52 Creating function to configrure tables

Code

tbl_style <- function(df){
    df %>% 
        gt::gt() %>% 
        gt::tab_options(
            table.font.size = 14, 
            table.font.names = "serif", 
            data_row.padding = gt::px(2)
        ) %>% 
        gt::opt_stylize(style = 5)
}

53 Manual data entry

Code

dat <- tribble(~"name", ~"day", ~"month", ~"year", ~"bp",
               "Ama", 12, 05, 2020, "120/80",
               "Kwame", 14, 02, 2019, "132/66",
               "Akosua", 21, 12, 2010, "110/76",
               "Yaw", 13, 03, 1982, "144/98",
               "Yaa", 19, 08, 2000, "117/77")
dat %>% 
tbl_style()

name	day	month	year	bp
Ama	12	5	2020	120/80
Kwame	14	2	2019	132/66
Akosua	21	12	2010	110/76
Yaw	13	3	1982	144/98
Yaa	19	8	2000	117/77

54 Reading in data

Code

dataF <-
    readxl::read_xlsx(
        "C:/Dataset/SBPDATA.xlsx"
    ) %>% 
    janitor::clean_names() %>% 
    rename(
        ageyrs = a3_how_old_are_you_years,
        dxs_class = disease_class,
        gender = a1_gender
    ) %>% 
    mutate(
        dxs_class = factor(dxs_class),
        gender = factor(gender, levels = c(0, 1), labels = c("Male", "Female"))
    )

55 `dplyr` functions

55.1 `arrange`

Code

dat %>% 
    arrange(name, desc(day))

# A tibble: 5 × 5
  name     day month  year bp    
  <chr>  <dbl> <dbl> <dbl> <chr> 
1 Akosua    21    12  2010 110/76
2 Ama       12     5  2020 120/80
3 Kwame     14     2  2019 132/66
4 Yaa       19     8  2000 117/77
5 Yaw       13     3  1982 144/98

55.2 `unite()`

Code

dat %>% 
    unite(col = "dob", c(day, month, year), sep="/") %>% 
    tbl_style()

name	dob	bp
Ama	12/5/2020	120/80
Kwame	14/2/2019	132/66
Akosua	21/12/2010	110/76
Yaw	13/3/1982	144/98
Yaa	19/8/2000	117/77

55.3 `seperate()`

Code

dat %>% 
    separate(col = bp, into = c("sbp", "dbp"), sep = "/") %>% 
    tbl_style()

name	day	month	year	sbp	dbp
Ama	12	5	2020	120	80
Kwame	14	2	2019	132	66
Akosua	21	12	2010	110	76
Yaw	13	3	1982	144	98
Yaa	19	8	2000	117	77

Code

dat %>% 
    separate(col = bp, into = c("sbp", "dbp"), sep = "/") %>% 
    unite(col = "dob", c(day, month, year), sep="/") %>% 
    mutate(dob_new = lubridate::dmy(dob)) %>% 
    tbl_style()

name	dob	sbp	dbp	dob_new
Ama	12/5/2020	120	80	2020-05-12
Kwame	14/2/2019	132	66	2019-02-14
Akosua	21/12/2010	110	76	2010-12-21
Yaw	13/3/1982	144	98	1982-03-13
Yaa	19/8/2000	117	77	2000-08-19

56 Visualise and summarize the data

Code

dataF %>% glimpse()

Rows: 3,296
Columns: 14
$ sid       <dbl> 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 1…
$ dxs_class <fct> HPT, DM+HPT, HPT, HPT, HPT, DM+HPT, DM+HPT, DM, HPT, HPT, HP…
$ sbp_0     <dbl> 139, 155, 109, 130, 124, 140, 137, 160, 153, 135, 112, 137, …
$ sbp_2     <dbl> 124, NA, 123, NA, 120, 114, 135, 130, 218, 130, 118, 150, 14…
$ sbp_4     <dbl> 130, NA, 109, NA, 146, 163, 132, NA, NA, 118, 112, 130, 138,…
$ sbp_6     <dbl> 130, NA, 126, NA, 144, 117, 147, NA, NA, 150, 141, 112, 120,…
$ sbp_8     <dbl> 104, NA, 108, NA, 157, 124, 130, NA, NA, NA, 120, 129, 148, …
$ sbp_10    <dbl> 129, NA, 115, NA, 123, 121, NA, NA, 218, 127, NA, 148, 143, …
$ sbp_12    <dbl> 80, NA, 115, NA, 120, 128, 124, NA, NA, NA, NA, 142, NA, 116…
$ sbp_14    <dbl> 129, NA, 122, NA, 131, 119, 142, NA, NA, 123, NA, 131, NA, 1…
$ sbp_16    <dbl> 126, NA, 131, NA, 120, 100, 144, NA, NA, 149, 96, 119, NA, 2…
$ sbp_18    <dbl> 135, NA, 102, NA, 123, 127, 128, NA, NA, 132, 119, 119, 167,…
$ ageyrs    <dbl> 75, 60, 62, 70, 72, 56, 51, 73, 61, 59, 75, 53, 43, 64, 70, …
$ gender    <fct> Male, Male, Male, Male, Male, Male, Male, Male, Female, Male…

Code

dataF %>% skimr::skim()

Data summary
Name	Piped data
Number of rows	3296
Number of columns	14
_______________________
Column type frequency:
factor	2
numeric	12
________________________
Group variables	None

Variable type: factor

skim_variable	n_missing	complete_rate	ordered	n_unique	top_counts
dxs_class	2	1	FALSE	3	HPT: 1867, DM+: 1005, DM: 422
gender	6	1	FALSE	2	Mal: 2520, Fem: 770

Variable type: numeric

skim_variable	n_missing	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
sid	0	1.00	1648.50	951.62	1	824.75	1648.5	2472.25	3296	▇▇▇▇▇
sbp_0	6	1.00	141.20	22.21	70	125.00	139.0	155.00	230	▁▇▇▂▁
sbp_2	499	0.85	139.49	23.34	70	123.00	137.0	153.00	250	▁▇▅▁▁
sbp_4	671	0.80	138.46	23.42	70	122.00	136.0	151.00	238	▁▇▆▂▁
sbp_6	751	0.77	137.82	22.55	70	122.00	135.0	151.00	234	▁▇▇▂▁
sbp_8	846	0.74	137.15	22.97	73	120.25	134.0	150.00	277	▂▇▂▁▁
sbp_10	867	0.74	136.83	22.12	74	121.00	134.0	150.00	250	▁▇▃▁▁
sbp_12	960	0.71	135.46	21.82	71	120.75	133.0	148.00	250	▁▇▃▁▁
sbp_14	1063	0.68	135.49	21.94	81	120.00	133.0	148.00	228	▂▇▅▁▁
sbp_16	1276	0.61	134.93	22.06	79	120.00	132.0	147.00	243	▂▇▃▁▁
sbp_18	1483	0.55	134.74	21.93	83	120.00	132.0	147.00	239	▂▇▃▁▁
ageyrs	5	1.00	57.53	12.71	1	49.00	58.0	66.00	99	▁▂▇▇▁

Code

dataF %>% summarytools::dfSummary(graph.col = FALSE)

Data Frame Summary  
dataF  
Dimensions: 3296 x 14  
Duplicates: 0  

-----------------------------------------------------------------------------------------
No   Variable    Stats / Values               Freqs (% of Valid)     Valid      Missing  
---- ----------- ---------------------------- ---------------------- ---------- ---------
1    sid         Mean (sd) : 1648.5 (951.6)   3296 distinct values   3296       0        
     [numeric]   min < med < max:                                    (100.0%)   (0.0%)   
                 1 < 1648.5 < 3296                                                       
                 IQR (CV) : 1647.5 (0.6)                                                 

2    dxs_class   1. DM                         422 (12.8%)           3294       2        
     [factor]    2. DM+HPT                    1005 (30.5%)           (99.9%)    (0.1%)   
                 3. HPT                       1867 (56.7%)                               

3    sbp_0       Mean (sd) : 141.2 (22.2)     137 distinct values    3290       6        
     [numeric]   min < med < max:                                    (99.8%)    (0.2%)   
                 70 < 139 < 230                                                          
                 IQR (CV) : 30 (0.2)                                                     

4    sbp_2       Mean (sd) : 139.5 (23.3)     140 distinct values    2797       499      
     [numeric]   min < med < max:                                    (84.9%)    (15.1%)  
                 70 < 137 < 250                                                          
                 IQR (CV) : 30 (0.2)                                                     

5    sbp_4       Mean (sd) : 138.5 (23.4)     144 distinct values    2625       671      
     [numeric]   min < med < max:                                    (79.6%)    (20.4%)  
                 70 < 136 < 238                                                          
                 IQR (CV) : 29 (0.2)                                                     

6    sbp_6       Mean (sd) : 137.8 (22.6)     137 distinct values    2545       751      
     [numeric]   min < med < max:                                    (77.2%)    (22.8%)  
                 70 < 135 < 234                                                          
                 IQR (CV) : 29 (0.2)                                                     

7    sbp_8       Mean (sd) : 137.1 (23)       134 distinct values    2450       846      
     [numeric]   min < med < max:                                    (74.3%)    (25.7%)  
                 73 < 134 < 277                                                          
                 IQR (CV) : 29.8 (0.2)                                                   

8    sbp_10      Mean (sd) : 136.8 (22.1)     133 distinct values    2429       867      
     [numeric]   min < med < max:                                    (73.7%)    (26.3%)  
                 74 < 134 < 250                                                          
                 IQR (CV) : 29 (0.2)                                                     

9    sbp_12      Mean (sd) : 135.5 (21.8)     133 distinct values    2336       960      
     [numeric]   min < med < max:                                    (70.9%)    (29.1%)  
                 71 < 133 < 250                                                          
                 IQR (CV) : 27.2 (0.2)                                                   

10   sbp_14      Mean (sd) : 135.5 (21.9)     132 distinct values    2233       1063     
     [numeric]   min < med < max:                                    (67.7%)    (32.3%)  
                 81 < 133 < 228                                                          
                 IQR (CV) : 28 (0.2)                                                     

11   sbp_16      Mean (sd) : 134.9 (22.1)     129 distinct values    2020       1276     
     [numeric]   min < med < max:                                    (61.3%)    (38.7%)  
                 79 < 132 < 243                                                          
                 IQR (CV) : 27 (0.2)                                                     

12   sbp_18      Mean (sd) : 134.7 (21.9)     126 distinct values    1813       1483     
     [numeric]   min < med < max:                                    (55.0%)    (45.0%)  
                 83 < 132 < 239                                                          
                 IQR (CV) : 27 (0.2)                                                     

13   ageyrs      Mean (sd) : 57.5 (12.7)      76 distinct values     3291       5        
     [numeric]   min < med < max:                                    (99.8%)    (0.2%)   
                 1 < 58 < 99                                                             
                 IQR (CV) : 17 (0.2)                                                     

14   gender      1. Male                      2520 (76.6%)           3290       6        
     [factor]    2. Female                     770 (23.4%)           (99.8%)    (0.2%)   
-----------------------------------------------------------------------------------------

Code

dataF %>% visdat::vis_dat(palette = "cb_safe")

Code

dataF %>% visdat::vis_miss()

57 The `relocate` function

Code

dataF %>% 
    relocate(ageyrs, gender, .before = sbp_0) %>% 
    slice_head(n=10) %>% 
    tbl_style()

sid	dxs_class	ageyrs	gender	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18
1	HPT	75	Male	139	124	130	130	104	129	80	129	126	135
2	DM+HPT	60	Male	155	NA	NA	NA	NA	NA	NA	NA	NA	NA
3	HPT	62	Male	109	123	109	126	108	115	115	122	131	102
4	HPT	70	Male	130	NA	NA	NA	NA	NA	NA	NA	NA	NA
5	HPT	72	Male	124	120	146	144	157	123	120	131	120	123
6	DM+HPT	56	Male	140	114	163	117	124	121	128	119	100	127
7	DM+HPT	51	Male	137	135	132	147	130	NA	124	142	144	128
8	DM	73	Male	160	130	NA	NA	NA	NA	NA	NA	NA	NA
9	HPT	61	Female	153	218	NA	NA	NA	218	NA	NA	NA	NA
10	HPT	59	Male	135	130	118	150	NA	127	NA	123	149	132

Code

dataF %>% 
    relocate(sid, .after = last_col()) %>% 
    slice_head(n=10) %>% 
    tbl_style()

dxs_class	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	ageyrs	gender	sid
HPT	139	124	130	130	104	129	80	129	126	135	75	Male	1
DM+HPT	155	NA	NA	NA	NA	NA	NA	NA	NA	NA	60	Male	2
HPT	109	123	109	126	108	115	115	122	131	102	62	Male	3
HPT	130	NA	NA	NA	NA	NA	NA	NA	NA	NA	70	Male	4
HPT	124	120	146	144	157	123	120	131	120	123	72	Male	5
DM+HPT	140	114	163	117	124	121	128	119	100	127	56	Male	6
DM+HPT	137	135	132	147	130	NA	124	142	144	128	51	Male	7
DM	160	130	NA	NA	NA	NA	NA	NA	NA	NA	73	Male	8
HPT	153	218	NA	NA	NA	218	NA	NA	NA	NA	61	Female	9
HPT	135	130	118	150	NA	127	NA	123	149	132	59	Male	10

Code

dataF %>% 
    relocate(where(is.numeric)) %>% 
    slice_head(n=10) %>% 
    tbl_style()

sid	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	ageyrs	dxs_class	gender
1	139	124	130	130	104	129	80	129	126	135	75	HPT	Male
2	155	NA	NA	NA	NA	NA	NA	NA	NA	NA	60	DM+HPT	Male
3	109	123	109	126	108	115	115	122	131	102	62	HPT	Male
4	130	NA	NA	NA	NA	NA	NA	NA	NA	NA	70	HPT	Male
5	124	120	146	144	157	123	120	131	120	123	72	HPT	Male
6	140	114	163	117	124	121	128	119	100	127	56	DM+HPT	Male
7	137	135	132	147	130	NA	124	142	144	128	51	DM+HPT	Male
8	160	130	NA	NA	NA	NA	NA	NA	NA	NA	73	DM	Male
9	153	218	NA	NA	NA	218	NA	NA	NA	NA	61	HPT	Female
10	135	130	118	150	NA	127	NA	123	149	132	59	HPT	Male

Code

dataF %>% 
    relocate(contains("sbp")) %>% 
    slice_head(n=10) %>% 
    tbl_style()

sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	sid	dxs_class	ageyrs	gender
139	124	130	130	104	129	80	129	126	135	1	HPT	75	Male
155	NA	NA	NA	NA	NA	NA	NA	NA	NA	2	DM+HPT	60	Male
109	123	109	126	108	115	115	122	131	102	3	HPT	62	Male
130	NA	NA	NA	NA	NA	NA	NA	NA	NA	4	HPT	70	Male
124	120	146	144	157	123	120	131	120	123	5	HPT	72	Male
140	114	163	117	124	121	128	119	100	127	6	DM+HPT	56	Male
137	135	132	147	130	NA	124	142	144	128	7	DM+HPT	51	Male
160	130	NA	NA	NA	NA	NA	NA	NA	NA	8	DM	73	Male
153	218	NA	NA	NA	218	NA	NA	NA	NA	9	HPT	61	Female
135	130	118	150	NA	127	NA	123	149	132	10	HPT	59	Male

58 The `summarize` and `across` functions

Code

dataF %>% 
    summarize(across(sbp_0:sbp_8, .fns = mean, na.rm=T)) %>% 
    tbl_style()

Warning: There was 1 warning in `summarize()`.
ℹ In argument: `across(sbp_0:sbp_8, .fns = mean, na.rm = T)`.
Caused by warning:
! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
Supply arguments directly to `.fns` through an anonymous function instead.

  # Previously
  across(a:b, mean, na.rm = TRUE)

  # Now
  across(a:b, \(x) mean(x, na.rm = TRUE))

sbp_0	sbp_2	sbp_4	sbp_6	sbp_8
141.2021	139.4923	138.457	137.8216	137.149

Code

dataF %>% 
    na.omit() %>% 
    group_by(dxs_class) %>% 
    summarize(across(where(is.numeric), ~quantile(.x))) %>% 
    ungroup() %>% 
    tbl_style()

Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
dplyr 1.1.0.
ℹ Please use `reframe()` instead.
ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
  always returns an ungrouped data frame and adjust accordingly.

`summarise()` has grouped output by 'dxs_class'. You can override using the
`.groups` argument.

dxs_class	sid	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	ageyrs
DM	23.00	81.00	70.0	84.0	94.0	87	74.00	71.0	85.0	79	86	27
DM	980.50	114.50	115.5	113.0	114.5	112	113.00	113.0	112.0	112	110	44
DM	1650.00	124.00	125.0	125.0	126.0	127	124.00	123.0	122.0	120	121	50
DM	2340.00	134.00	139.0	137.5	140.5	138	138.00	136.0	136.5	130	135	58
DM	3284.00	189.00	194.0	199.0	187.0	187	175.00	183.0	196.0	185	197	75
DM+HPT	6.00	98.00	81.0	88.0	70.0	82	90.00	83.0	87.0	87	83	25
DM+HPT	825.75	129.00	127.0	125.0	126.0	127	124.00	125.0	124.0	124	122	53
DM+HPT	1566.00	142.00	141.0	142.0	139.0	140	139.00	139.5	138.0	140	137	60
DM+HPT	2441.75	158.25	157.0	158.0	155.0	157	156.25	153.0	154.0	152	154	66
DM+HPT	3283.00	216.00	231.0	231.0	234.0	277	240.00	232.0	220.0	228	226	89
HPT	1.00	90.00	71.0	78.0	88.0	73	87.00	80.0	81.0	79	86	30
HPT	783.00	126.00	124.0	120.0	120.0	120	120.00	120.0	120.0	120	120	51
HPT	1593.00	138.00	135.0	132.0	131.0	131	132.00	130.0	131.0	130	130	59
HPT	2510.50	151.00	150.0	147.0	146.0	146	144.00	144.0	144.0	145	142	66
HPT	3294.00	219.00	221.0	220.0	209.0	202	217.00	228.0	215.0	201	213	99

59 Distinct observations

Code

dataF %>% 
    summarise(across(where(is.numeric), n_distinct)) %>% 
    tbl_style()

sid	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	ageyrs
3296	138	141	145	138	135	134	134	133	130	127	77

60 Using list of functions, defining column names and removing NA

Code

dataF %>% 
    filter(!is.na(dxs_class)&!is.na(gender)) %>% 
    group_by(dxs_class, gender) %>%
    summarise(
        across(
            starts_with("sbp"), 
            list(
                AVG = mean, 
                SD = sd, 
                N_missing = ~sum(is.na(.x), na.rm=TRUE)
                )
            )
        ) %>%
    ungroup() %>% 
    tbl_style()

`summarise()` has grouped output by 'dxs_class'. You can override using the
`.groups` argument.

dxs_class	gender	sbp_0_AVG	sbp_0_SD	sbp_0_N_missing	sbp_2_AVG	sbp_2_SD	sbp_2_N_missing	sbp_4_AVG	sbp_4_SD	sbp_4_N_missing	sbp_6_AVG	sbp_6_SD	sbp_6_N_missing	sbp_8_AVG	sbp_8_SD	sbp_8_N_missing	sbp_10_AVG	sbp_10_SD	sbp_10_N_missing	sbp_12_AVG	sbp_12_SD	sbp_12_N_missing	sbp_14_AVG	sbp_14_SD	sbp_14_N_missing	sbp_16_AVG	sbp_16_SD	sbp_16_N_missing	sbp_18_AVG	sbp_18_SD	sbp_18_N_missing
DM	Male	NA	NA	1	NA	NA	57	NA	NA	70	NA	NA	75	NA	NA	74	NA	NA	79	NA	NA	79	NA	NA	85	NA	NA	94	NA	NA	110
DM	Female	128.3596	19.83209	0	NA	NA	17	NA	NA	23	NA	NA	29	NA	NA	30	NA	NA	29	NA	NA	32	NA	NA	36	NA	NA	50	NA	NA	55
DM+HPT	Male	144.8366	22.95160	0	NA	NA	84	NA	NA	113	NA	NA	119	NA	NA	145	NA	NA	153	NA	NA	153	NA	NA	186	NA	NA	204	NA	NA	247
DM+HPT	Female	146.9735	21.95934	0	NA	NA	26	NA	NA	36	NA	NA	39	NA	NA	45	NA	NA	43	NA	NA	55	NA	NA	57	NA	NA	68	NA	NA	84
HPT	Male	NA	NA	3	NA	NA	237	NA	NA	309	NA	NA	354	NA	NA	401	NA	NA	414	NA	NA	473	NA	NA	522	NA	NA	639	NA	NA	741
HPT	Female	143.9884	20.86011	0	NA	NA	74	NA	NA	116	NA	NA	131	NA	NA	147	NA	NA	145	NA	NA	165	NA	NA	173	NA	NA	216	NA	NA	241

61 Summarizing by anonymous functions

Code

dataF %>% 
    filter(!is.na(dxs_class)) %>% 
    group_by(dxs_class) %>%
    summarise(across(.cols = c(sbp_0, sbp_18), 
                     .fns = list("Mean" = ~mean(.x, na.rm=T), 
                                 "UpperCI" = ~(mean(.x, na.rm=T) + 1.96*sd(.x, na.rm=T)/sqrt(n())) ,
                                 "LowerCI" = ~(mean(.x, na.rm=T) - 1.96*sd(.x, na.rm=T)/sqrt(n()))))) %>%
    ungroup() %>% 
    tbl_style()

dxs_class	sbp_0_Mean	sbp_0_UpperCI	sbp_0_LowerCI	sbp_18_Mean	sbp_18_UpperCI	sbp_18_LowerCI
DM	125.8385	127.5809	124.0960	123.5214	125.2375	121.8053
DM+HPT	145.3254	146.7299	143.9209	139.2685	140.7099	137.8272
HPT	142.4490	143.4152	141.4829	134.5420	135.4799	133.6040

62 Generating all combinations of variables: `expand`

Code

dataF %>% 
    filter(!is.na(dxs_class) & !is.na(gender)) %>% 
    expand(dxs_class, gender) %>% 
    tbl_style()

dxs_class	gender
DM	Male
DM	Female
DM+HPT	Male
DM+HPT	Female
HPT	Male
HPT	Female

Code

dataF %>% 
    filter(!is.na(dxs_class) & !is.na(gender)) %>% 
    select(dxs_class, gender) %>% 
    crossing() %>% 
    tbl_style()

dxs_class	gender
DM	Male
DM	Female
DM+HPT	Male
DM+HPT	Female
HPT	Male
HPT	Female

63 Adding a running id to data

Code

dataF %>% 
    filter(!is.na(dxs_class) & !is.na(gender)) %>% 
    select(dxs_class, gender) %>%
    mutate(running_id = row_number()) %>% 
    slice_head(n=10) %>% 
    tbl_style()

dxs_class	gender	running_id
HPT	Male	1
DM+HPT	Male	2
HPT	Male	3
HPT	Male	4
HPT	Male	5
DM+HPT	Male	6
DM+HPT	Male	7
DM	Male	8
HPT	Female	9
HPT	Male	10

64 Reshaping data `pivot_longer` & `pivot_wider`

Code

dataF_long <-
    dataF %>% 
    select(gender, dxs_class, sbp_0:sbp_18) %>% 
    pivot_longer(cols = starts_with("sbp"),
                 names_to = "measure",
                 values_to = "sbp",
                 values_drop_na = TRUE)
dataF_long %>% 
    slice_head(n=10) %>% 
    tbl_style()

gender	dxs_class	measure	sbp
Male	HPT	sbp_0	139
Male	HPT	sbp_2	124
Male	HPT	sbp_4	130
Male	HPT	sbp_6	130
Male	HPT	sbp_8	104
Male	HPT	sbp_10	129
Male	HPT	sbp_12	80
Male	HPT	sbp_14	129
Male	HPT	sbp_16	126
Male	HPT	sbp_18	135

Code

dataF %>% 
    select(dxs_class, gender, sbp_0, sbp_2, sbp_4) %>%
    na.omit() %>% 
    group_by(dxs_class) %>% 
    pivot_wider(names_from = gender, 
                values_from = c(sbp_0, sbp_2, sbp_4), 
                values_fn = ~mean(.x, na.rm = TRUE)) %>% 
    ungroup() %>% 
    slice_head(n=10) %>% 
    tbl_style()

dxs_class	sbp_0_Male	sbp_0_Female	sbp_2_Male	sbp_2_Female	sbp_4_Male	sbp_4_Female
HPT	141.1099	143.7839	138.6872	141.8000	136.3622	140.6677
DM+HPT	144.6651	146.3641	143.5340	145.5707	143.3594	146.3587
DM	126.3578	130.2381	126.5642	131.6548	124.9266	134.2857

65 `tidyquant` Tabulation

Code

dataF %>% 
    select(dxs_class, gender) %>% 
    na.omit() %>% 
    tidyquant::pivot_table(
        .rows = gender, .columns = dxs_class, .values = ~n()
    ) %>% 
    tbl_style()

Registered S3 method overwritten by 'quantmod':
  method            from
  as.zoo.data.frame zoo

gender	DM	DM+HPT	HPT
Male	308	777	1434
Female	114	226	430

Code

dataF %>% 
    select(dxs_class, gender, sbp_0, sbp_2) %>% 
    na.omit() %>% 
    tidyquant::pivot_table(.rows = gender, 
                           .columns = dxs_class, 
                           .values = ~quantile(sbp_0)) %>% 
    unnest(cols = c("DM","HPT","DM+HPT")) %>% 
    tbl_style()

Warning: Values from `quantile(sbp_0)` are not uniquely identified; output will contain
list-cols.
• Use `values_fn = list` to suppress this warning.
• Use `values_fn = {summary_fun}` to summarise duplicates.
• Use the following dplyr code to identify duplicates.
  {data} |>
  dplyr::summarise(n = dplyr::n(), .by = c(gender, dxs_class)) |>
  dplyr::filter(n > 1L)

gender	DM	DM+HPT	HPT
Male	90.00	95	70
Male	113.25	128	126
Male	124.00	142	140
Male	134.00	158	154
Male	182.00	228	224
Female	81.00	98	98
Female	117.00	131	129
Female	127.00	145	141
Female	138.00	161	159
Female	208.00	220	210

66 `rowwise` manipulations

Code

dataF %>% 
    rowwise() %>% 
    mutate(sbp_mean = mean(c(sbp_0,sbp_2,sbp_4,sbp_6,sbp_8, sbp_10, sbp_12,
                             sbp_14,sbp_16, sbp_18), na.rm=T),
           sbp_sd = sd(c(sbp_0,sbp_2,sbp_4,sbp_6,sbp_8, sbp_10, sbp_12,sbp_14,
                         sbp_16, sbp_18), na.rm=T),
           n=n()) %>% 
    ungroup() %>% 
    relocate(sid, dxs_class, ageyrs, gender, sbp_mean, sbp_sd, contains("sbp")) %>% 
    slice_head(n=10) %>% 
    tbl_style()

sid	dxs_class	ageyrs	gender	sbp_mean	sbp_sd	sbp_0	sbp_2	sbp_4	sbp_6	sbp_8	sbp_10	sbp_12	sbp_14	sbp_16	sbp_18	n
1	HPT	75	Male	122.6000	17.601768	139	124	130	130	104	129	80	129	126	135	1
2	DM+HPT	60	Male	155.0000	NA	155	NA	NA	NA	NA	NA	NA	NA	NA	NA	1
3	HPT	62	Male	116.0000	9.249625	109	123	109	126	108	115	115	122	131	102	1
4	HPT	70	Male	130.0000	NA	130	NA	NA	NA	NA	NA	NA	NA	NA	NA	1
5	HPT	72	Male	130.8000	13.373274	124	120	146	144	157	123	120	131	120	123	1
6	DM+HPT	56	Male	125.3000	16.813024	140	114	163	117	124	121	128	119	100	127	1
7	DM+HPT	51	Male	135.4444	7.747760	137	135	132	147	130	NA	124	142	144	128	1
8	DM	73	Male	145.0000	21.213203	160	130	NA	NA	NA	NA	NA	NA	NA	NA	1
9	HPT	61	Female	196.3333	37.527767	153	218	NA	NA	NA	218	NA	NA	NA	NA	1
10	HPT	59	Male	133.0000	11.464230	135	130	118	150	NA	127	NA	123	149	132	1

67 Glue function via `str_glue` functions

Code

x <- c("Ama", "is", "a", "Girl")
cat(x)

Ama is a Girl

Code

name <- "Fred"
str_glue('My name is {name}.')

My name is Fred.

Code

stringr_fcn <- "`stringr::str_glue()`"
glue_fcn    <- "`glue::glue()`"

str_glue('{stringr_fcn} is essentially an alias for {glue_fcn}.')

`stringr::str_glue()` is essentially an alias for `glue::glue()`.

Code

name <- "Fred"
age <- 50
anniversary <- as.Date("1991-10-12")
str_glue('My name is {name},',
  ' my age next year is {age + 1},',
  ' my anniversary is {format(anniversary, "%A, %B %d, %Y")}.')

My name is Fred, my age next year is 51, my anniversary is Saturday, October 12, 1991.

Code

str_glue('My name is {name},',
  ' my age next year is {age + 1},',
  ' my anniversary is {format(anniversary, "%A, %B %d, %Y")}.',
  name = "Joe",
  age = 40,
  anniversary = as.Date("2001-10-12"))

My name is Joe, my age next year is 41, my anniversary is Friday, October 12, 2001.

Code

mtcars %>% 
    head() %>% 
    tbl_style()

mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
21.0	6	160	110	3.90	2.620	16.46	0	1	4	4
21.0	6	160	110	3.90	2.875	17.02	0	1	4	4
22.8	4	108	93	3.85	2.320	18.61	1	1	4	1
21.4	6	258	110	3.08	3.215	19.44	1	0	3	1
18.7	8	360	175	3.15	3.440	17.02	0	0	3	2
18.1	6	225	105	2.76	3.460	20.22	1	0	3	1

Code

head(mtcars) %>% 
    glue::glue_data("{rownames(.)} has {hp} hp")

Mazda RX4 has 110 hp
Mazda RX4 Wag has 110 hp
Datsun 710 has 93 hp
Hornet 4 Drive has 110 hp
Hornet Sportabout has 175 hp
Valiant has 105 hp

Code

head(iris) %>%
  mutate(
      description = str_glue(
          "This {Species} has a petal length of {Petal.Length}"
          )
      ) %>% 
    tbl_style()

Sepal.Length	Sepal.Width	Petal.Length	Petal.Width	Species	description
5.1	3.5	1.4	0.2	setosa	This setosa has a petal length of 1.4
4.9	3.0	1.4	0.2	setosa	This setosa has a petal length of 1.4
4.7	3.2	1.3	0.2	setosa	This setosa has a petal length of 1.3
4.6	3.1	1.5	0.2	setosa	This setosa has a petal length of 1.5
5.0	3.6	1.4	0.2	setosa	This setosa has a petal length of 1.4
5.4	3.9	1.7	0.4	setosa	This setosa has a petal length of 1.7

Code

str_glue("
    A formatted string
    Can have multiple lines
      with additional indention preserved
    ")

A formatted string
Can have multiple lines
  with additional indention preserved

Code

str_glue("

  leading or trailing newlines can be added explicitly

  ")


leading or trailing newlines can be added explicitly

Code

str_glue("
    A formatted string \\
    can also be on a \\
    single line
    ")

A formatted string can also be on a single line

Code

name <- "Fred"
str_glue("My name is {name}, not {{name}}.")

My name is Fred, not {name}.

Code

one <- "1"
str_glue("The value of $e^{2\\pi i}$ is $<<one>>$.", .open = "<<", .close = ">>")

The value of $e^{2\pi i}$ is $1$.

Code

dataF %>% 
    filter(!is.na(sbp_0)) %>% 
    ggplot(aes(x=sbp_0)) +
    geom_histogram(col = "grey", fill = "wheat") +
    labs(title = str_glue("Histogram with Mean = {mean_sbp0}mmHg and \\
                          Standard Deviation = {sd_sbp0}",
                          mean_sbp0 = mean(dataF$sbp_0, na.rm=T) %>% round(1),
                          sd_sbp0   = sd(dataF$sbp_0,   na.rm=T) %>% round(1)),
         x = "Systolic Blood Pressure (mmHg)",
         y = "Frequency") +
    theme_light(base_size = 12, base_family = "serif")

`stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

52 Creating function to configrure tables

53 Manual data entry

54 Reading in data

55 dplyr functions

55.1 arrange

55.2 unite()

55.3 seperate()

56 Visualise and summarize the data

57 The relocate function

58 The summarize and across functions

59 Distinct observations

60 Using list of functions, defining column names and removing NA

61 Summarizing by anonymous functions

62 Generating all combinations of variables: expand

63 Adding a running id to data

64 Reshaping data pivot_longer & pivot_wider

65 tidyquant Tabulation

66 rowwise manipulations

67 Glue function via str_glue functions

55 `dplyr` functions

55.1 `arrange`

55.2 `unite()`

55.3 `seperate()`

57 The `relocate` function

58 The `summarize` and `across` functions

62 Generating all combinations of variables: `expand`

64 Reshaping data `pivot_longer` & `pivot_wider`

65 `tidyquant` Tabulation

66 `rowwise` manipulations

67 Glue function via `str_glue` functions