## ---- message=FALSE, warning=FALSE, cache=FALSE-------- library(tidyverse) ## ---- echo=FALSE, cache=FALSE-------------------------- library(dslabs) head(murders) ## ---- echo=FALSE--------------------------------------- tidy_data <- gapminder |> filter(country %in% c("South Korea", "Germany") & !is.na(fertility)) |> select(country, year, fertility) head(tidy_data, 6) ## ---- echo=FALSE, message=FALSE------------------------ path <- system.file("extdata", package = "dslabs") filename <- file.path(path, "fertility-two-countries-example.csv") wide_data <- read_csv(filename) select(wide_data, country, `1960`:`1962`) |> as.data.frame() ## ---- message=FALSE------------------------------------ murders <- mutate(murders, rate = total/population*100000) ## ------------------------------------------------------ head(murders) ## ------------------------------------------------------ filter(murders, rate <= 0.71) ## ------------------------------------------------------ new_dataframe <- select(murders, state, region, rate) filter(new_dataframe, rate <= 0.71) ## ------------------------------------------------------ new_dataframe <- select(murders, where(is.numeric)) names(new_dataframe) ## ------------------------------------------------------ new_dataframe <- select(murders, starts_with("r")) names(new_dataframe) ## ------------------------------------------------------ ## mutate(murders, population = log10(population)) ## ------------------------------------------------------ ## mutate(murders, across(c(population, total), log10)) ## ------------------------------------------------------ ## mutate(murders, across(where(is.numeric), log10)) ## ------------------------------------------------------ ## mutate(murders, across(where(is.character), tolower)) ## ------------------------------------------------------ murders |> select(state, region, rate) |> filter(rate <= 0.71) ## ------------------------------------------------------ 16 |> sqrt() ## ------------------------------------------------------ 16 |> sqrt() |> log2() ## ------------------------------------------------------ 16 |> sqrt() |> log(base = 2) ## ---- eval=FALSE--------------------------------------- murders |> select(state, region, rate) |> filter(rate <= 0.71) ## ---- message=FALSE, echo=FALSE------------------------ library(tidyverse) ## ------------------------------------------------------ library(dplyr) library(dslabs) ## ------------------------------------------------------ s <- heights |> filter(sex == "Female") |> summarize(average = mean(height), standard_deviation = sd(height)) s ## ------------------------------------------------------ s$average s$standard_deviation ## ------------------------------------------------------ murders <- murders |> mutate(rate = total/population*100000) ## ------------------------------------------------------ murders |> summarize(rate = mean(rate)) ## ------------------------------------------------------ us_murder_rate <- murders |> summarize(rate = sum(total)/sum(population)*100000) us_murder_rate ## ------------------------------------------------------ heights |> summarize(median = median(height), min = min(height), max = max(height)) ## ------------------------------------------------------ heights |> reframe(quantiles = quantile(height, c(0.5, 0, 1))) ## ------------------------------------------------------ median_min_max <- function(x){ qs <- quantile(x, c(0.5, 0, 1)) data.frame(median = qs[1], min = qs[2], max = qs[3]) } ## ------------------------------------------------------ heights |> summarize(median_min_max(height)) ## ------------------------------------------------------ heights |> group_by(sex) ## ------------------------------------------------------ heights |> group_by(sex) |> summarize(average = mean(height), standard_deviation = sd(height)) ## ------------------------------------------------------ murders |> group_by(region) |> summarize(median_min_max(rate)) ## ------------------------------------------------------ class(us_murder_rate) ## ------------------------------------------------------ us_murder_rate <- murders |> summarize(rate = sum(total)/sum(population)*100000) |> pull(rate) us_murder_rate ## ------------------------------------------------------ class(us_murder_rate) ## ------------------------------------------------------ murders |> arrange(population) |> head() ## ---- eval=FALSE--------------------------------------- ## murders |> arrange(desc(rate)) ## ------------------------------------------------------ murders |> arrange(region, rate) |> head() ## ------------------------------------------------------ murders |> top_n(5, rate) ## ------------------------------------------------------ murders |> group_by(region) ## ------------------------------------------------------ murders |> group_by(region) |> class() ## ------------------------------------------------------ class(murders[,4]) ## ------------------------------------------------------ class(as_tibble(murders)[,4]) ## ------------------------------------------------------ class(as_tibble(murders)$population) ## ------------------------------------------------------ murders$Population ## ------------------------------------------------------ as_tibble(murders)$Population ## ------------------------------------------------------ tibble(id = c(1, 2, 3), func = c(mean, median, sd)) ## ------------------------------------------------------ grades <- tibble(names = c("John", "Juan", "Jean", "Yao"), exam_1 = c(95, 80, 90, 85), exam_2 = c(90, 85, 85, 90)) ## ------------------------------------------------------ grades <- data.frame(names = c("John", "Juan", "Jean", "Yao"), exam_1 = c(95, 80, 90, 85), exam_2 = c(90, 85, 85, 90)) ## ------------------------------------------------------ as_tibble(grades) |> class() ## ---- eval=FALSE--------------------------------------- ## log(8, base = 2) ## 2 |> log(8, base = _) ## 2 %>% log(8, base = .) ## ------------------------------------------------------ compute_s_n <- function(n) { sum(1:n) } n <- 1:25 s_n <- sapply(n, compute_s_n) ## ------------------------------------------------------ library(purrr) s_n <- map(n, compute_s_n) class(s_n) ## ------------------------------------------------------ s_n <- map_dbl(n, compute_s_n) class(s_n) ## ---- eval=FALSE--------------------------------------- ## s_n <- map_df(n, compute_s_n) ## ------------------------------------------------------ compute_s_n <- function(n) { tibble(sum = sum(1:n)) } s_n <- map_df(n, compute_s_n) ## ------------------------------------------------------ x <- c(-2, -1, 0, 1, 2) case_when(x < 0 ~ "Negative", x > 0 ~ "Positive", TRUE ~ "Zero") ## ------------------------------------------------------ murders |> mutate(group = case_when( abb %in% c("ME", "NH", "VT", "MA", "RI", "CT") ~ "New England", abb %in% c("WA", "OR", "CA") ~ "West Coast", region == "South" ~ "South", TRUE ~ "Other")) |> group_by(group) |> summarize(rate = sum(total)/sum(population)*10^5) ## ---- eval=FALSE--------------------------------------- ## x >= a & x <= b ## ---- eval = FALSE------------------------------------- ## between(x, a, b) ## ---- eval=FALSE--------------------------------------- ## library(dplyr) ## library(dslabs) ## ---- eval=FALSE--------------------------------------- ## murders <- mutate(murders, population_in_millions = population/10^6) ## ---- eval=FALSE--------------------------------------- ## select(murders, state, population) ## ---- eval=FALSE--------------------------------------- ## filter(murders, state == "New York") ## ---- eval=FALSE--------------------------------------- ## no_florida <- filter(murders, state != "Florida") ## ---- eval=FALSE--------------------------------------- ## filter(murders, state %in% c("New York", "Texas")) ## ---- eval=FALSE--------------------------------------- ## filter(murders, population < 5000000 & region == "Northeast") ## ---- eval=FALSE--------------------------------------- ## murders <- mutate(murders, rate = total/population*100000, ## rank = rank(-rate)) ## ---- eval=FALSE--------------------------------------- ## my_states <- filter(murders, region %in% c("Northeast", "West") & ## rate < 1) ## ## select(my_states, state, rate, rank) ## ---- eval=FALSE--------------------------------------- ## mutate(murders, rate = total/population*100000, ## rank = rank(-rate)) |> ## select(state, rate, rank) ## ---- eval=FALSE--------------------------------------- ## my_states <- murders |> ## mutate SOMETHING |> ## filter SOMETHING |> ## select SOMETHING ## ------------------------------------------------------ library(NHANES) ## ------------------------------------------------------ library(dslabs) mean(na_example) sd(na_example) ## ------------------------------------------------------ mean(na_example, na.rm = TRUE) sd(na_example, na.rm = TRUE) ## ---- eval=FALSE--------------------------------------- ## exp(mean(log(murders$population)))