From 003d3850e373e1251150228bbd2bd4cdeb90184c Mon Sep 17 00:00:00 2001
From: "allcontributors[bot]"
<46447321+allcontributors[bot]@users.noreply.github.com>
Date: Mon, 7 Oct 2024 18:55:24 +0000
Subject: [PATCH 1/5] docs: update README.md
---
README.md | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/README.md b/README.md
index 6dd640d..c688b30 100644
--- a/README.md
+++ b/README.md
@@ -245,6 +245,13 @@ add_parent_interval(dat)
+
From b86513628fbab8e45b4845ff25d7639d158e184e Mon Sep 17 00:00:00 2001
From: "allcontributors[bot]"
<46447321+allcontributors[bot]@users.noreply.github.com>
Date: Mon, 7 Oct 2024 18:55:25 +0000
Subject: [PATCH 2/5] docs: update .all-contributorsrc
---
.all-contributorsrc | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/.all-contributorsrc b/.all-contributorsrc
index 7498da5..08e4d62 100644
--- a/.all-contributorsrc
+++ b/.all-contributorsrc
@@ -1,4 +1,21 @@
{
"projectName": "NHSRepisodes",
- "projectOwner": "nhs-r-community"
+ "projectOwner": "nhs-r-community",
+ "files": [
+ "README.md"
+ ],
+ "commitType": "docs",
+ "commitConvention": "angular",
+ "contributorsPerLine": 7,
+ "contributors": [
+ {
+ "login": "TimTaylor",
+ "name": "Tim Taylor",
+ "avatar_url": "https://avatars.githubusercontent.com/u/43499035?v=4",
+ "profile": "https://github.com/TimTaylor",
+ "contributions": [
+ "doc"
+ ]
+ }
+ ]
}
From 7b134875a44f60394f92b76740668f3aa3e38a08 Mon Sep 17 00:00:00 2001
From: "allcontributors[bot]"
<46447321+allcontributors[bot]@users.noreply.github.com>
Date: Mon, 7 Oct 2024 18:59:37 +0000
Subject: [PATCH 3/5] docs: update README.md
---
README.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/README.md b/README.md
index c688b30..19d5ba2 100644
--- a/README.md
+++ b/README.md
@@ -248,7 +248,7 @@ add_parent_interval(dat)
From 2863c6604725909240b96a4228c2f8d67a9358a1 Mon Sep 17 00:00:00 2001
From: "allcontributors[bot]"
<46447321+allcontributors[bot]@users.noreply.github.com>
Date: Mon, 7 Oct 2024 18:59:38 +0000
Subject: [PATCH 4/5] docs: update .all-contributorsrc
---
.all-contributorsrc | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/.all-contributorsrc b/.all-contributorsrc
index 08e4d62..0ac9b9a 100644
--- a/.all-contributorsrc
+++ b/.all-contributorsrc
@@ -14,7 +14,8 @@
"avatar_url": "https://avatars.githubusercontent.com/u/43499035?v=4",
"profile": "https://github.com/TimTaylor",
"contributions": [
- "doc"
+ "doc",
+ "test"
]
}
]
From 9b950e42d9a8b2ff6ea5bc333b39a057c60feab9 Mon Sep 17 00:00:00 2001
From: Lextuga007
Date: Mon, 7 Oct 2024 20:09:30 +0100
Subject: [PATCH 5/5] Added cache to TRUE so times are not rerun and added
Contributors badge
---
README.Rmd | 4 +++-
README.md | 68 +++++++++++++++++++++++++-----------------------------
2 files changed, 34 insertions(+), 38 deletions(-)
diff --git a/README.Rmd b/README.Rmd
index daf4b4b..91342f5 100644
--- a/README.Rmd
+++ b/README.Rmd
@@ -19,7 +19,8 @@ knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>",
fig.path = "man/figures/README-",
- out.width = "100%"
+ out.width = "100%",
+ cache = TRUE
)
```
@@ -28,6 +29,7 @@ knitr::opts_chunk$set(
[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
[![R-CMD-check](https://github.com/nhs-r-community/NHSRepisodes/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/nhs-r-community/NHSRepisodes/actions/workflows/R-CMD-check.yaml)
+[![All Contributors](https://img.shields.io/github/all-contributors/nhs-r-community/NHSRepisodes?color=ee8449&style=flat-square)](#contributors)
## Installation instructions
diff --git a/README.md b/README.md
index 19d5ba2..5374c1d 100644
--- a/README.md
+++ b/README.md
@@ -8,6 +8,8 @@
[![Lifecycle:
experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
[![R-CMD-check](https://github.com/nhs-r-community/NHSRepisodes/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/nhs-r-community/NHSRepisodes/actions/workflows/R-CMD-check.yaml)
+[![All
+Contributors](https://img.shields.io/github/all-contributors/nhs-r-community/NHSRepisodes?color=ee8449&style=flat-square)](#contributors)
## Installation instructions
@@ -57,7 +59,7 @@ mutate(tibble(packages), version = sapply(packages, getNamespaceVersion))
#> packages version
#>
#> 1 NHSRepisodes 0.1.0.9000
-#> 2 dplyr 1.1.4.9000
+#> 2 dplyr 1.1.4
#> 3 data.table 1.16.0
#> 4 ivs 0.2.0
@@ -126,18 +128,18 @@ end2 <- start2 + sample(1:100, size = n * 5, replace = TRUE)
# creates the object big_dat and shows the first 10 rows as a tibble in the console
(big_dat <- tibble(id = id2, start = start2, end = end2))
#> # A tibble: 625,000 × 3
-#> id start end
-#>
-#> 1 90983 2020-02-07 2020-03-18
-#> 2 59640 2020-07-05 2020-08-13
-#> 3 29543 2020-04-05 2020-05-28
-#> 4 17962 2020-06-07 2020-07-21
-#> 5 13032 2020-08-25 2020-09-08
-#> 6 94348 2020-05-11 2020-06-07
-#> 7 7770 2020-03-18 2020-04-03
-#> 8 9570 2020-09-25 2020-12-04
-#> 9 86687 2020-11-04 2021-01-09
-#> 10 66213 2020-04-09 2020-04-16
+#> id start end
+#>
+#> 1 47215 2020-12-29 2021-02-16
+#> 2 91739 2020-09-16 2020-11-12
+#> 3 114791 2020-01-31 2020-02-27
+#> 4 83644 2020-08-17 2020-11-04
+#> 5 68824 2020-02-14 2020-05-06
+#> 6 100194 2020-12-11 2021-03-18
+#> 7 3871 2020-06-21 2020-07-06
+#> 8 118901 2020-01-09 2020-03-23
+#> 9 80676 2020-07-23 2020-08-19
+#> 10 84580 2020-07-17 2020-10-07
#> # ℹ 624,990 more rows
# checking the time to run
@@ -148,7 +150,7 @@ system.time(
reframe(interval = iv_groups(interval, abutting = FALSE), .by = id)
)
#> user system elapsed
-#> 13.870 0.065 13.996
+#> 17.00 0.28 17.30
```
If you were not already using it, this is likely the time you would
@@ -175,32 +177,32 @@ fun <- function(s, e) {
system.time(out_dt <- DT[, fun(start, end + 1), by = id])
#> user system elapsed
-#> 14.972 0.022 14.984
+#> 19.26 0.49 19.77
```
***NHSRepisodes*** solves this with the `merge_episodes()` function:
``` r
merge_episodes(big_dat)
-#> # A tibble: 334,767 × 4
+#> # A tibble: 335,828 × 4
#> id .interval_number .episode_start .episode_end
#>
-#> 1 1 1 2020-04-16 2020-06-23
-#> 2 2 1 2020-01-12 2020-02-22
-#> 3 2 2 2020-07-22 2020-08-16
-#> 4 2 3 2020-09-27 2021-01-11
-#> 5 3 1 2020-01-06 2020-03-02
-#> 6 3 2 2020-03-08 2020-03-16
-#> 7 3 3 2020-06-05 2020-08-26
-#> 8 4 1 2020-02-05 2020-05-03
-#> 9 4 2 2020-05-19 2020-09-08
-#> 10 5 1 2020-01-14 2020-03-13
-#> # ℹ 334,757 more rows
+#> 1 1 1 2020-01-15 2020-01-27
+#> 2 1 2 2020-02-13 2020-11-14
+#> 3 1 3 2020-11-15 2021-02-13
+#> 4 2 1 2020-01-03 2020-03-25
+#> 5 2 2 2020-03-31 2020-06-09
+#> 6 2 3 2020-10-31 2020-11-08
+#> 7 2 4 2020-12-17 2021-01-23
+#> 8 3 1 2020-03-08 2020-03-19
+#> 9 3 2 2020-04-13 2020-05-26
+#> 10 3 3 2020-11-30 2020-12-01
+#> # ℹ 335,818 more rows
# And for comparison with earlier timings
system.time(out <- merge_episodes(big_dat))
#> user system elapsed
-#> 0.917 0.000 0.335
+#> 0.59 0.11 0.44
# equal output (subject to ordering)
out <- out |>
@@ -240,20 +242,12 @@ add_parent_interval(dat)
#> 7 1 2020-01-01 2020-01-10 2020-01-01 2020-01-10 1
#> 8 1 2020-01-11 2020-01-12 2020-01-11 2020-01-12 2
```
+
## Contributors
-
-
-