URL to this page: bit.ly/UseRSeattleOct2019
Seattle UseR meetup, October 2019
Get the data:
big_epa_cars <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-15/big_epa_cars.csv")
| library(tidyverse) | |
| big_epa_cars <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-10-15/big_epa_cars.csv") | |
| head(big_epa_cars) | |
| str(big_epa_cars) | |
| colnames(big_epa_cars) | |
| # selecting columns with dplyr | |
| sel_columns <- select(big_epa_cars, fuelType, city08, co2) | |
| # select range of columns | |
| sel_range <- select(big_epa_cars, barrels08:charge240) | |
| # select columns starting with the same thing | |
| sel_starts <- select(big_epa_cars, starts_with("comb")) | |
| # also ends_with(), contains() | |
| # select rows conditionally | |
| filtered_rows <- filter(big_epa_cars, fuelType == "Electricity") | |
| ## Challenge: create a new object from big_epa_cars called first_cols that includes only the first four columns | |
| ## Challenge: create a new object from big_epa_cars called city_cols that includes all columns containing "city" | |
| ## Challenge: create a new object from big_epa_cars called fuel_cols that includes the following columns: fuelType, drive, cylinders, year | |
| ## Challenge: create a new object from big_epa_cars called rear_rows that includes all cars with Rear-Wheel Drive (from column drive) | |
| #### Combining commands #### | |
| # use intermediate objects to combine commands (answer from previous challenge) | |
| fuel_cols <- select(big_epa_cars, fuelType, drive, cylinders, year) | |
| rear_rows <- filter(fuel_cols, drive == "Rear-Wheel Drive") | |
| # nest commands (same object as created above, but here only in two lines) | |
| rear_fuel <- filter(select(big_epa_cars, fuelType, drive, cylinders, year), drive == "Rear-Wheel Drive") | |
| # combine commands using pipes (improves readability of complex commands) | |
| # same example as above | |
| piped <- big_epa_cars %>% | |
| select(fuelType, drive, guzzler, year) %>% | |
| filter(drive == "Rear-Wheel Drive") | |
| # extract race, ethinicity, and disease from cases born prior to 1930 | |
| piped2 <- big_epa_cars %>% | |
| filter(cylinders > 8) %>% | |
| select(guzzler, year) | |
| # does the order of commands differ? | |
| piped3 <- big_epa_cars %>% | |
| select(guzzler, year) %>% | |
| filter(cylinders > 8) | |
| # in this case, yes it does matter! | |
| ## Challenge: Use pipes to extract the columns model, co2, and range from the object big_epa_cars for guzzlers (TRUE) that were manufactured after 2000 (column year) | |
| big_epa_cars %>% | |
| filter(guzzler == TRUE) %>% | |
| filter(year > 2000) %>% | |
| select(model, co2, range) | |
| #### Mutate #### | |
| # mutate allows unit conversions or ratios, creates a new column | |
| # convert miles to km | |
| city_mpg_km <- big_epa_cars %>% | |
| mutate(city_km = city08 * 1.6) | |
| # convert two columns at once, send to head for easier viewing | |
| big_epa_cars %>% | |
| mutate(city_km = city08 * 1.6, | |
| comb_km = comb08 * 1.6) %>% | |
| head() | |
| ## Challenge: extract only cars that are model Corolla or Prius and create a new column called diff_mpg representing the difference between highway mpg (highway08) and city mpg (city08) | |
| big_epa_cars %>% | |
| mutate(diff_mpg = highway08 - city08) %>% | |
| filter(model == "Corolla") %>% | |
| select(diff_mpg) | |
| #### Split-apply-combine #### | |
| # frame the problem: we want to summarize data by types of drive | |
| # show categories in drive | |
| distinct(big_epa_cars, drive) | |
| # group_by not always useful by itself, but powerful together with tally() | |
| # count number of individuals with each tumor stage | |
| big_epa_cars %>% | |
| group_by(drive) %>% | |
| tally() # empty parentheses not required, but good practice | |
| # shows missing data, too | |
| # the split/apply/combine approach: | |
| # split data into groups, | |
| # apply an analysis to each group, | |
| # combine results back into one object | |
| # summarize average city mpg by drive | |
| big_epa_cars %>% | |
| group_by(drive) %>% | |
| summarize(mean_city08 = mean(city08, na.rm = TRUE)) | |
| # why doesn't the above work to remove NA? | |
| # remove NA, add visualization | |
| big_epa_cars %>% | |
| filter(!is.na(drive)) %>% | |
| group_by(drive) %>% | |
| summarize(mean_city08 = mean(city08, na.rm = TRUE)) %>% | |
| ggplot() + | |
| geom_col(aes(x=drive, y=mean_city08)) | |
| # more complex | |
| big_epa_cars %>% | |
| filter(!is.na(drive)) %>% | |
| group_by(drive, model) %>% | |
| summarize(mean_city08 = mean(city08, na.rm = TRUE)) %>% | |
| ggplot() + | |
| geom_boxplot(aes(x=drive, y=mean_city08)) |