cymr

Package for fitting and simulating free recall data. Includes a fast implementation of the context maintenance and retrieval (CMR) model using Cython.

See the website for full documentation.

See here for release notes for version 0.12.1 and earlier.

Installation

For the latest stable version:

pip install cymr

To get the development version:

pip install git+https://github.com/cmr-sims/cymr

To install for development, clone the repository and run:

python install -e .

This will set links to the package modules so that you can edit the source code and have changes be reflected in your installation.

Quickstart

Fit the context maintenance and retrieval model (CMR) to sample data:

from cymr import fit, cmr
# load sample data
data = fit.sample_data('Morton2013_mixed').query('subject <= 3')

# define model weights
n_items = 768
param_def, patterns = cmr.config_loc_cmr(n_items)
param_def.set_fixed(
    T=0.1, Lfc=0.15, Lcf=0.15, Afc=0, Acf=0, Dfc=0.85, Dcf=0.85, 
    P1=0.2, P2=2, B_start=0.3, B_rec=0.9, X1=0.001, X2=0.25
)
param_def.set_free(B_enc=(0, 1))

# fit the model to sample data
model = cmr.CMR()
results = model.fit_indiv(data, param_def, patterns=patterns, tol=0.1)

See the documentation for details.

Unit tests

First, install extra packages needed for testing:

pip install .[test]

To run all tests (from the main repository directory)

pytest

Benchmark

To run a speed benchmark test, first install snakeviz (pip install snakeviz). To run likelihood calculation with a sample dataset and then display an html report:

./benchmark

Metadata

Release files for cymr 0.14.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cymr 0.14.3
File	Size	Uploaded
cymr-0.14.3.tar.gz	722.2 kB	Aug 20, 2025	Details

Release files / cymr-0.14.3.tar.gz

Download URL	cymr-0.14.3.tar.gz
Size	722.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`d68c102f9926038e9688b7810a7effdda0725a72aedc9230bef1ac5a0e5a779c`
BLAKE2b-256 checksum How to use checksums	`07ab15e262fa8265884c20d0a43a8dd413336d433f87f514d0b5c421fb99be47`
Upload date	Aug 20, 2025
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/6.1.0 CPython/3.12.9`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.