epiprocess 0.1.0

Implemented core functionality, vignettes

• Classes
  • epi_df: specialized tbl_df for geotemporal epidemiological time
    series data, with optional metadata recording other key columns (e.g.,
    demographic breakdowns) and as_of what time/version this data was
    current/published. Associated functions:
    • as_epi_df converts to an epi_df, guessing the geo_type,
      time_type, other_keys, and as_of if not specified.
    • as_epi_df.tbl_ts and as_tsibble.epi_df automatically set
      other_keys and key&index, respectively.
    • epi_slide applies a user-supplied computation to a sliding/rolling
      time window and user-specified groups, adding the results as new
      columns, and recycling/broadcasting results to keep the result size
      stable. Allows computation to be provided as a function, purrr-style
      formula, or tidyeval dots. Uses slider underneath for efficiency.
    • epi_cor calculates Pearson, Kendall, or Spearman correlations
      between two (optionally time-shifted) variables in an epi_df within
      user-specified groups.
    • Convenience function: is_epi_df.
  • epi_archive: R6 class for version (patch) data for geotemporal
    epidemiological time series data sets. Comes with S3 methods and regular
    functions that wrap around this functionality for those unfamiliar with R6
    methods. Associated functions:
    • as_epi_archive: prepares an epi_archive object from a data frame
      containing snapshots and/or patch data for every available version of
      the data set.
    • as_of: extracts a snapshot of the data set as of some requested
      version, in epi_df format.
    • epix_slide, <epi_archive>$slide: similar to epi_slide, but for
      epi_archives; for each requested ref_time_value and group, applies
      a time window and user-specified computation to a snapshot of the data
      as of ref_time_value.
    • epix_merge, <epi_archive>$merge: like merge for epi_archives,
      but allowing for the last version of each observation to be carried
      forward to fill in gaps in x or y.
    • Convenience function: is_epi_archive.
• Additional functions
  • growth_rate: estimates growth rate of a time series using one of a few
    built-in methods based on relative change, linear regression,
    smoothing splines, or trend filtering.
  • detect_outlr: applies one or more outlier detection methods to a given
    signal variable, and optionally aggregates the outputs to create a
    consensus result.
  • detect_outlr_rm: outlier detection function based on a
    rolling-median-based outlier detection function; one of the methods
    included in detect_outlr.
  • detect_outlr_stl: outlier detection function based on a seasonal-trend
    decomposition using LOESS (STL); one of the methods included in
    detect_outlr.

New Contributors

• @ryantibs made their first contribution in #13
• @elray1 made their first contribution in #19
• @qpmnguyen made their first contribution in #37
• @jacobbien made their first contribution in #44
• @rafaelcatoia made their first contribution in #43
• @dshemetov made their first contribution in #59

Full Changelog: https://github.com/cmu-delphi/epiprocess/commits/v0.1.0