library(grDevices)      # boxplot.stats()
library(operator.tools) # %!in% logical operator
library(tmap)           # 'metro' data set
library(magrittr)       # piping
library(dplyr)          # exploratory data analysis verbs
library(purrr)          # recursive mapping of functions
library(tibble)         # improved version of a data.frame
library(ggplot2)        # dot plot
library(ggrepel)        # avoid label overlap

options(scipen=999)
set.seed(888)

data("metro")

m_spdf <- metro
# Take a sample
m <-
        metro@data %>%
        as_tibble %>%
        select(-name_long,-iso_a3) %>%
        sample_n(50)

> m
# A tibble: 50 x 10
          name pop1950 pop1960 pop1970 pop1980 pop1990
         <chr>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
1       Sydney 1689935 2134673 2892477 3252111 3631940
2       Havana 1141959 1435511 1779491 1913377 2108381
3     Campinas  151977  293174  540430 1108903 1693359
4         Kano  123073  229203  541992 1349646 2095384
5         Omsk  444326  608363  829860 1032150 1143813
6  Ouagadougou   33035   59126  115374  265200  537441
7    Marseille  755805  928768 1182048 1372495 1418279
8      Taiyuan  196510  349535  621625 1105695 1636599
9       La Paz  319247  437687  600016  809218 1061850
10   Baltimore 1167656 1422067 1554538 1748983 1848834
# ... with 40 more rows, and 4 more variables:
#   pop2000 <dbl>, pop2010 <dbl>, pop2020 <dbl>,
#   pop2030 <dbl>

# Calculate the quintile groups for one variable (e.g., `pop1990`)
m_all <-
        m %>%
        mutate(qnt_1990_all = dplyr::ntile(pop1990,5))

# Find the outliers for a different variable (e.g., 'pop1950')
# and subset the df to exlcude these outlier records
m_out <- boxplot.stats(m$pop1950) %>% .[["out"]]

m_trim <-
        m %>%
        filter(pop1950 %!in% m_out) %>%
        mutate(qnt_1990_trim = dplyr::ntile(pop1990,5))

# Assess whether the outlier trimming impacted the first quintile group
m_comp <-
        m_trim %>%
        select(name,dplyr::contains("qnt")) %>%
        left_join(m_all,.,"name") %>%
        select(name,dplyr::contains("qnt"),everything()) %>%
        mutate(qnt_1990_chng_lgl = !is.na(qnt_1990_trim) & qnt_1990_trim != qnt_1990_all,
               qnt_1990_chng_dir = if_else(qnt_1990_chng_lgl,
                                           paste0(qnt_1990_all," to ",qnt_1990_trim),
                                           "No change"))

> m_comp %>% select(name,qnt_1990_chng_lgl,qnt_1990_chng_dir,everything())
# A tibble: 50 x 14
          name qnt_1990_chng_lgl qnt_1990_chng_dir qnt_1990_all qnt_1990_trim
         <chr>             <lgl>             <chr>        <dbl>         <dbl>
1       Sydney             FALSE         No change            5            NA
2       Havana              TRUE            4 to 5            4             5
3     Campinas              TRUE            3 to 4            3             4
4         Kano             FALSE         No change            4             4
5         Omsk             FALSE         No change            3             3
6  Ouagadougou             FALSE         No change            1             1
7    Marseille             FALSE         No change            3             3
8      Taiyuan              TRUE            3 to 4            3             4
9       La Paz             FALSE         No change            2             2
10   Baltimore             FALSE         No change            4             4
# ... with 40 more rows, and 9 more variables: pop1950 <dbl>, pop1960 <dbl>,
#   pop1970 <dbl>, pop1980 <dbl>, pop1990 <dbl>, pop2000 <dbl>, pop2010 <dbl>,
#   pop2020 <dbl>, pop2030 <dbl>