cis-ds / Discussion

Public discussion
10 stars 15 forks source link

In-class example #1 #193

Closed Maggie-Rivera closed 3 years ago

Maggie-Rivera commented 3 years ago
library(dplyr)
#> 
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#> 
#>     filter, lag
#> The following objects are masked from 'package:base':
#> 
#>     intersect, setdiff, setequal, union
library(ggplot2)

# get data from rcfss package
# install latest version if not already installed
# devtools::install_github("uc-cfss/rcfss")
library(rcfss)

# load the data
data("mass_shootings")
mass_shootings
#> # A tibble: 114 x 14
#>    case     year month   day location summary   fatalities injured total_victims
#>    <chr>   <dbl> <chr> <int> <chr>    <chr>          <dbl>   <dbl>         <dbl>
#>  1 Dayton…  2019 Aug       4 Dayton,… "PENDING"          9      27            36
#>  2 El Pas…  2019 Aug       3 El Paso… "PENDING"         20      26            46
#>  3 Gilroy…  2019 Jul      28 Gilroy,… "Santino…          3      12            15
#>  4 Virgin…  2019 May      31 Virgini… "DeWayne…         12       4            16
#>  5 Harry …  2019 Feb      15 Aurora,… "Gary Ma…          5       6            11
#>  6 Pennsy…  2019 Jan      24 State C… "Jordan …          3       1             4
#>  7 SunTru…  2019 Jan      23 Sebring… "Zephen …          5       0             5
#>  8 Mercy …  2018 Nov      19 Chicago… "Juan Lo…          3       0             3
#>  9 Thousa…  2018 Nov       7 Thousan… "Ian Dav…         12      22            34
#> 10 Tree o…  2018 Oct      27 Pittsbu… "Robert …         11       6            17
#> # … with 104 more rows, and 5 more variables: location_type <chr>, male <lgl>,
#> #   age_of_shooter <dbl>, race <chr>, prior_mental_illness <chr>

# Generate a bar chart that identifies the number of mass shooters
# associated with each race category. The bars should be sorted
# from highest to lowest.

# using reorder() and aggregating the data before plotting
mass_shootings %>%
  count(race) %>%
  drop_na(race) %>%
  ggplot(mapping = aes(x = reorder(race, -n), y = n)) +
  geom_col() +
  labs(
    title = "Mass shootings in the United States (1982-2019)",
    x = "Race of perpetrator",
    y = "Number of incidents"
  )
#> Error in drop_na(., race): could not find function "drop_na"

Created on 2021-07-13 by the reprex package (v2.0.0)

Session info ``` r sessioninfo::session_info() #> ─ Session info ─────────────────────────────────────────────────────────────── #> setting value #> version R version 4.0.1 (2020-06-06) #> os Red Hat Enterprise Linux 8.4 (Ootpa) #> system x86_64, linux-gnu #> ui X11 #> language (EN) #> collate en_US.UTF-8 #> ctype en_US.UTF-8 #> tz America/Chicago #> date 2021-07-13 #> #> ─ Packages ─────────────────────────────────────────────────────────────────── #> package * version date lib source #> assertthat 0.2.1 2019-03-21 [2] CRAN (R 4.0.1) #> backports 1.2.1 2020-12-09 [2] CRAN (R 4.0.1) #> cli 2.5.0 2021-04-26 [1] CRAN (R 4.0.1) #> colorspace 2.0-0 2020-11-11 [2] CRAN (R 4.0.1) #> crayon 1.4.1 2021-02-08 [2] CRAN (R 4.0.1) #> DBI 1.1.1 2021-01-15 [2] CRAN (R 4.0.1) #> digest 0.6.27 2020-10-24 [2] CRAN (R 4.0.1) #> dplyr * 1.0.5 2021-03-05 [2] CRAN (R 4.0.1) #> ellipsis 0.3.1 2020-05-15 [2] CRAN (R 4.0.1) #> evaluate 0.14 2019-05-28 [2] CRAN (R 4.0.1) #> fansi 0.4.2 2021-01-15 [2] CRAN (R 4.0.1) #> fs 1.5.0 2020-07-31 [2] CRAN (R 4.0.1) #> generics 0.1.0 2020-10-31 [2] CRAN (R 4.0.1) #> ggplot2 * 3.3.3 2020-12-30 [2] CRAN (R 4.0.1) #> glue 1.4.2 2020-08-27 [2] CRAN (R 4.0.1) #> gtable 0.3.0 2019-03-25 [2] CRAN (R 4.0.1) #> highr 0.8 2019-03-20 [2] CRAN (R 4.0.1) #> htmltools 0.5.1.1 2021-01-22 [2] CRAN (R 4.0.1) #> knitr 1.31 2021-01-27 [2] CRAN (R 4.0.1) #> lifecycle 1.0.0 2021-02-15 [2] CRAN (R 4.0.1) #> magrittr 2.0.1 2020-11-17 [2] CRAN (R 4.0.1) #> munsell 0.5.0 2018-06-12 [2] CRAN (R 4.0.1) #> pillar 1.5.1 2021-03-05 [2] CRAN (R 4.0.1) #> pkgconfig 2.0.3 2019-09-22 [2] CRAN (R 4.0.1) #> purrr 0.3.4 2020-04-17 [2] CRAN (R 4.0.1) #> R6 2.5.0 2020-10-28 [2] CRAN (R 4.0.1) #> rcfss * 0.2.1 2021-06-24 [1] Github (uc-cfss/rcfss@5b60f61) #> reprex 2.0.0 2021-04-02 [2] CRAN (R 4.0.1) #> rlang 0.4.11 2021-04-30 [1] CRAN (R 4.0.1) #> rmarkdown 2.7 2021-02-19 [2] CRAN (R 4.0.1) #> rstudioapi 0.13 2020-11-12 [2] CRAN (R 4.0.1) #> scales 1.1.1 2020-05-11 [2] CRAN (R 4.0.1) #> sessioninfo 1.1.1 2018-11-05 [2] CRAN (R 4.0.1) #> stringi 1.5.3 2020-09-09 [2] CRAN (R 4.0.1) #> stringr 1.4.0 2019-02-10 [2] CRAN (R 4.0.1) #> styler 1.4.1 2021-03-30 [2] CRAN (R 4.0.1) #> tibble 3.1.0 2021-02-25 [2] CRAN (R 4.0.1) #> tidyselect 1.1.0 2020-05-11 [2] CRAN (R 4.0.1) #> utf8 1.2.1 2021-03-12 [2] CRAN (R 4.0.1) #> vctrs 0.3.7 2021-03-29 [2] CRAN (R 4.0.1) #> withr 2.4.1 2021-01-26 [2] CRAN (R 4.0.1) #> xfun 0.22 2021-03-11 [2] CRAN (R 4.0.1) #> yaml 2.2.1 2020-02-01 [2] CRAN (R 4.0.1) #> #> [1] /home/mmrivera/R/x86_64-pc-linux-gnu-library/4.0 #> [2] /opt/R/4.0.1/lib/R/library ```