spaCy/spacy/errors.py

623 lines
40 KiB
Python
Raw Normal View History

def add_codes(err_cls):
"""Add error codes to string messages via class attribute names."""
class ErrorsWithCodes(err_cls):
def __getattribute__(self, code):
2020-05-21 21:52:48 +03:00
msg = super(ErrorsWithCodes, self).__getattribute__(code)
2020-05-21 15:14:01 +03:00
if code.startswith("__"): # python system attributes like __class__
return msg
else:
return "[{code}] {msg}".format(code=code, msg=msg)
return ErrorsWithCodes()
# fmt: off
@add_codes
class Warnings(object):
W001 = ("As of spaCy v2.0, the keyword argument `path=` is deprecated. "
"You can now call spacy.load with the path as its first argument, "
"and the model's meta.json will be used to determine the language "
"to load. For example:\nnlp = spacy.load('{path}')")
W002 = ("Tokenizer.from_list is now deprecated. Create a new Doc object "
"instead and pass in the strings as the `words` keyword argument, "
"for example:\nfrom spacy.tokens import Doc\n"
"doc = Doc(nlp.vocab, words=[...])")
W003 = ("Positional arguments to Doc.merge are deprecated. Instead, use "
"the keyword arguments, for example tag=, lemma= or ent_type=.")
W004 = ("No text fixing enabled. Run `pip install ftfy` to enable fixing "
"using ftfy.fix_text if necessary.")
W005 = ("Doc object not parsed. This means displaCy won't be able to "
"generate a dependency visualization for it. Make sure the Doc "
"was processed with a model that supports dependency parsing, and "
"not just a language class like `English()`. For more info, see "
"the docs:\nhttps://spacy.io/usage/models")
W006 = ("No entities to visualize found in Doc object. If this is "
"surprising to you, make sure the Doc was processed using a model "
"that supports named entity recognition, and check the `doc.ents` "
"property manually if necessary.")
W007 = ("The model you're using has no word vectors loaded, so the result "
"of the {obj}.similarity method will be based on the tagger, "
"parser and NER, which may not give useful similarity judgements. "
"This may happen if you're using one of the small models, e.g. "
"`en_core_web_sm`, which don't ship with word vectors and only "
"use context-sensitive tensors. You can always add your own word "
"vectors, or use one of the larger models instead if available.")
W008 = ("Evaluating {obj}.similarity based on empty vectors.")
W009 = ("Custom factory '{name}' provided by entry points of another "
"package overwrites built-in factory.")
W010 = ("As of v2.1.0, the PhraseMatcher doesn't have a phrase length "
"limit anymore, so the max_length argument is now deprecated. "
"If you did not specify this parameter, make sure you call the "
"constructor with named arguments instead of positional ones.")
W011 = ("It looks like you're calling displacy.serve from within a "
"Jupyter notebook or a similar environment. This likely means "
"you're already running a local web server, so there's no need to "
"make displaCy start another one. Instead, you should be able to "
"replace displacy.serve with displacy.render to show the "
"visualization.")
W012 = ("A Doc object you're adding to the PhraseMatcher for pattern "
"'{key}' is parsed and/or tagged, but to match on '{attr}', you "
"don't actually need this information. This means that creating "
"the patterns is potentially much slower, because all pipeline "
"components are applied. To only create tokenized Doc objects, "
"try using `nlp.make_doc(text)` or process all texts as a stream "
"using `list(nlp.tokenizer.pipe(all_texts))`.")
W013 = ("As of v2.1.0, {obj}.merge is deprecated. Please use the more "
"efficient and less error-prone Doc.retokenize context manager "
"instead.")
W014 = ("As of v2.1.0, the `disable` keyword argument on the serialization "
"methods is and should be replaced with `exclude`. This makes it "
2019-11-25 15:08:19 +03:00
"consistent with the other serializable objects.")
W015 = ("As of v2.1.0, the use of keyword arguments to exclude fields from "
"being serialized or deserialized is deprecated. Please use the "
"`exclude` argument instead. For example: exclude=['{arg}'].")
W016 = ("The keyword argument `n_threads` is now deprecated. As of v2.2.2, "
"the argument `n_process` controls parallel inference via "
"multiprocessing.")
W017 = ("Alias '{alias}' already exists in the Knowledge Base.")
W018 = ("Entity '{entity}' already exists in the Knowledge Base - "
"ignoring the duplicate entry.")
2019-07-11 15:44:32 +03:00
W019 = ("Changing vectors name from {old} to {new}, to avoid clash with "
"previously loaded vectors. See Issue #3853.")
W020 = ("Unnamed vectors. This won't allow multiple vectors models to be "
"loaded. (Shape: {shape})")
Replace PhraseMatcher with trie-based search (#4309) * Replace PhraseMatcher with Aho-Corasick Replace PhraseMatcher with the Aho-Corasick algorithm over numpy arrays of the hash values for the relevant attribute. The implementation is based on FlashText. The speed should be similar to the previous PhraseMatcher. It is now possible to easily remove match IDs and matches don't go missing with large keyword lists / vocabularies. Fixes #4308. * Restore support for pickling * Fix internal keyword add/remove for numpy arrays * Add missing loop for match ID set in search loop * Remove cruft in matching loop for partial matches There was a bit of unnecessary code left over from FlashText in the matching loop to handle partial token matches, which we don't have with PhraseMatcher. * Replace dict trie with MapStruct trie * Fix how match ID hash is stored/added * Update fix for match ID vocab * Switch from map_get_unless_missing to map_get * Switch from numpy array to Token.get_struct_attr Access token attributes directly in Doc instead of making a copy of the relevant values in a numpy array. Add unsatisfactory warning for hash collision with reserved terminal hash key. (Ideally it would change the reserved terminal hash and redo the whole trie, but for now, I'm hoping there won't be collisions.) * Restructure imports to export find_matches * Implement full remove() Remove unnecessary trie paths and free unused maps. Parallel to Matcher, raise KeyError when attempting to remove a match ID that has not been added. * Store docs internally only as attr lists * Reduces size for pickle * Remove duplicate keywords store Now that docs are stored as lists of attr hashes, there's no need to have the duplicate _keywords store.
2019-09-27 17:22:34 +03:00
W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be "
"incorrect. Modify PhraseMatcher._terminal_hash to fix.")
W022 = ("Training a new part-of-speech tagger using a model with no "
"lemmatization rules or data. This means that the trained model "
"may not be able to lemmatize correctly. If this is intentional "
"or the language you're using doesn't have lemmatization data, "
2020-02-28 14:23:31 +03:00
"you can ignore this warning. If this is surprising, make sure you "
"have the spacy-lookups-data package installed.")
2019-10-18 12:33:38 +03:00
W023 = ("Multiprocessing of Language.pipe is not supported in Python 2. "
"'n_process' will be set to 1.")
W024 = ("Entity '{entity}' - Alias '{alias}' combination already exists in "
"the Knowledge Base.")
W025 = ("'{name}' requires '{attr}' to be assigned, but none of the "
"previous components in the pipeline declare that they assign it.")
W026 = ("Unable to set all sentence boundaries from dependency parses.")
W027 = ("Found a large training file of {size} bytes. Note that it may "
"be more efficient to split your training data into multiple "
"smaller JSON files instead.")
W028 = ("Doc.from_array was called with a vector of type '{type}', "
"but is expecting one of type 'uint64' instead. This may result "
"in problems with the vocab further on in the pipeline.")
W029 = ("Unable to align tokens with entities from character offsets. "
"Discarding entity annotation for the text: {text}.")
W030 = ("Some entities could not be aligned in the text \"{text}\" with "
"entities \"{entities}\". Use "
"`spacy.gold.biluo_tags_from_offsets(nlp.make_doc(text), entities)`"
" to check the alignment. Misaligned entities ('-') will be "
"ignored during training.")
W031 = ("Model '{model}' ({model_version}) requires spaCy {version} and "
"is incompatible with the current spaCy version ({current}). This "
"may lead to unexpected results or runtime errors. To resolve "
"this, download a newer compatible model or retrain your custom "
"model with the current spaCy version. For more details and "
"available updates, run: python -m spacy validate")
W032 = ("Unable to determine model compatibility for model '{model}' "
"({model_version}) with the current spaCy version ({current}). "
"This may lead to unexpected results or runtime errors. To resolve "
"this, download a newer compatible model or retrain your custom "
"model with the current spaCy version. For more details and "
"available updates, run: python -m spacy validate")
W033 = ("Training a new {model} using a model with no lexeme normalization "
"table. This may degrade the performance of the model to some "
"degree. If this is intentional or the language you're using "
"doesn't have a normalization table, please ignore this warning. "
"If this is surprising, make sure you have the spacy-lookups-data "
"package installed. The languages with lexeme normalization tables "
"are currently: da, de, el, en, id, lb, pt, ru, sr, ta, th.")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
# TODO: fix numbering after merging develop into master
W092 = ("Ignoring annotations for sentence starts, as dependency heads are set.")
Improve spacy.gold (no GoldParse, no json format!) (#5555) * Update errors * Remove beam for now (maybe) Remove beam_utils Update setup.py Remove beam * Remove GoldParse WIP on removing goldparse Get ArcEager compiling after GoldParse excise Update setup.py Get spacy.syntax compiling after removing GoldParse Rename NewExample -> Example and clean up Clean html files Start updating tests Update Morphologizer * fix error numbers * fix merge conflict * informative error when calling to_array with wrong field * fix error catching * fixing language and scoring tests * start testing get_aligned * additional tests for new get_aligned function * Draft create_gold_state for arc_eager oracle * Fix import * Fix import * Remove TokenAnnotation code from nonproj * fixing NER one-to-many alignment * Fix many-to-one IOB codes * fix test for misaligned * attempt to fix cases with weird spaces * fix spaces * test_gold_biluo_different_tokenization works * allow None as BILUO annotation * fixed some tests + WIP roundtrip unit test * add spaces to json output format * minibatch utiltiy can deal with strings, docs or examples * fix augment (needs further testing) * various fixes in scripts - needs to be further tested * fix test_cli * cleanup * correct silly typo * add support for MORPH in to/from_array, fix morphologizer overfitting test * fix tagger * fix entity linker * ensure test keeps working with non-linked entities * pipe() takes docs, not examples * small bug fix * textcat bugfix * throw informative error when running the components with the wrong type of objects * fix parser tests to work with example (most still failing) * fix BiluoPushDown parsing entities * small fixes * bugfix tok2vec * fix renames and simple_ner labels * various small fixes * prevent writing dummy values like deps because that could interfer with sent_start values * fix the fix * implement split_sent with aligned SENT_START attribute * test for split sentences with various alignment issues, works * Return ArcEagerGoldParse from ArcEager * Update parser and NER gold stuff * Draft new GoldCorpus class * add links to to_dict * clean up * fix test checking for variants * Fix oracles * Start updating converters * Move converters under spacy.gold * Move things around * Fix naming * Fix name * Update converter to produce DocBin * Update converters * Allow DocBin to take list of Doc objects. * Make spacy convert output docbin * Fix import * Fix docbin * Fix compile in ArcEager * Fix import * Serialize all attrs by default * Update converter * Remove jsonl converter * Add json2docs converter * Draft Corpus class for DocBin * Work on train script * Update Corpus * Update DocBin * Allocate Doc before starting to add words * Make doc.from_array several times faster * Update train.py * Fix Corpus * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests * Skip tests that cause crashes * Skip test causing segfault * Remove GoldCorpus * Update imports * Update after removing GoldCorpus * Fix module name of corpus * Fix mimport * Work on parser oracle * Update arc_eager oracle * Restore ArcEager.get_cost function * Update transition system * Update test_arc_eager_oracle * Remove beam test * Update test * Unskip * Unskip tests * add links to to_dict * clean up * fix test checking for variants * Allow DocBin to take list of Doc objects. * Fix compile in ArcEager * Serialize all attrs by default Move converters under spacy.gold Move things around Fix naming Fix name Update converter to produce DocBin Update converters Make spacy convert output docbin Fix import Fix docbin Fix import Update converter Remove jsonl converter Add json2docs converter * Allocate Doc before starting to add words * Make doc.from_array several times faster * Start updating converters * Work on train script * Draft Corpus class for DocBin Update Corpus Fix Corpus * Update DocBin Add missing strings when serializing * Update train.py * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests Skip tests that cause crashes Skip test causing segfault * Remove GoldCorpus Update imports Update after removing GoldCorpus Fix module name of corpus Fix mimport * Work on parser oracle Update arc_eager oracle Restore ArcEager.get_cost function Update transition system * Update tests Remove beam test Update test Unskip Unskip tests * Add get_aligned_parse method in Example Fix Example.get_aligned_parse * Add kwargs to Corpus.dev_dataset to match train_dataset * Update nonproj * Use get_aligned_parse in ArcEager * Add another arc-eager oracle test * Remove Example.doc property Remove Example.doc Remove Example.doc Remove Example.doc Remove Example.doc * Update ArcEager oracle Fix Break oracle * Debugging * Fix Corpus * Fix eg.doc * Format * small fixes * limit arg for Corpus * fix test_roundtrip_docs_to_docbin * fix test_make_orth_variants * fix add_label test * Update tests * avoid writing temp dir in json2docs, fixing 4402 test * Update test * Add missing costs to NER oracle * Update test * Work on Example.get_aligned_ner method * Clean up debugging * Xfail tests * Remove prints * Remove print * Xfail some tests * Replace unseen labels for parser * Update test * Update test * Xfail test * Fix Corpus * fix imports * fix docs_to_json * various small fixes * cleanup * Support gold_preproc in Corpus * Support gold_preproc * Pass gold_preproc setting into corpus * Remove debugging * Fix gold_preproc * Fix json2docs converter * Fix convert command * Fix flake8 * Fix import * fix output_dir (converted to Path by typer) * fix var * bugfix: update states after creating golds to avoid out of bounds indexing * Improve efficiency of ArEager oracle * pull merge_sent into iob2docs to avoid Doc creation for each line * fix asserts * bugfix excl Span.end in iob2docs * Support max_length in Corpus * Fix arc_eager oracle * Filter out uannotated sentences in NER * Remove debugging in parser * Simplify NER alignment * Fix conversion of NER data * Fix NER init_gold_batch * Tweak efficiency of precomputable affine * Update onto-json default * Update gold test for NER * Fix parser test * Update test * Add NER data test * Fix convert for single file * Fix test * Hack scorer to avoid evaluating non-nered data * Fix handling of NER data in Example * Output unlabelled spans from O biluo tags in iob_utils * Fix unset variable * Return kept examples from init_gold_batch * Return examples from init_gold_batch * Dont return Example from init_gold_batch * Set spaces on gold doc after conversion * Add test * Fix spaces reading * Improve NER alignment * Improve handling of missing values in NER * Restore the 'cutting' in parser training * Add assertion * Print epochs * Restore random cuts in parser/ner training * Implement Doc.copy * Implement Example.copy * Copy examples at the start of Language.update * Don't unset example docs * Tweak parser model slightly * attempt to fix _guess_spaces * _add_entities_to_doc first, so that links don't get overwritten * fixing get_aligned_ner for one-to-many * fix indexing into x_text * small fix biluo_tags_from_offsets * Add onto-ner config * Simplify NER alignment * Fix NER scoring for partially annotated documents * fix indexing into x_text * fix test_cli failing tests by ignoring spans in doc.ents with empty label * Fix limit * Improve NER alignment * Fix count_train * Remove print statement * fix tests, we're not having nothing but None * fix clumsy fingers * Fix tests * Fix doc.ents * Remove empty docs in Corpus and improve limit * Update config Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
2020-06-26 20:34:12 +03:00
W093 = ("Could not find any data to train the {name} on. Is your "
"input data correctly formatted ?")
W094 = ("Model '{model}' ({model_version}) specifies an under-constrained "
"spaCy version requirement: {version}. This can lead to compatibility "
"problems with older versions, or as new spaCy versions are "
"released, because the model may say it's compatible when it's "
'not. Consider changing the "spacy_version" in your meta.json to a '
"version range, with a lower and upper pin. For example: {example}")
2020-05-30 16:34:54 +03:00
W095 = ("Model '{model}' ({model_version}) requires spaCy {version} and is "
"incompatible with the current version ({current}). This may lead "
"to unexpected results or runtime errors. To resolve this, "
"download a newer compatible model or retrain your custom model "
"with the current spaCy version. For more details and available "
"updates, run: python -m spacy validate")
W096 = ("The method 'disable_pipes' has become deprecated - use 'select_pipes' "
"instead.")
2020-05-15 12:02:10 +03:00
W097 = ("No Model config was provided to create the '{name}' component, "
"and no default configuration could be found either.")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
W098 = ("No Model config was provided to create the '{name}' component, "
"so a default configuration was used.")
W099 = ("Expected 'dict' type for the 'model' argument of pipe '{pipe}', "
"but got '{type}' instead, so ignoring it.")
W100 = ("Skipping unsupported morphological feature(s): '{feature}'. "
2020-06-03 15:36:59 +03:00
"Provide features as a dict {{\"Field1\": \"Value1,Value2\"}} or "
"string \"Field1=Value1,Value2|Field2=Value3\".")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
2020-05-21 15:14:01 +03:00
@add_codes
class Errors(object):
E001 = ("No component '{name}' found in pipeline. Available names: {opts}")
E002 = ("Can't find factory for '{name}'. This usually happens when spaCy "
"calls `nlp.create_pipe` with a component name that's not built "
"in - for example, when constructing the pipeline from a model's "
"meta.json. If you're using a custom component, you can write to "
"`Language.factories['{name}']` or remove it from the model meta "
"and add it via `nlp.add_pipe` instead.")
E003 = ("Not a valid pipeline component. Expected callable, but "
"got {component} (name: '{name}').")
E004 = ("If you meant to add a built-in component, use `create_pipe`: "
"`nlp.add_pipe(nlp.create_pipe('{component}'))`")
E005 = ("Pipeline component '{name}' returned None. If you're using a "
"custom component, maybe you forgot to return the processed Doc?")
E006 = ("Invalid constraints. You can only set one of the following: "
"before, after, first, last.")
E007 = ("'{name}' already exists in pipeline. Existing names: {opts}")
E008 = ("Some current components would be lost when restoring previous "
"pipeline state. If you added components after calling "
"`nlp.select_pipes()`, you should remove them explicitly with "
"`nlp.remove_pipe()` before the pipeline is restored. Names of "
"the new components: {names}")
E010 = ("Word vectors set to length 0. This may be because you don't have "
"a model installed or loaded, or because your model doesn't "
"include word vectors. For more info, see the docs:\n"
"https://spacy.io/usage/models")
E011 = ("Unknown operator: '{op}'. Options: {opts}")
E012 = ("Cannot add pattern for zero tokens to matcher.\nKey: {key}")
E014 = ("Unknown tag ID: {tag}")
E016 = ("MultitaskObjective target should be function or one of: dep, "
"tag, ent, dep_tag_offset, ent_tag.")
E017 = ("Can only add unicode or bytes. Got type: {value_type}")
2019-08-20 17:03:45 +03:00
E018 = ("Can't retrieve string for hash '{hash_value}'. This usually "
"refers to an issue with the `Vocab` or `StringStore`.")
E019 = ("Can't create transition with unknown action ID: {action}. Action "
"IDs are enumerated in spacy/syntax/{src}.pyx.")
E022 = ("Could not find a transition with the name '{name}' in the NER "
"model.")
E024 = ("Could not find an optimal move to supervise the parser. Usually, "
"this means that the model can't be updated in a way that's valid "
"and satisfies the correct annotations specified in the GoldParse. "
"For example, are all labels added to the model? If you're "
"training a named entity recognizer, also make sure that none of "
"your annotated entity spans have leading or trailing whitespace "
"or punctuation. "
"You can also use the experimental `debug-data` command to "
"validate your JSON-formatted training data. For details, run:\n"
"python -m spacy debug-data --help")
E025 = ("String is too long: {length} characters. Max is 2**30.")
E026 = ("Error accessing token at position {i}: out of bounds in Doc of "
"length {length}.")
E027 = ("Arguments 'words' and 'spaces' should be sequences of the same "
"length, or 'spaces' should be left default at None. spaces "
"should be a sequence of booleans, with True meaning that the "
"word owns a ' ' character following it.")
E028 = ("orths_and_spaces expects either a list of unicode string or a "
"list of (unicode, bool) tuples. Got bytes instance: {value}")
E029 = ("noun_chunks requires the dependency parse, which requires a "
"statistical model to be installed and loaded. For more info, see "
"the documentation:\nhttps://spacy.io/usage/models")
E030 = ("Sentence boundaries unset. You can add the 'sentencizer' "
"component to the pipeline with: "
"nlp.add_pipe(nlp.create_pipe('sentencizer')). "
"Alternatively, add the dependency parser, or set sentence "
"boundaries by setting doc[i].is_sent_start.")
E031 = ("Invalid token: empty string ('') at position {i}.")
E032 = ("Conflicting attributes specified in doc.from_array(): "
"(HEAD, SENT_START). The HEAD attribute currently sets sentence "
"boundaries implicitly, based on the tree structure. This means "
"the HEAD attribute would potentially override the sentence "
"boundaries set by SENT_START.")
E033 = ("Cannot load into non-empty Doc of length {length}.")
E034 = ("Doc.merge received {n_args} non-keyword arguments. Expected "
"either 3 arguments (deprecated), or 0 (use keyword arguments).\n"
"Arguments supplied:\n{args}\nKeyword arguments:{kwargs}")
E035 = ("Error creating span with start {start} and end {end} for Doc of "
"length {length}.")
E036 = ("Error calculating span: Can't find a token starting at character "
"offset {start}.")
E037 = ("Error calculating span: Can't find a token ending at character "
"offset {end}.")
E039 = ("Array bounds exceeded while searching for root word. This likely "
"means the parse tree is in an invalid state. Please report this "
"issue here: http://github.com/explosion/spaCy/issues")
E040 = ("Attempt to access token at {i}, max length {max_length}.")
E041 = ("Invalid comparison operator: {op}. Likely a Cython bug?")
E042 = ("Error accessing doc[{i}].nbor({j}), for doc of length {length}.")
E043 = ("Refusing to write to token.sent_start if its document is parsed, "
"because this may cause inconsistent state.")
E044 = ("Invalid value for token.sent_start: {value}. Must be one of: "
"None, True, False")
E045 = ("Possibly infinite loop encountered while looking for {attr}.")
E046 = ("Can't retrieve unregistered extension attribute '{name}'. Did "
"you forget to call the `set_extension` method?")
E047 = ("Can't assign a value to unregistered extension attribute "
"'{name}'. Did you forget to call the `set_extension` method?")
E048 = ("Can't import language {lang} from spacy.lang: {err}")
E050 = ("Can't find model '{name}'. It doesn't seem to be a Python "
"package or a valid path to a data directory.")
E052 = ("Can't find model directory: {path}")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
E053 = ("Could not read {name} from {path}")
E054 = ("No valid '{setting}' setting found in model meta.json.")
E055 = ("Invalid ORTH value in exception:\nKey: {key}\nOrths: {orths}")
E056 = ("Invalid tokenizer exception: ORTH values combined don't match "
"original string.\nKey: {key}\nOrths: {orths}")
E057 = ("Stepped slices not supported in Span objects. Try: "
"list(tokens)[start:stop:step] instead.")
E058 = ("Could not retrieve vector for key {key}.")
E059 = ("One (and only one) keyword arg must be set. Got: {kwargs}")
E060 = ("Cannot add new key to vectors: the table is full. Current shape: "
"({rows}, {cols}).")
E062 = ("Cannot find empty bit for new lexical flag. All bits between 0 "
"and 63 are occupied. You can replace one by specifying the "
"`flag_id` explicitly, e.g. "
"`nlp.vocab.add_flag(your_func, flag_id=IS_ALPHA`.")
E063 = ("Invalid value for flag_id: {value}. Flag IDs must be between 1 "
"and 63 (inclusive).")
E064 = ("Error fetching a Lexeme from the Vocab. When looking up a "
"string, the lexeme returned had an orth ID that did not match "
"the query string. This means that the cached lexeme structs are "
"mismatched to the string encoding table. The mismatched:\n"
"Query string: {string}\nOrth cached: {orth}\nOrth ID: {orth_id}")
E065 = ("Only one of the vector table's width and shape can be specified. "
"Got width {width} and shape {shape}.")
E067 = ("Invalid BILUO tag sequence: Got a tag starting with 'I' (inside "
"an entity) without a preceding 'B' (beginning of an entity). "
"Tag sequence:\n{tags}")
E068 = ("Invalid BILUO tag: '{tag}'.")
E071 = ("Error creating lexeme: specified orth ID ({orth}) does not "
"match the one in the vocab ({vocab_orth}).")
E073 = ("Cannot assign vector of length {new_length}. Existing vectors "
"are of length {length}. You can use `vocab.reset_vectors` to "
"clear the existing vectors and resize the table.")
E074 = ("Error interpreting compiled match pattern: patterns are expected "
"to end with the attribute {attr}. Got: {bad_attr}.")
E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
"projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
"match.")
E083 = ("Error setting extension: only one of `default`, `method`, or "
"`getter` (plus optional `setter`) is allowed. Got: {nr_defined}")
E084 = ("Error assigning label ID {label} to span: not in StringStore.")
E085 = ("Can't create lexeme for string '{string}'.")
E087 = ("Unknown displaCy style: {style}.")
E088 = ("Text of length {length} exceeds maximum of {max_length}. The "
"v2.x parser and NER models require roughly 1GB of temporary "
"memory per 100,000 characters in the input. This means long "
"texts may cause memory allocation errors. If you're not using "
"the parser or NER, it's probably safe to increase the "
"`nlp.max_length` limit. The limit is in number of characters, so "
"you can check whether your inputs are too long by checking "
"`len(text)`.")
E089 = ("Extensions can't have a setter argument without a getter "
"argument. Check the keyword arguments on `set_extension`.")
E090 = ("Extension '{name}' already exists on {obj}. To overwrite the "
"existing extension, set `force=True` on `{obj}.set_extension`.")
E091 = ("Invalid extension attribute {name}: expected callable or None, "
"but got: {value}")
2018-04-03 22:40:29 +03:00
E092 = ("Could not find or assign name for word vectors. Ususally, the "
"name is read from the model's meta.json in vector.name. "
"Alternatively, it is built from the 'lang' and 'name' keys in "
"the meta.json. Vector names are required to avoid issue #1660.")
E093 = ("token.ent_iob values make invalid sequence: I without B\n{seq}")
E094 = ("Error reading line {line_num} in vectors file {loc}.")
E095 = ("Can't write to frozen dictionary. This is likely an internal "
"error. Are you writing to a default function argument?")
E096 = ("Invalid object passed to displaCy: Can only visualize Doc or "
"Span objects, or dicts if set to manual=True.")
E097 = ("Invalid pattern: expected token pattern (list of dicts) or "
"phrase pattern (string) but got:\n{pattern}")
E098 = ("Invalid pattern specified: expected both SPEC and PATTERN.")
E099 = ("First node of pattern should be a root node. The root should "
"only contain NODE_NAME.")
E100 = ("Nodes apart from the root should contain NODE_NAME, NBOR_NAME and "
"NBOR_RELOP.")
E101 = ("NODE_NAME should be a new node and NBOR_NAME should already have "
"have been declared in previous edges.")
2019-02-24 17:11:28 +03:00
E102 = ("Can't merge non-disjoint spans. '{token}' is already part of "
"tokens to merge. If you want to find the longest non-overlapping "
"spans, you can use the util.filter_spans helper:\n"
"https://spacy.io/api/top-level#util.filter_spans")
2019-08-20 17:03:45 +03:00
E103 = ("Trying to set conflicting doc.ents: '{span1}' and '{span2}'. A "
"token can only be part of one entity, so make sure the entities "
"you're setting don't overlap.")
💫 New JSON helpers, training data internals & CLI rewrite (#2932) * 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
2018-11-30 22:16:14 +03:00
E105 = ("The Doc.print_tree() method is now deprecated. Please use "
"Doc.to_json() instead or write your own function.")
💫 New JSON helpers, training data internals & CLI rewrite (#2932) * 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
2018-11-30 22:16:14 +03:00
E106 = ("Can't find doc._.{attr} attribute specified in the underscore "
"settings: {opts}")
E107 = ("Value of doc._.{attr} is not JSON-serializable: {value}")
E108 = ("As of spaCy v2.1, the pipe name `sbd` has been deprecated "
"in favor of the pipe name `sentencizer`, which does the same "
"thing. For example, use `nlp.create_pipeline('sentencizer')`")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
E109 = ("Component '{name}' could not be run. Did you forget to "
"call begin_training()?")
E110 = ("Invalid displaCy render wrapper. Expected callable, got: {obj}")
E111 = ("Pickling a token is not supported, because tokens are only views "
"of the parent Doc and can't exist on their own. A pickled token "
"would always have to include its Doc and Vocab, which has "
"practically no advantage over pickling the parent Doc directly. "
"So instead of pickling the token, pickle the Doc it belongs to.")
2019-02-13 15:22:05 +03:00
E112 = ("Pickling a span is not supported, because spans are only views "
"of the parent Doc and can't exist on their own. A pickled span "
"would always have to include its Doc and Vocab, which has "
"practically no advantage over pickling the parent Doc directly. "
"So instead of pickling the span, pickle the Doc it belongs to or "
"use Span.as_doc to convert the span to a standalone Doc object.")
2019-02-24 17:11:28 +03:00
E115 = ("All subtokens must have associated heads.")
2019-10-02 11:37:39 +03:00
E116 = ("Cannot currently add labels to pretrained text classifier. Add "
"labels before training begins. This functionality was available "
"in previous versions, but had significant bugs that led to poor "
2019-02-24 17:11:28 +03:00
"performance.")
E117 = ("The newly split tokens must match the text of the original token. "
2019-02-17 14:22:07 +03:00
"New orths: {new}. Old text: {old}.")
E118 = ("The custom extension attribute '{attr}' is not registered on the "
"Token object so it can't be set during retokenization. To "
"register an attribute, use the Token.set_extension classmethod.")
2019-08-20 17:03:45 +03:00
E119 = ("Can't set custom extension attribute '{attr}' during "
"retokenization because it's not writable. This usually means it "
"was registered with a getter function (and no setter) or as a "
"method extension, so the value is computed dynamically. To "
"overwrite a custom attribute manually, it should be registered "
"with a default value or with a getter AND setter.")
E120 = ("Can't set custom extension attributes during retokenization. "
"Expected dict mapping attribute names to values, but got: {value}")
E121 = ("Can't bulk merge spans. Attribute length {attr_len} should be "
"equal to span length ({span_len}).")
E122 = ("Cannot find token to be split. Did it get merged?")
E123 = ("Cannot find head of token to be split. Did it get merged?")
E125 = ("Unexpected value: {value}")
E126 = ("Unexpected matcher predicate: '{bad}'. Expected one of: {good}. "
"This is likely a bug in spaCy, so feel free to open an issue.")
E128 = ("Unsupported serialization argument: '{arg}'. The use of keyword "
"arguments to exclude fields from being serialized or deserialized "
"is now deprecated. Please use the `exclude` argument instead. "
"For example: exclude=['{arg}'].")
E129 = ("Cannot write the label of an existing Span object because a Span "
2019-08-20 17:03:45 +03:00
"is a read-only view of the underlying Token objects stored in the "
"Doc. Instead, create a new Span object and specify the `label` "
"keyword argument, for example:\nfrom spacy.tokens import Span\n"
"span = Span(doc, start={start}, end={end}, label='{label}')")
E130 = ("You are running a narrow unicode build, which is incompatible "
"with spacy >= 2.1.0. To fix this, reinstall Python and use a wide "
"unicode build instead. You can also rebuild Python and set the "
"--enable-unicode=ucs4 flag.")
E131 = ("Cannot write the kb_id of an existing Span object because a Span "
2019-08-20 17:03:45 +03:00
"is a read-only view of the underlying Token objects stored in "
"the Doc. Instead, create a new Span object and specify the "
"`kb_id` keyword argument, for example:\nfrom spacy.tokens "
"import Span\nspan = Span(doc, start={start}, end={end}, "
"label='{label}', kb_id='{kb_id}')")
E132 = ("The vectors for entities and probabilities for alias '{alias}' "
"should have equal length, but found {entities_length} and "
"{probabilities_length} respectively.")
E133 = ("The sum of prior probabilities for alias '{alias}' should not "
"exceed 1, but found {sum}.")
E134 = ("Entity '{entity}' is not defined in the Knowledge Base.")
E135 = ("If you meant to replace a built-in component, use `create_pipe`: "
"`nlp.replace_pipe('{name}', nlp.create_pipe('{name}'))`")
2019-08-20 17:03:45 +03:00
E137 = ("Expected 'dict' type, but got '{type}' from '{line}'. Make sure "
"to provide a valid JSON object as input with either the `text` "
"or `tokens` key. For more info, see the docs:\n"
"https://spacy.io/api/cli#pretrain-jsonl")
2019-08-20 17:03:45 +03:00
E138 = ("Invalid JSONL format for raw text '{text}'. Make sure the input "
"includes either the `text` or `tokens` key. For more info, see "
"the docs:\nhttps://spacy.io/api/cli#pretrain-jsonl")
E139 = ("Knowledge Base for component '{name}' is empty.")
2019-08-20 17:03:45 +03:00
E140 = ("The list of entities, prior probabilities and entity vectors "
"should be of equal length.")
E141 = ("Entity vectors should be of length {required} instead of the "
"provided {found}.")
E143 = ("Labels for component '{name}' not initialized. Did you forget to "
"call add_label()?")
E145 = ("Error reading `{param}` from input file.")
E146 = ("Could not access `{path}`.")
2019-08-20 17:03:45 +03:00
E147 = ("Unexpected error in the {method} functionality of the "
"EntityLinker: {msg}. This is likely a bug in spaCy, so feel free "
"to open an issue.")
E148 = ("Expected {ents} KB identifiers but got {ids}. Make sure that "
"each entity in `doc.ents` is assigned to a KB identifier.")
E149 = ("Error deserializing model. Check that the config used to create "
"the component matches the model being loaded.")
E150 = ("The language of the `nlp` object and the `vocab` should be the "
"same, but found '{nlp}' and '{vocab}' respectively.")
2019-08-21 15:00:37 +03:00
E152 = ("The attribute {attr} is not supported for token patterns. "
"Please use the option validate=True with Matcher, PhraseMatcher, "
"or EntityRuler for more details.")
E153 = ("The value type {vtype} is not supported for token patterns. "
"Please use the option validate=True with Matcher, PhraseMatcher, "
"or EntityRuler for more details.")
E154 = ("One of the attributes or values is not supported for token "
"patterns. Please use the option validate=True with Matcher, "
"PhraseMatcher, or EntityRuler for more details.")
E155 = ("The pipeline needs to include a tagger in order to use "
"Matcher or PhraseMatcher with the attributes POS, TAG, or LEMMA. "
"Try using nlp() instead of nlp.make_doc() or list(nlp.pipe()) "
"instead of list(nlp.tokenizer.pipe()).")
2019-08-21 15:00:37 +03:00
E156 = ("The pipeline needs to include a parser in order to use "
"Matcher or PhraseMatcher with the attribute DEP. Try using "
2019-08-21 15:00:37 +03:00
"nlp() instead of nlp.make_doc() or list(nlp.pipe()) instead of "
"list(nlp.tokenizer.pipe()).")
E157 = ("Can't render negative values for dependency arc start or end. "
"Make sure that you're passing in absolute token indices, not "
"relative token offsets.\nstart: {start}, end: {end}, label: "
"{label}, direction: {dir}")
E158 = ("Can't add table '{name}' to lookups because it already exists.")
E159 = ("Can't find table '{name}' in lookups. Available tables: {tables}")
E160 = ("Can't find language data file: {path}")
E161 = ("Found an internal inconsistency when predicting entity links. "
"This is likely a bug in spaCy, so feel free to open an issue.")
Add textcat to train CLI (#4226) * Add doc.cats to spacy.gold at the paragraph level Support `doc.cats` as `"cats": [{"label": string, "value": number}]` in the spacy JSON training format at the paragraph level. * `spacy.gold.docs_to_json()` writes `docs.cats` * `GoldCorpus` reads in cats in each `GoldParse` * Update instances of gold_tuples to handle cats Update iteration over gold_tuples / gold_parses to handle addition of cats at the paragraph level. * Add textcat to train CLI * Add textcat options to train CLI * Add textcat labels in `TextCategorizer.begin_training()` * Add textcat evaluation to `Scorer`: * For binary exclusive classes with provided label: F1 for label * For 2+ exclusive classes: F1 macro average * For multilabel (not exclusive): ROC AUC macro average (currently relying on sklearn) * Provide user info on textcat evaluation settings, potential incompatibilities * Provide pipeline to Scorer in `Language.evaluate` for textcat config * Customize train CLI output to include only metrics relevant to current pipeline * Add textcat evaluation to evaluate CLI * Fix handling of unset arguments and config params Fix handling of unset arguments and model confiug parameters in Scorer initialization. * Temporarily add sklearn requirement * Remove sklearn version number * Improve Scorer handling of models without textcats * Fixing Scorer handling of models without textcats * Update Scorer output for python 2.7 * Modify inf in Scorer for python 2.7 * Auto-format Also make small adjustments to make auto-formatting with black easier and produce nicer results * Move error message to Errors * Update documentation * Add cats to annotation JSON format [ci skip] * Fix tpl flag and docs [ci skip] * Switch to internal roc_auc_score Switch to internal `roc_auc_score()` adapted from scikit-learn. * Add AUCROCScore tests and improve errors/warnings * Add tests for AUCROCScore and roc_auc_score * Add missing error for only positive/negative values * Remove unnecessary warnings and errors * Make reduced roc_auc_score functions private Because most of the checks and warnings have been stripped for the internal functions and access is only intended through `ROCAUCScore`, make the functions for roc_auc_score adapted from scikit-learn private. * Check that data corresponds with multilabel flag Check that the training instances correspond with the multilabel flag, adding the multilabel flag if required. * Add textcat score to early stopping check * Add more checks to debug-data for textcat * Add example training data for textcat * Add more checks to textcat train CLI * Check configuration when extending base model * Fix typos * Update textcat example data * Provide licensing details and licenses for data * Remove two labels with no positive instances from jigsaw-toxic-comment data. Co-authored-by: Ines Montani <ines@ines.io>
2019-09-15 23:31:31 +03:00
E162 = ("Cannot evaluate textcat model on data with different labels.\n"
"Labels in model: {model_labels}\nLabels in evaluation "
"data: {eval_labels}")
E163 = ("cumsum was found to be unstable: its last element does not "
"correspond to sum")
E164 = ("x is neither increasing nor decreasing: {}.")
E165 = ("Only one class present in y_true. ROC AUC score is not defined in "
"that case.")
2019-09-18 21:23:21 +03:00
E166 = ("Can only merge DocBins with the same pre-defined attributes.\n"
"Current DocBin: {current}\nOther DocBin: {other}")
E169 = ("Can't find module: {module}")
E170 = ("Cannot apply transition {name}: invalid for the current state.")
E171 = ("Matcher.add received invalid on_match callback argument: expected "
"callable or None, but got: {arg_type}")
E172 = ("The Lemmatizer.load classmethod is deprecated. To create a "
"Lemmatizer, initialize the class directly. See the docs for "
"details: https://spacy.io/api/lemmatizer")
E173 = ("As of v2.2, the Lemmatizer is initialized with an instance of "
"Lookups containing the lemmatization tables. See the docs for "
"details: https://spacy.io/api/lemmatizer#init")
E175 = ("Can't remove rule for unknown match pattern ID: {key}")
E176 = ("Alias '{alias}' is not defined in the Knowledge Base.")
E177 = ("Ill-formed IOB input detected: {tag}")
E178 = ("Invalid pattern. Expected list of dicts but got: {pat}. Maybe you "
"accidentally passed a single pattern to Matcher.add instead of a "
"list of patterns? If you only want to add one pattern, make sure "
"to wrap it in a list. For example: matcher.add('{key}', [pattern])")
E179 = ("Invalid pattern. Expected a list of Doc objects but got a single "
"Doc. If you only want to add one pattern, make sure to wrap it "
"in a list. For example: matcher.add('{key}', [doc])")
E180 = ("Span attributes can't be declared as required or assigned by "
"components, since spans are only views of the Doc. Use Doc and "
"Token attributes (or custom extension attributes) only and remove "
"the following: {attrs}")
E181 = ("Received invalid attributes for unkown object {obj}: {attrs}. "
"Only Doc and Token attributes are supported.")
E182 = ("Received invalid attribute declaration: {attr}\nDid you forget "
"to define the attribute? For example: {attr}.???")
E183 = ("Received invalid attribute declaration: {attr}\nOnly top-level "
"attributes are supported, for example: {solution}")
E184 = ("Only attributes without underscores are supported in component "
"attribute declarations (because underscore and non-underscore "
"attributes are connected anyways): {attr} -> {solution}")
E185 = ("Received invalid attribute in component attribute declaration: "
"{obj}.{attr}\nAttribute '{attr}' does not exist on {obj}.")
2019-10-28 14:36:23 +03:00
E186 = ("'{tok_a}' and '{tok_b}' are different texts.")
E187 = ("Only unicode strings are supported as labels.")
E189 = ("Each argument to `get_doc` should be of equal length.")
E190 = ("Token head out of range in `Doc.from_array()` for token index "
"'{index}' with value '{value}' (equivalent to relative head "
"index: '{rel_head_index}'). The head indices should be relative "
"to the current token index rather than absolute indices in the "
"array.")
E191 = ("Invalid head: the head token must be from the same doc as the "
"token itself.")
E192 = ("Unable to resize vectors in place with cupy.")
E193 = ("Unable to resize vectors in place if the resized vector dimension "
"({new_dim}) is not the same as the current vector dimension "
"({curr_dim}).")
E194 = ("Unable to aligned mismatched text '{text}' and words '{words}'.")
E195 = ("Matcher can be called on {good} only, got {got}.")
E196 = ("Refusing to write to token.is_sent_end. Sentence boundaries can "
"only be fixed with token.is_sent_start.")
E197 = ("Row out of bounds, unable to add row {row} for key {key}.")
E198 = ("Unable to return {n} most similar vectors for the current vectors "
"table, which contains {n_rows} vectors.")
2020-05-22 11:14:34 +03:00
E199 = ("Unable to merge 0-length span at doc[{start}:{end}].")
2019-02-13 17:29:08 +03:00
2019-12-21 20:55:03 +03:00
# TODO: fix numbering after merging develop into master
E971 = ("Found incompatible lengths in Doc.from_array: {array_length} for the "
"array and {doc_length} for the Doc itself.")
E972 = ("Example.__init__ got None for '{arg}'. Requires Doc.")
E973 = ("Unexpected type for NER data")
E974 = ("Unknown {obj} attribute: {key}")
E975 = ("The method Example.from_dict expects a Doc as first argument, "
"but got {type}")
E976 = ("The method Example.from_dict expects a dict as second argument, "
"but received None.")
E977 = ("Can not compare a MorphAnalysis with a string object. "
"This is likely a bug in spaCy, so feel free to open an issue.")
Improve spacy.gold (no GoldParse, no json format!) (#5555) * Update errors * Remove beam for now (maybe) Remove beam_utils Update setup.py Remove beam * Remove GoldParse WIP on removing goldparse Get ArcEager compiling after GoldParse excise Update setup.py Get spacy.syntax compiling after removing GoldParse Rename NewExample -> Example and clean up Clean html files Start updating tests Update Morphologizer * fix error numbers * fix merge conflict * informative error when calling to_array with wrong field * fix error catching * fixing language and scoring tests * start testing get_aligned * additional tests for new get_aligned function * Draft create_gold_state for arc_eager oracle * Fix import * Fix import * Remove TokenAnnotation code from nonproj * fixing NER one-to-many alignment * Fix many-to-one IOB codes * fix test for misaligned * attempt to fix cases with weird spaces * fix spaces * test_gold_biluo_different_tokenization works * allow None as BILUO annotation * fixed some tests + WIP roundtrip unit test * add spaces to json output format * minibatch utiltiy can deal with strings, docs or examples * fix augment (needs further testing) * various fixes in scripts - needs to be further tested * fix test_cli * cleanup * correct silly typo * add support for MORPH in to/from_array, fix morphologizer overfitting test * fix tagger * fix entity linker * ensure test keeps working with non-linked entities * pipe() takes docs, not examples * small bug fix * textcat bugfix * throw informative error when running the components with the wrong type of objects * fix parser tests to work with example (most still failing) * fix BiluoPushDown parsing entities * small fixes * bugfix tok2vec * fix renames and simple_ner labels * various small fixes * prevent writing dummy values like deps because that could interfer with sent_start values * fix the fix * implement split_sent with aligned SENT_START attribute * test for split sentences with various alignment issues, works * Return ArcEagerGoldParse from ArcEager * Update parser and NER gold stuff * Draft new GoldCorpus class * add links to to_dict * clean up * fix test checking for variants * Fix oracles * Start updating converters * Move converters under spacy.gold * Move things around * Fix naming * Fix name * Update converter to produce DocBin * Update converters * Allow DocBin to take list of Doc objects. * Make spacy convert output docbin * Fix import * Fix docbin * Fix compile in ArcEager * Fix import * Serialize all attrs by default * Update converter * Remove jsonl converter * Add json2docs converter * Draft Corpus class for DocBin * Work on train script * Update Corpus * Update DocBin * Allocate Doc before starting to add words * Make doc.from_array several times faster * Update train.py * Fix Corpus * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests * Skip tests that cause crashes * Skip test causing segfault * Remove GoldCorpus * Update imports * Update after removing GoldCorpus * Fix module name of corpus * Fix mimport * Work on parser oracle * Update arc_eager oracle * Restore ArcEager.get_cost function * Update transition system * Update test_arc_eager_oracle * Remove beam test * Update test * Unskip * Unskip tests * add links to to_dict * clean up * fix test checking for variants * Allow DocBin to take list of Doc objects. * Fix compile in ArcEager * Serialize all attrs by default Move converters under spacy.gold Move things around Fix naming Fix name Update converter to produce DocBin Update converters Make spacy convert output docbin Fix import Fix docbin Fix import Update converter Remove jsonl converter Add json2docs converter * Allocate Doc before starting to add words * Make doc.from_array several times faster * Start updating converters * Work on train script * Draft Corpus class for DocBin Update Corpus Fix Corpus * Update DocBin Add missing strings when serializing * Update train.py * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests Skip tests that cause crashes Skip test causing segfault * Remove GoldCorpus Update imports Update after removing GoldCorpus Fix module name of corpus Fix mimport * Work on parser oracle Update arc_eager oracle Restore ArcEager.get_cost function Update transition system * Update tests Remove beam test Update test Unskip Unskip tests * Add get_aligned_parse method in Example Fix Example.get_aligned_parse * Add kwargs to Corpus.dev_dataset to match train_dataset * Update nonproj * Use get_aligned_parse in ArcEager * Add another arc-eager oracle test * Remove Example.doc property Remove Example.doc Remove Example.doc Remove Example.doc Remove Example.doc * Update ArcEager oracle Fix Break oracle * Debugging * Fix Corpus * Fix eg.doc * Format * small fixes * limit arg for Corpus * fix test_roundtrip_docs_to_docbin * fix test_make_orth_variants * fix add_label test * Update tests * avoid writing temp dir in json2docs, fixing 4402 test * Update test * Add missing costs to NER oracle * Update test * Work on Example.get_aligned_ner method * Clean up debugging * Xfail tests * Remove prints * Remove print * Xfail some tests * Replace unseen labels for parser * Update test * Update test * Xfail test * Fix Corpus * fix imports * fix docs_to_json * various small fixes * cleanup * Support gold_preproc in Corpus * Support gold_preproc * Pass gold_preproc setting into corpus * Remove debugging * Fix gold_preproc * Fix json2docs converter * Fix convert command * Fix flake8 * Fix import * fix output_dir (converted to Path by typer) * fix var * bugfix: update states after creating golds to avoid out of bounds indexing * Improve efficiency of ArEager oracle * pull merge_sent into iob2docs to avoid Doc creation for each line * fix asserts * bugfix excl Span.end in iob2docs * Support max_length in Corpus * Fix arc_eager oracle * Filter out uannotated sentences in NER * Remove debugging in parser * Simplify NER alignment * Fix conversion of NER data * Fix NER init_gold_batch * Tweak efficiency of precomputable affine * Update onto-json default * Update gold test for NER * Fix parser test * Update test * Add NER data test * Fix convert for single file * Fix test * Hack scorer to avoid evaluating non-nered data * Fix handling of NER data in Example * Output unlabelled spans from O biluo tags in iob_utils * Fix unset variable * Return kept examples from init_gold_batch * Return examples from init_gold_batch * Dont return Example from init_gold_batch * Set spaces on gold doc after conversion * Add test * Fix spaces reading * Improve NER alignment * Improve handling of missing values in NER * Restore the 'cutting' in parser training * Add assertion * Print epochs * Restore random cuts in parser/ner training * Implement Doc.copy * Implement Example.copy * Copy examples at the start of Language.update * Don't unset example docs * Tweak parser model slightly * attempt to fix _guess_spaces * _add_entities_to_doc first, so that links don't get overwritten * fixing get_aligned_ner for one-to-many * fix indexing into x_text * small fix biluo_tags_from_offsets * Add onto-ner config * Simplify NER alignment * Fix NER scoring for partially annotated documents * fix indexing into x_text * fix test_cli failing tests by ignoring spans in doc.ents with empty label * Fix limit * Improve NER alignment * Fix count_train * Remove print statement * fix tests, we're not having nothing but None * fix clumsy fingers * Fix tests * Fix doc.ents * Remove empty docs in Corpus and improve limit * Update config Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
2020-06-26 20:34:12 +03:00
E978 = ("The {method} method of component {name} takes a list of Example objects, "
"but found {types} instead.")
E979 = ("Cannot convert {type} to an Example object.")
E980 = ("Each link annotation should refer to a dictionary with at most one "
"identifier mapping to 1.0, and all others to 0.0.")
E981 = ("The offsets of the annotations for 'links' need to refer exactly "
"to the offsets of the 'entities' annotations.")
E982 = ("The 'ent_iob' attribute of a Token should be an integer indexing "
"into {values}, but found {value}.")
E983 = ("Invalid key for '{dict}': {key}. Available keys: "
"{keys}")
E985 = ("The pipeline component '{component}' is already available in the base "
"model. The settings in the component block in the config file are "
"being ignored. If you want to replace this component instead, set "
"'replace' to True in the training configuration.")
2020-06-03 11:00:21 +03:00
E986 = ("Could not create any training batches: check your input. "
"Perhaps discard_oversize should be set to False ?")
E987 = ("The text of an example training instance is either a Doc or "
"a string, but found {type} instead.")
E988 = ("Could not parse any training examples. Ensure the data is "
"formatted correctly.")
E989 = ("'nlp.update()' was called with two positional arguments. This "
"may be due to a backwards-incompatible change to the format "
"of the training data in spaCy 3.0 onwards. The 'update' "
"function should now be called with a batch of 'Example' "
"objects, instead of (text, annotation) tuples. ")
E990 = ("An entity linking component needs to be initialized with a "
"KnowledgeBase object, but found {type} instead.")
E991 = ("The function 'select_pipes' should be called with either a "
"'disable' argument to list the names of the pipe components "
"that should be disabled, or with an 'enable' argument that "
"specifies which pipes should not be disabled.")
E992 = ("The function `select_pipes` was called with `enable`={enable} "
"and `disable`={disable} but that information is conflicting "
"for the `nlp` pipeline with components {names}.")
Default settings to configurations (#4995) * fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
2020-02-27 20:42:27 +03:00
E993 = ("The config for 'nlp' should include either a key 'name' to "
"refer to an existing model by name or path, or a key 'lang' "
"to create a new blank model.")
E996 = ("Could not parse {file}: {msg}")
2019-12-21 20:55:03 +03:00
E997 = ("Tokenizer special cases are not allowed to modify the text. "
Generalize handling of tokenizer special cases (#4259) * Generalize handling of tokenizer special cases Handle tokenizer special cases more generally by using the Matcher internally to match special cases after the affix/token_match tokenization is complete. Instead of only matching special cases while processing balanced or nearly balanced prefixes and suffixes, this recognizes special cases in a wider range of contexts: * Allows arbitrary numbers of prefixes/affixes around special cases * Allows special cases separated by infixes Existing tests/settings that couldn't be preserved as before: * The emoticon '")' is no longer a supported special case * The emoticon ':)' in "example:)" is a false positive again When merged with #4258 (or the relevant cache bugfix), the affix and token_match properties should be modified to flush and reload all special cases to use the updated internal tokenization with the Matcher. * Remove accidentally added test case * Really remove accidentally added test * Reload special cases when necessary Reload special cases when affixes or token_match are modified. Skip reloading during initialization. * Update error code number * Fix offset and whitespace in Matcher special cases * Fix offset bugs when merging and splitting tokens * Set final whitespace on final token in inserted special case * Improve cache flushing in tokenizer * Separate cache and specials memory (temporarily) * Flush cache when adding special cases * Repeated `self._cache = PreshMap()` and `self._specials = PreshMap()` are necessary due to this bug: https://github.com/explosion/preshed/issues/21 * Remove reinitialized PreshMaps on cache flush * Update UD bin scripts * Update imports for `bin/` * Add all currently supported languages * Update subtok merger for new Matcher validation * Modify blinded check to look at tokens instead of lemmas (for corpora with tokens but not lemmas like Telugu) * Use special Matcher only for cases with affixes * Reinsert specials cache checks during normal tokenization for special cases as much as possible * Additionally include specials cache checks while splitting on infixes * Since the special Matcher needs consistent affix-only tokenization for the special cases themselves, introduce the argument `with_special_cases` in order to do tokenization with or without specials cache checks * After normal tokenization, postprocess with special cases Matcher for special cases containing affixes * Replace PhraseMatcher with Aho-Corasick Replace PhraseMatcher with the Aho-Corasick algorithm over numpy arrays of the hash values for the relevant attribute. The implementation is based on FlashText. The speed should be similar to the previous PhraseMatcher. It is now possible to easily remove match IDs and matches don't go missing with large keyword lists / vocabularies. Fixes #4308. * Restore support for pickling * Fix internal keyword add/remove for numpy arrays * Add test for #4248, clean up test * Improve efficiency of special cases handling * Use PhraseMatcher instead of Matcher * Improve efficiency of merging/splitting special cases in document * Process merge/splits in one pass without repeated token shifting * Merge in place if no splits * Update error message number * Remove UD script modifications Only used for timing/testing, should be a separate PR * Remove final traces of UD script modifications * Update UD bin scripts * Update imports for `bin/` * Add all currently supported languages * Update subtok merger for new Matcher validation * Modify blinded check to look at tokens instead of lemmas (for corpora with tokens but not lemmas like Telugu) * Add missing loop for match ID set in search loop * Remove cruft in matching loop for partial matches There was a bit of unnecessary code left over from FlashText in the matching loop to handle partial token matches, which we don't have with PhraseMatcher. * Replace dict trie with MapStruct trie * Fix how match ID hash is stored/added * Update fix for match ID vocab * Switch from map_get_unless_missing to map_get * Switch from numpy array to Token.get_struct_attr Access token attributes directly in Doc instead of making a copy of the relevant values in a numpy array. Add unsatisfactory warning for hash collision with reserved terminal hash key. (Ideally it would change the reserved terminal hash and redo the whole trie, but for now, I'm hoping there won't be collisions.) * Restructure imports to export find_matches * Implement full remove() Remove unnecessary trie paths and free unused maps. Parallel to Matcher, raise KeyError when attempting to remove a match ID that has not been added. * Switch to PhraseMatcher.find_matches * Switch to local cdef functions for span filtering * Switch special case reload threshold to variable Refer to variable instead of hard-coded threshold * Move more of special case retokenize to cdef nogil Move as much of the special case retokenization to nogil as possible. * Rewrap sort as stdsort for OS X * Rewrap stdsort with specific types * Switch to qsort * Fix merge * Improve cmp functions * Fix realloc * Fix realloc again * Initialize span struct while retokenizing * Temporarily skip retokenizing * Revert "Move more of special case retokenize to cdef nogil" This reverts commit 0b7e52c797cd8ff1548f214bd4186ebb3a7ce8b1. * Revert "Switch to qsort" This reverts commit a98d71a942fc9bca531cf5eb05cf89fa88153b60. * Fix specials check while caching * Modify URL test with emoticons The multiple suffix tests result in the emoticon `:>`, which is now retokenized into one token as a special case after the suffixes are split off. * Refactor _apply_special_cases() * Use cdef ints for span info used in multiple spots * Modify _filter_special_spans() to prefer earlier Parallel to #4414, modify _filter_special_spans() so that the earlier span is preferred for overlapping spans of the same length. * Replace MatchStruct with Entity Replace MatchStruct with Entity since the existing Entity struct is nearly identical. * Replace Entity with more general SpanC * Replace MatchStruct with SpanC * Add error in debug-data if no dev docs are available (see #4575) * Update azure-pipelines.yml * Revert "Update azure-pipelines.yml" This reverts commit ed1060cf59e5895b5fe92ad5b894fd1078ec4c49. * Use latest wasabi * Reorganise install_requires * add dframcy to universe.json (#4580) * Update universe.json [ci skip] * Fix multiprocessing for as_tuples=True (#4582) * Fix conllu script (#4579) * force extensions to avoid clash between example scripts * fix arg order and default file encoding * add example config for conllu script * newline * move extension definitions to main function * few more encodings fixes * Add load_from_docbin example [ci skip] TODO: upload the file somewhere * Update README.md * Add warnings about 3.8 (resolves #4593) [ci skip] * Fixed typo: Added space between "recognize" and "various" (#4600) * Fix DocBin.merge() example (#4599) * Replace function registries with catalogue (#4584) * Replace functions registries with catalogue * Update __init__.py * Fix test * Revert unrelated flag [ci skip] * Bugfix/dep matcher issue 4590 (#4601) * add contributor agreement for prilopes * add test for issue #4590 * fix on_match params for DependencyMacther (#4590) * Minor updates to language example sentences (#4608) * Add punctuation to Spanish example sentences * Combine multilanguage examples for lang xx * Add punctuation to nb examples * Always realloc to a larger size Avoid potential (unlikely) edge case and cymem error seen in #4604. * Add error in debug-data if no dev docs are available (see #4575) * Update debug-data for GoldCorpus / Example * Ignore None label in misaligned NER data
2019-11-13 23:24:35 +03:00
"This would map '{chunk}' to '{orth}' given token attributes "
"'{token_attrs}'.")
Improve spacy.gold (no GoldParse, no json format!) (#5555) * Update errors * Remove beam for now (maybe) Remove beam_utils Update setup.py Remove beam * Remove GoldParse WIP on removing goldparse Get ArcEager compiling after GoldParse excise Update setup.py Get spacy.syntax compiling after removing GoldParse Rename NewExample -> Example and clean up Clean html files Start updating tests Update Morphologizer * fix error numbers * fix merge conflict * informative error when calling to_array with wrong field * fix error catching * fixing language and scoring tests * start testing get_aligned * additional tests for new get_aligned function * Draft create_gold_state for arc_eager oracle * Fix import * Fix import * Remove TokenAnnotation code from nonproj * fixing NER one-to-many alignment * Fix many-to-one IOB codes * fix test for misaligned * attempt to fix cases with weird spaces * fix spaces * test_gold_biluo_different_tokenization works * allow None as BILUO annotation * fixed some tests + WIP roundtrip unit test * add spaces to json output format * minibatch utiltiy can deal with strings, docs or examples * fix augment (needs further testing) * various fixes in scripts - needs to be further tested * fix test_cli * cleanup * correct silly typo * add support for MORPH in to/from_array, fix morphologizer overfitting test * fix tagger * fix entity linker * ensure test keeps working with non-linked entities * pipe() takes docs, not examples * small bug fix * textcat bugfix * throw informative error when running the components with the wrong type of objects * fix parser tests to work with example (most still failing) * fix BiluoPushDown parsing entities * small fixes * bugfix tok2vec * fix renames and simple_ner labels * various small fixes * prevent writing dummy values like deps because that could interfer with sent_start values * fix the fix * implement split_sent with aligned SENT_START attribute * test for split sentences with various alignment issues, works * Return ArcEagerGoldParse from ArcEager * Update parser and NER gold stuff * Draft new GoldCorpus class * add links to to_dict * clean up * fix test checking for variants * Fix oracles * Start updating converters * Move converters under spacy.gold * Move things around * Fix naming * Fix name * Update converter to produce DocBin * Update converters * Allow DocBin to take list of Doc objects. * Make spacy convert output docbin * Fix import * Fix docbin * Fix compile in ArcEager * Fix import * Serialize all attrs by default * Update converter * Remove jsonl converter * Add json2docs converter * Draft Corpus class for DocBin * Work on train script * Update Corpus * Update DocBin * Allocate Doc before starting to add words * Make doc.from_array several times faster * Update train.py * Fix Corpus * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests * Skip tests that cause crashes * Skip test causing segfault * Remove GoldCorpus * Update imports * Update after removing GoldCorpus * Fix module name of corpus * Fix mimport * Work on parser oracle * Update arc_eager oracle * Restore ArcEager.get_cost function * Update transition system * Update test_arc_eager_oracle * Remove beam test * Update test * Unskip * Unskip tests * add links to to_dict * clean up * fix test checking for variants * Allow DocBin to take list of Doc objects. * Fix compile in ArcEager * Serialize all attrs by default Move converters under spacy.gold Move things around Fix naming Fix name Update converter to produce DocBin Update converters Make spacy convert output docbin Fix import Fix docbin Fix import Update converter Remove jsonl converter Add json2docs converter * Allocate Doc before starting to add words * Make doc.from_array several times faster * Start updating converters * Work on train script * Draft Corpus class for DocBin Update Corpus Fix Corpus * Update DocBin Add missing strings when serializing * Update train.py * Fix parser model * Start debugging arc_eager oracle * Update header * Fix parser declaration * Xfail some tests Skip tests that cause crashes Skip test causing segfault * Remove GoldCorpus Update imports Update after removing GoldCorpus Fix module name of corpus Fix mimport * Work on parser oracle Update arc_eager oracle Restore ArcEager.get_cost function Update transition system * Update tests Remove beam test Update test Unskip Unskip tests * Add get_aligned_parse method in Example Fix Example.get_aligned_parse * Add kwargs to Corpus.dev_dataset to match train_dataset * Update nonproj * Use get_aligned_parse in ArcEager * Add another arc-eager oracle test * Remove Example.doc property Remove Example.doc Remove Example.doc Remove Example.doc Remove Example.doc * Update ArcEager oracle Fix Break oracle * Debugging * Fix Corpus * Fix eg.doc * Format * small fixes * limit arg for Corpus * fix test_roundtrip_docs_to_docbin * fix test_make_orth_variants * fix add_label test * Update tests * avoid writing temp dir in json2docs, fixing 4402 test * Update test * Add missing costs to NER oracle * Update test * Work on Example.get_aligned_ner method * Clean up debugging * Xfail tests * Remove prints * Remove print * Xfail some tests * Replace unseen labels for parser * Update test * Update test * Xfail test * Fix Corpus * fix imports * fix docs_to_json * various small fixes * cleanup * Support gold_preproc in Corpus * Support gold_preproc * Pass gold_preproc setting into corpus * Remove debugging * Fix gold_preproc * Fix json2docs converter * Fix convert command * Fix flake8 * Fix import * fix output_dir (converted to Path by typer) * fix var * bugfix: update states after creating golds to avoid out of bounds indexing * Improve efficiency of ArEager oracle * pull merge_sent into iob2docs to avoid Doc creation for each line * fix asserts * bugfix excl Span.end in iob2docs * Support max_length in Corpus * Fix arc_eager oracle * Filter out uannotated sentences in NER * Remove debugging in parser * Simplify NER alignment * Fix conversion of NER data * Fix NER init_gold_batch * Tweak efficiency of precomputable affine * Update onto-json default * Update gold test for NER * Fix parser test * Update test * Add NER data test * Fix convert for single file * Fix test * Hack scorer to avoid evaluating non-nered data * Fix handling of NER data in Example * Output unlabelled spans from O biluo tags in iob_utils * Fix unset variable * Return kept examples from init_gold_batch * Return examples from init_gold_batch * Dont return Example from init_gold_batch * Set spaces on gold doc after conversion * Add test * Fix spaces reading * Improve NER alignment * Improve handling of missing values in NER * Restore the 'cutting' in parser training * Add assertion * Print epochs * Restore random cuts in parser/ner training * Implement Doc.copy * Implement Example.copy * Copy examples at the start of Language.update * Don't unset example docs * Tweak parser model slightly * attempt to fix _guess_spaces * _add_entities_to_doc first, so that links don't get overwritten * fixing get_aligned_ner for one-to-many * fix indexing into x_text * small fix biluo_tags_from_offsets * Add onto-ner config * Simplify NER alignment * Fix NER scoring for partially annotated documents * fix indexing into x_text * fix test_cli failing tests by ignoring spans in doc.ents with empty label * Fix limit * Improve NER alignment * Fix count_train * Remove print statement * fix tests, we're not having nothing but None * fix clumsy fingers * Fix tests * Fix doc.ents * Remove empty docs in Corpus and improve limit * Update config Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
2020-06-26 20:34:12 +03:00
2019-08-18 16:09:16 +03:00
@add_codes
class TempErrors(object):
2019-10-02 11:37:39 +03:00
T003 = ("Resizing pretrained Tagger models is not currently supported.")
T007 = ("Can't yet set {attr} from Span. Vote for this feature on the "
"issue tracker: http://github.com/explosion/spaCy/issues")
# fmt: on
class MatchPatternError(ValueError):
def __init__(self, key, errors):
"""Custom error for validating match patterns.
2020-05-24 18:20:58 +03:00
key (str): The name of the matcher rule.
errors (dict): Validation errors (sequence of strings) mapped to pattern
ID, i.e. the index of the added pattern.
"""
msg = f"Invalid token patterns for matcher rule '{key}'\n"
for pattern_idx, error_msgs in errors.items():
pattern_errors = "\n".join([f"- {e}" for e in error_msgs])
msg += f"\nPattern {pattern_idx}:\n{pattern_errors}\n"
ValueError.__init__(self, msg)
2019-10-28 14:36:23 +03:00
class AlignmentError(ValueError):
pass