Metadata-Version: 2.4
Name: jiku-data
Version: 0.2.0
Summary: Open source datasets, component of Jiku Core
Author-email: Jiku Pro <admin@jiku.pro>
License-Expression: GPL-3.0-or-later
Project-URL: Homepage, https://github.com/jiku-pro/jiku-data
Project-URL: Source, https://github.com/jiku-pro/jiku-data
Project-URL: Bug Reports, https://github.com/jiku-pro/jiku-data/issues
Keywords: datasets,data analysis,functional data analysis,time series analysis
Classifier: Development Status :: 4 - Beta
Classifier: Topic :: Scientific/Engineering
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Requires-Python: >=3.9
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: tables
Dynamic: license-file

[![Python](https://img.shields.io/badge/Python-FFD43B?style=for-the-badge&logo=python&logoColor=blue)](https://www.python.org)
[![Numpy](https://img.shields.io/badge/Numpy-777BB4?style=for-the-badge&logo=numpy&logoColor=white)](https://numpy.org)
[![License: GPL-3.0](https://img.shields.io/badge/License-GPL--3.0-blue.svg)](https://www.gnu.org/licenses/gpl-3.0)
![version](https://img.shields.io/badge/version-0.2.0-blue)



<img src="https://github.com/jiku-pro/jiku-data/blob/ee4a7ccc53b7badedc14d7c93b2b40af783b4f75/jiku-core.jpg?raw=true" alt="JikuCore" width="600">

# JIKU DATA

Public repository of open-source datasets, and a component of the [Jiku Core](https://jiku-core.org) software suite.



Datasets appear in `./src/jikudata/datasets`. The GPL license covers the code in this repository. There are four kinds of data.

- **Synthetic data** were generated for this package and are distributed under its license. These are `Gen0D_*`, `Syn0D_*`, `SPM1D_*`, `Random` and `Simulated*`.
- **Data from R packages** keep the license of their R package. Every one of these licenses permits redistribution under the GPL. These are `R_*`, `Datarium*`, `MASS_*`, `Lme4Pastes`, `Nlme_Oxide`, `Rohwer` and `Weather`.
- **Open datasets** were published by their authors under an open license (CC0, CC BY 4.0 or MIT). These are `Dorn2012*`, `Fukuchi*`, `GaitRec`, `Gutenberg*`, `Lencioni2019*` and `Reznick2021`.
- **Research data** from the articles that the datasets cite are distributed under the license CC BY 4.0. These are `Pataky2014cop`, `PlantarArchAngle`, `SpeedGRF*` and `SpeedPP2D*`.

For data from R packages and for open datasets the README in the dataset folder names the source and its license.

The expected results of the 0D datasets are computed in R. Each folder holds a `target.R` script and its output `expected.csv`. Run `Rscript scripts/make_targets.R` to recompute every target.



Example use:

```python
import jikudata as jd

dataset = jd.R_Cars()
y       = dataset.y  # dependent variable
x       = dataset.x  # independent variable(s)

print( dataset )
print( dataset.www )


```

Output:

```
R_Cars:
    design : Linear regression
    dim    : 0
    y      : (50,) array
    expected : 
        ExpectedResultsSPM1D:
            STAT : T
            z    : 9.46399
            df   : (1.0, 48.0)
            p    : 0.0000
            
https://www.r-project.org/Licenses/
```





Iterate through all datasets:

```python
for dataset in jd.datasets.iter_all():
		print( dataset.name )
```






Comparison with R:

The notebook [examples/compare_with_R.ipynb](examples/compare_with_R.ipynb) runs four datasets in spm1d and in R. The script `examples/verify_all.py` compares all datasets with the installed spm1d.

```
python examples/verify_all.py
```
