Sample Code: R
Due by 11:59 PM on Sunday, December 31, 0000
Elements of R
library(tidyverse)## ── Attaching packages ────────────────────────────────── tidyverse 1.2.1 ──## ✔ ggplot2 3.1.0 ✔ purrr 0.2.5
## ✔ tibble 2.0.99.9000 ✔ dplyr 0.8.0.9000
## ✔ tidyr 0.8.2 ✔ stringr 1.3.1
## ✔ readr 1.3.1 ✔ forcats 0.3.0## ── Conflicts ───────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ purrr::is_null() masks testthat::is_null()
## ✖ dplyr::lag() masks stats::lag()
## ✖ dplyr::matches() masks testthat::matches()library(socviz)##
## Attaching package: 'socviz'## The following object is masked from 'package:kjhutils':
##
## %nin%c(1, 2, 3, 1, 3, 5, 25)## [1] 1 2 3 1 3 5 25my_numbers <- c(1, 2, 3, 1, 3, 5, 25)
your_numbers <- c(5, 31, 71, 1, 3, 21, 6)my_numbers## [1] 1 2 3 1 3 5 25mean()
# Error in mean.default() : argument "x" is missing, with no defaultmean(x = my_numbers)## [1] 5.714286mean(x = your_numbers)## [1] 19.71429my_summary <- summary(my_numbers)table(my_numbers)## my_numbers
## 1 2 3 5 25
## 2 1 2 1 1sd(my_numbers)## [1] 8.616153my_numbers * 5## [1] 5 10 15 5 15 25 125my_numbers + 1## [1] 2 3 4 2 4 6 26my_numbers + my_numbers## [1] 2 4 6 2 6 10 50class(my_numbers)## [1] "numeric"class(my_summary)## [1] "summaryDefault" "table"class(summary)## [1] "function"titanic## fate sex n percent
## 1 perished male 1364 62.0
## 2 perished female 126 5.7
## 3 survived male 367 16.7
## 4 survived female 344 15.6class(titanic)## [1] "data.frame"titanic_tb <- as_tibble(titanic)
titanic_tb## # A tibble: 4 x 4
## fate sex n percent
## <fct> <fct> <dbl> <dbl>
## 1 perished male 1364 62
## 2 perished female 126 5.7
## 3 survived male 367 16.7
## 4 survived female 344 15.6str(my_numbers)## num [1:7] 1 2 3 1 3 5 25str(my_summary)## 'summaryDefault' Named num [1:6] 1 1.5 3 5.71 4 ...
## - attr(*, "names")= chr [1:6] "Min." "1st Qu." "Median" "Mean" ...The CQ data
knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
library(janitor)
library(lubridate)##
## Attaching package: 'lubridate'## The following object is masked from 'package:base':
##
## datelibrary(socviz)## Calculate age in years, months, or days
calc_age <- function(birth_date, ref_date = Sys.Date(), unit = "year") {
require(lubridate)
period <- as.period(interval(birth_date, ref_date),
unit = unit)
switch(unit,
year = year(period),
month = month(period),
day = day(period),
stop = "Unknown time unit. Choose year, month, or day.")
}Load it
filenames <- dir(path = "data/clean",
pattern = "*.csv",
full.names = TRUE)
filenames## [1] "data/clean/01_79_congress.csv" "data/clean/02_80_congress.csv"
## [3] "data/clean/03_81_congress.csv" "data/clean/04_82_congress.csv"
## [5] "data/clean/05_83_congress.csv" "data/clean/06_84_congress.csv"
## [7] "data/clean/07_85_congress.csv" "data/clean/08_86_congress.csv"
## [9] "data/clean/09_87_congress.csv" "data/clean/10_88_congress.csv"
## [11] "data/clean/11_89_congress.csv" "data/clean/12_90_congress.csv"
## [13] "data/clean/13_91_congress.csv" "data/clean/14_92_congress.csv"
## [15] "data/clean/15_93_congress.csv" "data/clean/16_94_congress.csv"
## [17] "data/clean/17_95_congress.csv" "data/clean/18_96_congress.csv"
## [19] "data/clean/19_97_congress.csv" "data/clean/20_98_congress.csv"
## [21] "data/clean/21_99_congress.csv" "data/clean/22_100_congress.csv"
## [23] "data/clean/23_101_congress.csv" "data/clean/24_102_congress.csv"
## [25] "data/clean/25_103_congress.csv" "data/clean/26_104_congress.csv"
## [27] "data/clean/27_105_congress.csv" "data/clean/28_106_congress.csv"
## [29] "data/clean/29_107_congress.csv" "data/clean/30_108_congress.csv"
## [31] "data/clean/31_109_congress.csv" "data/clean/32_110_congress.csv"
## [33] "data/clean/33_111_congress.csv" "data/clean/34_112_congress.csv"
## [35] "data/clean/35_113_congress.csv" "data/clean/36_114_congress.csv"
## [37] "data/clean/37_115_congress.csv" "data/clean/38_116_congress.csv"specs <- spec_csv(filenames[1])## Parsed with column specification:
## cols(
## .default = col_character()
## )## See spec(...) for full column specifications.specs## cols(
## Last = col_character(),
## First = col_character(),
## Middle = col_character(),
## Suffix = col_character(),
## Nickname = col_character(),
## Born = col_character(),
## Death = col_character(),
## Sex = col_character(),
## Position = col_character(),
## Party = col_character(),
## State = col_character(),
## District = col_character(),
## Start = col_character(),
## End = col_character(),
## Religion = col_character(),
## Race = col_character(),
## `Educational Attainment` = col_character(),
## JobType1 = col_character(),
## JobType2 = col_character(),
## JobType3 = col_character(),
## JobType4 = col_character(),
## JobType5 = col_character(),
## Mil1 = col_character(),
## Mil2 = col_character(),
## Mil3 = col_character()
## )data <- filenames %>%
map_dfr(read_csv, .id = "congress", col_types = specs)
data <- clean_names(data)
data## # A tibble: 20,580 x 26
## congress last first middle suffix nickname born death sex position
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 1 Aber… Thom… Gerst… <NA> <NA> 05/1… 01/2… M U.S. Re…
## 2 1 Adams Sher… <NA> <NA> <NA> 01/0… 10/2… M U.S. Re…
## 3 1 Aiken Geor… David <NA> <NA> 08/2… 11/1… M U.S. Se…
## 4 1 Allen Asa Leona… <NA> <NA> 01/0… 01/0… M U.S. Re…
## 5 1 Allen Leo Elwood <NA> <NA> 10/0… 01/1… M U.S. Re…
## 6 1 Almo… J. Linds… Jr. <NA> 06/1… 04/1… M U.S. Re…
## 7 1 Ande… Herm… Carl <NA> <NA> 01/2… 07/2… M U.S. Re…
## 8 1 Ande… Clin… Presba <NA> <NA> 10/2… 11/1… M U.S. Re…
## 9 1 Ande… John Zuing… <NA> <NA> 03/2… 02/0… M U.S. Re…
## 10 1 Andr… Augu… Herman <NA> <NA> 10/1… 01/1… M U.S. Re…
## # … with 20,570 more rows, and 16 more variables: party <chr>,
## # state <chr>, district <chr>, start <chr>, end <chr>, religion <chr>,
## # race <chr>, educational_attainment <chr>, job_type1 <chr>,
## # job_type2 <chr>, job_type3 <chr>, job_type4 <chr>, job_type5 <chr>,
## # mil1 <chr>, mil2 <chr>, mil3 <chr>