From e640ddadafd0a86f2b2a4ff6e1418b40bf70efb8 Mon Sep 17 00:00:00 2001
From: Ebie Dambo <ebiekiemiete@gmail.com>
Date: Wed, 5 Jun 2024 13:17:11 -0500
Subject: [PATCH 1/3] Code to inject arbitrary summary tables into the codebook

If this commit is accepted, files for modifying the codebookr package to allow for the injection of arbitrary summary statistics will be created.
---
 .../1/s/c05vsgsjeetha/00000f.csv              |   7 -
 .../1/s/c0yswsfciymt1/00000f.csv              |  26 --
 .../1/s/c1vjzynphpouz/00000f.csv              |   1 -
 .../1/s/c3xs7awex8c96/00000f.csv              |  22 --
 .../1/s/c4ys1zykv84zs/00000f.csv              |   1 -
 .../1/s/c5j4cj1d6h4fn/00000f.csv              |   1 -
 .../1/s/c5lkhfys19zhb/00000f.csv              |  39 ---
 .../1/s/c5lwfbhkyscks/00000f.csv              |   1 -
 .../1/s/c62qty2tdap88/00000f.csv              |   7 -
 .../1/s/c7un1gfify09i/00000f.csv              |   9 -
 .../1/s/c81xp8u6qkx0s/00000f.csv              |   1 -
 .../1/s/c8gyssxaibaxd/00000f.csv              |  17 --
 .../1/s/c99s4pgb0u0bv/00000f.csv              |   1 -
 .../1/s/c9bz8t8xn83ld/000011.csv              |   5 -
 .../1/s/cb27j2lesd65y/00000f.csv              |   2 -
 .../1/s/cbvjplhy7jk0p/00000f.csv              |  68 -----
 .../1/s/ce27lx9w91hu6/00000f.csv              |   1 -
 .../1/s/cgfcy2ty8h1w9/00000f.csv              |   1 -
 .../notebooks/19D3CF1A-README/1/s/chunks.json |   1 -
 .../1/s/chwix01h46w6z/00000f.csv              |   8 -
 .../1/s/cjz4ieuexoxz5/00000f.csv              |   1 -
 .../1/s/cl8xydwb9kgmh/00000f.csv              |   7 -
 .../1/s/clegrvw8b73hi/00000f.csv              |   1 -
 .../1/s/coktz8j1ax7ez/00000f.csv              |   1 -
 .../1/s/cqenx2m2b8qix/00000f.csv              |  25 --
 .../1/s/cqg3c8cszvq9o/00000f.csv              |  22 --
 .../1/s/cr1z52xcmfewa/00000f.csv              |   1 -
 .../1/s/crgltl84sy4fz/00000f.csv              |   1 -
 .../1/s/cs4oh80233rdu/00000f.csv              |  67 -----
 .../1/s/csnuixqhrh2ve/00000f.csv              |   2 -
 .../1/s/ctcrzlg9ec52m/00000f.csv              |   3 -
 .../1/s/cv63qyqu0ql3w/00000f.csv              |   4 -
 .../1/s/cvjj8okp10rl8/00000f.csv              |   1 -
 .../1/s/cvubqyl0dsdd6/00000f.csv              |   2 -
 .../1/s/cyonc8ut9eh7p/00000f.csv              |   2 -
 R/cb_custom_summary_stats_to_ft.R             |  32 +++
 R/cb_inject_custom_summary_table.R            | 268 ++++++++++++++++++
 37 files changed, 300 insertions(+), 359 deletions(-)
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c05vsgsjeetha/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c0yswsfciymt1/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c1vjzynphpouz/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c3xs7awex8c96/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c4ys1zykv84zs/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5j4cj1d6h4fn/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lkhfys19zhb/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lwfbhkyscks/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c62qty2tdap88/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c7un1gfify09i/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c81xp8u6qkx0s/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c8gyssxaibaxd/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c99s4pgb0u0bv/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c9bz8t8xn83ld/000011.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cb27j2lesd65y/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cbvjplhy7jk0p/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ce27lx9w91hu6/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cgfcy2ty8h1w9/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chunks.json
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chwix01h46w6z/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cjz4ieuexoxz5/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cl8xydwb9kgmh/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/clegrvw8b73hi/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/coktz8j1ax7ez/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqenx2m2b8qix/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqg3c8cszvq9o/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cr1z52xcmfewa/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/crgltl84sy4fz/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cs4oh80233rdu/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/csnuixqhrh2ve/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ctcrzlg9ec52m/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cv63qyqu0ql3w/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvjj8okp10rl8/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvubqyl0dsdd6/00000f.csv
 delete mode 100644 .Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cyonc8ut9eh7p/00000f.csv
 create mode 100644 R/cb_custom_summary_stats_to_ft.R
 create mode 100644 R/cb_inject_custom_summary_table.R

diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c05vsgsjeetha/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c05vsgsjeetha/00000f.csv
deleted file mode 100644
index f9f1257..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c05vsgsjeetha/00000f.csv
+++ /dev/null
@@ -1,7 +0,0 @@
-"0","admin_vars <- study %>% "
-"0","  select(id, date, time) %>% "
-"0","  names()"
-"0",""
-"0","for(i in admin_vars) {"
-"0","  attr(study[[i]], ""source"") <- ""Administrative data"""
-"0","}"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c0yswsfciymt1/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c0yswsfciymt1/00000f.csv
deleted file mode 100644
index 0144298..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c0yswsfciymt1/00000f.csv
+++ /dev/null
@@ -1,26 +0,0 @@
-"0","attributes(study$time)"
-"1","$units
-"
-"1","[1]"
-"1"," ""secs"""
-"1","
-"
-"1","
-"
-"1","$class
-"
-"1","[1]"
-"1"," ""hms""     "
-"1"," ""difftime"""
-"1","
-"
-"1","
-"
-"1","$source
-"
-"1","[1]"
-"1"," ""Administrative data"""
-"1","
-"
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c1vjzynphpouz/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c1vjzynphpouz/00000f.csv
deleted file mode 100644
index ebcea7a..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c1vjzynphpouz/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(codebook(study), ""stata_codebook_1.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c3xs7awex8c96/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c3xs7awex8c96/00000f.csv
deleted file mode 100644
index 56425f6..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c3xs7awex8c96/00000f.csv
+++ /dev/null
@@ -1,22 +0,0 @@
-"0","glimpse(study)"
-"1","Rows: 20"
-"1",""
-"1","
-"
-"1","Columns: 10"
-"1",""
-"1","
-"
-"1","$ id        <chr> ""1001"", ""1002"", NA, ""1004"", ""1005"", ""1006"", ""1007"", ""1008"", ""1009"", ""1010"", ""1011"", ""1012"", ""1013"", ""1014"", ""1015"", ""1…
-$ address   <chr> ""101 A st."", ""101 B st."", ""101 C st."", ""101 D st."", ""101 E st."", ""101 F st."", ""101 G st."", ""101 H st."", ""101 I st."", ""…
-$ sex       <fct> Female, Female, Female, NA, Female, Male, Male, Male, Female, Female, Male, Male, Male, Female, Male, Female, Male, Fe…
-$ date      <date> 2021-10-12, 2021-09-23, 2021-10-13, 2021-10-19, NA, 2021-10-10, 2021-09-21, 2021-10-26, 2021-09-23, 2021-10-03, 2021-…
-$ time      <time> 08:56:40, 13:26:09, 09:24:22, 08:37:26, 09:20:59, 11:14:52, 12:40:06, 13:46:52, 10:25:26, 16:59:31, 11:30:37, 13:15:2…
-$ date_time <dttm> 2021-10-12 08:56:40, 2021-09-23 13:26:09, 2021-10-13 09:24:22, 2021-10-19 08:37:26, 2021-09-22 09:20:59, 2021-10-10 1…
-$ days      <int> 3, 15, 21, 5, 8, NA, 10, 18, 10, 12, 2, 10, 12, 20, 14, 17, 14, 3, 8, 14
-$ height    <dbl> 81.25571, 68.15227, 58.79282, 72.81303, 69.61109, 71.05764, NA, 67.29340, 77.44377, 68.79513, 74.31782, 81.96839, 75.3…
-$ likert    <int> 5, 3, 4, 4, 1, 4, 1, 3, 4, 3, 5, 4, 4, 4, 1, 2, 3, 4, 3, 1
-$ outcome   <lgl> TRUE, FALSE, FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, …"
-"1",""
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c4ys1zykv84zs/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c4ys1zykv84zs/00000f.csv
deleted file mode 100644
index 0199a72..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c4ys1zykv84zs/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(study_codebook, ""study_codebook_3.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5j4cj1d6h4fn/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5j4cj1d6h4fn/00000f.csv
deleted file mode 100644
index 2e709eb..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5j4cj1d6h4fn/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","study_codebook <- codebook(df = study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lkhfys19zhb/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lkhfys19zhb/00000f.csv
deleted file mode 100644
index 1ea6e62..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lkhfys19zhb/00000f.csv
+++ /dev/null
@@ -1,39 +0,0 @@
-"0","attributes(study$sex)"
-"1","$label
-"
-"1","[1]"
-"1"," ""Biological sex of the participant assigned at birth"""
-"1","
-"
-"1","
-"
-"1","$format.stata
-"
-"1","[1]"
-"1"," ""%8.0g"""
-"1","
-"
-"1","
-"
-"1","$class
-"
-"1","[1]"
-"1"," ""haven_labelled"""
-"1"," ""vctrs_vctr""    "
-"1"," ""double""        "
-"1","
-"
-"1","
-"
-"1","$labels
-"
-"1","Female "
-"1","  Male "
-"1","
-"
-"1","     1 "
-"1","     2 "
-"1","
-"
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lwfbhkyscks/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lwfbhkyscks/00000f.csv
deleted file mode 100644
index c40196e..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c5lwfbhkyscks/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(study_codebook, ""study_codebook_4.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c62qty2tdap88/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c62qty2tdap88/00000f.csv
deleted file mode 100644
index c6cae7d..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c62qty2tdap88/00000f.csv
+++ /dev/null
@@ -1,7 +0,0 @@
-"0","study <- study %>%"
-"0","  cb_add_col_attributes("
-"0","    likert,"
-"0","    col_type = ""Categorical"""
-"0","  )"
-"2","The following attribute(s) are being added to a variable in the data frame for the first time: col_type. If you believe this/these attribute(s) were previously added, then check for a typo in the attribute name. If you are adding this/these attribute(s) for the first time, you can probably safely ignore this message.
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c7un1gfify09i/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c7un1gfify09i/00000f.csv
deleted file mode 100644
index 1e5cfbc..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c7un1gfify09i/00000f.csv
+++ /dev/null
@@ -1,9 +0,0 @@
-"0","attributes(study$id)"
-"1","$source
-"
-"1","[1]"
-"1"," ""Administrative data"""
-"1","
-"
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c81xp8u6qkx0s/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c81xp8u6qkx0s/00000f.csv
deleted file mode 100644
index 2bcb726..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c81xp8u6qkx0s/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","rm(admin_vars, i)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c8gyssxaibaxd/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c8gyssxaibaxd/00000f.csv
deleted file mode 100644
index 1acc495..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c8gyssxaibaxd/00000f.csv
+++ /dev/null
@@ -1,17 +0,0 @@
-"0","attributes(study$date)"
-"1","$class
-"
-"1","[1]"
-"1"," ""Date"""
-"1","
-"
-"1","
-"
-"1","$source
-"
-"1","[1]"
-"1"," ""Administrative data"""
-"1","
-"
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c99s4pgb0u0bv/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c99s4pgb0u0bv/00000f.csv
deleted file mode 100644
index 08d4bac..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c99s4pgb0u0bv/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(x = study_codebook, target = ""study_codebook_1.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c9bz8t8xn83ld/000011.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c9bz8t8xn83ld/000011.csv
deleted file mode 100644
index f88458e..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/c9bz8t8xn83ld/000011.csv
+++ /dev/null
@@ -1,5 +0,0 @@
-"0","study_codebook <- codebook(study, no_summary_stats = ""address"")"
-"2","Registered S3 method overwritten by 'data.table':
-  method           from
-  print.data.table     
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cb27j2lesd65y/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cb27j2lesd65y/00000f.csv
deleted file mode 100644
index dc9e988..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cb27j2lesd65y/00000f.csv
+++ /dev/null
@@ -1,2 +0,0 @@
-"0","# Load example data"
-"0","data(study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cbvjplhy7jk0p/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cbvjplhy7jk0p/00000f.csv
deleted file mode 100644
index 4859e36..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cbvjplhy7jk0p/00000f.csv
+++ /dev/null
@@ -1,68 +0,0 @@
-"0","for (i in seq_along(names(study))) {"
-"0","  cat(paste0('"
-"0","    codebook_add_col_attributes( \n    ',"
-"0","      ""  "", names(study)[i], ', \n    ',"
-"0","      ""  "", 'description = """""
-"0","    ) %>%"
-"0","  '))"
-"0","}"
-"1","
-    codebook_add_col_attributes( 
-      id, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      address, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      sex, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      date, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      time, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      date_time, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      days, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      height, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      likert, 
-      description = """"
-    ) %>%
-  "
-"1","
-    codebook_add_col_attributes( 
-      outcome, 
-      description = """"
-    ) %>%
-  "
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ce27lx9w91hu6/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ce27lx9w91hu6/00000f.csv
deleted file mode 100644
index 68f0e18..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ce27lx9w91hu6/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(codebook(study), ""stata_codebook_2.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cgfcy2ty8h1w9/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cgfcy2ty8h1w9/00000f.csv
deleted file mode 100644
index 3f3e83f..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cgfcy2ty8h1w9/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(x = codebook(study), target = ""study_codebook_2.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chunks.json b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chunks.json
deleted file mode 100644
index b514b82..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chunks.json
+++ /dev/null
@@ -1 +0,0 @@
-{"chunk_definitions":[],"doc_write_time":1673568894}
\ No newline at end of file
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chwix01h46w6z/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chwix01h46w6z/00000f.csv
deleted file mode 100644
index 1d256a1..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/chwix01h46w6z/00000f.csv
+++ /dev/null
@@ -1,8 +0,0 @@
-"0","study_codebook <- codebook("
-"0","  df = study,"
-"0","  title = ""My Example Study"","
-"0","  subtitle = ""A Subtitle for My Example Study Codebook"","
-"0","  description = ""In collaboration with Texas Adult Protective Services (APS) and one of the largest mobile healthcare providers in North Texas — MedStar Mobile Healthcare (MedStar) — our team developed and piloted an EA screening tool: Detection of Elder Abuse Through Emergency Care Technicians (DETECT). The DETECT tool was designed specifically to help medics identify potential EA among community-dwelling older adults during an emergency response. DETECT relies entirely on the medics’ systematic observations of the older adults’ physical and social environment — no direct questioning of the older adult or their caregivers is involved. The intent was to create an EA screening tool that was easy for medics to use in the field and that helped medics capture information about older adults, their environments, and their caregivers that is thought to be associated with the occurrence of EA. "
-"0",""
-"0","We pilot tested using the DETECT screening tool with medics in the field between September 17th and October 26th, 2015. During the pilot test, MedStar’s Electronic Patient Care Reporting system (ePCR) was programmed to automatically prompt all medics to complete an EA screening using the DETECT tool while on an eligible 911 response. An eligible 911 response was defined as a call for a community-dwelling patient who was 65 years of age or older, the setting was the patient’s residence, and the patient resided in the community (e.g., private home, unlicensed adult foster homes, unlicensed board and care homes, etc.). Other types of residences (e.g., licensed skilled nursing facilities) were excluded because reports of EA in these settings are generally not investigated by APS in Texas. By definition, older adults who participated in the pilot study had to live in MedStar’s service area of an estimated (978,000 residents), which included Fort Worth, Texas, and 14 surrounding communities."""
-"0",")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cjz4ieuexoxz5/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cjz4ieuexoxz5/00000f.csv
deleted file mode 100644
index 827f4d6..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cjz4ieuexoxz5/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","study_codebook <- codebook(study, keep_blank_attributes = TRUE)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cl8xydwb9kgmh/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cl8xydwb9kgmh/00000f.csv
deleted file mode 100644
index d9706c1..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cl8xydwb9kgmh/00000f.csv
+++ /dev/null
@@ -1,7 +0,0 @@
-"0","class(study$sex)"
-"1","[1]"
-"1"," ""haven_labelled"""
-"1"," ""vctrs_vctr""    "
-"1"," ""double""        "
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/clegrvw8b73hi/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/clegrvw8b73hi/00000f.csv
deleted file mode 100644
index b5e5d23..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/clegrvw8b73hi/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","study <- read_dta(""inst/extdata/study.dta"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/coktz8j1ax7ez/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/coktz8j1ax7ez/00000f.csv
deleted file mode 100644
index 7f19e41..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/coktz8j1ax7ez/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","study_codebook <- codebook(study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqenx2m2b8qix/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqenx2m2b8qix/00000f.csv
deleted file mode 100644
index f7e9e7e..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqenx2m2b8qix/00000f.csv
+++ /dev/null
@@ -1,25 +0,0 @@
-"0","attributes(study$id)"
-"1","$label
-"
-"1","[1]"
-"1"," ""Participant's study identification number"""
-"1","
-"
-"1","
-"
-"1","$format.stata
-"
-"1","[1]"
-"1"," ""%9s"""
-"1","
-"
-"1","
-"
-"1","$description
-"
-"1","[1]"
-"1"," ""My new description"""
-"1","
-"
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqg3c8cszvq9o/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqg3c8cszvq9o/00000f.csv
deleted file mode 100644
index 56425f6..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cqg3c8cszvq9o/00000f.csv
+++ /dev/null
@@ -1,22 +0,0 @@
-"0","glimpse(study)"
-"1","Rows: 20"
-"1",""
-"1","
-"
-"1","Columns: 10"
-"1",""
-"1","
-"
-"1","$ id        <chr> ""1001"", ""1002"", NA, ""1004"", ""1005"", ""1006"", ""1007"", ""1008"", ""1009"", ""1010"", ""1011"", ""1012"", ""1013"", ""1014"", ""1015"", ""1…
-$ address   <chr> ""101 A st."", ""101 B st."", ""101 C st."", ""101 D st."", ""101 E st."", ""101 F st."", ""101 G st."", ""101 H st."", ""101 I st."", ""…
-$ sex       <fct> Female, Female, Female, NA, Female, Male, Male, Male, Female, Female, Male, Male, Male, Female, Male, Female, Male, Fe…
-$ date      <date> 2021-10-12, 2021-09-23, 2021-10-13, 2021-10-19, NA, 2021-10-10, 2021-09-21, 2021-10-26, 2021-09-23, 2021-10-03, 2021-…
-$ time      <time> 08:56:40, 13:26:09, 09:24:22, 08:37:26, 09:20:59, 11:14:52, 12:40:06, 13:46:52, 10:25:26, 16:59:31, 11:30:37, 13:15:2…
-$ date_time <dttm> 2021-10-12 08:56:40, 2021-09-23 13:26:09, 2021-10-13 09:24:22, 2021-10-19 08:37:26, 2021-09-22 09:20:59, 2021-10-10 1…
-$ days      <int> 3, 15, 21, 5, 8, NA, 10, 18, 10, 12, 2, 10, 12, 20, 14, 17, 14, 3, 8, 14
-$ height    <dbl> 81.25571, 68.15227, 58.79282, 72.81303, 69.61109, 71.05764, NA, 67.29340, 77.44377, 68.79513, 74.31782, 81.96839, 75.3…
-$ likert    <int> 5, 3, 4, 4, 1, 4, 1, 3, 4, 3, 5, 4, 4, 4, 1, 2, 3, 4, 3, 1
-$ outcome   <lgl> TRUE, FALSE, FALSE, TRUE, TRUE, FALSE, TRUE, TRUE, FALSE, FALSE, TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, TRUE, TRUE, …"
-"1",""
-"1","
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cr1z52xcmfewa/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cr1z52xcmfewa/00000f.csv
deleted file mode 100644
index b70b094..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cr1z52xcmfewa/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","stata_codebook <- codebook(study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/crgltl84sy4fz/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/crgltl84sy4fz/00000f.csv
deleted file mode 100644
index cf7474e..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/crgltl84sy4fz/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(codebook(study), ""basic_study_codebook.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cs4oh80233rdu/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cs4oh80233rdu/00000f.csv
deleted file mode 100644
index 60e3dc8..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cs4oh80233rdu/00000f.csv
+++ /dev/null
@@ -1,67 +0,0 @@
-"0","study <- study %>%"
-"0","  cb_add_col_attributes("
-"0","    id,"
-"0","    description = ""Participant's study identification number"","
-"0","    source = ""Administrative data"","
-"0","    other_attribute = ""What happens?"""
-"0","  ) %>%"
-"0","  "
-"0","  cb_add_col_attributes("
-"0","    address,"
-"0","    description = ""Participant's home address"","
-"0","    source = ""Administrative data"""
-"0","  ) %>%"
-"0",""
-"0","  cb_add_col_attributes("
-"0","    sex,"
-"0","    description = ""Biological sex of the participant assigned at birth"","
-"0","    source = ""Sociodemographic questionnaire"""
-"0","  ) %>%"
-"0",""
-"0","  cb_add_col_attributes("
-"0","    date,"
-"0","    description = ""Participant's date of enrollment"","
-"0","    source = ""Administrative data"""
-"0","  ) %>%"
-"0","  "
-"0","  cb_add_col_attributes("
-"0","    time,"
-"0","    description = ""Participant's time of enrollemnt"","
-"0","    source = ""Administrative data"""
-"0","  ) %>% "
-"0","  "
-"0","  cb_add_col_attributes("
-"0","    days,"
-"0","    description = ""Total number of days the participant was enrolled in the study"","
-"0","    source = ""Calculated variable"""
-"0","  ) %>% "
-"0",""
-"0","  cb_add_col_attributes("
-"0","    height,"
-"0","    description = ""Participant's height in inches at date of enrollment"","
-"0","    source = ""Anthropometric measurements"""
-"0","  ) %>% "
-"0",""
-"0","  cb_add_col_attributes("
-"0","    likert,"
-"0","    description = ""An example Likert scale item"","
-"0","    source = ""Exposure questionnaire"","
-"0","    value_labels = c("
-"0","      ""Very dissatisfied"" = 1, "
-"0","      ""Somewhat dissatisfied"" = 2,"
-"0","      ""Neither satisfied nor dissatisfied"" = 3,"
-"0","      ""Somewhat satisfied"" = 4,"
-"0","      ""Very satisfied"" = 5"
-"0","    ),"
-"0","    skip_pattern = ""Not asked if days < 10"""
-"0","  ) %>% "
-"0","    "
-"0","  cb_add_col_attributes("
-"0","    outcome,"
-"0","    description = ""Participant experienced the outcome of interest"","
-"0","    source = ""Adjudicated outcomes data"""
-"0","  )"
-"2","The following attribute(s) are being added to a variable in the data frame for the first time: description, source, other_attribute. If you believe this/these attribute(s) were previously added, then check for a typo in the attribute name. If you are adding this/these attribute(s) for the first time, you can probably safely ignore this message.
-"
-"2","The following attribute(s) are being added to a variable in the data frame for the first time: value_labels, skip_pattern. If you believe this/these attribute(s) were previously added, then check for a typo in the attribute name. If you are adding this/these attribute(s) for the first time, you can probably safely ignore this message.
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/csnuixqhrh2ve/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/csnuixqhrh2ve/00000f.csv
deleted file mode 100644
index dc9e988..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/csnuixqhrh2ve/00000f.csv
+++ /dev/null
@@ -1,2 +0,0 @@
-"0","# Load example data"
-"0","data(study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ctcrzlg9ec52m/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ctcrzlg9ec52m/00000f.csv
deleted file mode 100644
index bb15654..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/ctcrzlg9ec52m/00000f.csv
+++ /dev/null
@@ -1,3 +0,0 @@
-"0","library(codebookr)"
-"0","library(dplyr, warn.conflicts = FALSE)"
-"0","library(haven)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cv63qyqu0ql3w/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cv63qyqu0ql3w/00000f.csv
deleted file mode 100644
index b1957e0..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cv63qyqu0ql3w/00000f.csv
+++ /dev/null
@@ -1,4 +0,0 @@
-"0","study <- study %>% "
-"0","  cb_add_col_attributes(id, description = ""My new description"")"
-"2","The following attribute(s) are being added to a variable in the data frame for the first time: description. If you believe this/these attribute(s) were previously added, then check for a typo in the attribute name. If you are adding this/these attribute(s) for the first time, you can probably safely ignore this message.
-"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvjj8okp10rl8/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvjj8okp10rl8/00000f.csv
deleted file mode 100644
index fc106e8..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvjj8okp10rl8/00000f.csv
+++ /dev/null
@@ -1 +0,0 @@
-"0","print(study_codebook, ""basic_study_codebook.docx"")"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvubqyl0dsdd6/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvubqyl0dsdd6/00000f.csv
deleted file mode 100644
index 983bbf3..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cvubqyl0dsdd6/00000f.csv
+++ /dev/null
@@ -1,2 +0,0 @@
-"0","# Refresh data"
-"0","data(study)"
diff --git a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cyonc8ut9eh7p/00000f.csv b/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cyonc8ut9eh7p/00000f.csv
deleted file mode 100644
index 259bb81..0000000
--- a/.Rproj.user/shared/notebooks/19D3CF1A-README/1/s/cyonc8ut9eh7p/00000f.csv
+++ /dev/null
@@ -1,2 +0,0 @@
-"0","# Load study again to remove the attributes we added above"
-"0","data(study)"
diff --git a/R/cb_custom_summary_stats_to_ft.R b/R/cb_custom_summary_stats_to_ft.R
new file mode 100644
index 0000000..e2c50db
--- /dev/null
+++ b/R/cb_custom_summary_stats_to_ft.R
@@ -0,0 +1,32 @@
+#' Create Formatted Flextable From Custom Summary Statistics
+#'
+#' @param df Data frame of summary statistics
+#' @param ... Other stuff
+#' @param col_width Set the width of the column that will appear in the Word table
+#'
+#' @return Flextable object
+#' @importFrom dplyr %>%
+#' @keywords internal
+
+cb_custom_summary_stats_to_ft <- function(df, col_width = 1.3, ...) {
+  ft <- df %>%
+    flextable::regulartable() %>%
+    # Set font to TNR 11
+    flextable::font(fontname = "Times New Roman", part = "all") %>%
+    flextable::fontsize(size = 11, part = "all") %>%
+    # Center align text
+    flextable::align(align = "center", part = "all") %>%
+    # Bold header
+    # bold(part = "header") %>%
+    # Set the column width
+    flextable::width(width = col_width) %>%
+
+    # Format borders
+    # Remove default borders
+    flextable::border_remove() %>%
+    # Add light gray top border
+    flextable::hline_top(border = officer::fp_border(color = "gray80", width = 1), part = "all")
+
+  # Return formatted flextable
+  ft
+}
diff --git a/R/cb_inject_custom_summary_table.R b/R/cb_inject_custom_summary_table.R
new file mode 100644
index 0000000..a7ccccf
--- /dev/null
+++ b/R/cb_inject_custom_summary_table.R
@@ -0,0 +1,268 @@
+#' Adjust the codebook function so that it allows for the injection of arbitrary summary tables into the codebook.
+
+#' Automate creation of a data codebook
+#'
+#' The codebook function assists with the creation of a codebook for a given
+#' data frame.
+#'
+#' Codebook expects that `df ` is a data frame that you have read into memory
+#' from a saved data file. Please provide the path to the saved data file. This
+#' function gets selected attributes about file saved at `path` and stores
+#' those attributes in a data frame, which is later turned into a flextable and
+#' added to the codebook document.
+#'
+#' @details Typically, though not necessarily, the first step in creating your
+#'   codebook will be to add column attributes to your data. The
+#'   `cb_add_col_attributes()` function is a convenience function that allows
+#'   you to add arbitrary attributes to the columns of the data frame. These
+#'   attributes can later be accessed to fill in the column attributes table of
+#'   the codebook document. Column attributes _can_ serve a similar function to
+#'   variable labels in SAS or Stata; however, you can assign many different
+#'   attributes to a column and they can contain any kind of information you want.
+#'   For details see \link{cb_add_col_attributes}
+#'
+#' @param df The data frame the codebook will describe
+#' @param title An optional title that will appear at the top of the Word
+#'   codebook document
+#' @param subtitle An optional subtitle that will appear at the top of the Word
+#'   codebook document
+#' @param description An optional text description of the dataset that will
+#'   appear on the first page of the Word codebook document
+#' @param keep_blank_attributes TRUE or FALSE. By default, the column attributes
+#'   table will omit the Column description, Source information, Column type,
+#'   value labels, and skip pattern rows from the column attributes table in
+#'   the codebook document if those attributes haven't been set. In other
+#'   words, it won't show blank rows for those attributes. Passing `TRUE` to
+#'   the keep_blank_attributes argument will cause the opposite to happen.
+#'   The column attributes table will include a Column description, Source
+#'   information, Column type, and value labels row for every column in the
+#'   data frame - even if they don't have those attributes set.
+#' @param no_summary_stats A character vector of column names. The summary
+#'   statistics will not be added to column attributes table for any
+#'   column passed to this argument. This can be useful when a column contains
+#'   values that are sensitive or may be used to identify individual people
+#'   (e.g., names, addresses, etc.) and the individual values for that column
+#'   should not appear in the codebook.
+#' @param custom_summary_stats_list A list of named data frames with each data
+#' frame containing user-prepared summary statistics for a column. Each column
+#' that has a corresponding data frame in this list will have a table containing
+#' user-prepared statistics in the codebook instead of generated summary
+#' statistics.
+#' @return An rdocx object that can be printed to a Word document
+#' @importFrom dplyr %>%
+#' @import haven
+#' @export
+#'
+#' @examples
+#' \dontrun{
+#' study_codebook <- codebook(
+#'   df = study,
+#'   title = "My Example Study",
+#'   subtitle = "A Subtitle for My Example Study Codebook",
+#'   description = "Brief (or long) description of the data."
+#' )
+#'
+#' # Create the Word codebook document
+#' print(study_codebook, path = "example_codebook.docx")
+#' }
+codebook <- function(
+    df, title = NA, subtitle = NA, description = NA,
+    keep_blank_attributes = FALSE, no_summary_stats = NULL, custom_summary_stats_list = NULL) {
+
+  # Create character vector of column names in custom_summary_stats_list
+  custom_summary_stats_cols <- names(custom_summary_stats_list)
+
+  # ===========================================================================
+  # Checks
+  # ===========================================================================
+  # Check to make sure df is a data frame
+  if ( !("data.frame" %in% class(df)) ) {
+    stop("Expecting df to be of class data.frame. Instead it was ", class(df))
+  }
+
+  # Check to make sure the user is not piping in the data frame
+  # When they do, `Dataset name:` in the metadata table (below) is ".".
+  # Apparently, there is no way around this:
+  # https://stackoverflow.com/questions/30057278/get-lhs-object-name-when-piping-with-dplyr
+  df_name <- deparse(substitute(df))
+  if (df_name == ".") {
+    message(
+      "The codebook function currently sees the name of the data frame you ",
+      "passed to the `df` argument as '.'. This is probably because you used ",
+      "a pipe to pass the data frame name into the codebook function. If you ",
+      "want the actual name of the data frame to be printed in the `Dataset ",
+      "name:` row of the metadata table, do not use a pipe to pass the data ",
+      "frame name into the codebook function."
+    )
+  }
+
+  # ===========================================================================
+  # Create an empty Word rdocx object
+  # ===========================================================================
+  rdocx <- officer::read_docx() %>%
+    officer::cursor_begin()
+
+  # ===========================================================================
+  # Optionally add title and subtitle to top of codebook
+  # ===========================================================================
+  rdocx <- cb_add_title(
+    rdocx = rdocx,
+    title = title,
+    subtitle = subtitle
+  )
+
+  # ===========================================================================
+  # Add metadata to codebook shell
+  # ===========================================================================
+  # Create tibble of metadata
+  meta <- tibble::tibble(
+    `Dataset name:` = df_name,
+    `Dataset size:` = df %>% utils::object.size() %>% format(units = "auto"),
+    `Column count:` = df %>% ncol() %>% format(big.mark = ","),
+    `Row count:`    = df %>% nrow() %>% format(big.mark = ","),
+    `Updated date:` = Sys.Date()
+  )
+
+  # Pivot the metadata to a vertical orientation
+  # Must covert all values to character to pivot them into the same column
+  meta <- meta %>%
+    dplyr::mutate(dplyr::across(dplyr::everything(), as.character)) %>%
+    tidyr::pivot_longer(
+      cols = dplyr::everything(),
+      names_to = "key",
+      values_to = "value"
+    )
+
+  # Convert to flextable
+  meta <- meta %>%
+    flextable::regulartable() %>%
+    cb_theme_df_attributes() # Format
+
+  # Add metadata to codebook
+  rdocx <- rdocx %>%
+    flextable::body_add_flextable(meta)
+
+  # ===========================================================================
+  # Optionally Add dataset description
+  # ===========================================================================
+  if (!is.na(description)) {
+    # Add Description header
+    rdocx <- rdocx %>%
+      cb_add_section_header("Description:")
+
+    # Add dataset description to codebook
+    rdocx <- rdocx %>%
+      cb_add_description(description)
+  }
+
+  # ===========================================================================
+  # Iterate over every column in df
+  # Add column attributes and summary statistics to rdocx object
+  #
+  # Issue 17: Codebook is really slow when the data frame is even moderately
+  # large. Upon investigation, it appears as though the time it takes to
+  # complete each iteration of the loop below grows almost exponentially with
+  # the number of variables. The solution for this problem came from:
+  # https://ardata-fr.github.io/officeverse/officer-for-word.html#external-documents
+  # It is necessary to generate smaller Word documents and to insert them into
+  # the main Word document using .
+  # ===========================================================================
+
+  # Add column Attributes header
+  rdocx <- rdocx %>%
+    cb_add_section_header("Column Attributes:")
+
+  # Create vector of column names
+  col_nms <- names(df)
+
+  # External documents approach to speed up the function
+  # Create temporary external files. These will be filled with a single
+  # Word document for each column. Then, each temporary Word document will be
+  # added to the main document
+  tmpdir <- tempfile()
+  dir.create(tmpdir, showWarnings = FALSE, recursive = TRUE)
+  tempfiles <- file.path(tmpdir, paste0(seq_along(col_nms), ".docx") )
+
+  # Iterate over all columns
+  # ------------------------
+  for (i in seq_along(col_nms)) {
+
+    # Create a temporary rdocx object just for the current column
+    temp_doc <- officer::read_docx()
+
+    # Get column attributes
+    table_var_attributes <- df %>%
+      cb_get_col_attributes(col_nms[[i]], keep_blank_attributes = keep_blank_attributes)
+    # Iss 10: Add column number to the column attributes table
+    table_var_attributes$Column <- i
+    table_var_attributes$Column[-1] <- NA
+    table_var_attributes <- table_var_attributes[, c("Column", "Attribute", "value")]
+    # Make into a flextable and format
+    table_var_attributes <- table_var_attributes %>%
+      flextable::flextable() %>%
+      cb_theme_col_attr()
+
+    # Add column attributes flextable to the temporary rdocx object
+    temp_doc <- temp_doc %>%
+      flextable::body_add_flextable(table_var_attributes)
+
+    # Get summary statistics
+    # Iss 22. Add option to prevent summary stats table for selected columns
+    if (!(col_nms[[i]] %in% no_summary_stats) & !(col_nms[[i]] %in% custom_summary_stats_cols)) {
+      summary_stats <- df %>%
+        cb_add_summary_stats(col_nms[[i]]) %>%
+        cb_summary_stats_to_ft()
+    }
+
+    # Use arbitrary summary stats instead of generated summary stats for specified columns
+    else if (col_nms[[i]] %in% custom_summary_stats_cols){
+      summary_stats <- custom_summary_stats_list[[paste0(col_nms[[i]])]] %>%
+        cb_custom_summary_stats_to_ft()
+    }
+    # Add summary statistics flextable to the codebook object
+    temp_doc <- temp_doc %>%
+      flextable::body_add_flextable(summary_stats)
+
+
+    # Create temporary Word document from the temporary rdocx object
+    # Put it in one of the temporary files created above the loop.
+    print(temp_doc, target = tempfiles[i])
+  }
+
+  # tempfiles contains all generated docx paths from the loop. We will
+  # iteratively add each of the temporary Word documents to the main
+  # rdocx object.
+  for (tempfile in tempfiles){
+    rdocx <- rdocx %>%
+      officer::body_add_docx(src = tempfile)
+  }
+
+  # ===========================================================================
+  # Return rdocx object that can be printed to a Word document
+  # ===========================================================================
+  rdocx
+}
+
+# For testing
+
+
+# data(study)
+# devtools::load_all()
+
+# # Test named list of data frames
+# days <- data.frame(y1 = c(1, 2, 3),
+#                    y2 = c(4, 5, 6))
+# height <- data.frame(y1 = c(3, 2, 1),
+#                      y2 = c(6, 5, 4))
+# list_test <- list(days, height)
+# names(list_test) <- c("days","height")
+#
+#
+# test_codebook <- codebook(
+#   df = study,
+#   title = "Test study",
+#   description = "Testing! Testing",
+#   custom_summary_stats_list = list_test
+# )
+#
+# print(test_codebook, "test.docx")

From 3dad9a8aeb7ee9c948d57ae28fe653b376c6282b Mon Sep 17 00:00:00 2001
From: Ebie Dambo <ebiekiemiete@gmail.com>
Date: Fri, 7 Jun 2024 12:25:06 -0500
Subject: [PATCH 2/3] Create new function for adding attributes using CSV file

If this commit is accepted, files for adding column attributes using a CSV file will be created.
---
 R/cb_add_col_attributes_from_csv_file.R | 187 ++++++++++++++++++++++++
 data/test_attributes.csv                |   5 +
 2 files changed, 192 insertions(+)
 create mode 100644 R/cb_add_col_attributes_from_csv_file.R
 create mode 100644 data/test_attributes.csv

diff --git a/R/cb_add_col_attributes_from_csv_file.R b/R/cb_add_col_attributes_from_csv_file.R
new file mode 100644
index 0000000..06a1aca
--- /dev/null
+++ b/R/cb_add_col_attributes_from_csv_file.R
@@ -0,0 +1,187 @@
+#' Add Attributes to Columns
+#'
+#' @description Add arbitrary attributes to columns (e.g., description, source,
+#'   column type). These attributes can later be accessed to fill in the column
+#'   attributes table.
+#'
+#' @details Typically, though not necessarily, the first step in creating your
+#'   codebook will be to add column attributes to your data. The
+#'   `cb_add_col_attributes()` function is a convenience function that allows
+#'   you to add arbitrary attributes to the columns of the data frame. These
+#'   attributes can later be accessed to fill in the column attributes table of
+#'   the codebook document. Column attributes _can_ serve a similar function to
+#'   variable labels in SAS or Stata; however, you can assign many different
+#'   attributes to a column and they can contain any kind of information you want.
+#'
+#'   Although the `cb_add_col_attributes()` function will allow you to add any
+#'   attributes you want, there are currently **only five** special attributes
+#'   that the `codebook()` function will recognize and add to the column
+#'   attributes table of the codebook document. They are:
+#'
+#'   \describe{
+#'     \item{description:}{
+#'       Although you may add any text you desire to the
+#'       `description` attribute, it is intended to be used describe the
+#'       question/process that generated the data contained in the column.
+#'       Many statistical software packages refer to this as a variable label.
+#'       If the data was imported from SAS, Stata, or SPSS with variable labels
+#'       using the `haven` package, `codebook` will automatically recognize them.
+#'       There is no need to manually create them. However, you may overwrite the
+#'       imported variable label for any column by adding a `description`
+#'       attribute.}
+#'     \item{source:}{
+#'       Although you may add any text you desire to the `source`
+#'       attribute, it is intended to be used describe where the data contained
+#'       in the column originally came from. For example, if the current data
+#'       frame was created by merging multiple data sets together, you may want
+#'       to use the source attribute to identify the data set it originates from.
+#'       As another example, if the current data frame contains longitudinal
+#'       data, you may want to use the source attribute to identify the wave(s)
+#'       in which data for this column was collected.}
+#'     \item{col_type:}{
+#'       The `col_type` attribute is intended to provide additional
+#'       information above and beyond the `Data type` (i.e., column class) about
+#'       the values in the column. For example, you may have a column of 0's
+#'       and 1's, which will have a _numeric_ data type. However, you may want
+#'       to inform data users that this is really a dummy variable where the
+#'       0's and 1's represent discrete categories (No and Yes). Another way to
+#'       think about it is that the `Data type` attribute is how _R_
+#'       understands the column and the `Column type` attribute is how _humans_
+#'       should understand the column.
+#'       Currently accepted values are:
+#'       \itemize{
+#'         \item{`Numeric`}{}
+#'         \item{`Categorical`}{}
+#'         \item{`Time`}{}
+#'       }
+#'       Perhaps even more importantly, setting the `col_type` attribute helps
+#'       R determine which descriptive statistics to calculate for the bottom
+#'       half of the column attributes table. Inside of the `codebook()`
+#'       function, the `cb_add_summary_stats()` function will attempt to figure
+#'       out whether the column is:
+#'       \itemize{
+#'         \item{numeric}{}
+#'         \item{categorical - many categories (e.g. participant id)}{}
+#'         \item{categorical - few categories (e.g. sex)}{}
+#'         \item{time - including dates}{}
+#'       }
+#'       Again, this matters because the table of summary stats shown in the
+#'       codebook document depends on the value `cb_add_summary_stats()`
+#'       chooses. However, the user can directly tell `cb_add_summary_stats()`
+#'       which summary stats to calculate by providing a `col_type` attribute
+#'       to a column with one of the following values: `Numeric`,
+#'       `Categorical`, or `Time`.}
+#'     \item{value_labels:}{
+#'       Although you may pass any named vector you desire to the `value_labels`
+#'       attribute, it is intended to inform your data users about how to
+#'       correctly interpret numerically coded categorical variables. For
+#'       example, you may have a column of 0's and 1's that represent discrete
+#'       categories (i.e., "No" and "Yes") instead of numerical quantities. In
+#'       many other software packages (e.g., SAS, Stata, and SPSS), you can
+#'       layer "No" and "Yes" labels on top of the 0's and 1's to improve the
+#'       readability of your analysis output. These are commonly referred to
+#'       as _value labels_. The R programming language does not really have
+#'       value labels in the same way that other popular statistical software
+#'       applications do. R users can (and typically should) coerce numerically
+#'       coded categorical variables into factors; however, coercing a numeric
+#'       vector to a factor is not the same as adding value labels to a numeric
+#'       vector because the underlying numeric values can change in the process
+#'       of creating the factor. For this, and other reasons, many R programmers
+#'       choose to create a _new_ factor version of a numerically encoded
+#'       variable as opposed to overwriting/transforming the numerically encoded
+#'       variable. In those cases, you may want to inform your data users about
+#'       how to correctly interpret numerically coded categorical variables.
+#'       Adding value labels to your codebook is one way of doing so.
+#'       \itemize{
+#'         \item{
+#'           Add value labels to columns as a named vector to the
+#'           `value_labels` attribute. For example, `value_labels` =
+#'           c("No" = 0, "Yes" = 1).
+#'         }{}
+#'         \item{
+#'           If the data was imported from SAS, Stata, or SPSS with value labels
+#'           using the `haven` package, `codebook` will automatically recognize
+#'           them. There is no need to manually create them. However, you may
+#'           overwrite the imported value labels for any column by adding a
+#'           `value_labels` attribute as shown in the example below.
+#'         }{}
+#'       }}
+#'     \item{skip_pattern:}{
+#'       Although you may add any text you desire to the `skip_pattern`
+#'       attribute, it is intended to be used describe skip patterns in the
+#'       data collection tools that impact which study participants were exposed
+#'       to each study item. For example, If a question in your data was only
+#'       asked of participants who were enrolled in the study for at least
+#'       10 days, then you may want to add a note like "Not asked if
+#'       days < 10" to the skip pattern section of
+#'       the column attributes table.}
+#'   }
+#'
+#' @param df Data frame of interest
+#' @param attr_csv_path CSV file containing the column attributes.
+#' @examples
+#' +-----------+-------------------------------+--------+-------------+--------------------------------------------+-----------------------+
+#' | variable  | description                   | source | col_type    |value_labels                                |skip_pattern           |
+#' +===========+===============================+========+=============+============================================+=======================+
+#' | id        | Study identification variable | study  |             |                                            |                       |
+#' +-----------+-------------------------------+----------------------+--------------------------------------------+-----------------------+
+#' | likert    | An example Likert scale item  | study  | Categorical | c("Very dissatisfied" = 1,                 |Not asked if days < 10 |
+#' |           |                               |        |             |   "Somewhat dissatisfied" = 2,             |                       |
+#' |           |                               |        |             |   "Neither satisfied nor dissatisfied" = 3,|                       |
+#' |           |                               |        |             |   "Somewhat satisfied" = 4,                |                       |
+#' |           |                               |        |             |   "Very satisfied" = 5)                    |                       |
+#' +-----------+-------------------------------+--------+-------------+--------------------------------------------+-----------------------+
+#'
+#' @return Returns the same data frame (or tibble) passed to the `df` argument
+#'   with column attributes added.
+#' @importFrom dplyr %>%
+#' @export
+#'
+
+cb_add_column_attributes_from_csv_file <- function(df, attr_csv_path){
+
+  # Read csv file, with empty strings and "NA" represented by NA.
+  attr_df <- read.csv(attr_csv_path, na.strings=c("","NA"))
+
+  # Initialize empty large list of attributes
+  attr_list <- list()
+
+  # Create list of variable names
+  attr_vars <- attr_df %>% select(variable) %>% as.vector() %>% unlist()
+
+  # Iteratively add list of attributes from input attributes data frame for each variable to the large nested list
+  for (i in attr_vars){
+    test <- attr_df %>% filter(variable == i) %>% select(-c(variable)) %>%
+      as.list()
+
+    # Remove any elements with missing values
+    test <- Filter(Negate(anyNA), test)
+
+    # Add attributes to large list
+    attr_list <- append(attr_list, list(test))
+  }
+
+  # Name each sublist by variable
+  names(attr_list) <- attr_vars
+
+  for (i in attr_vars){
+    # Convert input strings of value_labels to named lists
+    attr_list[[i]][["value_labels"]] <- eval(parse(text = attr_list[[i]]["value_labels"]))
+    # Set df attributes from nested list of attributes
+    attributes(df[[i]]) <- attr_list[[i]]
+  }
+  df
+}
+
+# # Test
+# # Set column attributes
+# test_study <- cb_add_column_attributes_from_csv_file(df = study, attr_csv_path = here::here("data", "test_attributes.csv"))
+#
+# # Generate codebook
+# test_codebook <- codebook(
+#   df = test_study,
+#   title = "Test study",
+#   description = "Testing! Testing"
+# )
+
+# print(test_codebook, "test.docx")
diff --git a/data/test_attributes.csv b/data/test_attributes.csv
new file mode 100644
index 0000000..10b50ae
--- /dev/null
+++ b/data/test_attributes.csv
@@ -0,0 +1,5 @@
+variable,description,source,col_type,value_labels,skip_pattern
+id,Study identification variable,study,,,
+address,Participant address,study,,,
+sex,Participant sex,study,Categorical,,
+likert,An example Likert scale item,study,Categorical,"c(""Very dissatisfied"" = 1, ""Somewhat dissatisfied"" = 2, ""Neither satisfied nor dissatisfied"" = 3,""Somewhat satisfied"" = 4,""Very satisfied"" = 5)",Not asked if days < 10

From 8ebe41797561d2e34bd0a906093afc3384732f7a Mon Sep 17 00:00:00 2001
From: Ebie Dambo <ebiekiemiete@gmail.com>
Date: Wed, 12 Jun 2024 14:04:54 -0500
Subject: [PATCH 3/3] Include code to inject custom summary stats into
 codebookr file

- Related to issue # 53.
- If this commit is accepted, the code for injecting custom summary stats will be added into the codebookr file and some style issues will be fixed.
---
 R/cb_custom_summary_stats_to_ft.R |  8 +--
 R/codebook.R                      | 82 +++++++++++++++++++++++++------
 2 files changed, 70 insertions(+), 20 deletions(-)

diff --git a/R/cb_custom_summary_stats_to_ft.R b/R/cb_custom_summary_stats_to_ft.R
index e2c50db..0791e5a 100644
--- a/R/cb_custom_summary_stats_to_ft.R
+++ b/R/cb_custom_summary_stats_to_ft.R
@@ -2,7 +2,8 @@
 #'
 #' @param df Data frame of summary statistics
 #' @param ... Other stuff
-#' @param col_width Set the width of the column that will appear in the Word table
+#' @param col_width Set the width of the column that will appear in the Word
+#' table
 #'
 #' @return Flextable object
 #' @importFrom dplyr %>%
@@ -16,8 +17,6 @@ cb_custom_summary_stats_to_ft <- function(df, col_width = 1.3, ...) {
     flextable::fontsize(size = 11, part = "all") %>%
     # Center align text
     flextable::align(align = "center", part = "all") %>%
-    # Bold header
-    # bold(part = "header") %>%
     # Set the column width
     flextable::width(width = col_width) %>%
 
@@ -25,7 +24,8 @@ cb_custom_summary_stats_to_ft <- function(df, col_width = 1.3, ...) {
     # Remove default borders
     flextable::border_remove() %>%
     # Add light gray top border
-    flextable::hline_top(border = officer::fp_border(color = "gray80", width = 1), part = "all")
+    flextable::hline_top(border = officer::fp_border(color = "gray80",
+                                                     width = 1), part = "all")
 
   # Return formatted flextable
   ft
diff --git a/R/codebook.R b/R/codebook.R
index ebf9ae5..aa00ccc 100644
--- a/R/codebook.R
+++ b/R/codebook.R
@@ -41,7 +41,14 @@
 #'   values that are sensitive or may be used to identify individual people
 #'   (e.g., names, addresses, etc.) and the individual values for that column
 #'   should not appear in the codebook.
-#'
+#' @param custom_summary_stats_list A list of named data frames with each data
+#' frame containing user-prepared summary statistics for a column. Each column
+#' that has a corresponding data frame in this list will have a table containing
+#' user-prepared statistics in the codebook instead of generated summary
+#' statistics.
+#' @param omit_na_columns A list of variable names. Variables in this list will
+#' have all missing values omitted and 'Missing' will not be included as a
+#' category for each of these variables in the resulting codebook file.
 #' @return An rdocx object that can be printed to a Word document
 #' @importFrom dplyr %>%
 #' @import haven
@@ -61,7 +68,12 @@
 #' }
 codebook <- function(
     df, title = NA, subtitle = NA, description = NA,
-    keep_blank_attributes = FALSE, no_summary_stats = NULL) {
+    keep_blank_attributes = FALSE, no_summary_stats = NULL,
+    custom_summary_stats_list = NULL,
+    omit_na_columns = NULL) {
+
+  # Create character vector of column names in custom_summary_stats_list
+  custom_summary_stats_cols <- names(custom_summary_stats_list)
 
   # ===========================================================================
   # Checks
@@ -183,11 +195,13 @@ codebook <- function(
 
     # Get column attributes
     table_var_attributes <- df %>%
-      cb_get_col_attributes(col_nms[[i]], keep_blank_attributes = keep_blank_attributes)
+      cb_get_col_attributes(col_nms[[i]], keep_blank_attributes =
+                              keep_blank_attributes)
     # Iss 10: Add column number to the column attributes table
     table_var_attributes$Column <- i
     table_var_attributes$Column[-1] <- NA
-    table_var_attributes <- table_var_attributes[, c("Column", "Attribute", "value")]
+    table_var_attributes <- table_var_attributes[, c("Column", "Attribute",
+                                                     "value")]
     # Make into a flextable and format
     table_var_attributes <- table_var_attributes %>%
       flextable::flextable() %>%
@@ -199,18 +213,36 @@ codebook <- function(
 
     # Get summary statistics
     # Iss 22. Add option to prevent summary stats table for selected columns
-    if (!(col_nms[[i]] %in% no_summary_stats)) {
-      summary_stats <- df %>%
-        cb_add_summary_stats(col_nms[[i]]) %>%
-        cb_summary_stats_to_ft()
-
-      # Add summary statistics flextable to the codebook object
-      temp_doc <- temp_doc %>%
-        flextable::body_add_flextable(summary_stats)
+    if (!(col_nms[[i]] %in% no_summary_stats) & !(col_nms[[i]] %in%
+                                                  custom_summary_stats_cols)) {
+      # Add option to remove missing values for each column
+      if (!(col_nms[[i]] %in% no_summary_stats) & !(col_nms[[i]] %in%
+                                                    custom_summary_stats_cols) &
+          col_nms[[i]] %in% omit_na_columns){
+        summary_stats <- df %>% select(col_nms[[i]]) %>% drop_na(.) %>%
+          cb_add_summary_stats(col_nms[[i]]) %>%
+          cb_summary_stats_to_ft()
+      }
+      else{
+        summary_stats <- df %>%
+          cb_add_summary_stats(col_nms[[i]]) %>%
+          cb_summary_stats_to_ft()
+      }
+    }
+
+    # Use arbitrary summary stats instead of generated summary stats for
+    # specified columns
+    else if (col_nms[[i]] %in% custom_summary_stats_cols){
+      summary_stats <- custom_summary_stats_list[[paste0(col_nms[[i]])]] %>%
+        cb_custom_summary_stats_to_ft()
     }
+    # Add summary statistics flextable to the codebook object
+    temp_doc <- temp_doc %>%
+      flextable::body_add_flextable(summary_stats)
+
 
     # Create temporary Word document from the temporary rdocx object
-    # Put it in one of the tempory files created above the loop.
+    # Put it in one of the temporary files created above the loop.
     print(temp_doc, target = tempfiles[i])
   }
 
@@ -229,8 +261,26 @@ codebook <- function(
 }
 
 # For testing
+
+
 # data(study)
 # devtools::load_all()
-# codebook(study)
-# print(codebook(study), "test.docx")
-# print(codebook(study, no_summary_stats = "address"), "test.docx")
+#
+# # Test named list of data frames
+# days <- data.frame(y1 = c(1, 2, 3),
+#                    y2 = c(4, 5, 6))
+# height <- data.frame(y1 = c(3, 2, 1),
+#                      y2 = c(6, 5, 4))
+# list_test <- list(days, height)
+# names(list_test) <- c("days","height")
+#
+#
+# test_codebook <- codebook(
+#   df = study,
+#   title = "Test study",
+#   description = "Testing! Testing",
+#   custom_summary_stats_list = list_test,
+#   omit_na_columns = c("sex")
+# )
+#
+# print(test_codebook, "test.docx")