Data Set Examination
Patrick Ford
2024-02-28
install.packages("skimr") ## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorslibrary(dplyr)
library(ggplot2)
library(skimr)
# Load the data set
my_data <- read.csv("ED.csv")
# Basic Summary
summary(my_data)## COUNTRY Country WEEK Week.number
## Length:135628 Length:135628 Min. : 1.00 Min. : 1.00
## Class :character Class :character 1st Qu.:13.00 1st Qu.:13.00
## Mode :character Mode :character Median :26.00 Median :26.00
## Mean :25.78 Mean :25.78
## 3rd Qu.:38.00 3rd Qu.:38.00
## Max. :53.00 Max. :53.00
## GENDER Gender AGE Age
## Length:135628 Length:135628 Length:135628 Length:135628
## Class :character Class :character Class :character Class :character
## Mode :character Mode :character Mode :character Mode :character
##
##
##
## VARIABLE Variable YEAR Year
## Length:135628 Length:135628 Min. :2020 Min. :2020
## Class :character Class :character 1st Qu.:2020 1st Qu.:2020
## Mode :character Mode :character Median :2021 Median :2021
## Mean :2021 Mean :2021
## 3rd Qu.:2022 3rd Qu.:2022
## Max. :2023 Max. :2023
## Value Flag.Codes Flags
## Min. :-12788.8 Length:135628 Length:135628
## 1st Qu.: -4.6 Class :character Class :character
## Median : 6.2 Mode :character Mode :character
## Mean : 116.9
## 3rd Qu.: 29.4
## Max. : 28262.9# Extended Summary with 'skimr'
skim(my_data)| Name | my_data |
| Number of rows | 135628 |
| Number of columns | 15 |
| _______________________ | |
| Column type frequency: | |
| character | 10 |
| numeric | 5 |
| ________________________ | |
| Group variables | None |
Variable type: character
| skim_variable | n_missing | complete_rate | min | max | empty | n_unique | whitespace |
|---|---|---|---|---|---|---|---|
| COUNTRY | 0 | 1 | 3 | 3 | 0 | 34 | 0 |
| Country | 0 | 1 | 5 | 15 | 0 | 34 | 0 |
| GENDER | 0 | 1 | 4 | 6 | 0 | 3 | 0 |
| Gender | 0 | 1 | 5 | 7 | 0 | 3 | 0 |
| AGE | 0 | 1 | 5 | 6 | 0 | 4 | 0 |
| Age | 0 | 1 | 5 | 11 | 0 | 4 | 0 |
| VARIABLE | 0 | 1 | 8 | 8 | 0 | 2 | 0 |
| Variable | 0 | 1 | 22 | 37 | 0 | 2 | 0 |
| Flag.Codes | 0 | 1 | 0 | 1 | 134938 | 2 | 0 |
| Flags | 0 | 1 | 0 | 25 | 134938 | 2 | 0 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| WEEK | 0 | 1 | 25.78 | 14.75 | 1.0 | 13.0 | 26.0 | 38.0 | 53.0 | ▇▇▇▇▆ |
| Week.number | 0 | 1 | 25.78 | 14.75 | 1.0 | 13.0 | 26.0 | 38.0 | 53.0 | ▇▇▇▇▆ |
| YEAR | 0 | 1 | 2021.41 | 1.10 | 2020.0 | 2020.0 | 2021.0 | 2022.0 | 2023.0 | ▇▇▁▇▆ |
| Year | 0 | 1 | 2021.41 | 1.10 | 2020.0 | 2020.0 | 2021.0 | 2022.0 | 2023.0 | ▇▇▁▇▆ |
| Value | 0 | 1 | 116.92 | 766.43 | -12788.8 | -4.6 | 6.2 | 29.4 | 28262.9 | ▁▇▁▁▁ |
# Missing Values
sum(is.na(my_data)) ## [1] 0colSums(is.na(my_data))## COUNTRY Country WEEK Week.number GENDER Gender
## 0 0 0 0 0 0
## AGE Age VARIABLE Variable YEAR Year
## 0 0 0 0 0 0
## Value Flag.Codes Flags
## 0 0 0# Visualisations for Structure
str(my_data) ## 'data.frame': 135628 obs. of 15 variables:
## $ COUNTRY : chr "CZE" "CZE" "CZE" "NLD" ...
## $ Country : chr "Czechia" "Czechia" "Czechia" "Netherlands" ...
## $ WEEK : int 46 46 46 3 3 3 3 37 37 37 ...
## $ Week.number: int 46 46 46 3 3 3 3 37 37 37 ...
## $ GENDER : chr "TOTAL" "TOTAL" "TOTAL" "TOTAL" ...
## $ Gender : chr "Total" "Total" "Total" "Total" ...
## $ AGE : chr "Y0T44" "Y0T44" "Y0T44" "Y_GE65" ...
## $ Age : chr "0 to 44" "0 to 44" "0 to 44" "65 and over" ...
## $ VARIABLE : chr "EXCESSNB" "EXCESSNB" "EXCESSNB" "EXCESSNB" ...
## $ Variable : chr "Excess deaths (number)" "Excess deaths (number)" "Excess deaths (number)" "Excess deaths (number)" ...
## $ YEAR : int 2020 2021 2022 2020 2021 2022 2023 2020 2021 2022 ...
## $ Year : int 2020 2021 2022 2020 2021 2022 2023 2020 2021 2022 ...
## $ Value : num 2.2 8.2 4.2 -127.4 569.6 ...
## $ Flag.Codes : chr "" "" "" "" ...
## $ Flags : chr "" "" "" "" ...# Histograms (for numeric columns) with bins = 30
my_data %>%
select_if(is.numeric) %>%
pivot_longer(cols = everything(), names_to = "key", values_to = "value") %>%
ggplot(aes(value)) +
geom_histogram(bins = 30) +
facet_wrap(~key, scales = 'free')
# Box plots (for numeric columns)
my_data %>%
select_if(is.numeric) %>%
pivot_longer(cols = everything(), names_to = "key", values_to = "value") %>%
ggplot(aes(key, value)) +
geom_boxplot()
# Scatter plots (for pairs of numeric columns)
pairs(my_data[, sapply(my_data, is.numeric)])