#Load Tidyverse
library(tidyverse)## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.3 v dplyr 1.0.7
## v tidyr 1.1.3 v stringr 1.4.0
## v readr 2.0.1 v forcats 0.5.1## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()#Read Data Presidential
library(datasets)
data(presidential)
presidential## # A tibble: 11 x 4
## name start end party
## <chr> <date> <date> <chr>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican
## 2 Kennedy 1961-01-20 1963-11-22 Democratic
## 3 Johnson 1963-11-22 1969-01-20 Democratic
## 4 Nixon 1969-01-20 1974-08-09 Republican
## 5 Ford 1974-08-09 1977-01-20 Republican
## 6 Carter 1977-01-20 1981-01-20 Democratic
## 7 Reagan 1981-01-20 1989-01-20 Republican
## 8 Bush 1989-01-20 1993-01-20 Republican
## 9 Clinton 1993-01-20 2001-01-20 Democratic
## 10 Bush 2001-01-20 2009-01-20 Republican
## 11 Obama 2009-01-20 2017-01-20 Democratic#Knowing the Dimension of Data
dim(presidential)## [1] 11 4#Showing The Top 6 Data
head(presidential)## # A tibble: 6 x 4
## name start end party
## <chr> <date> <date> <chr>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican
## 2 Kennedy 1961-01-20 1963-11-22 Democratic
## 3 Johnson 1963-11-22 1969-01-20 Democratic
## 4 Nixon 1969-01-20 1974-08-09 Republican
## 5 Ford 1974-08-09 1977-01-20 Republican
## 6 Carter 1977-01-20 1981-01-20 Democratic#Glimpse
glimpse(presidential)## Rows: 11
## Columns: 4
## $ name <chr> "Eisenhower", "Kennedy", "Johnson", "Nixon", "Ford", "Carter", "~
## $ start <date> 1953-01-20, 1961-01-20, 1963-11-22, 1969-01-20, 1974-08-09, 197~
## $ end <date> 1961-01-20, 1963-11-22, 1969-01-20, 1974-08-09, 1977-01-20, 198~
## $ party <chr> "Republican", "Democratic", "Democratic", "Republican", "Republi~#Select Name and Party
select(presidential, name, party)## # A tibble: 11 x 2
## name party
## <chr> <chr>
## 1 Eisenhower Republican
## 2 Kennedy Democratic
## 3 Johnson Democratic
## 4 Nixon Republican
## 5 Ford Republican
## 6 Carter Democratic
## 7 Reagan Republican
## 8 Bush Republican
## 9 Clinton Democratic
## 10 Bush Republican
## 11 Obama Democratic#Select Name and Party with Pipes Operator
presidential %>% select(name, party)## # A tibble: 11 x 2
## name party
## <chr> <chr>
## 1 Eisenhower Republican
## 2 Kennedy Democratic
## 3 Johnson Democratic
## 4 Nixon Republican
## 5 Ford Republican
## 6 Carter Democratic
## 7 Reagan Republican
## 8 Bush Republican
## 9 Clinton Democratic
## 10 Bush Republican
## 11 Obama Democratic#Filter Party = Democratic
filter(presidential, party=="Democratic")## # A tibble: 5 x 4
## name start end party
## <chr> <date> <date> <chr>
## 1 Kennedy 1961-01-20 1963-11-22 Democratic
## 2 Johnson 1963-11-22 1969-01-20 Democratic
## 3 Carter 1977-01-20 1981-01-20 Democratic
## 4 Clinton 1993-01-20 2001-01-20 Democratic
## 5 Obama 2009-01-20 2017-01-20 Democratic#Filter party = Democratic with Pipes Operator
Democratic <- presidential %>% filter(party=="Democratic")
Democratic## # A tibble: 5 x 4
## name start end party
## <chr> <date> <date> <chr>
## 1 Kennedy 1961-01-20 1963-11-22 Democratic
## 2 Johnson 1963-11-22 1969-01-20 Democratic
## 3 Carter 1977-01-20 1981-01-20 Democratic
## 4 Clinton 1993-01-20 2001-01-20 Democratic
## 5 Obama 2009-01-20 2017-01-20 Democratic#Nrow of Party=Democratic
nrow(Democratic)## [1] 5#Combine Select() and Filter()
presidential %>% filter(start > "1980-01-01", party=="Democratic") %>% select(name)## # A tibble: 2 x 1
## name
## <chr>
## 1 Clinton
## 2 Obama#Mutate
library(lubridate)##
## Attaching package: 'lubridate'## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, unionmypresidents <- presidential %>% mutate(term.length = interval(start, end) /years(1))
mypresidents## # A tibble: 11 x 5
## name start end party term.length
## <chr> <date> <date> <chr> <dbl>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican 8
## 2 Kennedy 1961-01-20 1963-11-22 Democratic 2.84
## 3 Johnson 1963-11-22 1969-01-20 Democratic 5.16
## 4 Nixon 1969-01-20 1974-08-09 Republican 5.55
## 5 Ford 1974-08-09 1977-01-20 Republican 2.45
## 6 Carter 1977-01-20 1981-01-20 Democratic 4
## 7 Reagan 1981-01-20 1989-01-20 Republican 8
## 8 Bush 1989-01-20 1993-01-20 Republican 4
## 9 Clinton 1993-01-20 2001-01-20 Democratic 8
## 10 Bush 2001-01-20 2009-01-20 Republican 8
## 11 Obama 2009-01-20 2017-01-20 Democratic 8#Mean of Term.Length then Round(1)
mypresidents$term.length %>% mean() %>% round(1)## [1] 5.8#Summarize The Mean of Term Length of Each Party
mypresidents %>% group_by(party) %>% summarise(mean=mean(term.length))## # A tibble: 2 x 2
## party mean
## <chr> <dbl>
## 1 Democratic 5.6
## 2 Republican 6#Mutate with Pipes Operator
mypresidents <- mypresidents %>% mutate(elected = year(start) - 1)
mypresidents## # A tibble: 11 x 6
## name start end party term.length elected
## <chr> <date> <date> <chr> <dbl> <dbl>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican 8 1952
## 2 Kennedy 1961-01-20 1963-11-22 Democratic 2.84 1960
## 3 Johnson 1963-11-22 1969-01-20 Democratic 5.16 1962
## 4 Nixon 1969-01-20 1974-08-09 Republican 5.55 1968
## 5 Ford 1974-08-09 1977-01-20 Republican 2.45 1973
## 6 Carter 1977-01-20 1981-01-20 Democratic 4 1976
## 7 Reagan 1981-01-20 1989-01-20 Republican 8 1980
## 8 Bush 1989-01-20 1993-01-20 Republican 4 1988
## 9 Clinton 1993-01-20 2001-01-20 Democratic 8 1992
## 10 Bush 2001-01-20 2009-01-20 Republican 8 2000
## 11 Obama 2009-01-20 2017-01-20 Democratic 8 2008#Arrange from Term.Length
mypresidents %>% arrange(term.length)## # A tibble: 11 x 6
## name start end party term.length elected
## <chr> <date> <date> <chr> <dbl> <dbl>
## 1 Ford 1974-08-09 1977-01-20 Republican 2.45 1973
## 2 Kennedy 1961-01-20 1963-11-22 Democratic 2.84 1960
## 3 Carter 1977-01-20 1981-01-20 Democratic 4 1976
## 4 Bush 1989-01-20 1993-01-20 Republican 4 1988
## 5 Johnson 1963-11-22 1969-01-20 Democratic 5.16 1962
## 6 Nixon 1969-01-20 1974-08-09 Republican 5.55 1968
## 7 Eisenhower 1953-01-20 1961-01-20 Republican 8 1952
## 8 Reagan 1981-01-20 1989-01-20 Republican 8 1980
## 9 Clinton 1993-01-20 2001-01-20 Democratic 8 1992
## 10 Bush 2001-01-20 2009-01-20 Republican 8 2000
## 11 Obama 2009-01-20 2017-01-20 Democratic 8 2008#Arrange Descending of Term.Length and Elected with Pipes Operator
mypresidents %>% arrange(desc(term.length), elected)## # A tibble: 11 x 6
## name start end party term.length elected
## <chr> <date> <date> <chr> <dbl> <dbl>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican 8 1952
## 2 Reagan 1981-01-20 1989-01-20 Republican 8 1980
## 3 Clinton 1993-01-20 2001-01-20 Democratic 8 1992
## 4 Bush 2001-01-20 2009-01-20 Republican 8 2000
## 5 Obama 2009-01-20 2017-01-20 Democratic 8 2008
## 6 Nixon 1969-01-20 1974-08-09 Republican 5.55 1968
## 7 Johnson 1963-11-22 1969-01-20 Democratic 5.16 1962
## 8 Carter 1977-01-20 1981-01-20 Democratic 4 1976
## 9 Bush 1989-01-20 1993-01-20 Republican 4 1988
## 10 Kennedy 1961-01-20 1963-11-22 Democratic 2.84 1960
## 11 Ford 1974-08-09 1977-01-20 Republican 2.45 1973#Mutate Rename term.length with term_length
mypresidents %>% rename(term_length = term.length)## # A tibble: 11 x 6
## name start end party term_length elected
## <chr> <date> <date> <chr> <dbl> <dbl>
## 1 Eisenhower 1953-01-20 1961-01-20 Republican 8 1952
## 2 Kennedy 1961-01-20 1963-11-22 Democratic 2.84 1960
## 3 Johnson 1963-11-22 1969-01-20 Democratic 5.16 1962
## 4 Nixon 1969-01-20 1974-08-09 Republican 5.55 1968
## 5 Ford 1974-08-09 1977-01-20 Republican 2.45 1973
## 6 Carter 1977-01-20 1981-01-20 Democratic 4 1976
## 7 Reagan 1981-01-20 1989-01-20 Republican 8 1980
## 8 Bush 1989-01-20 1993-01-20 Republican 4 1988
## 9 Clinton 1993-01-20 2001-01-20 Democratic 8 1992
## 10 Bush 2001-01-20 2009-01-20 Republican 8 2000
## 11 Obama 2009-01-20 2017-01-20 Democratic 8 2008#Summarize
mypresidents %>% summarise(N = n(), first_year = min(year(start)), last_year = max(year(end)), num_dems = sum(party == "Democratic"), years = sum(term.length), avg_term.length = mean(term.length))## # A tibble: 1 x 6
## N first_year last_year num_dems years avg_term.length
## <int> <dbl> <dbl> <int> <dbl> <dbl>
## 1 11 1953 2017 5 64 5.82