[Bug] Pii Redactor fail when running on Windows

[touma-I]

Search before asking

• I searched the issues and found no similar issues.

Component

Transforms/Other

What happened + What you expected to happen

---

ImportError Traceback (most recent call last)
Cell In[4], line 1
----> 1 from dpk_pii_redactor.transform_python import PIIRedactor

File ~\OneDrive\Documents\GitHub\data-prep-kit\transforms\language\pii_redactor\dpk_pii_redactor_init_.py:1
----> 1 from .transform import *

File ~\OneDrive\Documents\GitHub\data-prep-kit\transforms\language\pii_redactor\dpk_pii_redactor\transform.py:24
     22 from data_processing.transform import AbstractTableTransform, TransformConfiguration
     23 from data_processing.utils import CLIArgumentProvider, TransformUtils, get_logger
---> 24 from dpk_pii_redactor.pii_analyzer import PIIAnalyzerEngine
     25 from dpk_pii_redactor.pii_anonymizer import PIIAnonymizer
     28 short_name = "pii_redactor"

File ~\OneDrive\Documents\GitHub\data-prep-kit\transforms\language\pii_redactor\dpk_pii_redactor\pii_analyzer.py:15
     12 import logging
     14 import spacy
---> 15 from dpk_pii_redactor.flair_recognizer import FlairRecognizer
     16 from presidio_analyzer import AnalyzerEngine, RecognizerRegistry
     17 from presidio_analyzer.nlp_engine import NlpEngineProvider

File ~\OneDrive\Documents\GitHub\data-prep-kit\transforms\language\pii_redactor\dpk_pii_redactor\flair_recognizer.py:20
     17 from typing import List, Optional, Set, Tuple
     19 from data_processing.utils import get_logger
---> 20 from flair.data import Sentence
     21 from flair.models import SequenceTagger
     22 from presidio_analyzer import AnalysisExplanation, EntityRecognizer, RecognizerResult

File ~\anaconda3\Lib\site-packages\flair\__init__.py:6
      3 from pathlib import Path
      5 import torch
----> 6 from transformers import set_seed as hf_set_seed
      8 # global variable: cache_root
      9 from .file_utils import set_proxies

File ~\AppData\Roaming\Python\Python312\site-packages\transformers\__init__.py:26
     23 from typing import TYPE_CHECKING
     25 # Check the dependencies satisfy the minimal versions required.
---> 26 from . import dependency_versions_check
     27 from .utils import (
     28     OptionalDependencyNotAvailable,
     29     _LazyModule,
   (...)
     48     logging,
     49 )
     52 logger = logging.get_logger(__name__)  # pylint: disable=invalid-name

File ~\AppData\Roaming\Python\Python312\site-packages\transformers\dependency_versions_check.py:16
      1 # Copyright 2020 The HuggingFace Team. All rights reserved.
      2 #
      3 # Licensed under the Apache License, Version 2.0 (the "License");
   (...)
     12 # See the License for the specific language governing permissions and
     13 # limitations under the License.
     15 from .dependency_versions_table import deps
---> 16 from .utils.versions import require_version, require_version_core
     19 # define which module versions we always want to check at run time
     20 # (usually the ones defined in `install_requires` in setup.py)
     21 #
     22 # order specific notes:
     23 # - tqdm must be checked before tokenizers
     25 pkgs_to_check_at_runtime = [
     26     "python",
     27     "tqdm",
   (...)
     37     "pyyaml",
     38 ]

File ~\AppData\Roaming\Python\Python312\site-packages\transformers\utils\__init__.py:27
     25 from .. import __version__
     26 from .backbone_utils import BackboneConfigMixin, BackboneMixin
---> 27 from .chat_template_utils import DocstringParsingException, TypeHintParsingException, get_json_schema
     28 from .constants import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD, IMAGENET_STANDARD_MEAN, IMAGENET_STANDARD_STD
     29 from .doc import (
     30     add_code_sample_docstrings,
     31     add_end_docstrings,
   (...)
     35     replace_return_docstrings,
     36 )

File ~\AppData\Roaming\Python\Python312\site-packages\transformers\utils\chat_template_utils.py:39
     36     from PIL.Image import Image
     38 if is_torch_available():
---> 39     from torch import Tensor
     42 BASIC_TYPES = (int, float, str, bool, Any, type(None), ...)
     43 # Extracts the initial segment of the docstring, containing the function description

ImportError: cannot import name 'Tensor' from 'torch' (unknown location)

Reproduction script

On Windows 11, start Conda Navigator with python 3.12 and run the pii redactor notebook from here:
data-prep-kit/transforms/language/pii_redactor/piiredactor.ipynb

Anything else

No response

OS

Windows WSL

Python

Other

Are you willing to submit a PR?

• Yes I am willing to submit a PR!