The codes below are all taken from websites listed in the Reference Section. This post is to let me practice on the past exam questions.
Load required packages
Brendan Cullen’s website
https://tidyverse-exam-v2-solutions.netlify.app/
Basic Operations
# Read in person.csv and store result in a tibble called person
person <- read_csv("https://tidyverse-exam-v2-solutions.netlify.app/person.csv")
person
# A tibble: 5 x 3
person_id personal_name family_name
<chr> <chr> <chr>
1 dyer William Dyer
2 pb Frank Pabodie
3 lake Anderson Lake
4 roe Valentina Roerich
5 danforth Frank Danforth # Create a tibble containing only family name and personal names.
person %>%
select(family_name, personal_name)
# A tibble: 5 x 2
family_name personal_name
<chr> <chr>
1 Dyer William
2 Pabodie Frank
3 Lake Anderson
4 Roerich Valentina
5 Danforth Frank # Create a new tibble containing only the rows in which family names come before the letter M.
person %>%
filter(family_name < "M")
# A tibble: 3 x 3
person_id personal_name family_name
<chr> <chr> <chr>
1 dyer William Dyer
2 lake Anderson Lake
3 danforth Frank Danforth # Display all the rows in person sorted by family name length with the longest name first
person
# A tibble: 5 x 3
person_id personal_name family_name
<chr> <chr> <chr>
1 dyer William Dyer
2 pb Frank Pabodie
3 lake Anderson Lake
4 roe Valentina Roerich
5 danforth Frank Danforth person %>%
arrange(desc(str_length(family_name)))
# A tibble: 5 x 3
person_id personal_name family_name
<chr> <chr> <chr>
1 danforth Frank Danforth
2 pb Frank Pabodie
3 roe Valentina Roerich
4 dyer William Dyer
5 lake Anderson Lake Cleaning and counting
# Read the file measurement.csv to create a tibble called measurements
measurements <- read_csv("https://tidyverse-exam-v2-solutions.netlify.app/measurements.csv")
glimpse(measurements)
Rows: 21
Columns: 4
$ visit_id <dbl> 619, 619, 622, 622, 734, 734, 734, 735, 735, 735, 7…
$ visitor <chr> "dyer", "dyer", "dyer", "dyer", "pb", "lake", "pb",…
$ quantity <chr> "rad", "sal", "rad", "sal", "rad", "sal", "temp", "…
$ reading <dbl> 9.82, 0.13, 7.80, 0.09, 8.41, 0.05, -21.50, 7.22, 0…# Create a tibble containing only rows where none of the values are NA and save in a tibble called cleaned
cleaned <- measurements %>%
drop_na()
cleaned
# A tibble: 18 x 4
visit_id visitor quantity reading
<dbl> <chr> <chr> <dbl>
1 619 dyer rad 9.82
2 619 dyer sal 0.13
3 622 dyer rad 7.8
4 622 dyer sal 0.09
5 734 pb rad 8.41
6 734 lake sal 0.05
7 734 pb temp -21.5
8 735 pb rad 7.22
9 751 pb rad 4.35
10 751 pb temp -18.5
11 752 lake rad 2.19
12 752 lake sal 0.09
13 752 lake temp -16
14 752 roe sal 41.6
15 837 lake rad 1.46
16 837 lake sal 0.21
17 837 roe sal 22.5
18 844 roe rad 11.2 # Count the number of measurements of each type of quantity in cleaned. Your result should have one row for each quantity "rad", "sal", "temp"
cleaned %>%
group_by(quantity) %>%
summarise(n = n())
# A tibble: 3 x 2
quantity n
<chr> <int>
1 rad 8
2 sal 7
3 temp 3# Display the minimum and maximum value or reading separately for each quantity in cleaned
cleaned %>%
group_by(quantity) %>%
summarise(min_reading = min(reading),
max_reading = max(reading))
# A tibble: 3 x 3
quantity min_reading max_reading
<chr> <dbl> <dbl>
1 rad 1.46 11.2
2 sal 0.05 41.6
3 temp -21.5 -16 # Create a tibble in which all salinity readings greater than 1 are divided by 100.
cleaned %>%
mutate(reading = case_when(
quantity == "sal" & reading > 1 ~ reading/100,
T ~ reading
))
# A tibble: 18 x 4
visit_id visitor quantity reading
<dbl> <chr> <chr> <dbl>
1 619 dyer rad 9.82
2 619 dyer sal 0.13
3 622 dyer rad 7.8
4 622 dyer sal 0.09
5 734 pb rad 8.41
6 734 lake sal 0.05
7 734 pb temp -21.5
8 735 pb rad 7.22
9 751 pb rad 4.35
10 751 pb temp -18.5
11 752 lake rad 2.19
12 752 lake sal 0.09
13 752 lake temp -16
14 752 roe sal 0.416
15 837 lake rad 1.46
16 837 lake sal 0.21
17 837 roe sal 0.225
18 844 roe rad 11.2 Combining Data
# Read visited.csv and drop rows containing any NAs, assigning the results to a new tibble called visited
visited <- read_csv("https://tidyverse-exam-v2-solutions.netlify.app/visited.csv") %>%
drop_na()
visited
# A tibble: 7 x 3
visit_id site_id visit_date
<dbl> <chr> <date>
1 619 DR-1 1927-02-08
2 622 DR-1 1927-02-10
3 734 DR-3 1930-01-07
4 735 DR-3 1930-01-12
5 751 DR-3 1930-02-26
6 837 MSK-4 1932-01-14
7 844 DR-1 1932-03-22# Use an innerjoin to combine visited with cleaned using visit_id for match
cleaned
# A tibble: 18 x 4
visit_id visitor quantity reading
<dbl> <chr> <chr> <dbl>
1 619 dyer rad 9.82
2 619 dyer sal 0.13
3 622 dyer rad 7.8
4 622 dyer sal 0.09
5 734 pb rad 8.41
6 734 lake sal 0.05
7 734 pb temp -21.5
8 735 pb rad 7.22
9 751 pb rad 4.35
10 751 pb temp -18.5
11 752 lake rad 2.19
12 752 lake sal 0.09
13 752 lake temp -16
14 752 roe sal 41.6
15 837 lake rad 1.46
16 837 lake sal 0.21
17 837 roe sal 22.5
18 844 roe rad 11.2 combined <- visited %>%
inner_join(cleaned, by = "visit_id")
combined
# A tibble: 14 x 6
visit_id site_id visit_date visitor quantity reading
<dbl> <chr> <date> <chr> <chr> <dbl>
1 619 DR-1 1927-02-08 dyer rad 9.82
2 619 DR-1 1927-02-08 dyer sal 0.13
3 622 DR-1 1927-02-10 dyer rad 7.8
4 622 DR-1 1927-02-10 dyer sal 0.09
5 734 DR-3 1930-01-07 pb rad 8.41
6 734 DR-3 1930-01-07 lake sal 0.05
7 734 DR-3 1930-01-07 pb temp -21.5
8 735 DR-3 1930-01-12 pb rad 7.22
9 751 DR-3 1930-02-26 pb rad 4.35
10 751 DR-3 1930-02-26 pb temp -18.5
11 837 MSK-4 1932-01-14 lake rad 1.46
12 837 MSK-4 1932-01-14 lake sal 0.21
13 837 MSK-4 1932-01-14 roe sal 22.5
14 844 DR-1 1932-03-22 roe rad 11.2 # find the highest rad reading at each site.
max_rad <- combined %>%
filter(quantity == "rad") %>%
group_by(site_id) %>%
summarise(max_rad = max(reading))
# Find the date of the highest radiation reading at each site
combined %>%
filter(quantity == "rad") %>%
group_by(site_id, visit_date) %>%
summarize(max_rad = max(reading)) %>%
semi_join(max_rad) %>% # returns all rows from x with a match in y
select(visit_date, everything())
# A tibble: 3 x 3
# Groups: site_id [3]
visit_date site_id max_rad
<date> <chr> <dbl>
1 1932-03-22 DR-1 11.2
2 1930-01-07 DR-3 8.41
3 1932-01-14 MSK-4 1.46Functional Programming
# Write a function called summarize_table that takes a title string and a tibble as input and returns a string that says something like "title has n rows and n columns
summarize_table <- function(title, df) {
nrow <- nrow(df)
ncol <- ncol(df)
glue::glue("{title} has {nrow} rows and {ncol} columns." )
}
summarize_table("mtcars", mtcars)
mtcars has 32 rows and 11 columns.# Write another function called show_columns that takes a string and a tibble as input and returns a string that says something like, “table has columns name, name, name”. For example, show_columns('person', person) should return the string "person has columns person_id, personal_name, family_name".
show_columns <- function(title, df) {
col_names <- names(df) %>%
str_c(collapse = ", ")
glue::glue("{title} has columns {col_names}")
}
show_columns('person', person)
person has columns person_id, personal_name, family_name# The function long_name checks whether a string is longer than 4 characters. Use this function and a function from purrr to create a logical vector that contains the value TRUE where family names in the tibble person are longer than 4 characters, and FALSE where they are 4 characters or less.
long_name <- function(name) {
stringr::str_length(name) > 4
}
person %>%
mutate(long_family_name = map_lgl(family_name, long_name))
# A tibble: 5 x 4
person_id personal_name family_name long_family_name
<chr> <chr> <chr> <lgl>
1 dyer William Dyer FALSE
2 pb Frank Pabodie TRUE
3 lake Anderson Lake FALSE
4 roe Valentina Roerich TRUE
5 danforth Frank Danforth TRUE Marly Gotti’s website
https://marlycormar.github.io/tidyverse_sample_exam/sample_exam_sols/sols.html
Q1
The file at_health_facilities.csv contains a tidy dataset with four columns:
The ISO3 code of the country that reported data. The year for which data was reported. The percentage of HIV-positive children born to HIV-positive mothers age 15–17. The percentage of HIV-positive children born to HIV-positive mothers age 20–34. Please answer the following questions:
How many countries reported data? What is the difference between the minimum and maximum year with valid data for each country? How many countries reported data in 3 or more years? Which countries reported 100% incidence for at least one year in either age group?
hiv <- read_csv("https://education.rstudio.com/blog/2020/02/instructor-certification-exams/at_health_facilities.csv") %>%
janitor::clean_names()
glimpse(hiv)
Rows: 225
Columns: 4
$ iso3 <chr> "AFG", "ALB", "ALB", "ARG", "ARM", "ARM", "ARM", "…
$ year <dbl> 2010, 2005, 2008, 2012, 2000, 2005, 2010, 2006, 20…
$ age_15_17 <dbl> 33, 98, 98, 100, 93, 99, 100, 81, 12, 16, 19, 31, …
$ age_20_34 <chr> "29", "96", "98", "100", "87", "100", "100", "87",…[1] 100# what is the difference between min and max year with valid data for each country?
# age 20-34 has some dashes to be filtered out
hiv %>%
filter(age_20_34 != "-") %>%
group_by(iso3) %>%
summarise(diff = max(year) - min(year))
# A tibble: 100 x 2
iso3 diff
<chr> <dbl>
1 AFG 0
2 ALB 3
3 ARG 0
4 ARM 10
5 AZE 0
6 BDI 5
7 BEN 10
8 BFA 7
9 BGD 8
10 BIH 5
# … with 90 more rows# how many countries reported data in 3 or more years?
hiv %>%
group_by(iso3) %>%
summarise(years_count = n_distinct(year)) %>%
filter(years_count >=3) # 34 countries
# A tibble: 34 x 2
iso3 years_count
<chr> <int>
1 ARM 3
2 BEN 3
3 BFA 3
4 BGD 6
5 CMR 3
6 COD 3
7 COL 3
8 DOM 3
9 EGY 5
10 ETH 3
# … with 24 more rows# which countries reported 100% incidence rate for at least one year in either age group?
hiv %>%
filter(age_15_17 == 100 | age_20_34 == 100) %>%
distinct(iso3) # 18 countries
# A tibble: 18 x 1
iso3
<chr>
1 ARG
2 ARM
3 BRB
4 BLR
5 BIH
6 CUB
7 DOM
8 JAM
9 KAZ
10 KGZ
11 MKD
12 MDA
13 MNE
14 LCA
15 SRB
16 THA
17 UKR
18 URY Q2
A student has sent you the file rmd-country-profile.Rmd, which is an R Markdown document analyzing the data in at_health_facilities.csv for Bangladesh. They could not knit the file, and are providing you with the raw .Rmd file instead of a rendered file.
Go through the file, fixing things that are preventing it from knitting cleanly. Change the two lines of bold text to H2-level headers to organize the document, and add a table of contents. Convert this R Markdown report for Bangladesh into a parameterized report with the country’s iso3 code as its parameter. Knit a new country profile for Egypt (ISO3 code “EGY”).
Q3
infant_hiv <- read_csv("https://education.rstudio.com/blog/2020/02/instructor-certification-exams/infant_hiv.csv")
# tidy the data into 3 col: iso3, year, state, number
tidy <- infant_hiv %>%
pivot_longer(!ISO3,
names_to = c("year", "state"),
names_pattern = "(.*) (.*)") %>%
mutate(value = case_when(
value == "-" | value == ">95%" ~NA_character_,
TRUE ~ str_replace(value, pattern = "%", replacement = "")
))
tidy
# A tibble: 5,184 x 4
ISO3 year state value
<chr> <chr> <chr> <chr>
1 AFG 2009 est <NA>
2 AFG 2009 hi <NA>
3 AFG 2009 lo <NA>
4 AFG 2010 est <NA>
5 AFG 2010 hi <NA>
6 AFG 2010 lo <NA>
7 AFG 2011 est <NA>
8 AFG 2011 hi <NA>
9 AFG 2011 lo <NA>
10 AFG 2012 est <NA>
# … with 5,174 more rows# write the function
tidy_data <- function(file) {
# Import data
raw_data <- read_csv(file)
# Tidy data
tidy <- raw_data %>%
pivot_longer(!ISO3,
names_to = c("year", "state"),
names_pattern = "(.*) (.*)") %>%
mutate(value = case_when(
value == "-" | value == ">95%" ~NA_character_,
TRUE ~ str_replace(value, pattern = "%", replacement = "")
))
tidy
}
tidy_data("https://education.rstudio.com/blog/2020/02/instructor-certification-exams/infant_hiv.csv")
# A tibble: 5,184 x 4
ISO3 year state value
<chr> <chr> <chr> <chr>
1 AFG 2009 est <NA>
2 AFG 2009 hi <NA>
3 AFG 2009 lo <NA>
4 AFG 2010 est <NA>
5 AFG 2010 hi <NA>
6 AFG 2010 lo <NA>
7 AFG 2011 est <NA>
8 AFG 2011 hi <NA>
9 AFG 2011 lo <NA>
10 AFG 2012 est <NA>
# … with 5,174 more rowsQ4
ranking <- read_csv("https://education.rstudio.com/blog/2020/02/instructor-certification-exams/ranking.csv")
ranking %>%
group_by(item) %>%
count(rank) %>%
pivot_wider(names_from = rank,
values_from = n) %>%
mutate(num = sum(positive, negative, indifferent, na.rm = T)) %>%
mutate_at(vars(-item, -num), .funs = list(~ round(./num, digits = 2))) %>%
ggplot(aes(negative, positive, size = num)) +
geom_point(aes(alpha = 0.25)) +
geom_smooth(method = "lm")
References
https://tidyverse-exam-v2-solutions.netlify.app/