spaCy/spacy/errors.py

432 lines
24 KiB
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
import os
import warnings
import inspect
def add_codes(err_cls):
"""Add error codes to string messages via class attribute names."""
class ErrorsWithCodes(object):
def __getattribute__(self, code):
msg = getattr(err_cls, code)
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.")
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.")
@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.disable_pipes()`, you should remove them explicitly with "
"`nlp.remove_pipe()` before the pipeline is restored. Names of "
"the new components: {names}")
E009 = ("The `update` method expects same number of docs and golds, but "
"got: {n_docs} docs, {n_golds} golds.")
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}")
E013 = ("Error selecting action in matcher")
E014 = ("Uknown tag ID: {tag}")
E015 = ("Conflicting morphology exception for ({tag}, {orth}). Use "
"`force=True` to overwrite.")
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}")
E018 = ("Can't retrieve string for hash '{hash_value}'.")
E019 = ("Can't create transition with unknown action ID: {action}. Action "
"IDs are enumerated in spacy/syntax/{src}.pyx.")
E020 = ("Could not find a gold-standard action to supervise the "
"dependency parser. The tree is non-projective (i.e. it has "
"crossing arcs - see spacy/syntax/nonproj.pyx for definitions). "
"The ArcEager transition system only supports projective trees. "
"To learn non-projective representations, transform the data "
"before training and after parsing. Either pass "
"`make_projective=True` to the GoldParse class, or use "
"spacy.syntax.nonproj.preprocess_training_data.")
E021 = ("Could not find a gold-standard action to supervise the "
"dependency parser. The GoldParse was projective. The transition "
"system has {n_actions} actions. State at failure: {state}")
E022 = ("Could not find a transition with the name '{name}' in the NER "
"model.")
E023 = ("Error cleaning up beam: The same state occurred twice at "
"memory address {addr} and position {i}.")
E024 = ("Could not find an optimal move to supervise the parser. Usually, "
"this means the GoldParse was not correct. For example, are all "
"labels added to the model?")
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}.")
E038 = ("Error finding sentence for span. Infinite loop detected.")
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}")
E049 = ("Can't find spaCy data directory: '{path}'. Check your "
"installation and permissions, or use spacy.util.set_data_path "
"to customise the location if necessary.")
E050 = ("Can't find model '{name}'. It doesn't seem to be a shortcut "
"link, a Python package or a valid path to a data directory.")
E051 = ("Cant' load '{name}'. If you're using a shortcut link, make sure "
"it points to a valid package (not just a data directory).")
E052 = ("Can't find model directory: {path}")
E053 = ("Could not read meta.json 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}).")
E061 = ("Bad file name: {filename}. Example of a valid file name: "
"'vectors.128.f.bin'")
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}.")
E066 = ("Error creating model helper for extracting columns. Can only "
"extract columns by positive integer. Got: {value}.")
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}'.")
E069 = ("Invalid gold-standard parse tree. Found cycle between word "
"IDs: {cycle}")
E070 = ("Invalid gold-standard data. Number of documents ({n_docs}) "
"does not align with number of annotations ({n_annots}).")
E071 = ("Error creating lexeme: specified orth ID ({orth}) does not "
"match the one in the vocab ({vocab_orth}).")
E072 = ("Error serializing lexeme: expected data length {length}, "
"got {bad_length}.")
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}.")
E075 = ("Error accepting match: length ({length}) > maximum length "
"({max_len}).")
E076 = ("Error setting tensor on Doc: tensor has {rows} rows, while Doc "
"has {words} words.")
E077 = ("Error computing {value}: number of Docs ({n_docs}) does not "
"equal number of GoldParse objects ({n_golds}) in batch.")
E078 = ("Error computing score: number of words in Doc ({words_doc}) does "
"not equal number of words in GoldParse ({words_gold}).")
E079 = ("Error computing states in beam: number of predicted beams "
"({pbeams}) does not equal number of gold beams ({gbeams}).")
E080 = ("Duplicate state found in beam: {key}.")
E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
"does not equal number of losses ({losses}).")
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}'.")
E086 = ("Error deserializing lexeme '{string}': orth ID {orth_id} does "
"not match hash {hash_id} in StringStore.")
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.")
💫 Port master changes over to develop (#2979) * Create aryaprabhudesai.md (#2681) * Update _install.jade (#2688) Typo fix: "models" -> "model" * Add FAC to spacy.explain (resolves #2706) * Remove docstrings for deprecated arguments (see #2703) * When calling getoption() in conftest.py, pass a default option (#2709) * When calling getoption() in conftest.py, pass a default option This is necessary to allow testing an installed spacy by running: pytest --pyargs spacy * Add contributor agreement * update bengali token rules for hyphen and digits (#2731) * Less norm computations in token similarity (#2730) * Less norm computations in token similarity * Contributor agreement * Remove ')' for clarity (#2737) Sorry, don't mean to be nitpicky, I just noticed this when going through the CLI and thought it was a quick fix. That said, if this was intention than please let me know. * added contributor agreement for mbkupfer (#2738) * Basic support for Telugu language (#2751) * Lex _attrs for polish language (#2750) * Signed spaCy contributor agreement * Added polish version of english lex_attrs * Introduces a bulk merge function, in order to solve issue #653 (#2696) * Fix comment * Introduce bulk merge to increase performance on many span merges * Sign contributor agreement * Implement pull request suggestions * Describe converters more explicitly (see #2643) * Add multi-threading note to Language.pipe (resolves #2582) [ci skip] * Fix formatting * Fix dependency scheme docs (closes #2705) [ci skip] * Don't set stop word in example (closes #2657) [ci skip] * Add words to portuguese language _num_words (#2759) * Add words to portuguese language _num_words * Add words to portuguese language _num_words * Update Indonesian model (#2752) * adding e-KTP in tokenizer exceptions list * add exception token * removing lines with containing space as it won't matter since we use .split() method in the end, added new tokens in exception * add tokenizer exceptions list * combining base_norms with norm_exceptions * adding norm_exception * fix double key in lemmatizer * remove unused import on punctuation.py * reformat stop_words to reduce number of lines, improve readibility * updating tokenizer exception * implement is_currency for lang/id * adding orth_first_upper in tokenizer_exceptions * update the norm_exception list * remove bunch of abbreviations * adding contributors file * Fixed spaCy+Keras example (#2763) * bug fixes in keras example * created contributor agreement * Adding French hyphenated first name (#2786) * Fix typo (closes #2784) * Fix typo (#2795) [ci skip] Fixed typo on line 6 "regcognizer --> recognizer" * Adding basic support for Sinhala language. (#2788) * adding Sinhala language package, stop words, examples and lex_attrs. * Adding contributor agreement * Updating contributor agreement * Also include lowercase norm exceptions * Fix error (#2802) * Fix error ValueError: cannot resize an array that references or is referenced by another array in this way. Use the resize function * added spaCy Contributor Agreement * Add charlax's contributor agreement (#2805) * agreement of contributor, may I introduce a tiny pl languge contribution (#2799) * Contributors agreement * Contributors agreement * Contributors agreement * Add jupyter=True to displacy.render in documentation (#2806) * Revert "Also include lowercase norm exceptions" This reverts commit 70f4e8adf37cfcfab60be2b97d6deae949b30e9e. * Remove deprecated encoding argument to msgpack * Set up dependency tree pattern matching skeleton (#2732) * Fix bug when too many entity types. Fixes #2800 * Fix Python 2 test failure * Require older msgpack-numpy * Restore encoding arg on msgpack-numpy * Try to fix version pin for msgpack-numpy * Update Portuguese Language (#2790) * Add words to portuguese language _num_words * Add words to portuguese language _num_words * Portuguese - Add/remove stopwords, fix tokenizer, add currency symbols * Extended punctuation and norm_exceptions in the Portuguese language * Correct error in spacy universe docs concerning spacy-lookup (#2814) * Update Keras Example for (Parikh et al, 2016) implementation (#2803) * bug fixes in keras example * created contributor agreement * baseline for Parikh model * initial version of parikh 2016 implemented * tested asymmetric models * fixed grevious error in normalization * use standard SNLI test file * begin to rework parikh example * initial version of running example * start to document the new version * start to document the new version * Update Decompositional Attention.ipynb * fixed calls to similarity * updated the README * import sys package duh * simplified indexing on mapping word to IDs * stupid python indent error * added code from https://github.com/tensorflow/tensorflow/issues/3388 for tf bug workaround * Fix typo (closes #2815) [ci skip] * Update regex version dependency * Set version to 2.0.13.dev3 * Skip seemingly problematic test * Remove problematic test * Try previous version of regex * Revert "Remove problematic test" This reverts commit bdebbef45552d698d390aa430b527ee27830f11b. * Unskip test * Try older version of regex * 💫 Update training examples and use minibatching (#2830) <!--- Provide a general summary of your changes in the title. --> ## Description Update the training examples in `/examples/training` to show usage of spaCy's `minibatch` and `compounding` helpers ([see here](https://spacy.io/usage/training#tips-batch-size) for details). The lack of batching in the examples has caused some confusion in the past, especially for beginners who would copy-paste the examples, update them with large training sets and experienced slow and unsatisfying results. ### Types of change enhancements ## 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. * Visual C++ link updated (#2842) (closes #2841) [ci skip] * New landing page * Add contribution agreement * Correcting lang/ru/examples.py (#2845) * Correct some grammatical inaccuracies in lang\ru\examples.py; filled Contributor Agreement * Correct some grammatical inaccuracies in lang\ru\examples.py * Move contributor agreement to separate file * Set version to 2.0.13.dev4 * Add Persian(Farsi) language support (#2797) * Also include lowercase norm exceptions * Remove in favour of https://github.com/explosion/spaCy/graphs/contributors * Rule-based French Lemmatizer (#2818) <!--- Provide a general summary of your changes in the title. --> ## Description <!--- Use this section to describe your changes. If your changes required testing, include information about the testing environment and the tests you ran. If your test fixes a bug reported in an issue, don't forget to include the issue number. If your PR is still a work in progress, that's totally fine – just include a note to let us know. --> Add a rule-based French Lemmatizer following the english one and the excellent PR for [greek language optimizations](https://github.com/explosion/spaCy/pull/2558) to adapt the Lemmatizer class. ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> - Lemma dictionary used can be found [here](http://infolingu.univ-mlv.fr/DonneesLinguistiques/Dictionnaires/telechargement.html), I used the XML version. - Add several files containing exhaustive list of words for each part of speech - Add some lemma rules - Add POS that are not checked in the standard Lemmatizer, i.e PRON, DET, ADV and AUX - Modify the Lemmatizer class to check in lookup table as a last resort if POS not mentionned - Modify the lemmatize function to check in lookup table as a last resort - Init files are updated so the model can support all the functionalities mentioned above - Add words to tokenizer_exceptions_list.py in respect to regex used in tokenizer_exceptions.py ## 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. * Set version to 2.0.13 * Fix formatting and consistency * Update docs for new version [ci skip] * Increment version [ci skip] * Add info on wheels [ci skip] * Adding "This is a sentence" example to Sinhala (#2846) * Add wheels badge * Update badge [ci skip] * Update README.rst [ci skip] * Update murmurhash pin * Increment version to 2.0.14.dev0 * Update GPU docs for v2.0.14 * Add wheel to setup_requires * Import prefer_gpu and require_gpu functions from Thinc * Add tests for prefer_gpu() and require_gpu() * Update requirements and setup.py * Workaround bug in thinc require_gpu * Set version to v2.0.14 * Update push-tag script * Unhack prefer_gpu * Require thinc 6.10.6 * Update prefer_gpu and require_gpu docs [ci skip] * Fix specifiers for GPU * Set version to 2.0.14.dev1 * Set version to 2.0.14 * Update Thinc version pin * Increment version * Fix msgpack-numpy version pin * Increment version * Update version to 2.0.16 * Update version [ci skip] * Redundant ')' in the Stop words' example (#2856) <!--- Provide a general summary of your changes in the title. --> ## Description <!--- Use this section to describe your changes. If your changes required testing, include information about the testing environment and the tests you ran. If your test fixes a bug reported in an issue, don't forget to include the issue number. If your PR is still a work in progress, that's totally fine – just include a note to let us know. --> ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> ## Checklist <!--- Before you submit the PR, go over this checklist and make sure you can tick off all the boxes. [] -> [x] --> - [ ] I have submitted the spaCy Contributor Agreement. - [ ] I ran the tests, and all new and existing tests passed. - [ ] My changes don't require a change to the documentation, or if they do, I've added all required information. * Documentation improvement regarding joblib and SO (#2867) Some documentation improvements ## Description 1. Fixed the dead URL to joblib 2. Fixed Stack Overflow brand name (with space) ### Types of change Documentation ## 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. * raise error when setting overlapping entities as doc.ents (#2880) * Fix out-of-bounds access in NER training The helper method state.B(1) gets the index of the first token of the buffer, or -1 if no such token exists. Normally this is safe because we pass this to functions like state.safe_get(), which returns an empty token. Here we used it directly as an array index, which is not okay! This error may have been the cause of out-of-bounds access errors during training. Similar errors may still be around, so much be hunted down. Hunting this one down took a long time...I printed out values across training runs and diffed, looking for points of divergence between runs, when no randomness should be allowed. * Change PyThaiNLP Url (#2876) * Fix missing comma * Add example showing a fix-up rule for space entities * Set version to 2.0.17.dev0 * Update regex version * Revert "Update regex version" This reverts commit 62358dd867d15bc6a475942dff34effba69dd70a. * Try setting older regex version, to align with conda * Set version to 2.0.17 * Add spacy-js to universe [ci-skip] * Add spacy-raspberry to universe (closes #2889) * Add script to validate universe json [ci skip] * Removed space in docs + added contributor indo (#2909) * - removed unneeded space in documentation * - added contributor info * Allow input text of length up to max_length, inclusive (#2922) * Include universe spec for spacy-wordnet component (#2919) * feat: include universe spec for spacy-wordnet component * chore: include spaCy contributor agreement * Minor formatting changes [ci skip] * Fix image [ci skip] Twitter URL doesn't work on live site * Check if the word is in one of the regular lists specific to each POS (#2886) * 💫 Create random IDs for SVGs to prevent ID clashes (#2927) Resolves #2924. ## Description Fixes problem where multiple visualizations in Jupyter notebooks would have clashing arc IDs, resulting in weirdly positioned arc labels. Generating a random ID prefix so even identical parses won't receive the same IDs for consistency (even if effect of ID clash isn't noticable here.) ### Types of change bug fix ## 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. * Fix typo [ci skip] * fixes symbolic link on py3 and windows (#2949) * fixes symbolic link on py3 and windows during setup of spacy using command python -m spacy link en_core_web_sm en closes #2948 * Update spacy/compat.py Co-Authored-By: cicorias <cicorias@users.noreply.github.com> * Fix formatting * Update universe [ci skip] * Catalan Language Support (#2940) * Catalan language Support * Ddding Catalan to documentation * Sort languages alphabetically [ci skip] * Update tests for pytest 4.x (#2965) <!--- Provide a general summary of your changes in the title. --> ## Description - [x] Replace marks in params for pytest 4.0 compat ([see here](https://docs.pytest.org/en/latest/deprecations.html#marks-in-pytest-mark-parametrize)) - [x] Un-xfail passing tests (some fixes in a recent update resolved a bunch of issues, but tests were apparently never updated here) ### Types of change <!-- What type of change does your PR cover? Is it a bug fix, an enhancement or new feature, or a change to the documentation? --> ## 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. * Fix regex pin to harmonize with conda (#2964) * Update README.rst * Fix bug where Vocab.prune_vector did not use 'batch_size' (#2977) Fixes #2976 * Fix typo * Fix typo * Remove duplicate file * Require thinc 7.0.0.dev2 Fixes bug in gpu_ops that would use cupy instead of numpy on CPU * Add missing import * Fix error IDs * Fix tests
2018-11-29 18:30:29 +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
E104 = ("Can't find JSON schema for '{name}'.")
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')`")
E109 = ("Model for component '{name}' not initialized. Did you forget to load "
"a model, or 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.")
2019-02-14 17:35:20 +03:00
E113 = ("The newly split token can only have one root (head = 0).")
2019-02-24 17:11:28 +03:00
E114 = ("The newly split token needs to have a root (head = 0).")
E115 = ("All subtokens must have associated heads.")
E116 = ("Cannot currently add labels to pre-trained 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.")
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}")
2019-02-13 17:29:08 +03:00
@add_codes
class TempErrors(object):
T003 = ("Resizing pre-trained Tagger models is not currently supported.")
T004 = ("Currently parser depth is hard-coded to 1. Received: {value}.")
T007 = ("Can't yet set {attr} from Span. Vote for this feature on the "
"issue tracker: http://github.com/explosion/spaCy/issues")
2018-04-03 22:40:29 +03:00
T008 = ("Bad configuration of Tagger. This is probably a bug within "
"spaCy. We changed the name of an internal attribute for loading "
"pre-trained vectors, and the class has been passed the old name "
"(pretrained_dims) but not the new name (pretrained_vectors).")
# fmt: on
class MatchPatternError(ValueError):
def __init__(self, key, errors):
"""Custom error for validating match patterns.
key (unicode): 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 = "Invalid token patterns for matcher rule '{}'\n".format(key)
for pattern_idx, error_msgs in errors.items():
pattern_errors = "\n".join(["- {}".format(e) for e in error_msgs])
msg += "\nPattern {}:\n{}\n".format(pattern_idx, pattern_errors)
ValueError.__init__(self, msg)
class ModelsWarning(UserWarning):
pass
WARNINGS = {
"user": UserWarning,
"deprecation": DeprecationWarning,
"models": ModelsWarning,
}
def _get_warn_types(arg):
if arg == "": # don't show any warnings
return []
if not arg or arg == "all": # show all available warnings
return WARNINGS.keys()
return [w_type.strip() for w_type in arg.split(",") if w_type.strip() in WARNINGS]
def _get_warn_excl(arg):
if not arg:
return []
return [w_id.strip() for w_id in arg.split(",")]
SPACY_WARNING_FILTER = os.environ.get("SPACY_WARNING_FILTER")
SPACY_WARNING_TYPES = _get_warn_types(os.environ.get("SPACY_WARNING_TYPES"))
SPACY_WARNING_IGNORE = _get_warn_excl(os.environ.get("SPACY_WARNING_IGNORE"))
def user_warning(message):
_warn(message, "user")
def deprecation_warning(message):
_warn(message, "deprecation")
def models_warning(message):
_warn(message, "models")
def _warn(message, warn_type="user"):
"""
message (unicode): The message to display.
category (Warning): The Warning to show.
"""
if message.startswith("["):
w_id = message.split("[", 1)[1].split("]", 1)[0] # get ID from string
else:
w_id = None
ignore_warning = w_id and w_id in SPACY_WARNING_IGNORE
if warn_type in SPACY_WARNING_TYPES and not ignore_warning:
category = WARNINGS[warn_type]
stack = inspect.stack()[-1]
with warnings.catch_warnings():
if SPACY_WARNING_FILTER:
warnings.simplefilter(SPACY_WARNING_FILTER, category)
warnings.warn_explicit(message, category, stack[1], stack[2])