martincjespersen / daanonymization Goto Github PK

from textprivacy import TextAnonymizer

# list of texts (example with cross-lingual transfer to english)
corpus = [
    "Hej, jeg hedder Martin Jespersen og er fra Danmark og arbejder i "
    "Deloitte, mit cpr er 010203-2010, telefon: +4545454545 "
    "og email: [email protected]",
    "Hi, my name is Martin Jespersen and work in Deloitte. "
    "I used to be a PhD. at DTU in Machine Learning and B-cell immunoinformatics "
    "at Anker Engelunds Vej 1 Bygning 101A, 2800 Kgs. Lyngby.",
]

Anonymizer = TextAnonymizer(corpus)

# Anonymize person, location, organization, emails, CPR and telephone numbers
anonymized_corpus = Anonymizer.mask_corpus()

for text in anonymized_corpus:
    print(text)

(anon): ~$ /home/akirkedal/software/anaconda/envs/anon/bin/python /home/akirkedal/software/anon/anon_test.py
/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/util.py:762: UserWarning: [W095] Model 'da_dacy_large_tft' (0.0.0) was trained with spaCy v3.0 and may not be 100% compatible with the current version (3.1.4). If you see errors or degraded performance, 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
  warnings.warn(warn_msg)
Traceback (most recent call last):
  File "/home/akirkedal/software/anon/anon_test.py", line 1, in <module>
    from textprivacy import TextAnonymizer
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/textprivacy/__init__.py", line 7, in <module>
    from textprivacy.textanonymization import TextAnonymizer
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/textprivacy/textanonymization.py", line 34, in <module>
    ner_model = dacy.load("da_dacy_large_tft-0.0.0")
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/dacy/load.py", line 39, in load
    return spacy.load(path)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/__init__.py", line 51, in load
    return util.load_model(
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/util.py", line 351, in load_model
    return load_model_from_path(Path(name), **kwargs)  # type: ignore[arg-type]
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/util.py", line 418, in load_model_from_path
    return nlp.from_disk(model_path, exclude=exclude, overrides=overrides)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/language.py", line 2021, in from_disk
    util.from_disk(path, deserializers, exclude)  # type: ignore[arg-type]
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/util.py", line 1229, in from_disk
    reader(path / key)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/language.py", line 2015, in <lambda>
    deserializers[name] = lambda p, proc=proc: proc.from_disk(  # type: ignore[misc]
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy_transformers/pipeline_component.py", line 402, in from_disk
    util.from_disk(path, deserialize, exclude)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy/util.py", line 1229, in from_disk
    reader(path / key)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy_transformers/pipeline_component.py", line 391, in load_model
    tokenizer, transformer = huggingface_from_pretrained(
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/spacy_transformers/util.py", line 31, in huggingface_from_pretrained
    tokenizer = AutoTokenizer.from_pretrained(str_path, **config)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/models/auto/tokenization_auto.py", line 568, in from_pretrained
    return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1732, in from_pretrained
    return cls._from_pretrained(
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/tokenization_utils_base.py", line 1850, in _from_pretrained
    tokenizer = cls(*init_inputs, **init_kwargs)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/models/xlm_roberta/tokenization_xlm_roberta_fast.py", line 134, in __init__
    super().__init__(
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/tokenization_utils_fast.py", line 110, in __init__
    fast_tokenizer = convert_slow_tokenizer(slow_tokenizer)
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/convert_slow_tokenizer.py", line 829, in convert_slow_tokenizer
    return converter_class(transformer_tokenizer).converted()
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/convert_slow_tokenizer.py", line 375, in __init__
    from .utils import sentencepiece_model_pb2 as model_pb2
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/transformers/utils/sentencepiece_model_pb2.py", line 52, in <module>
    _descriptor.EnumValueDescriptor(name="UNIGRAM", index=0, number=1, options=None, type=None),
  File "/home/akirkedal/software/anaconda/envs/anon/lib/python3.8/site-packages/google/protobuf/descriptor.py", line 755, in __new__
    _message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
 1. Downgrade the protobuf package to 3.20.x or lower.
 2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates```