Chapter 12 Assignment 3
Abbigale Mckay
2/24/2020
library(tidyverse)## ── Attaching packages ───── tidyverse 1.3.0 ──## ✓ ggplot2 3.2.1 ✓ purrr 0.3.3
## ✓ tibble 2.1.3 ✓ dplyr 0.8.3
## ✓ tidyr 1.0.0 ✓ stringr 1.4.0
## ✓ readr 1.3.1 ✓ forcats 0.4.0## ── Conflicts ──────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()table1## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583This code shows table 1, which has 4 variables: country, year, cases, and population.
table2## # A tibble: 12 x 4
## country year type count
## <chr> <int> <chr> <int>
## 1 Afghanistan 1999 cases 745
## 2 Afghanistan 1999 population 19987071
## 3 Afghanistan 2000 cases 2666
## 4 Afghanistan 2000 population 20595360
## 5 Brazil 1999 cases 37737
## 6 Brazil 1999 population 172006362
## 7 Brazil 2000 cases 80488
## 8 Brazil 2000 population 174504898
## 9 China 1999 cases 212258
## 10 China 1999 population 1272915272
## 11 China 2000 cases 213766
## 12 China 2000 population 1280428583This shows table 2 which shows the same data in a different way.
table3## # A tibble: 6 x 3
## country year rate
## * <chr> <int> <chr>
## 1 Afghanistan 1999 745/19987071
## 2 Afghanistan 2000 2666/20595360
## 3 Brazil 1999 37737/172006362
## 4 Brazil 2000 80488/174504898
## 5 China 1999 212258/1272915272
## 6 China 2000 213766/1280428583This shows table 3 which again shows the variables in a different way.
table4a## # A tibble: 3 x 3
## country `1999` `2000`
## * <chr> <int> <int>
## 1 Afghanistan 745 2666
## 2 Brazil 37737 80488
## 3 China 212258 213766This shows table 4 which is 1 tibble.
table4b## # A tibble: 3 x 3
## country `1999` `2000`
## * <chr> <int> <int>
## 1 Afghanistan 19987071 20595360
## 2 Brazil 172006362 174504898
## 3 China 1272915272 1280428583This shows table which is tibble 2 of 4.
table1 %>%
mutate(rate = cases / population * 10000)## # A tibble: 6 x 5
## country year cases population rate
## <chr> <int> <int> <int> <dbl>
## 1 Afghanistan 1999 745 19987071 0.373
## 2 Afghanistan 2000 2666 20595360 1.29
## 3 Brazil 1999 37737 172006362 2.19
## 4 Brazil 2000 80488 174504898 4.61
## 5 China 1999 212258 1272915272 1.67
## 6 China 2000 213766 1280428583 1.67This code shows the rate per 10,000.
# Compute cases per year
table1 %>%
count(year, wt = cases)## # A tibble: 2 x 2
## year n
## <int> <int>
## 1 1999 250740
## 2 2000 296920This code computes the cases per year.
# Visualise changes over time
library(ggplot2)
ggplot(table1, aes(year, cases)) +
geom_line(aes(group = country), colour = "grey50") +
geom_point(aes(colour = country))
This code shhows a visual of changes ovre time in cases per year.
table4a## # A tibble: 3 x 3
## country `1999` `2000`
## * <chr> <int> <int>
## 1 Afghanistan 745 2666
## 2 Brazil 37737 80488
## 3 China 212258 213766This shows table 4 shows values of variables instead of names.
table4a %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")## # A tibble: 6 x 3
## country year cases
## <chr> <chr> <int>
## 1 Afghanistan 1999 745
## 2 Afghanistan 2000 2666
## 3 Brazil 1999 37737
## 4 Brazil 2000 80488
## 5 China 1999 212258
## 6 China 2000 213766This code drops the pivoted columns and shows the near year and case columns.
table4b %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "population")## # A tibble: 6 x 3
## country year population
## <chr> <chr> <int>
## 1 Afghanistan 1999 19987071
## 2 Afghanistan 2000 20595360
## 3 Brazil 1999 172006362
## 4 Brazil 2000 174504898
## 5 China 1999 1272915272
## 6 China 2000 1280428583This code tidies the data.
tidy4a <- table4a %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "cases")
tidy4b <- table4b %>%
pivot_longer(c(`1999`, `2000`), names_to = "year", values_to = "population")
left_join(tidy4a, tidy4b)## Joining, by = c("country", "year")## # A tibble: 6 x 4
## country year cases population
## <chr> <chr> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583This code combines the tidied versions of table 4a and table 4b.
table2## # A tibble: 12 x 4
## country year type count
## <chr> <int> <chr> <int>
## 1 Afghanistan 1999 cases 745
## 2 Afghanistan 1999 population 19987071
## 3 Afghanistan 2000 cases 2666
## 4 Afghanistan 2000 population 20595360
## 5 Brazil 1999 cases 37737
## 6 Brazil 1999 population 172006362
## 7 Brazil 2000 cases 80488
## 8 Brazil 2000 population 174504898
## 9 China 1999 cases 212258
## 10 China 1999 population 1272915272
## 11 China 2000 cases 213766
## 12 China 2000 population 1280428583This shows table 2 which scatters a country in a year across two rows.
table2 %>%
pivot_wider(names_from = type, values_from = count)## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583This makes the table longer.
table3## # A tibble: 6 x 3
## country year rate
## * <chr> <int> <chr>
## 1 Afghanistan 1999 745/19987071
## 2 Afghanistan 2000 2666/20595360
## 3 Brazil 1999 37737/172006362
## 4 Brazil 2000 80488/174504898
## 5 China 1999 212258/1272915272
## 6 China 2000 213766/1280428583This shows table 3.
table3 %>%
separate(rate, into = c("cases", "population"))## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <chr> <chr>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583This seperates cases and population variables.
table3 %>%
separate(rate, into = c("cases", "population"), convert = TRUE)## # A tibble: 6 x 4
## country year cases population
## <chr> <int> <int> <int>
## 1 Afghanistan 1999 745 19987071
## 2 Afghanistan 2000 2666 20595360
## 3 Brazil 1999 37737 172006362
## 4 Brazil 2000 80488 174504898
## 5 China 1999 212258 1272915272
## 6 China 2000 213766 1280428583This rewrites the code above.
table3 %>%
separate(year, into = c("century", "year"), sep = 2)## # A tibble: 6 x 4
## country century year rate
## <chr> <chr> <chr> <chr>
## 1 Afghanistan 19 99 745/19987071
## 2 Afghanistan 20 00 2666/20595360
## 3 Brazil 19 99 37737/172006362
## 4 Brazil 20 00 80488/174504898
## 5 China 19 99 212258/1272915272
## 6 China 20 00 213766/1280428583This converts them into better types.
table5 %>%
unite(new, century, year)## # A tibble: 6 x 3
## country new rate
## <chr> <chr> <chr>
## 1 Afghanistan 19_99 745/19987071
## 2 Afghanistan 20_00 2666/20595360
## 3 Brazil 19_99 37737/172006362
## 4 Brazil 20_00 80488/174504898
## 5 China 19_99 212258/1272915272
## 6 China 20_00 213766/1280428583This shows table 5.
table5 %>%
unite(new, century, year, sep = "")## # A tibble: 6 x 3
## country new rate
## <chr> <chr> <chr>
## 1 Afghanistan 1999 745/19987071
## 2 Afghanistan 2000 2666/20595360
## 3 Brazil 1999 37737/172006362
## 4 Brazil 2000 80488/174504898
## 5 China 1999 212258/1272915272
## 6 China 2000 213766/1280428583This code places an undersocre between values from different columns.
stocks <- tibble(
year = c(2015, 2015, 2015, 2015, 2016, 2016, 2016),
qtr = c( 1, 2, 3, 4, 2, 3, 4),
return = c(1.88, 0.59, 0.35, NA, 0.92, 0.17, 2.66)
)This shhows a table with missing values.
stocks %>%
pivot_wider(names_from = year, values_from = return)## # A tibble: 4 x 3
## qtr `2015` `2016`
## <dbl> <dbl> <dbl>
## 1 1 1.88 NA
## 2 2 0.59 0.92
## 3 3 0.35 0.17
## 4 4 NA 2.66this code makes the implicit missing value explicit by putting years into columns.
stocks %>%
pivot_wider(names_from = year, values_from = return) %>%
pivot_longer(
cols = c(`2015`, `2016`),
names_to = "year",
values_to = "return",
values_drop_na = TRUE
)## # A tibble: 6 x 3
## qtr year return
## <dbl> <chr> <dbl>
## 1 1 2015 1.88
## 2 2 2015 0.59
## 3 2 2016 0.92
## 4 3 2015 0.35
## 5 3 2016 0.17
## 6 4 2016 2.66This turns explicit missing values implicit.
stocks %>%
complete(year, qtr)## # A tibble: 8 x 3
## year qtr return
## <dbl> <dbl> <dbl>
## 1 2015 1 1.88
## 2 2015 2 0.59
## 3 2015 3 0.35
## 4 2015 4 NA
## 5 2016 1 NA
## 6 2016 2 0.92
## 7 2016 3 0.17
## 8 2016 4 2.66This takes a set of columns finds all the unique combinations and ensures the original dataset contains all these values filling in explicit NA where needed.
treatment <- tribble(
~ person, ~ treatment, ~response,
"Derrick Whitmore", 1, 7,
NA, 2, 10,
NA, 3, 9,
"Katherine Burke", 1, 4
)
treatment %>%
fill(person)## # A tibble: 4 x 3
## person treatment response
## <chr> <dbl> <dbl>
## 1 Derrick Whitmore 1 7
## 2 Derrick Whitmore 2 10
## 3 Derrick Whitmore 3 9
## 4 Katherine Burke 1 4This demonstartes when missing values are just where the previous value should be carried down.And then carries thhe mission person down.
tidyr::who## # A tibble: 7,240 x 60
## country iso2 iso3 year new_sp_m014 new_sp_m1524 new_sp_m2534 new_sp_m3544
## <chr> <chr> <chr> <int> <int> <int> <int> <int>
## 1 Afghan… AF AFG 1980 NA NA NA NA
## 2 Afghan… AF AFG 1981 NA NA NA NA
## 3 Afghan… AF AFG 1982 NA NA NA NA
## 4 Afghan… AF AFG 1983 NA NA NA NA
## 5 Afghan… AF AFG 1984 NA NA NA NA
## 6 Afghan… AF AFG 1985 NA NA NA NA
## 7 Afghan… AF AFG 1986 NA NA NA NA
## 8 Afghan… AF AFG 1987 NA NA NA NA
## 9 Afghan… AF AFG 1988 NA NA NA NA
## 10 Afghan… AF AFG 1989 NA NA NA NA
## # … with 7,230 more rows, and 52 more variables: new_sp_m4554 <int>,
## # new_sp_m5564 <int>, new_sp_m65 <int>, new_sp_f014 <int>,
## # new_sp_f1524 <int>, new_sp_f2534 <int>, new_sp_f3544 <int>,
## # new_sp_f4554 <int>, new_sp_f5564 <int>, new_sp_f65 <int>,
## # new_sn_m014 <int>, new_sn_m1524 <int>, new_sn_m2534 <int>,
## # new_sn_m3544 <int>, new_sn_m4554 <int>, new_sn_m5564 <int>,
## # new_sn_m65 <int>, new_sn_f014 <int>, new_sn_f1524 <int>,
## # new_sn_f2534 <int>, new_sn_f3544 <int>, new_sn_f4554 <int>,
## # new_sn_f5564 <int>, new_sn_f65 <int>, new_ep_m014 <int>,
## # new_ep_m1524 <int>, new_ep_m2534 <int>, new_ep_m3544 <int>,
## # new_ep_m4554 <int>, new_ep_m5564 <int>, new_ep_m65 <int>,
## # new_ep_f014 <int>, new_ep_f1524 <int>, new_ep_f2534 <int>,
## # new_ep_f3544 <int>, new_ep_f4554 <int>, new_ep_f5564 <int>,
## # new_ep_f65 <int>, newrel_m014 <int>, newrel_m1524 <int>,
## # newrel_m2534 <int>, newrel_m3544 <int>, newrel_m4554 <int>,
## # newrel_m5564 <int>, newrel_m65 <int>, newrel_f014 <int>,
## # newrel_f1524 <int>, newrel_f2534 <int>, newrel_f3544 <int>,
## # newrel_f4554 <int>, newrel_f5564 <int>, newrel_f65 <int>This shows the database of TB cases broken down by year, country, age, gender, and diagnosis method.
who1 <- who %>%
pivot_longer(
cols = new_sp_m014:newrel_f65,
names_to = "key",
values_to = "cases",
values_drop_na = TRUE
)
who1## # A tibble: 76,046 x 6
## country iso2 iso3 year key cases
## <chr> <chr> <chr> <int> <chr> <int>
## 1 Afghanistan AF AFG 1997 new_sp_m014 0
## 2 Afghanistan AF AFG 1997 new_sp_m1524 10
## 3 Afghanistan AF AFG 1997 new_sp_m2534 6
## 4 Afghanistan AF AFG 1997 new_sp_m3544 3
## 5 Afghanistan AF AFG 1997 new_sp_m4554 5
## 6 Afghanistan AF AFG 1997 new_sp_m5564 2
## 7 Afghanistan AF AFG 1997 new_sp_m65 0
## 8 Afghanistan AF AFG 1997 new_sp_f014 5
## 9 Afghanistan AF AFG 1997 new_sp_f1524 38
## 10 Afghanistan AF AFG 1997 new_sp_f2534 36
## # … with 76,036 more rowsThis focuses on the values thhat are present.
who1 %>%
count(key)## # A tibble: 56 x 2
## key n
## <chr> <int>
## 1 new_ep_f014 1032
## 2 new_ep_f1524 1021
## 3 new_ep_f2534 1021
## 4 new_ep_f3544 1021
## 5 new_ep_f4554 1017
## 6 new_ep_f5564 1017
## 7 new_ep_f65 1014
## 8 new_ep_m014 1038
## 9 new_ep_m1524 1026
## 10 new_ep_m2534 1020
## # … with 46 more rowsThis counts the values in the new key column.
who2 <- who1 %>%
mutate(names_from = stringr::str_replace(key, "newrel", "new_rel"))
who2## # A tibble: 76,046 x 7
## country iso2 iso3 year key cases names_from
## <chr> <chr> <chr> <int> <chr> <int> <chr>
## 1 Afghanistan AF AFG 1997 new_sp_m014 0 new_sp_m014
## 2 Afghanistan AF AFG 1997 new_sp_m1524 10 new_sp_m1524
## 3 Afghanistan AF AFG 1997 new_sp_m2534 6 new_sp_m2534
## 4 Afghanistan AF AFG 1997 new_sp_m3544 3 new_sp_m3544
## 5 Afghanistan AF AFG 1997 new_sp_m4554 5 new_sp_m4554
## 6 Afghanistan AF AFG 1997 new_sp_m5564 2 new_sp_m5564
## 7 Afghanistan AF AFG 1997 new_sp_m65 0 new_sp_m65
## 8 Afghanistan AF AFG 1997 new_sp_f014 5 new_sp_f014
## 9 Afghanistan AF AFG 1997 new_sp_f1524 38 new_sp_f1524
## 10 Afghanistan AF AFG 1997 new_sp_f2534 36 new_sp_f2534
## # … with 76,036 more rowsThis makes all variable names constant.
who3 <- who2 %>%
separate(key, c("new", "type", "sexage"), sep = "_")## Warning: Expected 3 pieces. Missing pieces filled with `NA` in 2580 rows [243,
## 244, 679, 680, 681, 682, 683, 684, 685, 686, 687, 688, 689, 690, 691, 692, 903,
## 904, 905, 906, ...].This seperates the values at each underscore.
who3 %>%
count(new)## # A tibble: 2 x 2
## new n
## <chr> <int>
## 1 new 73466
## 2 newrel 2580who4 <- who3 %>%
select(-new, -iso2, -iso3)This drops the new column into the dataset.
who5 <- who4 %>%
separate(sexage, c("sex", "age"), sep = 1)
who5## # A tibble: 76,046 x 7
## country year type sex age cases names_from
## <chr> <int> <chr> <chr> <chr> <int> <chr>
## 1 Afghanistan 1997 sp m 014 0 new_sp_m014
## 2 Afghanistan 1997 sp m 1524 10 new_sp_m1524
## 3 Afghanistan 1997 sp m 2534 6 new_sp_m2534
## 4 Afghanistan 1997 sp m 3544 3 new_sp_m3544
## 5 Afghanistan 1997 sp m 4554 5 new_sp_m4554
## 6 Afghanistan 1997 sp m 5564 2 new_sp_m5564
## 7 Afghanistan 1997 sp m 65 0 new_sp_m65
## 8 Afghanistan 1997 sp f 014 5 new_sp_f014
## 9 Afghanistan 1997 sp f 1524 38 new_sp_f1524
## 10 Afghanistan 1997 sp f 2534 36 new_sp_f2534
## # … with 76,036 more rowsThis seperates sexage into sex and age.