Magnes utility for the removal of artifacts from timeseries.
Project description
Magnes Artifact Removal
Magnes utility for the removal of artifacts from time series.
Installation
Install the package using
pip install artrem
Note, might need to be adapted to the final location of the package.
Quick Start
import numpy as np
from martrem import clean_with_adaptive_shape_correlation
from martrem.aux import templating
# Prepare your signal data
fs = 250.0 # Sampling frequency
signal_data = np.array([...]) # Your time series data
# Create a search template
psi_n = 25
psi = templating.mexican(psi_n, fs=fs, bound=3)
# Clean the signal
corrected, artifact = clean_with_adaptive_shape_correlation(
signal_data,
fs=fs,
psi=psi,
tau_n=50,
fco_hp=0.1,
xcorr_min_peak_distance=80
)
Submodules
Autoenc
Autoencoder-based signal filtering/artifact detection.
Auxiliary Tools
Collection of submodules for filtering, scaling, and generating signal templates (shapelets/wavelets).
Cleaning
Main interface of the package. Collection of functions cleaning corrupted time series using a specific method.
Scripts
The package is evaluated using a number of scripts. Scripts can be seen as studies of a specific
strategy or a comparison thereof. For example, scripts to evaluate the search-template-based ECG artifact
removal strategy from blurred-peak waves are provided, including a single-experiment run scripts/singlerun.py
and a parametric sweep scripts/sweep.py.
Due to the folder hierarchy, scripts are to be run from root as modules, i.e. to run the
script scripts/foo.py call
uv run -m scripts.foo [ARGS]
Note The scripts are not included in package, but are only available in the full source.
Testing
Testing is performed using pytest. Package tests are defined in tests/, replicating the
To run the package unittests, call
uv run -m pytest tests [OPTIONS]
To run the scripts' tests call
uv run -m pytest scripts [OPTIONS]
To run the all tests call
uv run -m pytest [OPTIONS]
All calls are assumed to be made from the project root.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file magnes_artifact_removal-0.1.0.tar.gz.
File metadata
- Download URL: magnes_artifact_removal-0.1.0.tar.gz
- Upload date:
- Size: 392.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5a807f845d53b17ae7ac2c91b5690606f65777148dfbeb2e8227bfb641a87a4e
|
|
| MD5 |
35695fa2f369c5ff4311eab5c078201e
|
|
| BLAKE2b-256 |
d4bf56af47b5a0802f97fd2cd448d65cee4c01b905ce4c3b350ddcf12b60f437
|
File details
Details for the file magnes_artifact_removal-0.1.0-py3-none-any.whl.
File metadata
- Download URL: magnes_artifact_removal-0.1.0-py3-none-any.whl
- Upload date:
- Size: 9.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.8.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
723468453e0f2c0d5e263b360bfe9873cf66120537da2815750367d8a158cd06
|
|
| MD5 |
c4bcfd5a768018c36495be79e160b8a6
|
|
| BLAKE2b-256 |
fe0686373a314967605130e1c36d715002281bbac79a905e146db117a66ba2a0
|