catch22: CAnonical Time-series CHaracteristics
catch22 GitHub
  • Welcome to catch22
    • Citing catch22
    • Publications using catch22
  • LANGUAGE-SPECIFIC DOCS
    • Python
    • MATLAB
    • R
    • Julia
    • C-compiled
  • INFORMATION ABOUT CATCH22
    • Feature Descriptions
      • Feature Overview Table
      • Distribution shape
      • Extreme event timing
      • Linear autocorrelation structure
      • Nonlinear autocorrelation
      • Symbolic
      • Incremental differences
      • Simple forecasting
      • Self-affine scaling
      • Other
    • API Reference
      • Python API
      • Julia API
      • R API
      • MATLAB API
    • Contributing to catch22
      • Contributor Code of Conduct
    • Related Packages
    • License
Powered by GitBook
On this page
  • Catch22 Module
  • Types
  • Functions
  • Example Usage
  1. INFORMATION ABOUT CATCH22
  2. API Reference

Julia API

This is the class and function reference of catch22.jl. Please refer to the user guide for further details as the class and function specifications may not be sufficient to give full context.

PreviousPython APINextR API

Last updated 1 year ago

Catch22 Module

The Catch22 module provides functionality for extracting the catch22 feature set from time series data.

Types

FeatureSet

FeatureSet(funcs::Vector{<:Function}, names::Vector{Symbol}, keywords::Vector{Vector{String}}, descriptions::Vector{String})

A collection of feature extraction functions, their names, keywords, and descriptions.

SuperFeatureSet

SuperFeatureSet(funcs::Vector{<:Function}, names::Vector{Symbol}, descriptions::Vector{String}, keywords::Vector{Vector{String}}, transform::Function)

A hierarchichalFeatureSet in which one or more evaluated features are non-independent, relying on some (potentially) common preprocessing transformations; e.g. the partial autocorrelation at successive lags. Feature sets of this type detect any common preprocessing transformations, as to only perform each calculation once. Catch22.jluses this to compute the zscore transformation, required by all catch22 features.

Further details on the custom types used by the Catch22.jl package can be found at .

Functions

catch22

catch22(𝐱::Vector)
catch22(X::Array)
catch22[featurename::Symbol](X::Array)

Evaluate all catch22 features for a time series vector 𝐱 or the columns of an array X. Can be indexed by feature names (as symbols) to return a subset of the available features.

catch24

catch24(𝐱::Vector)
catch24(X::Array)

Evaluate all catch22 features along with the mean (DN_Mean) and standard deviation (DN_Spread_Std) for a time series vector 𝐱 or the columns of an array X.

c22

c22(𝐱::Vector)
c22(X::Array)

Evaluate all catch22 features with shortened names for a time series vector 𝐱 or the columns of an array X.

c24

c24(𝐱::Vector)
c24(X::Array)

Evaluate all catch22 features with shortened names, along with the mean (mean) and standard deviation (std) for a time series vector 𝐱 or the columns of an array X.

Individual Feature Methods

Method
Parameters
Return Type
Description

DN_Mean

𝐱 (Vector)

Float64

Computes the mean of the input time series.

DN_Spread_Std

𝐱 (Vector)

Float64

Computes the standard deviation of the input time series.

DN_HistogramMode_5

𝐱 (Vector)

Float64

Computes the mode of the input time series using a histogram with 5 bins.

DN_HistogramMode_10

𝐱 (Vector)

Float64

Computes the mode of the input time series using a histogram with 10 bins.

...

...

...

...


Example Usage

using Catch22

# Load test data
𝐱 = Catch22.testdata[:test]

# Evaluate all catch22 features
features = catch22(𝐱)

# Evaluate specific feature
mode_5 = DN_HistogramMode_5(𝐱)

# Evaluate catch24 features (with mean and std)
features_with_stats = catch24(𝐱)

# Evaluate features with shortened names
short_features = c22(𝐱)

The Catch22 module also provides direct access to the individual feature extraction methods. These methods can be called directly using Catch22.{name}, where {name} is the name of the feature method (as given by the long name in the ).

TimeseriesFeatures.jl
table of features
Page cover image