Supporting Statistical Analysis for Research
5.7 Relationships between columns
These exercises use the Chile.csv data set.
Import the
Chile.csvfile.library(tidyverse)chile_path <- file.path("..", "datasets", "Chile.csv") chile_in <- read_csv(chile_path, col_types = cols())Warning: Missing column names filled in: 'X1' [1]chile_in <- chile_in %>% rename( status_quo = statusquo ) chile <- chile_in %>% select(-X1) glimpse(chile)Observations: 2,700 Variables: 8 $ region <chr> "N", "N", "N", "N", "N", "N", "N", "N", "N", "N", "... $ population <dbl> 175000, 175000, 175000, 175000, 175000, 175000, 175... $ sex <chr> "M", "M", "F", "F", "F", "F", "M", "F", "F", "M", "... $ age <dbl> 65, 29, 38, 49, 23, 28, 26, 24, 41, 41, 64, 19, 27,... $ education <chr> "P", "PS", "P", "P", "S", "P", "PS", "S", "P", "P",... $ income <dbl> 35000, 7500, 15000, 35000, 35000, 7500, 35000, 1500... $ status_quo <dbl> 1.00820, -1.29617, 1.23072, -1.03163, -1.10496, -1.... $ vote <chr> "Y", "N", "Y", "N", "N", "N", "N", "N", "U", "N", "...Find all rows with a missing value in any column using a related columns method.
chile_na_rows <- chile %>% mutate( missing = pmap_dbl(select(., region:vote), ~ sum(is.na(c(...))) ) >= 1 ) %>% filter(missing) %>% select(-missing) head(chile_na_rows)# A tibble: 6 x 8 region population sex age education income status_quo vote <chr> <dbl> <chr> <dbl> <chr> <dbl> <dbl> <chr> 1 N 175000 F 27 PS NA 1.43 Y 2 N 175000 M 36 PS 35000 1.49 <NA> 3 N 175000 F 43 P NA 0.155 A 4 N 125000 F 32 S NA -0.850 N 5 N 125000 F 34 P 2500 0.108 <NA> 6 N 250000 F 46 S NA 0.155 <NA>