Tools for Handling Extraction of Features from Time Series


[Up] [Top]

Documentation for package ‘theft’ version 0.5.4.1

Help Pages

theft-package Tools for Handling Extraction of Features from Time-series
calculate_features Compute features on an input time series dataset
calculate_interval Calculate interval summaries with a measure of central tendency of classification results
check_vector_quality Check for presence of NAs and non-numerics in a vector
compare_features Conduct statistical testing on time-series feature classification performance to identify top features or compare entire sets
feature_list All features available in theft in tidy format
filter_duplicates Remove duplicate features that exist in multiple feature sets and retain a reproducible random selection of one of them
filter_good_features Filter resample data sets according to good feature list
find_good_features Helper function to find features in both train and test set that are "good"
fit_models Fit classification model and compute key metrics
get_rescale_vals Calculate central tendency and spread values for all numeric columns in a dataset
init_theft Communicate to R the Python virtual environment containing the relevant libraries for calculating features
install_python_pkgs Download and install all the relevant Python packages into a target location
make_title Helper function for converting to title case
maxabs_scaler Rescales a numeric vector using maximum absolute scaling
minmax_scaler Rescales a numeric vector into the unit interval [0,1]
normalise Scale each feature vector into a user-specified range for visualisation and modelling
normalize Scale each feature vector into a user-specified range for visualisation and modelling
plot.feature_calculations Produce a plot for a feature_calculations object
plot.low_dimension Produce a plot for a low_dimension object
process_hctsa_file Load in hctsa formatted MATLAB files of time series data into a tidy format ready for feature extraction
reduce_dims Project a feature matrix into a low dimensional representation using PCA or t-SNE
resampled_ttest Compute correlated t-statistic and p-value for resampled data from correctR package
resample_data Helper function to create a resampled dataset
rescale_zscore Calculate z-score for all columns in a dataset using train set central tendency and spread
robustsigmoid_scaler Rescales a numeric vector using an outlier-robust Sigmoidal transformation
select_stat_cols Helper function to select only the relevant columns for statistical testing
sigmoid_scaler Rescales a numeric vector using a Sigmoidal transformation
simData Sample of randomly-generated time series to produce function tests and vignettes
stat_test Calculate p-values for feature sets or features relative to an empirical null or each other using resampled t-tests
theft Tools for Handling Extraction of Features from Time-series
tsfeature_classifier Fit classifiers using time-series features using a resample-based approach and get a fast understanding of performance
zscore_scaler Rescales a numeric vector into z-scores