From aae9dee3becd26dc59da73ed2c157eb4ba95240f Mon Sep 17 00:00:00 2001
From: Nat DeFries <42820733+nmdefries@users.noreply.github.com>
Date: Thu, 18 Jan 2024 11:27:23 -0500
Subject: [PATCH] document

---
 man/as_epi_archive.Rd       | 56 ++++++++++++++++++++-------------
 man/as_epi_df.Rd            | 44 +++++++++++++++-----------
 man/detect_outlr.Rd         | 62 +++++++++++++++++++++++--------------
 man/detect_outlr_rm.Rd      |  7 +++--
 man/detect_outlr_stl.Rd     |  7 +++--
 man/epi_archive.Rd          | 18 ++++++-----
 man/epi_cor.Rd              | 48 ++++++++++++++++------------
 man/epi_slide.Rd            | 22 +++++++------
 man/epix_as_of.Rd           | 25 ++++++++++-----
 man/epix_merge.Rd           | 10 +++---
 man/epix_slide.Rd           | 55 +++++++++++++++++---------------
 man/group_by.epi_archive.Rd | 48 ++++++++++++++++------------
 man/growth_rate.Rd          | 12 +++----
 man/is_epi_archive.Rd       |  4 +--
 14 files changed, 247 insertions(+), 171 deletions(-)

diff --git a/man/as_epi_archive.Rd b/man/as_epi_archive.Rd
index d63a5faa..a1c60687 100644
--- a/man/as_epi_archive.Rd
+++ b/man/as_epi_archive.Rd
@@ -99,32 +99,44 @@ would be equivalent to:
 # Simple ex. with necessary keys
 tib <- tibble::tibble(
   geo_value = rep(c("ca", "hi"), each = 5),
-  time_value = rep(seq(as.Date("2020-01-01"), 
-                       by = 1, length.out = 5), times = 2),
-  version = rep(seq(as.Date("2020-01-02"), 
-                    by = 1, length.out = 5), times = 2),
+  time_value = rep(seq(as.Date("2020-01-01"),
+    by = 1, length.out = 5
+  ), times = 2),
+  version = rep(seq(as.Date("2020-01-02"),
+    by = 1, length.out = 5
+  ), times = 2),
   value = rnorm(10, mean = 2, sd = 1)
 )
 
-toy_epi_archive <- tib \%>\% as_epi_archive(geo_type = "state", 
-                                          time_type = "day")
-toy_epi_archive 
+toy_epi_archive <- tib \%>\% as_epi_archive(
+  geo_type = "state",
+  time_type = "day"
+)
+toy_epi_archive
 
 # Ex. with an additional key for county
-df <- data.frame (geo_value  = c(replicate(2, "ca"), replicate(2, "fl")),
-                 county = c(1, 3, 2, 5),
-                 time_value = c("2020-06-01",
-                                "2020-06-02",
-                                "2020-06-01",
-                                "2020-06-02"),
-                 version = c("2020-06-02",
-                             "2020-06-03",
-                             "2020-06-02",
-                             "2020-06-03"),
-                 cases = c(1, 2, 3, 4),
-                 cases_rate = c(0.01, 0.02, 0.01, 0.05))
+df <- data.frame(
+  geo_value = c(replicate(2, "ca"), replicate(2, "fl")),
+  county = c(1, 3, 2, 5),
+  time_value = c(
+    "2020-06-01",
+    "2020-06-02",
+    "2020-06-01",
+    "2020-06-02"
+  ),
+  version = c(
+    "2020-06-02",
+    "2020-06-03",
+    "2020-06-02",
+    "2020-06-03"
+  ),
+  cases = c(1, 2, 3, 4),
+  cases_rate = c(0.01, 0.02, 0.01, 0.05)
+)
 
-x <- df \%>\% as_epi_archive(geo_type = "state",
-                           time_type = "day",
-                           other_keys = "county")
+x <- df \%>\% as_epi_archive(
+  geo_type = "state",
+  time_type = "day",
+  other_keys = "county"
+)
 }
diff --git a/man/as_epi_df.Rd b/man/as_epi_df.Rd
index 851aed7e..40c0a1c5 100644
--- a/man/as_epi_df.Rd
+++ b/man/as_epi_df.Rd
@@ -76,19 +76,22 @@ the \code{tbl_ts} class is dropped, and any key variables (other than
 
 ex1_input <- tibble::tibble(
   geo_value = rep(c("ca", "fl", "pa"), each = 3),
-  county_code = c("06059","06061","06067",
-                  "12111","12113","12117",
-                  "42101", "42103","42105"),
+  county_code = c(
+    "06059", "06061", "06067",
+    "12111", "12113", "12117",
+    "42101", "42103", "42105"
+  ),
   time_value = rep(seq(as.Date("2020-06-01"), as.Date("2020-06-03"),
-                       by = "day"), length.out = length(geo_value)),
+    by = "day"
+  ), length.out = length(geo_value)),
   value = 1:length(geo_value) + 0.01 * rnorm(length(geo_value))
-) \%>\% 
+) \%>\%
   tsibble::as_tsibble(index = time_value, key = c(geo_value, county_code))
 
 # The `other_keys` metadata (`"county_code"` in this case) is automatically
 # inferred from the `tsibble`'s `key`:
 ex1 <- as_epi_df(x = ex1_input, geo_type = "state", time_type = "day", as_of = "2020-06-03")
-attr(ex1,"metadata")[["other_keys"]]
+attr(ex1, "metadata")[["other_keys"]]
 
 
 
@@ -102,17 +105,21 @@ ex2_input <- tibble::tibble(
   state = rep(c("ca", "fl", "pa"), each = 3), # misnamed
   pol = rep(c("blue", "swing", "swing"), each = 3), # extra key
   reported_date = rep(seq(as.Date("2020-06-01"), as.Date("2020-06-03"),
-                          by = "day"), length.out = length(state)), # misnamed
+    by = "day"
+  ), length.out = length(state)), # misnamed
   value = 1:length(state) + 0.01 * rnorm(length(state))
-) 
+)
 
 print(ex2_input)
 
-ex2 <- ex2_input \%>\% dplyr::rename(geo_value = state, time_value = reported_date) \%>\%
-  as_epi_df(geo_type = "state", as_of = "2020-06-03", 
-            additional_metadata = list(other_keys = "pol")) 
+ex2 <- ex2_input \%>\%
+  dplyr::rename(geo_value = state, time_value = reported_date) \%>\%
+  as_epi_df(
+    geo_type = "state", as_of = "2020-06-03",
+    additional_metadata = list(other_keys = "pol")
+  )
 
-attr(ex2,"metadata")
+attr(ex2, "metadata")
 
 
 
@@ -120,17 +127,18 @@ attr(ex2,"metadata")
 
 ex3_input <- jhu_csse_county_level_subset \%>\%
   dplyr::filter(time_value > "2021-12-01", state_name == "Massachusetts") \%>\%
-  dplyr::slice_tail(n = 6) 
+  dplyr::slice_tail(n = 6)
 
-ex3 <- ex3_input \%>\% 
+ex3 <- ex3_input \%>\%
   tsibble::as_tsibble() \%>\% # needed to add the additional metadata
   # add 2 extra keys
   dplyr::mutate(
-    state = rep("MA",6),
-    pol = rep(c("blue", "swing", "swing"), each = 2)) \%>\% 
-  # the 2 extra keys we added have to be specified in the other_keys 
+    state = rep("MA", 6),
+    pol = rep(c("blue", "swing", "swing"), each = 2)
+  ) \%>\%
+  # the 2 extra keys we added have to be specified in the other_keys
   # component of additional_metadata.
   as_epi_df(additional_metadata = list(other_keys = c("state", "pol")))
 
-attr(ex3,"metadata")
+attr(ex3, "metadata")
 }
diff --git a/man/detect_outlr.Rd b/man/detect_outlr.Rd
index 4aa0b79c..3a793ebf 100644
--- a/man/detect_outlr.Rd
+++ b/man/detect_outlr.Rd
@@ -64,29 +64,43 @@ For convenience, the outlier detection method can be specified (in the
 STL decomposition.
 }
 \examples{
- detection_methods = dplyr::bind_rows(
-   dplyr::tibble(method = "rm",
-          args = list(list(detect_negatives = TRUE,
-                           detection_multiplier = 2.5)),
-          abbr = "rm"),
-   dplyr::tibble(method = "stl",
-          args = list(list(detect_negatives = TRUE,
-                           detection_multiplier = 2.5,
-                           seasonal_period = 7)),
-          abbr = "stl_seasonal"),
-   dplyr::tibble(method = "stl",
-          args = list(list(detect_negatives = TRUE,
-                           detection_multiplier = 2.5,
-                           seasonal_period = NULL)),
-          abbr = "stl_nonseasonal"))
+detection_methods <- dplyr::bind_rows(
+  dplyr::tibble(
+    method = "rm",
+    args = list(list(
+      detect_negatives = TRUE,
+      detection_multiplier = 2.5
+    )),
+    abbr = "rm"
+  ),
+  dplyr::tibble(
+    method = "stl",
+    args = list(list(
+      detect_negatives = TRUE,
+      detection_multiplier = 2.5,
+      seasonal_period = 7
+    )),
+    abbr = "stl_seasonal"
+  ),
+  dplyr::tibble(
+    method = "stl",
+    args = list(list(
+      detect_negatives = TRUE,
+      detection_multiplier = 2.5,
+      seasonal_period = NULL
+    )),
+    abbr = "stl_nonseasonal"
+  )
+)
 
- x <- incidence_num_outlier_example \%>\%
-   dplyr::select(geo_value,time_value,cases) \%>\%
-   as_epi_df() \%>\%
-   group_by(geo_value) \%>\%
-   mutate(outlier_info  = detect_outlr(
-     x = time_value, y = cases,
-     methods = detection_methods,
-     combiner = "median")) \%>\%
-   unnest(outlier_info)
+x <- incidence_num_outlier_example \%>\%
+  dplyr::select(geo_value, time_value, cases) \%>\%
+  as_epi_df() \%>\%
+  group_by(geo_value) \%>\%
+  mutate(outlier_info = detect_outlr(
+    x = time_value, y = cases,
+    methods = detection_methods,
+    combiner = "median"
+  )) \%>\%
+  unnest(outlier_info)
 }
diff --git a/man/detect_outlr_rm.Rd b/man/detect_outlr_rm.Rd
index 3efae55d..0d011619 100644
--- a/man/detect_outlr_rm.Rd
+++ b/man/detect_outlr_rm.Rd
@@ -59,10 +59,11 @@ terms of multiples of the rolling interquartile range (IQR).
 \examples{
 # Detect outliers based on a rolling median
 incidence_num_outlier_example \%>\%
-  dplyr::select(geo_value,time_value,cases) \%>\%
+  dplyr::select(geo_value, time_value, cases) \%>\%
   as_epi_df() \%>\%
   group_by(geo_value) \%>\%
-  mutate(outlier_info  = detect_outlr_rm(
-    x = time_value, y = cases)) \%>\%
+  mutate(outlier_info = detect_outlr_rm(
+    x = time_value, y = cases
+  )) \%>\%
   unnest(outlier_info)
 }
diff --git a/man/detect_outlr_stl.Rd b/man/detect_outlr_stl.Rd
index 7e724a4e..34a550d5 100644
--- a/man/detect_outlr_stl.Rd
+++ b/man/detect_outlr_stl.Rd
@@ -78,11 +78,12 @@ are exactly as in \code{detect_outlr_rm()}.
 \examples{
 # Detects outliers based on a seasonal-trend decomposition using LOESS
 incidence_num_outlier_example \%>\%
-  dplyr::select(geo_value,time_value,cases) \%>\%
+  dplyr::select(geo_value, time_value, cases) \%>\%
   as_epi_df() \%>\%
   group_by(geo_value) \%>\%
-  mutate(outlier_info  = detect_outlr_stl(
+  mutate(outlier_info = detect_outlr_stl(
     x = time_value, y = cases,
-    seasonal_period = 7 )) \%>\% # weekly seasonality for daily data
+    seasonal_period = 7
+  )) \%>\% # weekly seasonality for daily data
   unnest(outlier_info)
 }
diff --git a/man/epi_archive.Rd b/man/epi_archive.Rd
index a4a58645..366eafe0 100644
--- a/man/epi_archive.Rd
+++ b/man/epi_archive.Rd
@@ -100,16 +100,20 @@ are documented in the wrapper function \code{\link[=epix_slide]{epix_slide()}}.
 \examples{
 tib <- tibble::tibble(
   geo_value = rep(c("ca", "hi"), each = 5),
-  time_value = rep(seq(as.Date("2020-01-01"), 
-                       by = 1, length.out = 5), times = 2),
-  version = rep(seq(as.Date("2020-01-02"), 
-                    by = 1, length.out = 5), times = 2),
+  time_value = rep(seq(as.Date("2020-01-01"),
+    by = 1, length.out = 5
+  ), times = 2),
+  version = rep(seq(as.Date("2020-01-02"),
+    by = 1, length.out = 5
+  ), times = 2),
   value = rnorm(10, mean = 2, sd = 1)
 )
 
-toy_epi_archive <- tib \%>\% epi_archive$new(geo_type = "state", 
-                                           time_type = "day")
-toy_epi_archive 
+toy_epi_archive <- tib \%>\% epi_archive$new(
+  geo_type = "state",
+  time_type = "day"
+)
+toy_epi_archive
 }
 \section{Methods}{
 \subsection{Public methods}{
diff --git a/man/epi_cor.Rd b/man/epi_cor.Rd
index 6b2279db..fb56073f 100644
--- a/man/epi_cor.Rd
+++ b/man/epi_cor.Rd
@@ -58,30 +58,38 @@ grouping by geo value, time value, or any other variables. See the
 for examples.
 }
 \examples{
- 
+
 # linear association of case and death rates on any given day
-epi_cor(x = jhu_csse_daily_subset, 
-        var1 = case_rate_7d_av, 
-        var2 = death_rate_7d_av, 
-        cor_by = "time_value")
+epi_cor(
+  x = jhu_csse_daily_subset,
+  var1 = case_rate_7d_av,
+  var2 = death_rate_7d_av,
+  cor_by = "time_value"
+)
 
 # correlation of death rates and lagged case rates
-epi_cor(x = jhu_csse_daily_subset, 
-        var1 = case_rate_7d_av, 
-        var2 = death_rate_7d_av, 
-        cor_by = time_value, 
-        dt1 = -2)
+epi_cor(
+  x = jhu_csse_daily_subset,
+  var1 = case_rate_7d_av,
+  var2 = death_rate_7d_av,
+  cor_by = time_value,
+  dt1 = -2
+)
 
-# correlation grouped by location 
-epi_cor(x = jhu_csse_daily_subset, 
-        var1 = case_rate_7d_av, 
-        var2 = death_rate_7d_av, 
-        cor_by = geo_value)
+# correlation grouped by location
+epi_cor(
+  x = jhu_csse_daily_subset,
+  var1 = case_rate_7d_av,
+  var2 = death_rate_7d_av,
+  cor_by = geo_value
+)
 
 # correlation grouped by location and incorporates lagged cases rates
-epi_cor(x = jhu_csse_daily_subset, 
-        var1 = case_rate_7d_av, 
-        var2 = death_rate_7d_av, 
-        cor_by = geo_value, 
-        dt1 = -2)
+epi_cor(
+  x = jhu_csse_daily_subset,
+  var1 = case_rate_7d_av,
+  var2 = death_rate_7d_av,
+  cor_by = geo_value,
+  dt1 = -2
+)
 }
diff --git a/man/epi_slide.Rd b/man/epi_slide.Rd
index 33c3a7fb..668be9ff 100644
--- a/man/epi_slide.Rd
+++ b/man/epi_slide.Rd
@@ -156,9 +156,9 @@ through the \code{new_col_name} argument.
 # slide a 7-day trailing average formula on cases
 jhu_csse_daily_subset \%>\%
   group_by(geo_value) \%>\%
-  epi_slide(cases_7dav = mean(cases), before = 6) \%>\% 
+  epi_slide(cases_7dav = mean(cases), before = 6) \%>\%
   # rmv a nonessential var. to ensure new col is printed
-  dplyr::select(-death_rate_7d_av) 
+  dplyr::select(-death_rate_7d_av)
 
 # slide a 7-day leading average
 jhu_csse_daily_subset \%>\%
@@ -170,21 +170,25 @@ jhu_csse_daily_subset \%>\%
 # slide a 7-day centre-aligned average
 jhu_csse_daily_subset \%>\%
   group_by(geo_value) \%>\%
-  epi_slide(cases_7dav = mean(cases), before = 3, after = 3) \%>\% 
+  epi_slide(cases_7dav = mean(cases), before = 3, after = 3) \%>\%
   # rmv a nonessential var. to ensure new col is printed
-  dplyr::select(-death_rate_7d_av) 
+  dplyr::select(-death_rate_7d_av)
 
 # slide a 14-day centre-aligned average
 jhu_csse_daily_subset \%>\%
   group_by(geo_value) \%>\%
-  epi_slide(cases_7dav = mean(cases), before = 6, after = 7) \%>\% 
+  epi_slide(cases_7dav = mean(cases), before = 6, after = 7) \%>\%
   # rmv a nonessential var. to ensure new col is printed
-  dplyr::select(-death_rate_7d_av) 
+  dplyr::select(-death_rate_7d_av)
 
 # nested new columns
 jhu_csse_daily_subset \%>\%
   group_by(geo_value) \%>\%
-  epi_slide(a = data.frame(cases_2dav = mean(cases),
-                           cases_2dma = mad(cases)),
-            before = 1, as_list_col = TRUE)
+  epi_slide(
+    a = data.frame(
+      cases_2dav = mean(cases),
+      cases_2dma = mad(cases)
+    ),
+    before = 1, as_list_col = TRUE
+  )
 }
diff --git a/man/epix_as_of.Rd b/man/epix_as_of.Rd
index 51884597..9a0a53ce 100644
--- a/man/epix_as_of.Rd
+++ b/man/epix_as_of.Rd
@@ -55,14 +55,18 @@ in the future.
 }
 \examples{
 # warning message of data latency shown
-epix_as_of(x = archive_cases_dv_subset,
-           max_version = max(archive_cases_dv_subset$DT$version))
+epix_as_of(
+  x = archive_cases_dv_subset,
+  max_version = max(archive_cases_dv_subset$DT$version)
+)
 
 
 range(archive_cases_dv_subset$DT$version) # 2020-06-02 -- 2021-12-01
 
-epix_as_of(x = archive_cases_dv_subset,
-           max_version = as.Date("2020-06-12"))
+epix_as_of(
+  x = archive_cases_dv_subset,
+  max_version = as.Date("2020-06-12")
+)
 
 # When fetching a snapshot as of the latest version with update data in the
 # archive, a warning is issued by default, as this update data might not yet
@@ -72,10 +76,15 @@ epix_as_of(x = archive_cases_dv_subset,
 # based on database queries, the latest available update might still be
 # subject to change, but previous versions should be finalized). We can
 # muffle such warnings with the following pattern:
-withCallingHandlers({
-  epix_as_of(x = archive_cases_dv_subset,
-             max_version = max(archive_cases_dv_subset$DT$version))
-}, epiprocess__snapshot_as_of_clobberable_version = function(wrn) invokeRestart("muffleWarning"))
+withCallingHandlers(
+  {
+    epix_as_of(
+      x = archive_cases_dv_subset,
+      max_version = max(archive_cases_dv_subset$DT$version)
+    )
+  },
+  epiprocess__snapshot_as_of_clobberable_version = function(wrn) invokeRestart("muffleWarning")
+)
 # Since R 4.0, there is a `globalCallingHandlers` function that can be used
 # to globally toggle these warnings.
 
diff --git a/man/epix_merge.Rd b/man/epix_merge.Rd
index 09f67fa2..53dea071 100644
--- a/man/epix_merge.Rd
+++ b/man/epix_merge.Rd
@@ -60,13 +60,13 @@ be clobbered in either input archive.
 \examples{
 # create two example epi_archive datasets
 x <- archive_cases_dv_subset$DT \%>\%
-  dplyr::select(geo_value,time_value,version,case_rate_7d_av) \%>\%
-  as_epi_archive(compactify=TRUE)
+  dplyr::select(geo_value, time_value, version, case_rate_7d_av) \%>\%
+  as_epi_archive(compactify = TRUE)
 y <- archive_cases_dv_subset$DT \%>\%
-  dplyr::select(geo_value,time_value,version,percent_cli) \%>\%
-  as_epi_archive(compactify=TRUE)
+  dplyr::select(geo_value, time_value, version, percent_cli) \%>\%
+  as_epi_archive(compactify = TRUE)
 # merge results stored in a third object:
-xy = epix_merge(x, y)
+xy <- epix_merge(x, y)
 # vs. mutating x to hold the merge result:
 x$merge(y)
 
diff --git a/man/epix_slide.Rd b/man/epix_slide.Rd
index d94460af..3ac55a18 100644
--- a/man/epix_slide.Rd
+++ b/man/epix_slide.Rd
@@ -193,17 +193,20 @@ library(dplyr)
 
 # Reference time points for which we want to compute slide values:
 ref_time_values <- seq(as.Date("2020-06-01"),
-                       as.Date("2020-06-15"),
-                       by = "1 day")
+  as.Date("2020-06-15"),
+  by = "1 day"
+)
 
 # A simple (but not very useful) example (see the archive vignette for a more
 # realistic one):
 archive_cases_dv_subset \%>\%
   group_by(geo_value) \%>\%
-  epix_slide(f = ~ mean(.x$case_rate_7d_av),
-             before = 2,
-             ref_time_values = ref_time_values,
-             new_col_name = 'case_rate_7d_av_recent_av') \%>\%
+  epix_slide(
+    f = ~ mean(.x$case_rate_7d_av),
+    before = 2,
+    ref_time_values = ref_time_values,
+    new_col_name = "case_rate_7d_av_recent_av"
+  ) \%>\%
   ungroup()
 # We requested time windows that started 2 days before the corresponding time
 # values. The actual number of `time_value`s in each computation depends on
@@ -221,23 +224,24 @@ archive_cases_dv_subset \%>\%
 # Examining characteristics of the data passed to each computation with
 # `all_versions=FALSE`.
 archive_cases_dv_subset \%>\%
- group_by(geo_value) \%>\%
- epix_slide(
-   function(x, gk, rtv) {
-     tibble(
-       time_range = if(nrow(x) == 0L) {
-         "0 `time_value`s"
-       } else {
-         sprintf("\%s -- \%s", min(x$time_value), max(x$time_value))
-       },
-       n = nrow(x),
-       class1 = class(x)[[1L]]
-     )
-   },
-   before = 5, all_versions = FALSE,
-   ref_time_values = ref_time_values, names_sep=NULL) \%>\%
- ungroup() \%>\%
- arrange(geo_value, time_value)
+  group_by(geo_value) \%>\%
+  epix_slide(
+    function(x, gk, rtv) {
+      tibble(
+        time_range = if (nrow(x) == 0L) {
+          "0 `time_value`s"
+        } else {
+          sprintf("\%s -- \%s", min(x$time_value), max(x$time_value))
+        },
+        n = nrow(x),
+        class1 = class(x)[[1L]]
+      )
+    },
+    before = 5, all_versions = FALSE,
+    ref_time_values = ref_time_values, names_sep = NULL
+  ) \%>\%
+  ungroup() \%>\%
+  arrange(geo_value, time_value)
 
 # --- Advanced: ---
 
@@ -259,7 +263,7 @@ archive_cases_dv_subset \%>\%
           toString(min(x$DT$version))
         },
         versions_end = x$versions_end,
-        time_range = if(nrow(x$DT) == 0L) {
+        time_range = if (nrow(x$DT) == 0L) {
           "0 `time_value`s"
         } else {
           sprintf("\%s -- \%s", min(x$DT$time_value), max(x$DT$time_value))
@@ -269,7 +273,8 @@ archive_cases_dv_subset \%>\%
       )
     },
     before = 5, all_versions = TRUE,
-    ref_time_values = ref_time_values, names_sep=NULL) \%>\%
+    ref_time_values = ref_time_values, names_sep = NULL
+  ) \%>\%
   ungroup() \%>\%
   # Focus on one geo_value so we can better see the columns above:
   filter(geo_value == "ca") \%>\%
diff --git a/man/group_by.epi_archive.Rd b/man/group_by.epi_archive.Rd
index aee0a07b..5e867bf3 100644
--- a/man/group_by.epi_archive.Rd
+++ b/man/group_by.epi_archive.Rd
@@ -93,7 +93,7 @@ to \code{group_by_drop_default.default} (but there is a dedicated method for
 }
 \examples{
 
-grouped_archive = archive_cases_dv_subset \%>\% group_by(geo_value)
+grouped_archive <- archive_cases_dv_subset \%>\% group_by(geo_value)
 
 # `print` for metadata and method listing:
 grouped_archive \%>\% print()
@@ -102,10 +102,12 @@ grouped_archive \%>\% print()
 
 archive_cases_dv_subset \%>\%
   group_by(geo_value) \%>\%
-  epix_slide(f = ~ mean(.x$case_rate_7d_av),
-             before = 2,
-             ref_time_values = as.Date("2020-06-11") + 0:2,
-             new_col_name = 'case_rate_3d_av') \%>\%
+  epix_slide(
+    f = ~ mean(.x$case_rate_7d_av),
+    before = 2,
+    ref_time_values = as.Date("2020-06-11") + 0:2,
+    new_col_name = "case_rate_3d_av"
+  ) \%>\%
   ungroup()
 
 # -----------------------------------------------------------------
@@ -113,34 +115,42 @@ archive_cases_dv_subset \%>\%
 # Advanced: some other features of dplyr grouping are implemented:
 
 library(dplyr)
-toy_archive =
+toy_archive <-
   tribble(
-    ~geo_value,  ~age_group,  ~time_value,     ~version, ~value,
-          "us",     "adult", "2000-01-01", "2000-01-02",    121,
-          "us", "pediatric", "2000-01-02", "2000-01-03",      5, # (addition)
-          "us",     "adult", "2000-01-01", "2000-01-03",    125, # (revision)
-          "us",     "adult", "2000-01-02", "2000-01-03",    130  # (addition)
+    ~geo_value, ~age_group, ~time_value, ~version, ~value,
+    "us", "adult", "2000-01-01", "2000-01-02", 121,
+    "us", "pediatric", "2000-01-02", "2000-01-03", 5, # (addition)
+    "us", "adult", "2000-01-01", "2000-01-03", 125, # (revision)
+    "us", "adult", "2000-01-02", "2000-01-03", 130 # (addition)
+  ) \%>\%
+  mutate(
+    age_group = ordered(age_group, c("pediatric", "adult")),
+    time_value = as.Date(time_value),
+    version = as.Date(version)
   ) \%>\%
-  mutate(age_group = ordered(age_group, c("pediatric", "adult")),
-         time_value = as.Date(time_value),
-         version = as.Date(version)) \%>\%
   as_epi_archive(other_keys = "age_group")
 
 # The following are equivalent:
 toy_archive \%>\% group_by(geo_value, age_group)
-toy_archive \%>\% group_by(geo_value) \%>\% group_by(age_group, .add=TRUE)
-grouping_cols = c("geo_value", "age_group")
+toy_archive \%>\%
+  group_by(geo_value) \%>\%
+  group_by(age_group, .add = TRUE)
+grouping_cols <- c("geo_value", "age_group")
 toy_archive \%>\% group_by(across(all_of(grouping_cols)))
 
 # And these are equivalent:
 toy_archive \%>\% group_by(geo_value)
-toy_archive \%>\% group_by(geo_value, age_group) \%>\% ungroup(age_group)
+toy_archive \%>\%
+  group_by(geo_value, age_group) \%>\%
+  ungroup(age_group)
 
 # To get the grouping variable names as a `list` of `name`s (a.k.a. symbols):
-toy_archive \%>\% group_by(geo_value) \%>\% groups()
+toy_archive \%>\%
+  group_by(geo_value) \%>\%
+  groups()
 
 toy_archive \%>\%
-  group_by(geo_value, age_group, .drop=FALSE) \%>\%
+  group_by(geo_value, age_group, .drop = FALSE) \%>\%
   epix_slide(f = ~ sum(.x$value), before = 20) \%>\%
   ungroup()
 
diff --git a/man/growth_rate.Rd b/man/growth_rate.Rd
index 203d5d7d..7a3f1151 100644
--- a/man/growth_rate.Rd
+++ b/man/growth_rate.Rd
@@ -136,12 +136,12 @@ user.
 
 \examples{
 # COVID cases growth rate by state using default method relative change
-jhu_csse_daily_subset \%>\% 
-  group_by(geo_value) \%>\% 
-  mutate(cases_gr = growth_rate(x = time_value,  y = cases))
+jhu_csse_daily_subset \%>\%
+  group_by(geo_value) \%>\%
+  mutate(cases_gr = growth_rate(x = time_value, y = cases))
 
 # Log scale, degree 4 polynomial and 6-fold cross validation
-jhu_csse_daily_subset \%>\% 
-  group_by(geo_value) \%>\% 
-  mutate(gr_poly = growth_rate( x = time_value, y = cases, log_scale = TRUE,  ord = 4,  k = 6))
+jhu_csse_daily_subset \%>\%
+  group_by(geo_value) \%>\%
+  mutate(gr_poly = growth_rate(x = time_value, y = cases, log_scale = TRUE, ord = 4, k = 6))
 }
diff --git a/man/is_epi_archive.Rd b/man/is_epi_archive.Rd
index 5b133004..2beb3a8c 100644
--- a/man/is_epi_archive.Rd
+++ b/man/is_epi_archive.Rd
@@ -25,9 +25,9 @@ is_epi_archive(archive_cases_dv_subset) # TRUE
 # By default, grouped_epi_archives don't count as epi_archives, as they may
 # support a different set of operations from regular `epi_archives`. This
 # behavior can be controlled by `grouped_okay`.
-grouped_archive = archive_cases_dv_subset$group_by(geo_value)
+grouped_archive <- archive_cases_dv_subset$group_by(geo_value)
 is_epi_archive(grouped_archive) # FALSE
-is_epi_archive(grouped_archive, grouped_okay=TRUE) # TRUE
+is_epi_archive(grouped_archive, grouped_okay = TRUE) # TRUE
 
 }
 \seealso{