Packages testing

Libraries

library(vtable)
library(table1)
library(psych)

Base R

library(readxl)
usar <- read_excel('C:/Users/я/Documents/USArrests.xlsx')



summary(USArrests)

##      Murder          Assault         UrbanPop          Rape      
##  Min.   : 0.800   Min.   : 45.0   Min.   :32.00   Min.   : 7.30  
##  1st Qu.: 4.075   1st Qu.:109.0   1st Qu.:54.50   1st Qu.:15.07  
##  Median : 7.250   Median :159.0   Median :66.00   Median :20.10  
##  Mean   : 7.788   Mean   :170.8   Mean   :65.54   Mean   :21.23  
##  3rd Qu.:11.250   3rd Qu.:249.0   3rd Qu.:77.75   3rd Qu.:26.18  
##  Max.   :17.400   Max.   :337.0   Max.   :91.00   Max.   :46.00

Some improvements of representation with knitr:

library(knitr)
library(boot)

## 
## Attaching package: 'boot'

## The following object is masked from 'package:psych':
## 
##     logit

summary(usar) %>%
  kable() %>%
  kable_styling()

State	TypCrime	Arrests	UrbanPop
Length:150	Length:150	Min. : 0.80	Min. :32.00
Class :character	Class :character	1st Qu.: 9.55	1st Qu.:54.00
Mode :character	Mode :character	Median : 20.10	Median :66.00
NA	NA	Mean : 66.59	Mean :65.54
NA	NA	3rd Qu.:108.25	3rd Qu.:78.00
NA	NA	Max. :337.00	Max. :91.00

head(usar) %>%
  kable() %>%
  kable_styling()

State	TypCrime	Arrests	UrbanPop
Alabama	Murder	13.2	58
Alaska	Murder	10.0	48
Arizona	Murder	8.1	80
Arkansas	Murder	8.8	50
California	Murder	9.0	91
Colorado	Murder	7.9	78

head(melanoma) %>%
  kable() %>%
  kable_styling()

time	status	sex	age	year	thickness	ulcer
10	3	1	76	1972	6.76	1
30	3	1	56	1968	0.65	0
35	2	1	41	1977	1.34	0
99	3	0	71	1968	2.90	0
185	1	1	52	1965	12.08	1
204	1	1	28	1971	4.84	1

TABLE1

## One type of data - USArrests modified
usar1 <- usar

usar1$TypCrime <- 
  factor(usar$TypCrime, 
         levels=c("Murder","Assault","Rape"),
         labels=c("Murder", # Reference
                  "Assault", 
                  "Rape"))
usar1$State <-
  factor(usar$State)
label(usar1$State) <- "State"

table1(~State | TypCrime, data=usar1)

	Murder (N=50)	Assault (N=50)	Rape (N=50)	Overall (N=150)
State
Alabama	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Alaska	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Arizona	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Arkansas	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
California	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Colorado	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Connecticut	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Delaware	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Florida	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Georgia	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Hawaii	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Idaho	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Illinois	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Indiana	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Iowa	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Kansas	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Kentucky	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Louisiana	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Maine	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Maryland	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Massachusetts	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Michigan	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Minnesota	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Mississippi	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Missouri	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Montana	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Nebraska	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Nevada	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
New Hampshire	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
New Jersey	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
New Mexico	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
New York	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
North Carolina	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
North Dakota	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Ohio	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Oklahoma	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Oregon	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Pennsylvania	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Rhode Island	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
South Carolina	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
South Dakota	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Tennessee	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Texas	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Utah	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Vermont	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Virginia	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Washington	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
West Virginia	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Wisconsin	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)
Wyoming	1 (2.0%)	1 (2.0%)	1 (2.0%)	3 (2.0%)

summary(usar$Arrests)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    0.80    9.55   20.10   66.59  108.25  337.00

library(ggpubr)

## Loading required package: ggplot2

## Warning: package 'ggplot2' was built under R version 4.0.2

## 
## Attaching package: 'ggplot2'

## The following objects are masked from 'package:psych':
## 
##     %+%, alpha

ggplot(usar, aes(Arrests)) + geom_histogram(color = "Lightsteelblue2", fill = "lightsteelblue1") + theme_pubclean() + labs(y = NULL) + ylim(0,60)

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

usar1$Arrests <- ifelse(usar$Arrests <= 40, "Low",
                        ifelse(usar$Arrests > 40, "High", NA))

table1(~State + TypCrime | Arrests, data=usar1)

	High (N=53)	Low (N=97)	Overall (N=150)
State
Alabama	1 (1.9%)	2 (2.1%)	3 (2.0%)
Alaska	2 (3.8%)	1 (1.0%)	3 (2.0%)
Arizona	1 (1.9%)	2 (2.1%)	3 (2.0%)
Arkansas	1 (1.9%)	2 (2.1%)	3 (2.0%)
California	2 (3.8%)	1 (1.0%)	3 (2.0%)
Colorado	1 (1.9%)	2 (2.1%)	3 (2.0%)
Connecticut	1 (1.9%)	2 (2.1%)	3 (2.0%)
Delaware	1 (1.9%)	2 (2.1%)	3 (2.0%)
Florida	1 (1.9%)	2 (2.1%)	3 (2.0%)
Georgia	1 (1.9%)	2 (2.1%)	3 (2.0%)
Hawaii	1 (1.9%)	2 (2.1%)	3 (2.0%)
Idaho	1 (1.9%)	2 (2.1%)	3 (2.0%)
Illinois	1 (1.9%)	2 (2.1%)	3 (2.0%)
Indiana	1 (1.9%)	2 (2.1%)	3 (2.0%)
Iowa	1 (1.9%)	2 (2.1%)	3 (2.0%)
Kansas	1 (1.9%)	2 (2.1%)	3 (2.0%)
Kentucky	1 (1.9%)	2 (2.1%)	3 (2.0%)
Louisiana	1 (1.9%)	2 (2.1%)	3 (2.0%)
Maine	1 (1.9%)	2 (2.1%)	3 (2.0%)
Maryland	1 (1.9%)	2 (2.1%)	3 (2.0%)
Massachusetts	1 (1.9%)	2 (2.1%)	3 (2.0%)
Michigan	1 (1.9%)	2 (2.1%)	3 (2.0%)
Minnesota	1 (1.9%)	2 (2.1%)	3 (2.0%)
Mississippi	1 (1.9%)	2 (2.1%)	3 (2.0%)
Missouri	1 (1.9%)	2 (2.1%)	3 (2.0%)
Montana	1 (1.9%)	2 (2.1%)	3 (2.0%)
Nebraska	1 (1.9%)	2 (2.1%)	3 (2.0%)
Nevada	2 (3.8%)	1 (1.0%)	3 (2.0%)
New Hampshire	1 (1.9%)	2 (2.1%)	3 (2.0%)
New Jersey	1 (1.9%)	2 (2.1%)	3 (2.0%)
New Mexico	1 (1.9%)	2 (2.1%)	3 (2.0%)
New York	1 (1.9%)	2 (2.1%)	3 (2.0%)
North Carolina	1 (1.9%)	2 (2.1%)	3 (2.0%)
North Dakota	1 (1.9%)	2 (2.1%)	3 (2.0%)
Ohio	1 (1.9%)	2 (2.1%)	3 (2.0%)
Oklahoma	1 (1.9%)	2 (2.1%)	3 (2.0%)
Oregon	1 (1.9%)	2 (2.1%)	3 (2.0%)
Pennsylvania	1 (1.9%)	2 (2.1%)	3 (2.0%)
Rhode Island	1 (1.9%)	2 (2.1%)	3 (2.0%)
South Carolina	1 (1.9%)	2 (2.1%)	3 (2.0%)
South Dakota	1 (1.9%)	2 (2.1%)	3 (2.0%)
Tennessee	1 (1.9%)	2 (2.1%)	3 (2.0%)
Texas	1 (1.9%)	2 (2.1%)	3 (2.0%)
Utah	1 (1.9%)	2 (2.1%)	3 (2.0%)
Vermont	1 (1.9%)	2 (2.1%)	3 (2.0%)
Virginia	1 (1.9%)	2 (2.1%)	3 (2.0%)
Washington	1 (1.9%)	2 (2.1%)	3 (2.0%)
West Virginia	1 (1.9%)	2 (2.1%)	3 (2.0%)
Wisconsin	1 (1.9%)	2 (2.1%)	3 (2.0%)
Wyoming	1 (1.9%)	2 (2.1%)	3 (2.0%)
TypCrime
Murder	0 (0%)	50 (51.5%)	50 (33.3%)
Assault	50 (94.3%)	0 (0%)	50 (33.3%)
Rape	3 (5.7%)	47 (48.5%)	50 (33.3%)

###-------------------------------------------------------------------------------------

## Another type - melanoma dataset
melanoma2 <- melanoma
 
melanoma2$status <- 
  factor(melanoma2$status, 
         levels=c(2,1,3),
         labels=c("Alive", # Reference
                  "Melanoma death", 
                  "Non-melanoma death"))

melanoma2$sex <- 
  factor(melanoma2$sex, levels=c(1,0),
         labels=c("Male", 
                  "Female"))
 
melanoma2$ulcer <- 
  factor(melanoma2$ulcer, levels=c(0,1),
         labels=c("Absent", 
                  "Present"))

label(melanoma2$sex)       <- "Sex"
label(melanoma2$age)       <- "Age"
label(melanoma2$ulcer)     <- "Ulceration"
label(melanoma2$thickness) <- "Thickness"

units(melanoma2$age)       <- "years"
units(melanoma2$thickness) <- "mm"

table1(~ sex + age + ulcer + thickness | status, data=melanoma2, overall="Total")

	Alive (N=134)	Melanoma death (N=57)	Non-melanoma death (N=14)	Total (N=205)
Sex
Male	43 (32.1%)	29 (50.9%)	7 (50.0%)	79 (38.5%)
Female	91 (67.9%)	28 (49.1%)	7 (50.0%)	126 (61.5%)
Age (years)
Mean (SD)	50.0 (15.9)	55.1 (17.9)	65.3 (10.9)	52.5 (16.7)
Median [Min, Max]	52.0 [4.00, 84.0]	56.0 [14.0, 95.0]	65.0 [49.0, 86.0]	54.0 [4.00, 95.0]
Ulceration
Absent	92 (68.7%)	16 (28.1%)	7 (50.0%)	115 (56.1%)
Present	42 (31.3%)	41 (71.9%)	7 (50.0%)	90 (43.9%)
Thickness (mm)
Mean (SD)	2.24 (2.33)	4.31 (3.57)	3.72 (3.63)	2.92 (2.96)
Median [Min, Max]	1.36 [0.100, 12.9]	3.54 [0.320, 17.4]	2.26 [0.160, 12.6]	1.94 [0.100, 17.4]

VTABLE and PSYCH

## Psych and vtable comparison
vtable(usar, data.title = "USA arrests", char.values = TRUE, lush = TRUE, col.width = c(2,2,5,2,4), col.align = "left")

USA arrests
Name	Class	Values	Summary
State	character	‘Alabama’ ‘Alaska’ ‘Arizona’ ‘Arkansas’ ‘California’ and more	nuniq: 50
TypCrime	character	‘Assault’ ‘Murder’ ‘Rape’	nuniq: 3
Arrests	numeric	Num: 0.8 to 337	mean: 66.593<br>sd: 88.381<br>nuniq: 131
UrbanPop	numeric	Num: 32 to 91	mean: 65.54<br>sd: 14.377<br>nuniq: 36

describe(usar, check = TRUE)

## Warning in describe(usar, check = TRUE): в результате преобразования созданы NA

## Warning in describe(usar, check = TRUE): в результате преобразования созданы NA

## Warning in FUN(newX[, i], ...): у 'min' нет не пропущенных аргументов; возвращаю
## Inf

## Warning in FUN(newX[, i], ...): у 'min' нет не пропущенных аргументов; возвращаю
## Inf

## Warning in FUN(newX[, i], ...): у 'max' нет не пропущенных аргументов; возвращаю
## -Inf

## Warning in FUN(newX[, i], ...): у 'max' нет не пропущенных аргументов; возвращаю
## -Inf

##           vars   n  mean    sd median trimmed   mad  min  max range  skew
## State*       1 150   NaN    NA     NA     NaN    NA  Inf -Inf  -Inf    NA
## TypCrime*    2 150   NaN    NA     NA     NaN    NA  Inf -Inf  -Inf    NA
## Arrests      3 150 66.59 88.38   20.1   48.50 20.90  0.8  337 336.2  1.48
## UrbanPop     4 150 65.54 14.38   66.0   65.88 17.79 32.0   91  59.0 -0.22
##           kurtosis   se
## State*          NA   NA
## TypCrime*       NA   NA
## Arrests       0.94 7.22
## UrbanPop     -0.81 1.17

sumtable(usar, col.align = "left")

Summary Statistics
Variable	N	Mean	Std. Dev.	Min	Pctl. 25	Pctl. 75	Max
TypCrime	150
… Assault	50	33.3%
… Murder	50	33.3%
… Rape	50	33.3%
Arrests	150	66.593	88.381	0.8	9.55	108.25	337
UrbanPop	150	65.54	14.377	32	54	78	91

Psych feature:

## Model and base r summary
model1 <- lm(Arrests ~ UrbanPop, data = usar)
mod1 <- summary(model1)

## Diagram of the model
p <- setCor(Arrests ~ UrbanPop, data = usar, std=FALSE)

setCor.diagram(p)

Packages testing

Maria Nalivkina

02/12/2020

Libraries

Base R

TABLE1

VTABLE and PSYCH