Summary Statistics
library(skimr)
library(visdat)
library(tidyverse)
library(plotly)
library(knitr)
library(glancedata)
library(faraway)
data("teengamb")
kable(head(teengamb, col.names = c("Sex", "Status", "Income", "Verbal", "Gamble")))| sex | status | income | verbal | gamble |
|---|---|---|---|---|
| 1 | 51 | 2.00 | 8 | 0.0 |
| 1 | 28 | 2.50 | 8 | 0.0 |
| 1 | 37 | 2.00 | 6 | 0.0 |
| 1 | 28 | 7.00 | 4 | 7.3 |
| 1 | 65 | 2.00 | 8 | 19.6 |
| 1 | 61 | 3.47 | 6 | 0.1 |
skim(teengamb)| Name | teengamb |
| Number of rows | 47 |
| Number of columns | 5 |
| _______________________ | |
| Column type frequency: | |
| numeric | 5 |
| ________________________ | |
| Group variables | None |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| sex | 0 | 1 | 0.40 | 0.50 | 0.0 | 0.0 | 0.00 | 1.00 | 1 | ▇▁▁▁▆ |
| status | 0 | 1 | 45.23 | 17.26 | 18.0 | 28.0 | 43.00 | 61.50 | 75 | ▇▅▇▃▆ |
| income | 0 | 1 | 4.64 | 3.55 | 0.6 | 2.0 | 3.25 | 6.21 | 15 | ▇▃▂▂▁ |
| verbal | 0 | 1 | 6.66 | 1.86 | 1.0 | 6.0 | 7.00 | 8.00 | 10 | ▁▂▆▇▃ |
| gamble | 0 | 1 | 19.30 | 31.52 | 0.0 | 1.1 | 6.00 | 19.40 | 156 | ▇▁▁▁▁ |
glancedata::glance_data(teengamb)glancedata::glance_data_in_workbook(teengamb)## $all
## # A tibble: 5 x 11
## name type distinct_values minimum median maximum mean sd na_proportion
## <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 sex nume… 2 0 0 1 0.404 0.496 0
## 2 stat… nume… 16 18 43 75 45.2 17.3 0
## 3 inco… nume… 26 0.6 3.25 15 4.64 3.55 0
## 4 verb… nume… 9 1 7 10 6.66 1.86 0
## 5 gamb… nume… 36 0 6 156 19.3 31.5 0
## # … with 2 more variables: count <chr>, sample_values <chr>
##
## $summary
## # A tibble: 2 x 2
## cat n
## <chr> <int>
## 1 binary 1
## 2 numerical 4
##
## $all_nas
## # A tibble: 0 x 6
## # … with 6 variables: name <chr>, type <chr>, distinct_values <int>,
## # na_proportion <dbl>, count <chr>, sample_values <chr>
##
## $single_value
## # A tibble: 0 x 11
## # … with 11 variables: name <chr>, type <chr>, distinct_values <int>,
## # minimum <dbl>, median <dbl>, maximum <dbl>, mean <dbl>, sd <dbl>,
## # na_proportion <dbl>, count <chr>, sample_values <chr>
##
## $binary
## # A tibble: 1 x 11
## name type distinct_values minimum median maximum mean sd na_proportion
## <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 sex nume… 2 0 0 1 0.404 0.496 0
## # … with 2 more variables: count <chr>, sample_values <chr>
##
## $numerical
## # A tibble: 4 x 10
## name type distinct_values minimum median maximum mean sd na_proportion
## <chr> <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 stat… nume… 16 18 43 75 45.2 17.3 0
## 2 inco… nume… 26 0.6 3.25 15 4.64 3.55 0
## 3 verb… nume… 9 1 7 10 6.66 1.86 0
## 4 gamb… nume… 36 0 6 156 19.3 31.5 0
## # … with 1 more variable: sample_values <chr>
##
## $categorical
## # A tibble: 0 x 5
## # … with 5 variables: name <chr>, distinct_values <int>, na_proportion <dbl>,
## # count <chr>, sample_values <chr>glancedata::plot_discrete_vars(teengamb)## TableGrob (2 x 2) "arrange": 3 grobs
## z cells name grob
## sex 1 (1-1,1-1) arrange gtable[layout]
## verbal 2 (1-1,2-2) arrange gtable[layout]
## 3 (2-2,1-2) arrange text[GRID.text.89]glancedata::plot_numerical_vars(teengamb,plot_type = "histogram")glancedata::plot_numerical_vars(teengamb,plot_type = "density")glancedata::plot_numerical_vars(teengamb, plot_type = "boxplot")glancedata::plot_numerical_vars(teengamb, plot_type = "qqplot")glancedata::plot_numerical_vars(teengamb, plot_type = "pairwise")
teen = teengamb
teen$income = teen$income[teen$income>70]<-NA
teen$gamble = teen$gamble[teen$gamble>30]<-NA
teen$verbal= teen$verbal[teen$verbal<3]<-NA
visdat::vis_miss(teen,sort_miss = T, show_perc = T, cluster = T)
teengamb$sex = as.factor(teengamb$sex)
levels(teengamb$sex) = c("Male", "Female")
p = ggplot(teengamb, aes(x =status, y = income, color = sex)) + geom_point()
ggplotly(p)