Skip to main content
Ctrl+K
medkit documentation - Home

👥 User Guide

  • Installation
  • First steps
  • Using pipelines
  • Provenance tracing
  • Make your own module

🚀 Tutorial

  • Context Detection
  • Entity Matching
  • Text segmentation
    • Document splitter
    • Section Tokenizer
    • Syntagma Tokenizer

📖 Cookbook

  • Text spans
  • Cleaning text with a predefined operation
  • Brat integration
  • Spacy integration
    • Conversions to and from spaCy
    • Annotating with a spaCy pipeline
  • Creating a custom text operation
  • Using EDS-NLP with medkit
  • IAMSystem Matcher
  • Fine-tuning a Transformers model with medkit
  • Detecting text duplicates
  • Audio transcription
  • Computing metrics on an audio dataset
  • Finding relations, OntoTox implementation
  • Benchmark of NER methods on French clinical corpora
    • Preprocessing
    • Training
    • Evaluation
  • Comparative evaluation of drug recognition methods

🔍 Reference

  • API Reference
    • medkit
      • medkit.audio
        • medkit.audio.metrics
        • medkit.audio.preprocessing
        • medkit.audio.segmentation
        • medkit.audio.transcription
      • medkit.core
        • medkit.core.audio
        • medkit.core.text
        • medkit.core._prov_graph
        • medkit.core.annotation
        • medkit.core.annotation_container
        • medkit.core.attribute
        • medkit.core.attribute_container
        • medkit.core.collection
        • medkit.core.conversion
        • medkit.core.data_item
        • medkit.core.dict_conv
        • medkit.core.doc_pipeline
        • medkit.core.document
        • medkit.core.id
        • medkit.core.operation
        • medkit.core.operation_desc
        • medkit.core.pipeline
        • medkit.core.prov_store
        • medkit.core.prov_tracer
        • medkit.core.store
      • medkit.io
        • medkit.io.medkit_json
        • medkit.io._brat_utils
        • medkit.io._common
        • medkit.io.brat
        • medkit.io.doccano
        • medkit.io.rttm
        • medkit.io.spacy
        • medkit.io.srt
      • medkit.text
        • medkit.text.context
        • medkit.text.metrics
        • medkit.text.ner
        • medkit.text.postprocessing
        • medkit.text.preprocessing
        • medkit.text.relations
        • medkit.text.segmentation
        • medkit.text.spacy
        • medkit.text.translation
        • medkit.text.utils
        • medkit.text.deid
      • medkit.tools
        • medkit.tools._save_prov_to_dot
        • medkit.tools.e3c_corpus
        • medkit.tools.hf_utils
        • medkit.tools.mtsamples
      • medkit.training
        • medkit.training.callbacks
        • medkit.training.trainable_component
        • medkit.training.trainer
        • medkit.training.trainer_config
        • medkit.training.utils
      • medkit._compat
      • medkit._import
  • Audio Processing
  • Core Components
  • Audio Components
  • Text Components
  • I/O Components
  • Text Processing
  • Tools
  • Training
  • Changelog
  • License
  • .rst

medkit.text.deid

Contents

  • Classes
  • Module Contents
    • PIIDetector
      • PIIDetector._analyzer
      • PIIDetector.run()
      • PIIDetector._run_one()

medkit.text.deid#

Classes#

PIIDetector

Classify sensitive text information.

Module Contents#

class medkit.text.deid.PIIDetector(uid: str | None = None, name: str | None = None, **kwargs)#

Bases: medkit.core.text.operation.NEROperation

Classify sensitive text information.

_analyzer#
run(segments: list[medkit.core.text.Segment]) → list[medkit.core.text.Entity]#
_run_one(segment: medkit.core.text.Segment) → Iterator[medkit.core.text.Entity]#

previous

medkit.text.utils.decoding

next

medkit.tools

Contents
  • Classes
  • Module Contents
    • PIIDetector
      • PIIDetector._analyzer
      • PIIDetector.run()
      • PIIDetector._run_one()

By HeKA Research Team

© Copyright 2022-2024, HeKA Research Team.