This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Ctrl+Shift+Enter. Try also Ctrl+Alt+I, .

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   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── 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 errors
library(palmerpenguins)
library(ggthemes)
penguins
glimpse(penguins)
## Rows: 344
## Columns: 8
## $ species           <fct> Adelie, Adelie, Adelie, Adelie, Adelie, Adelie, Adel…
## $ island            <fct> Torgersen, Torgersen, Torgersen, Torgersen, Torgerse…
## $ bill_length_mm    <dbl> 39.1, 39.5, 40.3, NA, 36.7, 39.3, 38.9, 39.2, 34.1, …
## $ bill_depth_mm     <dbl> 18.7, 17.4, 18.0, NA, 19.3, 20.6, 17.8, 19.6, 18.1, …
## $ flipper_length_mm <int> 181, 186, 195, NA, 193, 190, 181, 195, 193, 190, 186…
## $ body_mass_g       <int> 3750, 3800, 3250, NA, 3450, 3650, 3625, 4675, 3475, …
## $ sex               <fct> male, female, female, NA, female, male, female, male…
## $ year              <int> 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007, 2007…
ggplot(
  data = penguins,
  mapping = aes(x = flipper_length_mm, y = body_mass_g, color = species)
) +
geom_point()
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(
  data = penguins,
  mapping = aes(x = flipper_length_mm, y = body_mass_g)
) +
geom_point(mapping = aes(color = species)) +
geom_smooth(method = "lm")
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(
  data = penguins,
  mapping = aes(x = flipper_length_mm, y = body_mass_g)
) +
geom_point(aes(color = species, shape = species)) +
geom_smooth(method = "lm") +
labs(
  title = "Body mass and flipper length",
  subtitle = "Dimensions for Adelie, Chinstrap, and Gentoo Penguins",
  x = "Flipper length (mm)", y = "Body mass (g)",
  color = "Species", shape = "Species"
) +
scale_color_colorblind()
## `geom_smooth()` using formula = 'y ~ x'
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_smooth()`).
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point()
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

ggplot(penguins, aes(x = species)) +
geom_bar()

ggplot(penguins, aes(x = body_mass_g)) +
geom_histogram(binwidth = 200)
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_bin()`).

ggplot(penguins, aes(x = body_mass_g)) +
geom_density()
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).

ggplot(penguins, aes(x = species, y = body_mass_g)) +
geom_boxplot()
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_boxplot()`).

ggplot(penguins, aes(x = body_mass_g, color = species)) +
geom_density(linewidth = 0.75)
## Warning: Removed 2 rows containing non-finite outside the scale range
## (`stat_density()`).

ggplot(penguins, aes(x = island, fill = species)) +
geom_bar()

ggplot(penguins, aes(x = island, fill = species)) +
geom_bar(position = "fill")

ggplot(penguins, aes(x = flipper_length_mm, y = body_mass_g)) +
geom_point(aes(color = species, shape = species)) +
facet_wrap(~island)
## Warning: Removed 2 rows containing missing values or values outside the scale range
## (`geom_point()`).

install.packages("nycflights13")
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.4'
## (as 'lib' is unspecified)
library(nycflights13)
library(tidyverse)
glimpse(flights)
## Rows: 336,776
## Columns: 19
## $ year           <int> 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2013, 2…
## $ month          <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ day            <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
## $ dep_time       <int> 517, 533, 542, 544, 554, 554, 555, 557, 557, 558, 558, …
## $ sched_dep_time <int> 515, 529, 540, 545, 600, 558, 600, 600, 600, 600, 600, …
## $ dep_delay      <dbl> 2, 4, 2, -1, -6, -4, -5, -3, -3, -2, -2, -2, -2, -2, -1…
## $ arr_time       <int> 830, 850, 923, 1004, 812, 740, 913, 709, 838, 753, 849,…
## $ sched_arr_time <int> 819, 830, 850, 1022, 837, 728, 854, 723, 846, 745, 851,…
## $ arr_delay      <dbl> 11, 20, 33, -18, -25, 12, 19, -14, -8, 8, -2, -3, 7, -1…
## $ carrier        <chr> "UA", "UA", "AA", "B6", "DL", "UA", "B6", "EV", "B6", "…
## $ flight         <int> 1545, 1714, 1141, 725, 461, 1696, 507, 5708, 79, 301, 4…
## $ tailnum        <chr> "N14228", "N24211", "N619AA", "N804JB", "N668DN", "N394…
## $ origin         <chr> "EWR", "LGA", "JFK", "JFK", "LGA", "EWR", "EWR", "LGA",…
## $ dest           <chr> "IAH", "IAH", "MIA", "BQN", "ATL", "ORD", "FLL", "IAD",…
## $ air_time       <dbl> 227, 227, 160, 183, 116, 150, 158, 53, 140, 138, 149, 1…
## $ distance       <dbl> 1400, 1416, 1089, 1576, 762, 719, 1065, 229, 944, 733, …
## $ hour           <dbl> 5, 5, 5, 5, 6, 5, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 6, 6, 6…
## $ minute         <dbl> 15, 29, 40, 45, 0, 58, 0, 0, 0, 0, 0, 0, 0, 0, 0, 59, 0…
## $ time_hour      <dttm> 2013-01-01 05:00:00, 2013-01-01 05:00:00, 2013-01-01 0…
flights |>
  filter(dest == "IAH") |>
  group_by(year, month, day) |>
  summarize(
    arr_delay = mean(arr_delay, na.rm = TRUE)
  )
## `summarise()` has grouped output by 'year', 'month'. You can override using the
## `.groups` argument.
flights |>
  filter(dep_delay > 120)
state <- read.csv('state.csv')
state
mean(state[['Population']])
## [1] 6162876
foo <- list(matrix(data=1:4,nrow=2,ncol=2),c(T,F,T,T),"hello")
foo
## [[1]]
##      [,1] [,2]
## [1,]    1    3
## [2,]    2    4
## 
## [[2]]
## [1]  TRUE FALSE  TRUE  TRUE
## 
## [[3]]
## [1] "hello"
state <- read.csv('state.csv')
glimpse(state)
## Rows: 50
## Columns: 4
## $ State        <chr> "Alabama", "Alaska", "Arizona", "Arkansas", "California",…
## $ Population   <int> 4779736, 710231, 6392017, 2915918, 37253956, 5029196, 357…
## $ Murder.Rate  <dbl> 5.7, 5.6, 4.7, 5.6, 4.4, 2.8, 2.4, 5.8, 5.8, 5.7, 1.8, 2.…
## $ Abbreviation <chr> "AL", "AK", "AZ", "AR", "CA", "CO", "CT", "DE", "FL", "GA…
mean(state[['Population']], trim = 0.1)
## [1] 4783697
median(state[['Population']])
## [1] 4436370