Merge pull request #617 from cmu-delphi/dev

merge dev -> main

Author: brookslogan

.github/workflows/doc-preview.yaml

@@ -0,0 +1,65 @@
+on:
+  issue_comment:
+    types: [created]
+
+name: doc-preview.yaml
+
+permissions: read-all
+
+jobs:
+  preview:
+    if: ${{ github.event.issue.pull_request && (github.event.comment.author_association == 'COLLABORATOR' || github.event.comment.author_association == 'CONTRIBUTOR' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'OWNER') && startsWith(github.event.comment.body, '/preview-docs') }}
+
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to write a comment on the PR
+      pull-requests: write
+      # Needed to read the PR branch
+      contents: read
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          # Checkout the PR branch
+          ref: refs/pull/${{ github.event.issue.number }}/head
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::pkgdown, local::.
+          needs: website
+
+      - name: Build site
+        run: pkgdown::build_site_github_pages(new_process = FALSE, install = FALSE)
+        shell: Rscript {0}
+
+      - name: Deploy to Netlify
+        uses: nwtgck/actions-netlify@v3.0
+        with:
+          # Standard config
+          github-token: ${{ secrets.GITHUB_TOKEN }}
+          deploy-message: "Deploy from GitHub Actions"
+          # 'docs/' is the default directory for pkgdown::build_site()
+          # we add 'dev' because _pkgdown.yml has 'development: mode: devel'
+          publish-dir: './docs/dev'
+          # Development deploys only
+          production-deploy: false
+          # Enable pull request comment (default)
+          enable-pull-request-comment: true
+          # Overwrite the pull request comment with updated link (default)
+          overwrites-pull-request-comment: true
+          # Don't deploy to GitHub
+          enable-github-deployment: false
+          # Don't update the status of the commit
+          enable-commit-status: false
+          # Don't comment on the commit
+          enable-commit-comment: false
+        env:
+          # Netlify credentials (currently from Dmitry's account)
+          NETLIFY_AUTH_TOKEN: ${{ secrets.NETLIFY_AUTH_TOKEN }}
+          NETLIFY_SITE_ID: ${{ secrets.NETLIFY_SITE_ID }}
+        timeout-minutes: 1

.lintr

@@ -1,6 +1,5 @@
 linters: linters_with_defaults(
   line_length_linter(120),
-  cyclocomp_linter = NULL,
   object_length_linter(length = 40L)
   )
 exclusions: list(

DESCRIPTION

@@ -1,7 +1,7 @@
-Package: epiprocess
 Type: Package
+Package: epiprocess
 Title: Tools for basic signal processing in epidemiology
-Version: 0.10.0
+Version: 0.11.0
 Authors@R: c(
     person("Jacob", "Bien", role = "ctb"),
     person("Logan", "Brooks", , "lcbrooks+github@andrew.cmu.edu", role = c("aut", "cre")),
@@ -23,60 +23,65 @@ Authors@R: c(
     person("Posit", role = "cph",
            comment = "Copyright holder of included rlang fragments"),
     person("Johns Hopkins University Center for Systems Science and Engineering", role = "dtc",
-            comment = "Owner of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
+           comment = "Owner of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
     person("Johns Hopkins University", role = "cph",
-            comment = "Copyright holder of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
+           comment = "Copyright holder of COVID-19 cases and deaths data from the COVID-19 Data Repository"),
     person("Carnegie Mellon University Delphi Group", role = "dtc",
-            comment = "Owner of claims-based CLI data from the Delphi Epidata API")
+           comment = "Owner of claims-based CLI data from the Delphi Epidata API")
   )
-Description: This package introduces common data structures for working with
-    epidemiological data reported by location and time and offers associated
-    utilities to perform basic signal processing tasks. The package is designed
-    to be used in conjunction with `epipredict` for building and evaluating
-    epidemiological models.
+Description: This package introduces common data structures for working
+    with epidemiological data reported by location and time and offers
+    associated utilities to perform basic signal processing tasks. The
+    package is designed to be used in conjunction with `epipredict` for
+    building and evaluating epidemiological models.
 License: MIT + file LICENSE
 URL: https://cmu-delphi.github.io/epiprocess/
 Depends:
+    epidatasets,
     R (>= 3.6)
 Imports:
     checkmate,
     cli,
     data.table,
     dplyr (>= 1.1.0),
-    epidatasets,
-    genlasso,
     ggplot2,
     glue,
     lifecycle (>= 1.0.1),
     lubridate,
     magrittr,
+    pkgconfig,
     purrr,
     rlang,
     slider,
     tibble,
     tidyr,
     tidyselect (>= 1.2.0),
+    tools,
     tsibble,
     utils,
     vctrs,
     waldo
 Suggests:
     devtools,
+    distributional,
     epidatr,
+    epipredict,
     here,
     knitr,
     outbreaks,
     readr,
     rmarkdown,
     testthat (>= 3.1.5),
+    trendfilter,
     withr
 VignetteBuilder:
     knitr
 Remotes:
     cmu-delphi/delphidocs,
     cmu-delphi/epidatasets,
     cmu-delphi/epidatr,
-    glmgen/genlasso,
+    cmu-delphi/epipredict,
+    glmgen/trendfilter,
     reconverse/outbreaks
 Config/Needs/website: cmu-delphi/delphidocs
 Config/testthat/edition: 3
@@ -103,5 +108,6 @@ Collate:
     'reexports.R'
     'revision_analysis.R'
     'slide.R'
+    'time-utils.R'
     'utils.R'
     'utils_pipe.R'

NAMESPACE

@@ -1,6 +1,9 @@
 # Generated by roxygen2: do not edit by hand
 
+S3method("$<-",epi_df)
 S3method("[",epi_df)
+S3method("[<-",epi_df)
+S3method("[[<-",epi_df)
 S3method("names<-",epi_df)
 S3method(Summary,epi_df)
 S3method(arrange_canonical,default)
@@ -39,31 +42,27 @@ S3method(guess_period,Date)
 S3method(guess_period,POSIXt)
 S3method(guess_period,default)
 S3method(key_colnames,data.frame)
-S3method(key_colnames,default)
 S3method(key_colnames,epi_archive)
 S3method(key_colnames,epi_df)
+S3method(key_colnames,tbl_ts)
 S3method(mean,epi_df)
 S3method(print,epi_archive)
 S3method(print,epi_df)
 S3method(print,grouped_epi_archive)
+S3method(print,growth_rate_params)
 S3method(summary,epi_df)
 S3method(ungroup,epi_df)
 S3method(ungroup,grouped_epi_archive)
 S3method(unnest,epi_df)
 export("%>%")
-export(archive_cases_dv_subset)
 export(arrange)
 export(arrange_canonical)
 export(as_epi_archive)
 export(as_epi_df)
 export(as_tsibble)
 export(autoplot)
-export(cases_deaths_subset)
 export(clone)
 export(complete)
-export(covid_case_death_rates_extended)
-export(covid_incidence_county_subset)
-export(covid_incidence_outliers)
 export(deprecated_quo_is_present)
 export(detect_outlr)
 export(detect_outlr_rm)
@@ -85,6 +84,7 @@ export(group_by)
 export(group_epi_df)
 export(group_modify)
 export(growth_rate)
+export(growth_rate_params)
 export(guess_period)
 export(is_epi_df)
 export(is_grouped_epi_archive)
@@ -114,6 +114,7 @@ importFrom(checkmate,assert_function)
 importFrom(checkmate,assert_int)
 importFrom(checkmate,assert_list)
 importFrom(checkmate,assert_logical)
+importFrom(checkmate,assert_number)
 importFrom(checkmate,assert_numeric)
 importFrom(checkmate,assert_scalar)
 importFrom(checkmate,assert_string)
@@ -135,6 +136,8 @@ importFrom(cli,cli_li)
 importFrom(cli,cli_vec)
 importFrom(cli,cli_warn)
 importFrom(cli,format_message)
+importFrom(cli,pluralize)
+importFrom(cli,qty)
 importFrom(data.table,":=")
 importFrom(data.table,address)
 importFrom(data.table,as.data.table)
@@ -143,6 +146,7 @@ importFrom(data.table,copy)
 importFrom(data.table,frollapply)
 importFrom(data.table,frollmean)
 importFrom(data.table,frollsum)
+importFrom(data.table,is.data.table)
 importFrom(data.table,key)
 importFrom(data.table,rbindlist)
 importFrom(data.table,set)
@@ -152,7 +156,6 @@ importFrom(dplyr,"%>%")
 importFrom(dplyr,across)
 importFrom(dplyr,all_of)
 importFrom(dplyr,arrange)
-importFrom(dplyr,bind_rows)
 importFrom(dplyr,c_across)
 importFrom(dplyr,dplyr_col_modify)
 importFrom(dplyr,dplyr_reconstruct)
@@ -164,14 +167,14 @@ importFrom(dplyr,group_by_drop_default)
 importFrom(dplyr,group_map)
 importFrom(dplyr,group_modify)
 importFrom(dplyr,group_vars)
+importFrom(dplyr,grouped_df)
 importFrom(dplyr,groups)
 importFrom(dplyr,if_all)
 importFrom(dplyr,if_any)
 importFrom(dplyr,if_else)
 importFrom(dplyr,is_grouped_df)
 importFrom(dplyr,lag)
 importFrom(dplyr,mutate)
-importFrom(dplyr,near)
 importFrom(dplyr,pick)
 importFrom(dplyr,pull)
 importFrom(dplyr,relocate)
@@ -188,6 +191,7 @@ importFrom(lubridate,as.period)
 importFrom(lubridate,days)
 importFrom(lubridate,weeks)
 importFrom(magrittr,"%>%")
+importFrom(purrr,list_rbind)
 importFrom(purrr,map)
 importFrom(purrr,map_lgl)
 importFrom(rlang,"!!!")
@@ -199,13 +203,16 @@ importFrom(rlang,arg_match)
 importFrom(rlang,caller_arg)
 importFrom(rlang,caller_env)
 importFrom(rlang,check_dots_empty)
+importFrom(rlang,check_dots_empty0)
+importFrom(rlang,dots_n)
 importFrom(rlang,enquo)
 importFrom(rlang,enquos)
 importFrom(rlang,env)
 importFrom(rlang,expr_label)
 importFrom(rlang,f_env)
 importFrom(rlang,f_rhs)
 importFrom(rlang,is_bare_integerish)
+importFrom(rlang,is_bare_numeric)
 importFrom(rlang,is_environment)
 importFrom(rlang,is_formula)
 importFrom(rlang,is_function)
@@ -236,8 +243,20 @@ importFrom(tidyr,unnest)
 importFrom(tidyselect,any_of)
 importFrom(tidyselect,eval_select)
 importFrom(tidyselect,starts_with)
+importFrom(tools,toTitleCase)
 importFrom(tsibble,as_tsibble)
 importFrom(utils,capture.output)
 importFrom(utils,tail)
+importFrom(vctrs,"vec_slice<-")
+importFrom(vctrs,vec_cast)
 importFrom(vctrs,vec_data)
+importFrom(vctrs,vec_duplicate_any)
 importFrom(vctrs,vec_equal)
+importFrom(vctrs,vec_in)
+importFrom(vctrs,vec_order)
+importFrom(vctrs,vec_rbind)
+importFrom(vctrs,vec_recycle_common)
+importFrom(vctrs,vec_rep)
+importFrom(vctrs,vec_size)
+importFrom(vctrs,vec_slice)
+importFrom(vctrs,vec_sort)

NEWS.md

@@ -2,6 +2,73 @@
 
 Pre-1.0.0 numbering scheme: 0.x will indicate releases, while 0.x.y will indicate PR's.
 
+# epiprocess 0.11
+
+## Breaking changes
+
+- `growth_rate()` argument order and names have changed. You will need to
+  rewrite `growth_rate(x, y)` as `growth_rate(y, x)`. The interface for passing
+  arguments to the `"smooth_spline"` and `"trend_filter"` methods has also
+  changed. Finally, `growth_rate()` with `method = "trendfilter"` now uses the
+  `{trendfilter}` package rather than `{genlasso}`; results for this method will
+  be different than before. In order to make `{epiprocess}` installation easier
+  for users without a compiler, we have placed `{trendfilter}` in Suggests:; if
+  you want to use `method = "trendfilter"` you will need to manually install
+  this dependency (e.g., with `remotes::install_github("glmgen/trendfilter")`).
+- In `revision_summary()`:
+  - The `should_compactify` argument is now called `compactify`. To migrate,
+    change any calls with `should_compactfiy =` to `compactify =`.
+  - Output now uses the name `lag_near_latest` instead of `time_near_latest`. To
+    migrate, update references to `time_near_latest` to `lag_near_latest`.
+  - `revision_summary(epi_arch)` without specifying the measurement column to
+    analyze in `...` will no longer attempt to guess which one you intended if
+    there are multiple possibilities to choose from (#571). If you attempt a
+    complicated tidyselection that selects zero columns, this is also now an
+    error. If you encounter such errors, manually specify the measurement column
+    in `...`.
+  - `min_waiting_period` now defines a nonstrict inequality instead of a strict
+    one. To obtain the old bounds, bump the `min_waiting_period` up to the next
+    possible value for your `time_type`.
+- In `key_colnames()`:
+  - On regular (non-`epi_df`) data frames, now requires manual specification of
+    `geo_keys`, `other_keys`, and `time_keys`.
+  - The `extra_keys` argument has been deprecated and replaced with
+    `other_keys`.
+- The compactification tolerance argument has been renamed to
+  `compactify_abs_tol` or `abs_tol`, depending on the function; now defines a
+  nonstrict tolerances; and defaults to 0 (requiring exact matches in order to
+  compactify). This argument has been added to `as_epi_archive()` and
+  `epix_merge()` and removed (along with all compactification options) from
+  `new_epi_archive()`.
+- `validate_epi_archive()` now follows the validator convention of operating on
+  an "unvalidated" `epi_archive` (from `new_epi_archive`) rather than arguments.
+
+## Improvements
+- `revision_summary()` now supports all `time_type`s.
+- The compactification tolerance setting now works with integer-type columns.
+- Various functions are now faster, using faster variants of core operations and
+  avoiding reconstructing grouped `epi_df`s when unnecessary.
+
+## Bug fixes
+
+- Fixed aggregation of age-group-specific rates to overall rates in `epi_df` vignette (#587).
+- Fixed `key_colnames()` omitting some key columns on `epi_archive`s (#565).
+- Fixed `epi_archive` compactification raising an error on certain value column
+  classes such as `"distribution"` (#541); it's now easier to form an archive of
+  forecasts in that format.
+- Fixed large compactification tolerances potentially removing all versions of
+  some observations in certain cases when activity was flat.
+- `[<-`, `[[<-`, and `$<-` now properly retain `epi_df`-ness when used on
+  grouped `epi_df`s.
+
+## Cleanup
+
+- Moved example datasets from being reexported in the package to being fetched
+  from `epidatasets`. The `epidatasets` package is now auto-loaded as a
+  dependency of `epiprocess`. The datasets can still be accessed, after loading
+  the package, with `data()` or the name of the dataset alone, or with
+  `epidatasets::` (#577).
+
 # epiprocess 0.10
 
 ## Breaking changes