Package 'theft'

Title: Tools for Handling Extraction of Features from Time Series
Description: Consolidates and calculates different sets of time-series features from multiple 'R' and 'Python' packages including 'Rcatch22' Henderson, T. (2021) <doi:10.5281/zenodo.5546815>, 'feasts' O'Hara-Wild, M., Hyndman, R., and Wang, E. (2021) <https://CRAN.R-project.org/package=feasts>, 'tsfeatures' Hyndman, R., Kang, Y., Montero-Manso, P., Talagala, T., Wang, E., Yang, Y., and O'Hara-Wild, M. (2020) <https://CRAN.R-project.org/package=tsfeatures>, 'tsfresh' Christ, M., Braun, N., Neuffer, J., and Kempa-Liehr A.W. (2018) <doi:10.1016/j.neucom.2018.03.067>, 'TSFEL' Barandas, M., et al. (2020) <doi:10.1016/j.softx.2020.100456>, and 'Kats' Facebook Infrastructure Data Science (2021) <https://facebookresearch.github.io/Kats/>.
Authors: Trent Henderson [cre, aut], Annie Bryant [ctb]
Maintainer: Trent Henderson <[email protected]>
License: MIT + file LICENSE
Version: 0.6.3
Built: 2024-11-02 05:29:55 UTC
Source: https://github.com/hendersontrent/theft

Help Index

Compute features on an input time series dataset

Description

Compute features on an input time series dataset

Usage

calculate_features(
  data,
  id_var = "id",
  time_var = "timepoint",
  values_var = "values",
  group_var = NULL,
  feature_set = c("catch22", "feasts", "tsfeatures", "Kats", "tsfresh", "TSFEL"),
  catch24 = FALSE,
  tsfresh_cleanup = FALSE,
  features = NULL,
  seed = 123
)

Arguments

data

data.frame with at least 4 columns: id variable, group variable, time variable, value variable
id_var

character specifying the ID variable to identify each time series. Defaults to "id"
time_var

character specifying the time index variable. Defaults to "timepoint"
values_var

character specifying the values variable. Defaults to "values"
group_var

character specifying the grouping variable that each unique series sits under (if one exists). Defaults to NULL
feature_set

character or vector of character denoting the set of time-series features to calculate. Defaults to "catch22"
catch24

Boolean specifying whether to compute catch24 in addition to catch22 if catch22 is one of the feature sets selected. Defaults to FALSE
tsfresh_cleanup

Boolean specifying whether to use the in-built tsfresh relevant feature filter or not. Defaults to FALSE
features

named list containing a set of user-supplied functions to calculate on data. Each function should take a single argument which is the time series. Defaults to NULL for no manually-specified features. Each list entry must have a name as calculate_features looks for these to name the features. If you don't want to use the existing feature sets and only compute those passed to features, set feature_set = NULL
seed

integer denoting a fixed number for R's random number generator to ensure reproducibility. Defaults to 123

Value

object of class feature_calculations that contains the summary statistics for each feature

Author(s)

Trent Henderson

Examples

featMat <- calculate_features(data = simData, 
  id_var = "id", 
  time_var = "timepoint", 
  values_var = "values", 
  group_var = "process", 
  feature_set = "catch22",
  seed = 123)

Check for presence of NAs and non-numerics in a vector

Description

Check for presence of NAs and non-numerics in a vector

Usage

check_vector_quality(x)

Arguments

x

input vector

Value

Boolean of whether the data is good to extract features on or not

Author(s)

Trent Henderson

All features available in theft in tidy format

Description

The variables include:

Usage

feature_list

Format

A tidy data frame with 2 variables:

feature_set

Name of the set the feature is from

feature

Name of the feature

Communicate to R the Python virtual environment containing the relevant libraries for calculating features

Description

Communicate to R the Python virtual environment containing the relevant libraries for calculating features

Usage

init_theft(venv)

Arguments

venv

character specifying the name of the to the Python virtual environment where "tsfresh", "TSFEL", and/or "Kats" are installed

Value

no return value; called for side effects

Author(s)

Trent Henderson

Examples

## Not run: 
install_python_pkgs("theft-test")
init_theft("theft-test")

## End(Not run)

Download and install all the relevant Python packages into a target location

Description

Download and install all the relevant Python packages into a target location

Usage

install_python_pkgs(venv, standard_kats = TRUE)

Arguments

venv

character specifying the name of the new virtual environment to create
standard_kats

Boolean denoting whether to try a standard installation of Kats from PyPI using reticulate::virtualenv_install or to install a safer version with less dependencies. Defaults to TRUE

Value

no return value; called for side effects

Author(s)

Trent Henderson

Examples

## Not run: 
install_python_pkgs("theft-test")

## End(Not run)

Load in hctsa formatted MATLAB files of time series data into a tidy format ready for feature extraction

Description

Load in hctsa formatted MATLAB files of time series data into a tidy format ready for feature extraction

Usage

process_hctsa_file(data)

Arguments

data

string specifying the filepath to the MATLAB file to parse

Value

an object of class data.frame in tidy format

Author(s)

Trent Henderson

Sample of randomly-generated time series to produce function tests and vignettes

Description

The variables include:

Usage

simData

Format

A tidy data frame with 4 variables:

id

Unique identifier for the time series

timepoint

Time index

values

Value

process

Group label for the type of time series

Tools for Handling Extraction of Features from Time-series

Description

Tools for Handling Extraction of Features from Time-series