This package provides programs to perform EM based segmentation of images in nifti or analyse format.

Nilearn enables approachable and versatile analyses of brain volumes and surfaces. It provides statistical and machine-learning tools, with instructive documentation & open community.

Nifti_clib is a set of I/O libraries for reading and writing files in the nifti-1, nifti-2, and (to some degree) cifti file formats. These are binary file formats for storing medical image data, e.g. MRI and fMRI brain images.

This package provides utilities for feature analysis, preprocessing and visualization of image quality metrics generated by MRIQC.

Nipype provides a uniform interface to existing neuroimaging software and facilitates interaction between these packages within a single workflow. Nipype provides an environment that encourages interactive exploration of algorithms from different packages.

Convert data from DICOM and organise the resulting NIfTI files into BIDS.

fMRIPrep is a fMRI data preprocessing pipeline that is designed to provide an easily accessible, state-of-the-art interface that is robust to variations in scan acquisition protocols and that requires minimal user input, while providing easily interpretable and comprehensive error and output reporting. It performs basic processing steps (coregistration, normalization, unwarping, noise component extraction, segmentation, skull-stripping, etc.) providing outputs that can be easily submitted to a variety of group level analyses, including task-based or resting-state fMRI, graph theory measures, and surface or volume-based statistics.

Convert3d is a command-line tool for converting 3D images between common file formats. The tool also includes a growing list of commands for image manipulation, such as thresholding and resampling. The tool can also be used to obtain information about image files.

NiReports contains the two main components of the visual reporting system of NiPreps: 1) reportlets, visualizations for assessing the quality of a particular processing step within the neuroimaging pipeline, and 2) assemblers, end-user write out reportlets to a predetermined folder.

This module provides simple, consistent access to package resources.

seqeval is a Python framework for sequence labeling evaluation. seqeval can evaluate the performance of chunking tasks such as named-entity recognition, part-of-speech tagging, semantic role labeling and so on.

This package provides a fast implementation of the Levenshtein distance with C++ and Cython.

Quicksectx is a simple, fast and no-dependency Python implementation of interval search, adapted from the bx-python project.

Modular, fast NLP framework, compatible with Pytorch and spaCy, offering tailored support for French clinical notes.

Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Target audience is the NLP and IR communities.

PyRuSH is the python implementation of RuSH, which is originally developed using Java. RuSH is an efficient, reliable, and easy adaptable rule-based sentence segmentation solution. It is specifically designed to handle the telegraphic written text in clinical note. It leverages a nested hash table to execute simultaneous rule processing, which reduces the impact of the rule-base growth on execution time and eliminates the effect of rule order on accuracy.

Extremely fast spelling checker and suggester in Python.

The following algorithms are supported currently:

• Edit-distance

• Editex

• Soundex

• Caverphone 1.0 and 2.0

• Typox

All the above algorithms use an underlying Trie-based dictionary for efficient storage and fast computation.

This module can be used to extract or replace keywords in sentences, based on the FlashText algorithm.

PyFastNER is the Python implementation of FastNER. It uses hash function to process multiple rules at the same time. Similar to FastNER, PyFastNER supports token-based rules and character-based rules.

This package provides a Python implementation of IAMsystem algorithm, a fast dictionary-based approach for semantic annotation, a.k.a entity linking.

The EDS-Pseudo project aims at detecting identifying entities in clinical documents, and was primarily tested on clinical reports at AP-HP's clinical data warehouse. The model is built on top of edsnlp, and consists in a hybrid model (rule-based + deep learning) for which we provide rules (eds-pseudo/pipes) and a training recipe. We also provide some fictitious templates and a script to generate a synthetic dataset.

This package provides Python bindings for the simstring text similarity matching library.

WORLD Vocoder is a fast and high-quality vocoder which parameterizes speech into three components:

• f0: Pitch contour

• sp: Harmonic spectral envelope

• ap: Aperiodic spectral envelope

It can also (re)synthesize speech using these features.

This package provides tools for unsupervised and semi-supervised morphological segmentation.