACY` | Token has a trailing space. ~~bool~~ | -| `TAG` | The token's fine-grained part of speech. ~~str~~ | +| Attribute | Description | +| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `DEP` | The token's dependency label. ~~str~~ | +| `ENT_ID` | The token's entity ID (`ent_id`). ~~str~~ | +| `ENT_IOB` | The IOB part of the token's entity tag. Uses custom integer values rather than the string store: unset is `0`, `I` is `1`, `O` is `2`, and `B` is `3`. ~~str~~ | +| `ENT_KB_ID` | The token's entity knowledge base ID. ~~str~~ | +| `ENT_TYPE` | The token's entity label. ~~str~~ | +| `IS_ALPHA` | Token text consists of alphabetic characters. ~~bool~~ | +| `IS_ASCII` | Token text consists of ASCII characters. ~~bool~~ | +| `IS_DIGIT` | Token text consists of digits. ~~bool~~ | +| `IS_LOWER` | Token text is in lowercase. ~~bool~~ | +| `IS_PUNCT` | Token is punctuation. ~~bool~~ | +| `IS_SPACE` | Token is whitespace. ~~bool~~ | +| `IS_STOP` | Token is a stop word. ~~bool~~ | +| `IS_TITLE` | Token text is in titlecase. ~~bool~~ | +| `IS_UPPER` | Token text is in uppercase. ~~bool~~ | +| `LEMMA` | The token's lemma. ~~str~~ | +| `LENGTH` | The length of the token text. ~~int~~ | +| `LIKE_EMAIL` | Token text resembles an email address. ~~bool~~ | +| `LIKE_NUM` | Token text resembles a number. ~~bool~~ | +| `LIKE_URL` | Token text resembles a URL. ~~bool~~ | +| `LOWER` | The lowercase form of the token text. ~~str~~ | +| `MORPH` | The token's morphological analysis. ~~MorphAnalysis~~ | +| `NORM` | The normalized form of the token text. ~~str~~ | +| `ORTH` | The exact verbatim text of a token. ~~str~~ | +| `POS` | The token's universal part of speech (UPOS). ~~str~~ | +| `SENT_START` | Token is start of sentence. ~~bool~~ | +| `SHAPE` | The token's shape. ~~str~~ | +| `SPACY` | Token has a trailing space. ~~bool~~ | +| `TAG` | The token's fine-grained part of speech. ~~str~~ | diff --git a/website/docs/api/cli.mdx b/website/docs/api/cli.mdx index 950d98c1f..6c47c8f1e 100644 --- a/website/docs/api/cli.mdx +++ b/website/docs/api/cli.mdx @@ -567,7 +567,7 @@ New: 'ORG' (23860), 'PERSON' (21395), 'GPE' (21193), 'DATE' (18080), 'CARDINAL' 'LOC' (2113), 'TIME' (1616), 'WORK_OF_ART' (1229), 'QUANTITY' (1150), 'FAC' (1134), 'EVENT' (974), 'PRODUCT' (935), 'LAW' (444), 'LANGUAGE' (338) ✔ Good amount of examples for all labels -✔ Examples without occurences available for all labels +✔ Examples without occurrences available for all labels ✔ No entities consisting of or starting/ending with whitespace =========================== Part-of-speech Tagging =========================== @@ -1320,7 +1320,7 @@ $ python -m spacy apply [model] [data-path] [output-file] [--code] [--text-key] ## find-threshold {id="find-threshold",version="3.5",tag="command"} -Runs prediction trials for a trained model with varying tresholds to maximize +Runs prediction trials for a trained model with varying thresholds to maximize the specified metric. The search space for the threshold is traversed linearly from 0 to 1 in `n_trials` steps. Results are displayed in a table on `stdout` (the corresponding API call to `spacy.cli.find_threshold.find_threshold()` diff --git a/website/docs/api/entitylinker.mdx b/website/docs/api/entitylinker.mdx index c7b11985a..f4b83d88b 100644 --- a/website/docs/api/entitylinker.mdx +++ b/website/docs/api/entitylinker.mdx @@ -67,7 +67,7 @@ architectures and their arguments and hyperparameters. | `generate_empty_kb` 3.5.1 | Function that generates an empty `KnowledgeBase` object. Defaults to [`spacy.EmptyKB.v2`](/api/architectures#EmptyKB), which generates an empty [`InMemoryLookupKB`](/api/inmemorylookupkb). ~~Callable[[Vocab, int], KnowledgeBase]~~ | | `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `True`. ~~bool~~ | | `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~ | -| `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the treshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ | +| `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the threshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ | ```python %%GITHUB_SPACY/spacy/pipeline/entity_linker.py @@ -100,21 +100,21 @@ custom knowledge base, you should either call [`set_kb`](/api/entitylinker#set_kb) or provide a `kb_loader` in the [`initialize`](/api/entitylinker#initialize) call. -| Name | Description | -| ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -| `vocab` | The shared vocabulary. ~~Vocab~~ | -| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model~~ | -| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | -| _keyword-only_ | | -| `entity_vector_length` | Size of encoding vectors in the KB. ~~int~~ | -| `get_candidates` | Function that generates plausible candidates for a given `Span` object. ~~Callable[[KnowledgeBase, Span], Iterable[Candidate]]~~ | -| `labels_discard` | NER labels that will automatically get a `"NIL"` prediction. ~~Iterable[str]~~ | -| `n_sents` | The number of neighbouring sentences to take into account. ~~int~~ | -| `incl_prior` | Whether or not to include prior probabilities from the KB in the model. ~~bool~~ | -| `incl_context` | Whether or not to include the local context in the model. ~~bool~~ | -| `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `True`. ~~bool~~ | -| `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~ | -| `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the treshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ | +| Name | Description | +| ---------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| `vocab` | The shared vocabulary. ~~Vocab~~ | +| `model` | The [`Model`](https://thinc.ai/docs/api-model) powering the pipeline component. ~~Model~~ | +| `name` | String name of the component instance. Used to add entries to the `losses` during training. ~~str~~ | +| _keyword-only_ | | +| `entity_vector_length` | Size of encoding vectors in the KB. ~~int~~ | +| `get_candidates` | Function that generates plausible candidates for a given `Span` object. ~~Callable[[KnowledgeBase, Span], Iterable[Candidate]]~~ | +| `labels_discard` | NER labels that will automatically get a `"NIL"` prediction. ~~Iterable[str]~~ | +| `n_sents` | The number of neighbouring sentences to take into account. ~~int~~ | +| `incl_prior` | Whether or not to include prior probabilities from the KB in the model. ~~bool~~ | +| `incl_context` | Whether or not to include the local context in the model. ~~bool~~ | +| `overwrite` 3.2 | Whether existing annotation is overwritten. Defaults to `True`. ~~bool~~ | +| `scorer` 3.2 | The scoring method. Defaults to [`Scorer.score_links`](/api/scorer#score_links). ~~Optional[Callable]~~ | +| `threshold` 3.4 | Confidence threshold for entity predictions. The default of `None` implies that all predictions are accepted, otherwise those with a score beneath the threshold are discarded. If there are no predictions with scores above the threshold, the linked entity is `NIL`. ~~Optional[float]~~ | ## EntityLinker.\_\_call\_\_ {id="call",tag="method"} diff --git a/website/docs/api/entityruler.mdx b/website/docs/api/entityruler.mdx index 27624398e..335e87676 100644 --- a/website/docs/api/entityruler.mdx +++ b/website/docs/api/entityruler.mdx @@ -58,7 +58,7 @@ how the component should be configured. You can override its settings via the | Setting | Description | | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `phrase_matcher_attr` | Optional attribute name match on for the internal [`PhraseMatcher`](/api/phrasematcher), e.g. `LOWER` to match on the lowercase token text. Defaults to `None`. ~~Optional[Union[int, str]]~~ | -| `matcher_fuzzy_compare` 3.5 | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~ | +| `matcher_fuzzy_compare` 3.5 | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~ | | `validate` | Whether patterns should be validated (passed to the `Matcher` and `PhraseMatcher`). Defaults to `False`. ~~bool~~ | | `overwrite_ents` | If existing entities are present, e.g. entities added by the model, overwrite them by matches if necessary. Defaults to `False`. ~~bool~~ | | `ent_id_sep` | Separator used internally for entity IDs. Defaults to `"\|\|"`. ~~str~~ | @@ -92,7 +92,7 @@ be a token pattern (list) or a phrase pattern (string). For example: | `name` 3 | Instance name of the current pipeline component. Typically passed in automatically from the factory when the component is added. Used to disable the current entity ruler while creating phrase patterns with the nlp object. ~~str~~ | | _keyword-only_ | | | `phrase_matcher_attr` | Optional attribute name match on for the internal [`PhraseMatcher`](/api/phrasematcher), e.g. `LOWER` to match on the lowercase token text. Defaults to `None`. ~~Optional[Union[int, str]]~~ | -| `matcher_fuzzy_compare` 3.5 | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~ | +| `matcher_fuzzy_compare` 3.5 | The fuzzy comparison method, passed on to the internal `Matcher`. Defaults to `spacy.matcher.levenshtein.levenshtein_compare`. ~~Callable~~ | | `validate` | Whether patterns should be validated, passed to Matcher and PhraseMatcher as `validate`. Defaults to `False`. ~~bool~~ | | `overwrite_ents` | If existing entities are present, e.g. entities added by the model, overwrite them by matches if necessary. Defaults to `False`. ~~bool~~ | | `ent_id_sep` | Separator used internally for entity IDs. Defaults to `"\|\|"`. ~~str~~ | @@ -173,7 +173,7 @@ happens automatically after the component has been added to the pipeline using [`nlp.add_pipe`](/api/language#add_pipe). If the entity ruler was initialized with `overwrite_ents=True`, existing entities will be replaced if they overlap with the matches. When matches overlap in a Doc, the entity ruler prioritizes -longer patterns over shorter, and if equal the match occuring first in the Doc +longer patterns over shorter, and if equal the match occurring first in the Doc is chosen. > #### Example diff --git a/website/docs/api/span.mdx b/website/docs/api/span.mdx index 41422a5b4..225ff6e6a 100644 --- a/website/docs/api/span.mdx +++ b/website/docs/api/span.mdx @@ -288,7 +288,7 @@ it – so no NP-level coordination, no prepositional phrases, and no relative clauses. If the `noun_chunk` [syntax iterator](/usage/linguistic-features#language-data) -has not been implemeted for the given language, a `NotImplementedError` is +has not been implemented for the given language, a `NotImplementedError` is raised. > #### Example diff --git a/website/docs/api/transformer.mdx b/website/docs/api/transformer.mdx index 8f024553d..9dcafb557 100644 --- a/website/docs/api/transformer.mdx +++ b/website/docs/api/transformer.mdx @@ -416,7 +416,7 @@ by this class. Instances of this class are typically assigned to the | `align` | Alignment from the `Doc`'s tokenization to the wordpieces. This is a ragged array, where `align.lengths[i]` indicates the number of wordpiece tokens that token `i` aligns against. The actual indices are provided at `align[i].dataXd`. ~~Ragged~~ | | `width` | The width of the last hidden layer. ~~int~~ | -### TransformerData.empty {id="transformerdata-emoty",tag="classmethod"} +### TransformerData.empty {id="transformerdata-empty",tag="classmethod"} Create an empty `TransformerData` container. diff --git a/website/docs/usage/layers-architectures.mdx b/website/docs/usage/layers-architectures.mdx index 03b85f5af..344c66e8d 100644 --- a/website/docs/usage/layers-architectures.mdx +++ b/website/docs/usage/layers-architectures.mdx @@ -832,7 +832,7 @@ retrieve and add to them. After creation, the component needs to be [initialized](/usage/training#initialization). This method can define the -relevant labels in two ways: explicitely by setting the `labels` argument in the +relevant labels in two ways: explicitly by setting the `labels` argument in the [`initialize` block](/api/data-formats#config-initialize) of the config, or implicately by deducing them from the `get_examples` callback that generates the full **training data set**, or a representative sample. diff --git a/website/docs/usage/linguistic-features.mdx b/website/docs/usage/linguistic-features.mdx index 21cedd1ef..6ca970407 100644 --- a/website/docs/usage/linguistic-features.mdx +++ b/website/docs/usage/linguistic-features.mdx @@ -1899,7 +1899,7 @@ the two words. "Shore": ("coast", 0.732257), "Precautionary": ("caution", 0.490973), "hopelessness": ("sadness", 0.742366), - "Continous": ("continuous", 0.732549), + "Continuous": ("continuous", 0.732549), "Disemboweled": ("corpse", 0.499432), "biostatistician": ("scientist", 0.339724), "somewheres": ("somewheres", 0.402736), diff --git a/website/docs/usage/projects.mdx b/website/docs/usage/projects.mdx index b089a7ab5..e10ba4c50 100644 --- a/website/docs/usage/projects.mdx +++ b/website/docs/usage/projects.mdx @@ -173,7 +173,7 @@ detected, a corresponding warning is displayed. If you'd like to disable the dependency check, set `check_requirements: false` in your project's `project.yml`. -### 4. Run a workflow {id="run-workfow"} +### 4. Run a workflow {id="run-workflow"} > #### project.yml > @@ -286,7 +286,7 @@ pipelines. | --------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `title` | An optional project title used in `--help` message and [auto-generated docs](#custom-docs). | | `description` | An optional project description used in [auto-generated docs](#custom-docs). | -| `vars` | A dictionary of variables that can be referenced in paths, URLs and scripts and overriden on the CLI, just like [`config.cfg` variables](/usage/training#config-interpolation). For example, `${vars.name}` will use the value of the variable `name`. Variables need to be defined in the section `vars`, but can be a nested dict, so you're able to reference `${vars.model.name}`. | +| `vars` | A dictionary of variables that can be referenced in paths, URLs and scripts and overridden on the CLI, just like [`config.cfg` variables](/usage/training#config-interpolation). For example, `${vars.name}` will use the value of the variable `name`. Variables need to be defined in the section `vars`, but can be a nested dict, so you're able to reference `${vars.model.name}`. | | `env` | A dictionary of variables, mapped to the names of environment variables that will be read in when running the project. For example, `${env.name}` will use the value of the environment variable defined as `name`. | | `directories` | An optional list of [directories](#project-files) that should be created in the project for assets, training outputs, metrics etc. spaCy will make sure that these directories always exist. | | `assets` | A list of assets that can be fetched with the [`project assets`](/api/cli#project-assets) command. `url` defines a URL or local path, `dest` is the destination file relative to the project directory, and an optional `checksum` ensures that an error is raised if the file's checksum doesn't match. Instead of `url`, you can also provide a `git` block with the keys `repo`, `branch` and `path`, to download from a Git repo. | diff --git a/website/docs/usage/saving-loading.mdx b/website/docs/usage/saving-loading.mdx index 9a6791d5e..0b0b759e9 100644 --- a/website/docs/usage/saving-loading.mdx +++ b/website/docs/usage/saving-loading.mdx @@ -306,7 +306,9 @@ installed in the same environment – that's it. ### Loading probability tables into existing models -You can load a probability table from [spacy-lookups-data](https://github.com/explosion/spacy-lookups-data) into an existing spaCy model like `en_core_web_sm`. +You can load a probability table from +[spacy-lookups-data](https://github.com/explosion/spacy-lookups-data) into an +existing spaCy model like `en_core_web_sm`. ```python # Requirements: pip install spacy-lookups-data @@ -317,7 +319,8 @@ lookups = load_lookups("en", ["lexeme_prob"]) nlp.vocab.lookups.add_table("lexeme_prob", lookups.get_table("lexeme_prob")) ``` -When training a model from scratch you can also specify probability tables in the `config.cfg`. +When training a model from scratch you can also specify probability tables in +the `config.cfg`. ```ini {title="config.cfg (excerpt)"} [initialize.lookups] @@ -346,8 +349,8 @@ them**! To stick with the theme of [this entry points blog post](https://amir.rachum.com/blog/2017/07/28/python-entry-points/), consider the following custom spaCy -[pipeline component](/usage/processing-pipelines#custom-coponents) that prints a -snake when it's called: +[pipeline component](/usage/processing-pipelines#custom-components) that prints +a snake when it's called: > #### Package directory structure > diff --git a/website/docs/usage/v2-2.mdx b/website/docs/usage/v2-2.mdx index 84129657d..cf4f7c5bf 100644 --- a/website/docs/usage/v2-2.mdx +++ b/website/docs/usage/v2-2.mdx @@ -185,7 +185,7 @@ New: 'ORG' (23860), 'PERSON' (21395), 'GPE' (21193), 'DATE' (18080), 'CARDINAL' 'LOC' (2113), 'TIME' (1616), 'WORK_OF_ART' (1229), 'QUANTITY' (1150), 'FAC' (1134), 'EVENT' (974), 'PRODUCT' (935), 'LAW' (444), 'LANGUAGE' (338) ✔ Good amount of examples for all labels -✔ Examples without occurences available for all labels +✔ Examples without occurrences available for all labels ✔ No entities consisting of or starting/ending with whitespace =========================== Part-of-speech Tagging =========================== diff --git a/website/docs/usage/v3-2.mdx b/website/docs/usage/v3-2.mdx index b4a4ef672..b3ffd5d68 100644 --- a/website/docs/usage/v3-2.mdx +++ b/website/docs/usage/v3-2.mdx @@ -138,7 +138,7 @@ backwards compatibility, the tuple format remains available under `TransformerData.tensors` and `FullTransformerBatch.tensors`. See more details in the [transformer API docs](/api/architectures#TransformerModel). -`spacy-transfomers` v1.1 also adds support for `transformer_config` settings +`spacy-transformers` v1.1 also adds support for `transformer_config` settings such as `output_attentions`. Additional output is stored under `TransformerData.model_output`. More details are in the [TransformerModel docs](/api/architectures#TransformerModel). The training speed