ps4_tonyzhang

Code Appendix # This template file is based off of a template created by Alex Hayes # https://github.com/alexpghayes/rmarkdown_homework_template # Setting Document Options knitr :: opts_chunk $ set ( echo = TRUE , warning = FALSE , message = FALSE , fig.align = "center" ) install.packages ( "mdsr" , repos = "http://cran.us.r-project.org" ) install.packages ( "dplyr" , repos = "http://cran.us.r-project.org" ) library (mdsr) library (dplyr) data ( "Minneapolis2013" ) same_first_second <- Minneapolis2013 %>% filter (First == Second) num_same_first_second <- nrow (same_first_second) head (same_first_second) top_3_choices <- same_first_second %>% count (First) %>% arrange ( desc (n)) %>% head ( 3 ) top_3_choices ole_savior_first <- Minneapolis2013 %>% filter (First == "Ole Savior" ) top_3_second_choices <- ole_savior_first %>% count (Second) %>% arrange ( desc (n)) %>% head ( 3 ) print (top_3_second_choices) install.packages ( "ggplot2" , repos = "http://cran.us.r-project.org" ) library (ggplot2) data (diamonds) diamonds %>% group_by (color) %>% summarise ( avg_carat = mean (carat)) %>% arrange ( desc (avg_carat)) %>% head ( 1 ) diamonds %>% group_by (clarity) %>% summarise ( avg_table_per_carat = mean (table / carat)) %>% arrange ( desc (avg_table_per_carat)) %>% head ( 1 ) Minneapolis2013 <- Minneapolis2013 %>% group_by (First) %>% mutate ( name_count = n ()) %>% mutate ( First = if_else (name_count < 5000 , "minor" , First)) %>% select ( - name_count) head (Minneapolis2013) 3

Part 5 select() Problem 10.5 Part 1 I want to use filter() to include only rows where First and Second are the Same install.packages ( "mdsr" , repos = "http://cran.us.r-project.org" ) ## package ’mdsr’ successfully unpacked and MD5 sums checked ## ## The downloaded binary packages are in ## C:\Users\tonyz\AppData\Local\Temp\RtmpU1K5gg\downloaded_packages install.packages ( "dplyr" , repos = "http://cran.us.r-project.org" ) ## package ’dplyr’ successfully unpacked and MD5 sums checked ## ## The downloaded binary packages are in ## C:\Users\tonyz\AppData\Local\Temp\RtmpU1K5gg\downloaded_packages library (mdsr) library (dplyr) data ( "Minneapolis2013" ) same_first_second <- Minneapolis2013 %>% filter (First == Second) num_same_first_second <- nrow (same_first_second) head (same_first_second) ## Precinct First Second Third Ward ## 1 P-04 undervote undervote undervote W-6 ## 2 P-08 undervote undervote undervote W-5 ## 3 P-03 OLE SAVIOR OLE SAVIOR OLE SAVIOR W-6 ## 4 P-02 undervote undervote MARK ANDREW W-6 ## 5 P-02 undervote undervote undervote W-3 ## 6 P-01 BETSY HODGES BETSY HODGES BETSY HODGES W-8 Part 2 I want to count the frequency of each candidate and use sort() to sort the table in descending order and extract the top 3 choices. top_3_choices <- same_first_second %>% count (First) %>% arrange ( desc (n)) %>% head ( 3 ) top_3_choices ## First n ## 1 undervote 686 ## 2 MARK ANDREW 227 ## 3 BETSY HODGES 222 6