Package: TSrepr 1.1.0

Peter Laurinec

TSrepr: Time Series Representations

Methods for representations (i.e. dimensionality reduction, preprocessing, feature extraction) of time series to help more accurate and effective time series data mining. Non-data adaptive, data adaptive, model-based and data dictated (clipped) representation methods are implemented. Also various normalisation methods (min-max, z-score, Box-Cox, Yeo-Johnson), and forecasting accuracy measures are implemented.

Authors:Peter Laurinec [aut, cre]

TSrepr_1.1.0.tar.gz
TSrepr_1.1.0.zip(r-4.5)TSrepr_1.1.0.zip(r-4.4)TSrepr_1.1.0.zip(r-4.3)
TSrepr_1.1.0.tgz(r-4.4-x86_64)TSrepr_1.1.0.tgz(r-4.4-arm64)TSrepr_1.1.0.tgz(r-4.3-x86_64)TSrepr_1.1.0.tgz(r-4.3-arm64)
TSrepr_1.1.0.tar.gz(r-4.5-noble)TSrepr_1.1.0.tar.gz(r-4.4-noble)
TSrepr_1.1.0.tgz(r-4.4-emscripten)TSrepr_1.1.0.tgz(r-4.3-emscripten)
TSrepr.pdf |TSrepr.html
TSrepr/json (API)
NEWS

# Install 'TSrepr' in R:
install.packages('TSrepr', repos = c('https://petolau.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/petolau/tsrepr/issues

Uses libs:
  • c++– GNU Standard C++ Library v3
Datasets:
  • elec_load - 2 weeks of electricity load data from 50 consumers.

On CRAN:

data-analysisdata-miningdata-mining-algorithmsdata-sciencerepresentationtime-seriestime-series-analysistime-series-classificationtime-series-clusteringtime-series-data-miningtime-series-representations

51 exports 96 stars 4.09 score 12 dependencies 1 mentions 116 scripts 452 downloads

Last updated 4 years agofrom:1dd7ea8064. Checks:OK: 4 NOTE: 5. Indexed: yes.

TargetResultDate
Doc / VignettesOKSep 07 2024
R-4.5-win-x86_64NOTESep 07 2024
R-4.5-linux-x86_64NOTESep 07 2024
R-4.4-win-x86_64NOTESep 07 2024
R-4.4-mac-x86_64NOTESep 07 2024
R-4.4-mac-aarch64NOTESep 07 2024
R-4.3-win-x86_64OKSep 07 2024
R-4.3-mac-x86_64OKSep 07 2024
R-4.3-mac-aarch64OKSep 07 2024

Exports:clippingdenorm_atandenorm_boxcoxdenorm_min_maxdenorm_yjdenorm_zl1CoeflmCoefmaapemaemapemasemaxCmdaemeanCmedianCminCmsenorm_atannorm_boxcoxnorm_min_maxnorm_min_max_listnorm_min_max_paramsnorm_yjnorm_znorm_z_listnorm_z_paramsrepr_dctrepr_dftrepr_dwtrepr_exprepr_feacliprepr_feacliptrendrepr_featrendrepr_gamrepr_listrepr_lmrepr_matrixrepr_paarepr_piprepr_plarepr_saxrepr_seas_profilerepr_smarepr_windowingrleCrlmCoefrmsesmapesumCtrending

Dependencies:dttlatticeMASSMatrixMatrixModelsmgcvnlmequantregRcppSparseMsurvivalwavelets

TSrepr: Simple extensible framework

Rendered fromTSrepr_extentions.Rmdusingknitr::rmarkdownon Sep 07 2024.

Last update: 2020-03-23
Started: 2018-01-01

TSrepr: Time series representations in R

Rendered fromTSrepr_representations_of_time_series.Rmdusingknitr::rmarkdownon Sep 07 2024.

Last update: 2018-11-22
Started: 2017-11-09

TSrepr: Time series representations in a use case

Rendered fromTSrepr_representations_use_case.Rmdusingknitr::rmarkdownon Sep 07 2024.

Last update: 2020-03-23
Started: 2017-12-08

Readme and manuals

Help Manual

Help pageTopics
Creates bit-level (clipped representation) from a vectorclipping
Functions for linear regression model coefficients extractioncoefComp l1Coef lmCoef rlmCoef
Arctangent denormalisationdenorm_atan
Two-parameter Box-Cox denormalisationdenorm_boxcox
Min-Max denormalisationdenorm_min_max
Yeo-Johnson denormalisationdenorm_yj
Z-score denormalisationdenorm_z
2 weeks of electricity load data from 50 consumers.elec_load
Fast statistic functions (helpers)fast_stat maxC meanC medianC minC sumC
MAAPEmaape
MAEmae
MAPEmape
MASEmase
MdAEmdae
MSEmse
Arctangent normalisationnorm_atan
Two-parameter Box-Cox normalisationnorm_boxcox
Min-Max normalisationnorm_min_max
Min-Max normalization listnorm_min_max_list
Min-Max normalisation with parametersnorm_min_max_params
Yeo-Johnson normalisationnorm_yj
Z-score normalisationnorm_z
Z-score normalization listnorm_z_list
Z-score normalisation with parametersnorm_z_params
DCT representationrepr_dct
DFT representation by FFTrepr_dft
DWT representationrepr_dwt
Exponential smoothing seasonal coefficients as representationrepr_exp
FeaClip representation of time seriesrepr_feaclip
FeaClipTrend representation of time seriesrepr_feacliptrend
FeaTrend representation of time seriesrepr_featrend
GAM regression coefficients as representationrepr_gam
Computation of list of representations list of time series with different lengthsrepr_list
Regression coefficients from linear model as representationrepr_lm
Computation of matrix of representations from matrix of time seriesrepr_matrix
PAA - Piecewise Aggregate Approximationrepr_paa
PIP representationrepr_pip
PLA representationrepr_pla
SAX - Symbolic Aggregate Approximationrepr_sax
Mean seasonal profile of time seriesrepr_seas_profile
Simple Moving Average representationrepr_sma
Windowing of time seriesrepr_windowing
RLE (Run Length Encoding) written in C++rleC
RMSErmse
sMAPEsmape
Creates bit-level (trending) representation from a vectortrending
TSrepr packageTSrepr