Untitled

library(tidyverse) 

Warning: package 'tidyverse' was built under R version 4.5.2

Warning: package 'ggplot2' was built under R version 4.5.2

Warning: package 'tibble' was built under R version 4.5.2

Warning: package 'tidyr' was built under R version 4.5.2

Warning: package 'readr' was built under R version 4.5.2

Warning: package 'purrr' was built under R version 4.5.2

Warning: package 'dplyr' was built under R version 4.5.2

Warning: package 'stringr' was built under R version 4.5.2

Warning: package 'forcats' was built under R version 4.5.2

Warning: package 'lubridate' was built under R version 4.5.2

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.2.0     ✔ readr     2.2.0
✔ forcats   1.0.1     ✔ stringr   1.6.0
✔ ggplot2   4.0.2     ✔ tibble    3.3.1
✔ lubridate 1.9.5     ✔ tidyr     1.3.2
✔ purrr     1.2.1     
── 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(dslabs) 

Warning: package 'dslabs' was built under R version 4.5.2

path <- system.file("extdata", package="dslabs") 
filename <- file.path(path, "fertility-two-countries-example.csv") 
wide_data <- read.csv(filename) 

new_tidy_data <- pivot_longer(wide_data, `X1960`:`X2015`, names_to = "year", values_to = "fertility")

new_tidy_data$year <- str_sub(new_tidy_data$year, 2)

new_tidy_data <- new_tidy_data |>
  mutate(year = as.integer(year))

new_wide_data <- new_tidy_data %>% 
pivot_wider(names_from = year, values_from =fertility) 

data(murders)
data(polls_us_election_2016)
tab1 <- slice(murders, 1:6) %>% select(state, population) 

tab2 <- results_us_election_2016 %>% filter(state %in% c("Alabama", "Alaska", "Arizona",    "California", "Connecticut", "Delaware")) %>% select(state, electoral_votes) 

left_join(tab1, tab2, by="state")

       state population electoral_votes
1    Alabama    4779736               9
2     Alaska     710231               3
3    Arizona    6392017              11
4   Arkansas    2915918              NA
5 California   37253956              55
6   Colorado    5029196              NA

#Right join – adding a table where we keep the rows of the second table. 
right_join(tab2, tab1, by="state")

       state electoral_votes population
1 California              55   37253956
2    Arizona              11    6392017
3    Alabama               9    4779736
4     Alaska               3     710231
5   Arkansas              NA    2915918
6   Colorado              NA    5029196

right_join(tab1, tab2, by="state")

        state population electoral_votes
1     Alabama    4779736               9
2      Alaska     710231               3
3     Arizona    6392017              11
4  California   37253956              55
5 Connecticut         NA               7
6    Delaware         NA               3

#Inner join – keep only the rows that have information in both tables
inner_join(tab1, tab2, by="state") 

       state population electoral_votes
1    Alabama    4779736               9
2     Alaska     710231               3
3    Arizona    6392017              11
4 California   37253956              55

#Full join – keep all the rows (of both tables) filling in missing parts with NAs
full_join(tab1, tab2, by="state")

        state population electoral_votes
1     Alabama    4779736               9
2      Alaska     710231               3
3     Arizona    6392017              11
4    Arkansas    2915918              NA
5  California   37253956              55
6    Colorado    5029196              NA
7 Connecticut         NA               7
8    Delaware         NA               3

#Semi join – keep the part of the first table for which we have information in the 2nd.  
semi_join(tab1, tab2, by="state")

       state population
1    Alabama    4779736
2     Alaska     710231
3    Arizona    6392017
4 California   37253956

#Anti join – keep elements of the first table for which there is no information in the 2nd
anti_join(tab1, tab2, by="state")

     state population
1 Arkansas    2915918
2 Colorado    5029196