ps7_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 ( "dcData" , repos = "http://cran.us.r-project.org" ) library (dcData) data ( "ZipGeography" ) num_counties <- length ( unique (ZipGeography $ County)) num_counties city_states_count <- table (ZipGeography $ CityName, ZipGeography $ State) city_states_summary <- data.frame ( CityName = rownames (city_states_count), NumStates = rowSums (city_states_count > 0 ) ) city_states_summary <- city_states_summary[ trimws (city_states_summary $ CityName) != "" , ] city_states_summary <- city_states_summary[ order ( - city_states_summary $ NumStates), ] head (city_states_summary) state_populations <- aggregate (Population ~ State, data = ZipGeography, sum) city_state_populations <- aggregate (Population ~ CityName + State, data = ZipGeography, sum) city_state_population_ratio <- merge (city_state_populations, state_populations, by = "State" ) city_state_population_ratio $ Ratio <- city_state_population_ratio $ Population.x / city_state_population_ratio $ Pop cities_over_5_percent <- subset (city_state_population_ratio, Ratio > 0.05 ) result_df <- data.frame ( CityName = character (), NumStates = numeric ()) for (state in unique (cities_over_5_percent $ State)) { state_population <- subset (state_populations, State == state) $ Population cities_in_state <- subset (cities_over_5_percent, State == state & Ratio > 0.05 ) result_df <- rbind (result_df, data.frame ( CityName = cities_in_state $ CityName, NumStates = nrow (cities_in_stat } result_df <- result_df[ order ( - result_df $ NumStates), ] head (result_df) state_timezones <- aggregate (Timezone ~ State, data = ZipGeography, FUN = function (x) length ( unique (x))) total_states_multiple_timezones <- sum (state_timezones $ Timezone > 1 ) total_states_multiple_timezones city_timezones <- aggregate (Timezone ~ CityName, data = ZipGeography, FUN = function (x) length ( unique (x))) total_cities_multiple_timezones <- sum (city_timezones $ Timezone > 1 ) total_cities_multiple_timezones county_timezones <- aggregate (Timezone ~ County, data = ZipGeography, FUN = function (x) length ( unique (x))) total_counties_multiple_timezones <- sum (county_timezones $ Timezone > 1 ) total_counties_multiple_timezones install.packages ( "dcData" , repos = "http://cran.us.r-project.org" ) library (dcData) data ( "ZipGeography" ) Problem 11.1 The join family of data verbs requires a data table as one of the arguments because they merge datasets based on common variables or keys. 3

Part 3 The variables being matched for infantA are iso_a3 from HealthIndicators with countryA from the glyph ready table Part 4 The variables being matched for infantB are infantB are iso_a3 from HealthIndicators with countryB from the glpyn ready table. 6