Here we will write a function that multiplies some number x by 2:
times_2 <- function(x) x * 2+
div_100 <- function(x) x / 100
When you run the line of code above, you make it ready to use (no output yet!). Let’s test it!
-times_2(x = 10)+
div_100(x = 600)-
[1] 20+
[1] 6
{ }Adding the curly brackets - {} - allows you to use functions spanning multiple lines:
times_2 <- function(x) {
- x * 2
+div_100 <- function(x) {
+ x / 100
}
-times_2(x = 10)
+div_100(x = 10)
-[1] 20- -
is_even <- function(x) {
- x %% 2 == 0
-}
-is_even(x = 11)
-
-[1] FALSE- -
is_even(x = times_2(x = 10))- -
[1] TRUE+
[1] 0.1
returnIf we want something specific for the function’s output, we use return():
times_2_plus_4 <- function(x) {
- output_int <- x * 2
+div_100_plus_4 <- function(x) {
+ output_int <- x / 100
output <- output_int + 4
return(output)
}
-times_2_plus_4(x = 10)
+div_100_plus_4(x = 10)
-[1] 24+
[1] 4.1-
return not called, last evaluated expression is returnedreturn should be the last step (steps after may be skipped)times_2_plus_4 <- function(x) {
- output_int <- x * 2
- output <- output_int + 4
- print(paste("times2 result = ", output_int))
- return(output)
-}
+
+
+
+
+
+
+
-result <- times_2_plus_4(x = 10)
+
-[1] "times2 result = 20"+ -
result+ -
[1] 24+ + + + + + + + + + + + +
Functions can take multiple inputs:
-times_2_plus_y <- function(x, y) x * 2 + y -times_2_plus_y(x = 10, y = 3)+
div_100_plus_y <- function(x, y) x / 100 + y +div_100_plus_y(x = 10, y = 3)-
[1] 23+
[1] 3.1
Functions can have one returned result with multiple outputs.
+Functions can return a vector (or other object) with multiple outputs.
x_and_y_plus_2 <- function(x, y) {
output1 <- x + 2
@@ -3382,14 +3378,14 @@
Functions can have “default” arguments. This lets us use the function without using an argument later:
-times_2_plus_y <- function(x = 10, y = 3) x * 2 + y
-times_2_plus_y()
+div_100_plus_y <- function(x = 10, y = 3) x / 100 + y
+div_100_plus_y()
-[1] 23
+[1] 3.1
-times_2_plus_y(x = 11, y = 4)
+div_100_plus_y(x = 11, y = 4)
-[1] 26
+[1] 4.11
[1] "HOORAY!" "HOORAY!" "HOORAY!" "HOORAY!" "HOORAY!"-
We can use filter(row_number() == n) to extract a row of a tibble:
get_row <- function(dat, row) dat %>% filter(row_number() == row) + -ces <- calenviroscreen -ces_1_8 <- ces %>% select(1:8)+ -
get_row(dat = ces, row = 10)+ -
# A tibble: 1 × 67 - CensusTract CaliforniaCounty ZIP Longitude Latitude ApproxLocation - <dbl> <chr> <int> <dbl> <dbl> <chr> -1 6001401000 "Alameda " 94608 -122. 37.8 Oakland -# ℹ 61 more variables: CES4.0Score <dbl>, CES4.0Percentile <dbl>, -# CES4.0PercRange <chr>, Ozone <dbl>, OzonePctl <dbl>, PM2.5 <dbl>, -# PM2.5.Pctl <dbl>, DieselPM <dbl>, DieselPMPctl <dbl>, DrinkingWater <dbl>, -# DrinkingWaterPctl <dbl>, Lead <dbl>, LeadPctl <dbl>, Pesticides <dbl>, -# PesticidesPctl <dbl>, ToxRelease <dbl>, ToxReleasePctl <dbl>, -# Traffic <dbl>, TrafficPctl <dbl>, CleanupSites <dbl>, -# CleanupSitesPctl <dbl>, GroundwaterThreats <dbl>, …+ -
get_row(dat = ces, row = 4)+ -
# A tibble: 1 × 67 - CensusTract CaliforniaCounty ZIP Longitude Latitude ApproxLocation - <dbl> <chr> <int> <dbl> <dbl> <chr> -1 6001400400 "Alameda " 94609 -122. 37.8 Oakland -# ℹ 61 more variables: CES4.0Score <dbl>, CES4.0Percentile <dbl>, -# CES4.0PercRange <chr>, Ozone <dbl>, OzonePctl <dbl>, PM2.5 <dbl>, -# PM2.5.Pctl <dbl>, DieselPM <dbl>, DieselPMPctl <dbl>, DrinkingWater <dbl>, -# DrinkingWaterPctl <dbl>, Lead <dbl>, LeadPctl <dbl>, Pesticides <dbl>, -# PesticidesPctl <dbl>, ToxRelease <dbl>, ToxReleasePctl <dbl>, -# Traffic <dbl>, TrafficPctl <dbl>, CleanupSites <dbl>, -# CleanupSitesPctl <dbl>, GroundwaterThreats <dbl>, …+ -
Can create function with an argument that allows inputting a column name for select or other dplyr operation:
clean_dataset <- function(dataset, col_name) {
- my_data_out <- dataset %>% select({{col_name}}) # Note the curly braces
- return(my_data_out)
-}
+
-clean_dataset(dataset = ces, col_name = "CES4.0Score")
+# A tibble: 8,035 × 1 - CES4.0Score - <dbl> - 1 4.85 - 2 4.88 - 3 11.2 - 4 12.4 - 5 16.7 - 6 20.0 - 7 36.7 - 8 37.1 - 9 40.7 -10 43.7 -# ℹ 8,025 more rows+
# get means and missing for a specific column
+get_summary <- function(dataset, col_name) {
+ dataset %>%
+ summarise(mean = mean({{col_name}}, na.rm = TRUE),
+ na_count = sum(is.na({{col_name}})))
+}
-get_mean <- function(dat, county_name, col_name) {
- my_data_out <- dat %>%
- filter(str_detect(CaliforniaCounty, county_name)) %>%
- summarise(mean = mean({{col_name}}, na.rm = TRUE))
- return(my_data_out)
-}
+Examples:
-get_mean(dat = ces, county_name = "Alameda", col_name = CES4.0Score)
+get_summary(calenviroscreen, CES4.0Score)-
# A tibble: 1 × 1 - mean - <dbl> -1 22.9+
# A tibble: 1 × 2 + mean na_count + <dbl> <int> +1 28.3 103-
get_mean(dat = ces, county_name = "Fresno", col_name = CES4.0Score)+
get_summary(haa5, perc_pop_exposed_to_exceedances)-
# A tibble: 1 × 1 - mean - <dbl> -1 40.9+
# A tibble: 1 × 2 + mean na_count + <dbl> <int> +1 0.0591 11
sapply(<a vector, list, data frame>, some_function)-
sapply()🚨 There are no parentheses on the functions! 🚨
- -You can also pipe into your function.
+er_visits <- CO_heat_ER ++This dataset was gathered by the California Office of Environmental Health Hazard Assessment. CalEnviroScreen ranks census tracts in California based on potential exposures to pollutants, adverse environmental conditions, socioeconomic factors and the prevalence of certain health conditions. Read more at https://calenviroscreen-oehha.hub.arcgis.com/.
-head(er_visits, n = 2)
head(calenviroscreen)-
# A tibble: 2 × 7 - county rate lower95cl upper95cl visits year gender - <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr> -1 Statewide 5.64 4.70 6.59 140 2011 Female -2 Statewide 7.39 6.30 8.47 183 2011 Male+
# A tibble: 6 × 67 + CensusTract CaliforniaCounty ZIP Longitude Latitude ApproxLocation + <dbl> <chr> <int> <dbl> <dbl> <chr> +1 6001400100 "Alameda " 94704 -122. 37.9 Oakland +2 6001400200 "Alameda " 94618 -122. 37.8 Oakland +3 6001400300 "Alameda " 94618 -122. 37.8 Oakland +4 6001400400 "Alameda " 94609 -122. 37.8 Oakland +5 6001400500 "Alameda " 94609 -122. 37.8 Oakland +6 6001400600 "Alameda " 94609 -122. 37.8 Oakland +# ℹ 61 more variables: CES4.0Score <dbl>, CES4.0Percentile <dbl>, +# CES4.0PercRange <chr>, Ozone <dbl>, OzonePctl <dbl>, PM2.5 <dbl>, +# PM2.5.Pctl <dbl>, DieselPM <dbl>, DieselPMPctl <dbl>, DrinkingWater <dbl>, +# DrinkingWaterPctl <dbl>, Lead <dbl>, LeadPctl <dbl>, Pesticides <dbl>, +# PesticidesPctl <dbl>, ToxRelease <dbl>, ToxReleasePctl <dbl>, +# Traffic <dbl>, TrafficPctl <dbl>, CleanupSites <dbl>, +# CleanupSitesPctl <dbl>, GroundwaterThreats <dbl>, …-
sapply(er_visits, class)+
sapply()county rate lower95cl upper95cl visits year -"character" "numeric" "numeric" "numeric" "numeric" "numeric" - gender -"character"+
🚨 There are no parentheses on the functions! 🚨
-er_visits %>% sapply(class)+
You can also pipe into your function.
-county rate lower95cl upper95cl visits year -"character" "numeric" "numeric" "numeric" "numeric" "numeric" - gender -"character"+
sapply(calenviroscreen, class) # also: calenviroscreen %>% sapply(class)+ +
CensusTract CaliforniaCounty ZIP + "numeric" "character" "integer" + Longitude Latitude ApproxLocation + "numeric" "numeric" "character" + CES4.0Score CES4.0Percentile CES4.0PercRange + "numeric" "numeric" "character" + Ozone OzonePctl PM2.5 + "numeric" "numeric" "numeric" + PM2.5.Pctl DieselPM DieselPMPctl + "numeric" "numeric" "numeric" + DrinkingWater DrinkingWaterPctl Lead + "numeric" "numeric" "numeric" + LeadPctl Pesticides PesticidesPctl + "numeric" "numeric" "numeric" + ToxRelease ToxReleasePctl Traffic + "numeric" "numeric" "numeric" + TrafficPctl CleanupSites CleanupSitesPctl + "numeric" "numeric" "numeric" + GroundwaterThreats GroundwaterThreatsPctl HazWaste + "numeric" "numeric" "numeric" + HazWastePctl ImpWaterBodies ImpWaterBodiesPctl + "numeric" "integer" "numeric" + SolidWaste SolidWastePctl PollutionBurden + "numeric" "numeric" "numeric" + PollutionBurdenScore PollutionBurdenPctl Asthma + "numeric" "numeric" "numeric" + AsthmaPctl LowBirthWeight LowBirthWeightPctl + "numeric" "numeric" "numeric" + CardiovascularDisease CardiovascularDiseasePctl TotalPop + "numeric" "numeric" "integer" + ChildrenPercLess10 PopPerc10to64 ElderlyMore64 + "numeric" "numeric" "numeric" + HispanicPerc WhitePerc AfAmericanPerc + "numeric" "numeric" "numeric" + NativeAmericanPerc AsianAmericanPerc OtherMultiplePerc + "numeric" "numeric" "numeric" + PopChar PopCharScore PopCharPctl + "numeric" "numeric" "numeric" + Education EducationPctl LinguisticIsol + "numeric" "numeric" "numeric" + LinguisticIsolPctl Poverty PovertyPctl + "numeric" "numeric" "numeric" + Unemployment UnemploymentPctl HousingBurden + "numeric" "numeric" "numeric" + HousingBurdenPctl + "numeric"
sapply()select(er_visits, rate:upper95cl) %>% head()- -
# A tibble: 6 × 3 - rate lower95cl upper95cl - <dbl> <dbl> <dbl> -1 5.64 4.70 6.59 -2 7.39 6.30 8.47 -3 6.51 5.80 7.23 -4 5.64 4.72 6.57 -5 7.56 6.48 8.65 -6 6.58 5.88 7.29+
Use the div_100 function we created earlier to convert 0-100 percentiles to proportions.
select(er_visits, rate:upper95cl) %>% - sapply(times_2) %>% +calenviroscreen %>% + select(ends_with("Pctl")) %>% + sapply(div_100) %>% head()-rate lower95cl upper95cl -[1,] 11.28546 9.395283 13.17564 -[2,] 14.77374 12.597645 16.94983 -[3,] 13.02989 11.593179 14.46660 -[4,] 11.28268 9.430621 13.13474 -[5,] 15.12880 12.959418 17.29817 -[6,] 13.16714 11.750214 14.58407+OzonePctl PM2.5.Pctl DieselPMPctl DrinkingWaterPctl LeadPctl +[1,] 0.0312 0.3627 0.3476 0.0421 0.0774 +[2,] 0.0312 0.4197 0.9271 0.0421 0.6820 +[3,] 0.0312 0.4390 0.8977 0.0421 0.6418 +[4,] 0.0312 0.4281 0.7910 0.0421 0.6708 +[5,] 0.0312 0.4281 0.6758 0.0421 0.6795 +[6,] 0.0312 0.4281 0.8376 0.0421 0.6970 + PesticidesPctl ToxReleasePctl TrafficPctl CleanupSitesPctl +[1,] 0 0.5603 0.5594 0.5817 +[2,] 0 0.5543 0.3749 0.0000 +[3,] 0 0.5504 0.4248 0.1183 +[4,] 0 0.5590 0.3800 0.0000 +[5,] 0 0.5648 0.4868 0.3387 +[6,] 0 0.5565 0.6706 0.2262 + GroundwaterThreatsPctl HazWastePctl ImpWaterBodiesPctl SolidWastePctl +[1,] 0.5242 0.9252 0.2388 0.3572 +[2,] 0.8793 0.2851 0.0000 0.0000 +[3,] 0.8529 0.7407 0.0000 0.0000 +[4,] 0.9256 0.5189 0.0000 0.0000 +[5,] 0.8434 0.5640 0.0000 0.0000 +[6,] 0.7906 0.5827 0.0000 0.0000 + PollutionBurdenPctl AsthmaPctl LowBirthWeightPctl +[1,] 0.2662 0.0444 0.2306 +[2,] 0.2418 0.0980 0.2792 +[3,] 0.3337 0.2657 0.2162 +[4,] 0.2624 0.5598 0.3702 +[5,] 0.3140 0.8838 0.1900 +[6,] 0.3694 0.9307 0.0503 + CardiovascularDiseasePctl PopCharPctl EducationPctl LinguisticIsolPctl +[1,] 0.0142 0.0153 0.1255 0.0849 +[2,] 0.1453 0.0165 0.0042 0.0000 +[3,] 0.2011 0.1227 0.2412 0.5336 +[4,] 0.1428 0.1843 0.2029 0.0564 +[5,] 0.3887 0.3016 0.0740 0.1330 +[6,] 0.5278 0.3770 0.0973 0.0627 + PovertyPctl UnemploymentPctl HousingBurdenPctl +[1,] 0.1103 NA 0.1939 +[2,] 0.1144 0.1711 0.0067 +[3,] 0.1090 0.2941 0.0981 +[4,] 0.3642 0.1066 0.3748 +[5,] 0.3813 0.2820 0.3748 +[6,] 0.2442 0.7167 0.5407
select(er_visits, rate:upper95cl) %>% - sapply(function(x) x / 1000) %>% +Also called “anonymous function”.
+ +calenviroscreen %>% + select(ends_with("Pctl")) %>% + sapply(function(x) x / 100) %>% head()-rate lower95cl upper95cl -[1,] 0.005642730 0.004697642 0.006587819 -[2,] 0.007386868 0.006298822 0.008474914 -[3,] 0.006514945 0.005796590 0.007233300 -[4,] 0.005641341 0.004715311 0.006567371 -[5,] 0.007564398 0.006479709 0.008649086 -[6,] 0.006583570 0.005875107 0.007292033+OzonePctl PM2.5.Pctl DieselPMPctl DrinkingWaterPctl LeadPctl +[1,] 0.0312 0.3627 0.3476 0.0421 0.0774 +[2,] 0.0312 0.4197 0.9271 0.0421 0.6820 +[3,] 0.0312 0.4390 0.8977 0.0421 0.6418 +[4,] 0.0312 0.4281 0.7910 0.0421 0.6708 +[5,] 0.0312 0.4281 0.6758 0.0421 0.6795 +[6,] 0.0312 0.4281 0.8376 0.0421 0.6970 + PesticidesPctl ToxReleasePctl TrafficPctl CleanupSitesPctl +[1,] 0 0.5603 0.5594 0.5817 +[2,] 0 0.5543 0.3749 0.0000 +[3,] 0 0.5504 0.4248 0.1183 +[4,] 0 0.5590 0.3800 0.0000 +[5,] 0 0.5648 0.4868 0.3387 +[6,] 0 0.5565 0.6706 0.2262 + GroundwaterThreatsPctl HazWastePctl ImpWaterBodiesPctl SolidWastePctl +[1,] 0.5242 0.9252 0.2388 0.3572 +[2,] 0.8793 0.2851 0.0000 0.0000 +[3,] 0.8529 0.7407 0.0000 0.0000 +[4,] 0.9256 0.5189 0.0000 0.0000 +[5,] 0.8434 0.5640 0.0000 0.0000 +[6,] 0.7906 0.5827 0.0000 0.0000 + PollutionBurdenPctl AsthmaPctl LowBirthWeightPctl +[1,] 0.2662 0.0444 0.2306 +[2,] 0.2418 0.0980 0.2792 +[3,] 0.3337 0.2657 0.2162 +[4,] 0.2624 0.5598 0.3702 +[5,] 0.3140 0.8838 0.1900 +[6,] 0.3694 0.9307 0.0503 + CardiovascularDiseasePctl PopCharPctl EducationPctl LinguisticIsolPctl +[1,] 0.0142 0.0153 0.1255 0.0849 +[2,] 0.1453 0.0165 0.0042 0.0000 +[3,] 0.2011 0.1227 0.2412 0.5336 +[4,] 0.1428 0.1843 0.2029 0.0564 +[5,] 0.3887 0.3016 0.0740 0.1330 +[6,] 0.5278 0.3770 0.0973 0.0627 + PovertyPctl UnemploymentPctl HousingBurdenPctl +[1,] 0.1103 NA 0.1939 +[2,] 0.1144 0.1711 0.0067 +[3,] 0.1090 0.2941 0.0981 +[4,] 0.3642 0.1066 0.3748 +[5,] 0.3813 0.2820 0.3748 +[6,] 0.2442 0.7167 0.5407+ +
calenviroscreen %>%
+ select(ends_with("Pctl")) %>%
+ sapply(\(x) x / 100) %>%
+ head()
+
+OzonePctl PM2.5.Pctl DieselPMPctl DrinkingWaterPctl LeadPctl +[1,] 0.0312 0.3627 0.3476 0.0421 0.0774 +[2,] 0.0312 0.4197 0.9271 0.0421 0.6820 +[3,] 0.0312 0.4390 0.8977 0.0421 0.6418 +[4,] 0.0312 0.4281 0.7910 0.0421 0.6708 +[5,] 0.0312 0.4281 0.6758 0.0421 0.6795 +[6,] 0.0312 0.4281 0.8376 0.0421 0.6970 + PesticidesPctl ToxReleasePctl TrafficPctl CleanupSitesPctl +[1,] 0 0.5603 0.5594 0.5817 +[2,] 0 0.5543 0.3749 0.0000 +[3,] 0 0.5504 0.4248 0.1183 +[4,] 0 0.5590 0.3800 0.0000 +[5,] 0 0.5648 0.4868 0.3387 +[6,] 0 0.5565 0.6706 0.2262 + GroundwaterThreatsPctl HazWastePctl ImpWaterBodiesPctl SolidWastePctl +[1,] 0.5242 0.9252 0.2388 0.3572 +[2,] 0.8793 0.2851 0.0000 0.0000 +[3,] 0.8529 0.7407 0.0000 0.0000 +[4,] 0.9256 0.5189 0.0000 0.0000 +[5,] 0.8434 0.5640 0.0000 0.0000 +[6,] 0.7906 0.5827 0.0000 0.0000 + PollutionBurdenPctl AsthmaPctl LowBirthWeightPctl +[1,] 0.2662 0.0444 0.2306 +[2,] 0.2418 0.0980 0.2792 +[3,] 0.3337 0.2657 0.2162 +[4,] 0.2624 0.5598 0.3702 +[5,] 0.3140 0.8838 0.1900 +[6,] 0.3694 0.9307 0.0503 + CardiovascularDiseasePctl PopCharPctl EducationPctl LinguisticIsolPctl +[1,] 0.0142 0.0153 0.1255 0.0849 +[2,] 0.1453 0.0165 0.0042 0.0000 +[3,] 0.2011 0.1227 0.2412 0.5336 +[4,] 0.1428 0.1843 0.2029 0.0564 +[5,] 0.3887 0.3016 0.0740 0.1330 +[6,] 0.5278 0.3770 0.0973 0.0627 + PovertyPctl UnemploymentPctl HousingBurdenPctl +[1,] 0.1103 NA 0.1939 +[2,] 0.1144 0.1711 0.0067 +[3,] 0.1090 0.2941 0.0981 +[4,] 0.3642 0.1066 0.3748 +[5,] 0.3813 0.2820 0.3748 +[6,] 0.2442 0.7167 0.5407
Already know how to use functions to modify columns using mutate() or calculate summary statistics using summarize().
er_visits %>% - mutate(rate_round = round(rate, 2)) %>% - summarize(max_rate_round = max(rate_round, na.rm = T), - max_rate = max(rate, na.rm = T))+
# A tibble: 1 × 2 - max_rate_round max_rate - <dbl> <dbl> -1 89.3 89.3+
calenviroscreen %>% + summarize(max_pest = max(Pesticides, na.rm = T), + max_pov = max(Poverty, na.rm = T), + low_bw = max(LowBirthWeight, na.rm = T))+ +
# A tibble: 1 × 3 + max_pest max_pov low_bw + <dbl> <dbl> <dbl> +1 80811. 96.7 13.7
across from dplyracross() makes it easy to apply the same transformation to multiple columns. Usually used with summarize() or mutate().
summarize(across( .cols = <columns>, .fns = function))+
summarize(across(<columns>,function))
or
-mutate(across(.cols = <columns>, .fns = function))+
mutate(across(<columns>,function))
.cols =.fns =na.rm = TRUE), the function may need to be modified to an anonymous function, e.g., \(x) mean(x, na.rm = TRUE)na.rm = TRUE), use an anonymous function.across from dplyrCombining with summarize()
ces_dbl <- ces %>% select(CaliforniaCounty, CES4.0Score, CES4.0Percentile) - -ces_dbl %>% - summarize(across(.cols = everything(), .fns = mean, na.rm=T))+
calenviroscreen %>% + summarize(across( + c(Pesticides, Poverty, LowBirthWeight), + mean # no parentheses + ))
# A tibble: 1 × 3 - CaliforniaCounty CES4.0Score CES4.0Percentile - <dbl> <dbl> <dbl> -1 NA 28.3 50.0+ Pesticides Poverty LowBirthWeight + <dbl> <dbl> <dbl> +1 268. NA NA
across from dplyrCan use with other tidyverse functions like group_by!
Add anonymous function to include additional arguments (e.g., na.rm = T).
ces_dbl %>% - group_by(CaliforniaCounty) %>% - summarize(across(.cols = everything(), .fns = mean, na.rm=T))- -
# A tibble: 58 × 3 - CaliforniaCounty CES4.0Score CES4.0Percentile - <chr> <dbl> <dbl> - 1 "Alameda " 22.9 41.3 - 2 "Alpine " 13.6 22 - 3 "Amador " 20.7 38.8 - 4 "Butte " 21.7 39.8 - 5 "Calaveras " 16.1 28.0 - 6 "Colusa " 27.0 52.2 - 7 "Contra Costa" 21.0 36.7 - 8 "Del Norte" 21.4 40.3 - 9 "El Dorado" 10.2 14.6 -10 "Fresno " 40.9 69.5 -# ℹ 48 more rows+
calenviroscreen %>% + summarize(across( + c(Pesticides, Poverty, LowBirthWeight), + function(x) mean(x, na.rm = T) + ))+ +
# A tibble: 1 × 3 + Pesticides Poverty LowBirthWeight + <dbl> <dbl> <dbl> +1 268. 31.3 5.00
across from dplyrTo add arguments to functions, may need to use anonymous function. In this syntax, the shorthand \(x) is equivalent to function(x).
Can use with other tidyverse functions like group_by!
ces_dbl %>% - group_by(CaliforniaCounty) %>% - summarize(across(.cols = everything(), .fns = \(x) mean(x, na.rm = TRUE)))- -
# A tibble: 58 × 3 - CaliforniaCounty CES4.0Score CES4.0Percentile - <chr> <dbl> <dbl> - 1 "Alameda " 22.9 41.3 - 2 "Alpine " 13.6 22 - 3 "Amador " 20.7 38.8 - 4 "Butte " 21.7 39.8 - 5 "Calaveras " 16.1 28.0 - 6 "Colusa " 27.0 52.2 - 7 "Contra Costa" 21.0 36.7 - 8 "Del Norte" 21.4 40.3 - 9 "El Dorado" 10.2 14.6 -10 "Fresno " 40.9 69.5 +calenviroscreen %>% + group_by(CaliforniaCounty) %>% + summarize(across( + c(Pesticides, Poverty, LowBirthWeight), + function(x) mean(x, na.rm = T) + ))+ +# A tibble: 58 × 4 + CaliforniaCounty Pesticides Poverty LowBirthWeight + <chr> <dbl> <dbl> <dbl> + 1 "Alameda " 0.948 22.1 5.26 + 2 "Alpine " 0 38.9 NaN + 3 "Amador " 2.01 25.2 4.45 + 4 "Butte " 736. 39.9 4.64 + 5 "Calaveras " 1.20 28.2 3.55 + 6 "Colusa " 1186. 36.5 4.11 + 7 "Contra Costa" 10.5 20.6 4.71 + 8 "Del Norte" 47.4 48.4 NaN + 9 "El Dorado" 5.50 20.9 4.28 +10 "Fresno " 586. 45.8 5.96 # ℹ 48 more rows
across from dplyrUsing different tidyselect() options (e.g., starts_with(), ends_with(), contains())
ces_dbl %>% +calenviroscreen %>% group_by(CaliforniaCounty) %>% - summarize(across(.cols = contains("Perc"), .fns = mean))- -# A tibble: 58 × 2 - CaliforniaCounty CES4.0Percentile - <chr> <dbl> - 1 "Alameda " NA - 2 "Alpine " 22 - 3 "Amador " 38.8 - 4 "Butte " 39.8 - 5 "Calaveras " NA - 6 "Colusa " 52.2 - 7 "Contra Costa" 36.7 - 8 "Del Norte" 40.3 - 9 "El Dorado" 14.6 -10 "Fresno " NA + summarize(across(contains("PM"), mean))+ +# A tibble: 58 × 5 + CaliforniaCounty PM2.5 PM2.5.Pctl DieselPM DieselPMPctl + <chr> <dbl> <dbl> <dbl> <dbl> + 1 "Alameda " 8.87 31.9 0.350 66.4 + 2 "Alpine " 3.05 0.07 0.003 1.02 + 3 "Amador " 8.01 18.9 0.0111 4.18 + 4 "Butte " 8.22 23.0 0.106 33.1 + 5 "Calaveras " 8.12 22.6 0.0079 3.08 + 6 "Colusa " 7.54 13.3 0.0292 10.6 + 7 "Contra Costa" 8.76 31.0 0.210 48.6 + 8 "Del Norte" 5.71 2.93 0.0301 11.1 + 9 "El Dorado" 6.78 8.91 0.0380 13.6 +10 "Fresno " 13.2 91.4 0.181 44.8 # ℹ 48 more rows-
across from dplyrCombining with mutate(): rounding to the nearest power of 10 (with negative digits value)
ces_dbl %>%
- mutate(across(
- .cols = starts_with("CES"),
- .fns = round,
- digits = 3
- ))
+
+
+
-# A tibble: 8,035 × 3 - CaliforniaCounty CES4.0Score CES4.0Percentile - <chr> <dbl> <dbl> - 1 "Alameda " 4.85 2.8 - 2 "Alameda " 4.88 2.87 - 3 "Alameda " 11.2 15.9 - 4 "Alameda " 12.4 19.0 - 5 "Alameda " 16.7 29.7 - 6 "Alameda " 20.0 37.6 - 7 "Alameda " 36.7 70.1 - 8 "Alameda " 37.1 70.7 - 9 "Alameda " 40.7 76.2 -10 "Alameda " 43.7 80.4 -# ℹ 8,025 more rows- -
across from dplyracross from dplyrCombining with mutate() - the replace_na function
yearly_co2_emissions %>%
select(country, starts_with("194")) %>%
mutate(across(
- .cols = c(`1943`, `1944`, `1945`),
- .fns = replace_na,
- replace = 0
+ c(`1943`, `1944`, `1945`),
+ function(x) replace_na(x, replace = 0)
))
# A tibble: 192 × 11 @@ -3789,33 +3903,39 @@ # ℹ 182 more rows # ℹ 1 more variable: `1949` <dbl>-
mutate and acrossIf your function needs to span more than one line, better to define it first before using inside mutate() and across().
times1000 <- function(x) x * 1000 + -airquality %>% - mutate(across( - .cols = everything(), - .fns = times1000 - )) %>% - head(n = 2)+ -
Ozone Solar.R Wind Temp Month Day -1 41000 190000 7400 67000 5000 1000 -2 36000 118000 8000 72000 5000 2000+ -
airquality %>% - mutate(across( - .cols = everything(), - .fns = function(x) x * 1000 - )) %>% - head(n = 2)- -
Ozone Solar.R Wind Temp Month Day -1 41000 190000 7400 67000 5000 1000 -2 36000 118000 8000 72000 5000 2000+ + + + + + + + + + + + + + + + + + + + + + +
purrr packageLoad all the libraries we will use in this lab.
-library(readr)
-library(dplyr)
-library(ggplot2)library(tidyverse)Create a function that takes one argument, a vector, and returns the
-sum of the vector and squares the result. Call it “sum_squared”. Test
-your function on the vector c(2,7,21,30,90) - you should
-get the answer 22500.
c(2,7,21,30,90) - you
+should get the answer 22500.
# General format
NEW_FUNCTION <- function(x, y) x + y or
@@ -388,8 +386,8 @@Amend the function has_n from question 1.2 so that it
takes a default value of 21 for the numeric argument.
Create a new number b_num that is not contained with
nums. Use your updated has_n function with the
default value and add b_num as the n argument
@@ -398,12 +396,12 @@
Read in the CalEnviroScreen from https://daseh.org/data/CalEnviroScreen_data.csv. Assign the data the name “ces”.
We want to get some summary statistics on water contamination. Use
across inside summarize to get the sum total
@@ -415,34 +413,40 @@
# General format
data %>%
summarize(across(
- .cols = {vector or tidyselect},
- .fns = {some function},
- {additional arguments}
+ {vector or tidyselect},
+ {some function}
))Use across and mutate to convert all
columns containing the word “Pctl” into proportions (i.e., divide that
value by 100). Hint: use contains() to
-select the right columns within across(). Use a “function
-on the fly” to divide by 100. It will also be easier to check your work
-if you select() columns that match “Pctl”.
across(). Use an anonymous
+function (“function on the fly”) to divide by 100
+(function(x) x / 100). It will also be easier to check your
+work if you select() columns that match “Pctl”.
+# General format
+data %>%
+ mutate(across(
+ {vector or tidyselect},
+ {some function}
+ ))Use across and mutate to convert all
columns starting with the string “PM” into a binary variable: TRUE if
the value is greater than 10 and FALSE if less than or equal to 10.
Hint: use starts_with() to select the
-columns that start with “PM”. Use a “function on the fly” to do a
-logical test if the value is greater than 10.
Take your code from question 2.4 and assign it to the variable
ces_dat.
Load all the libraries we will use in this lab.
-library(readr)
-library(dplyr)
-library(ggplot2)library(tidyverse)Create a function that takes one argument, a vector, and returns the @@ -444,14 +442,13 @@
# General format
data %>%
summarize(across(
- .cols = {vector or tidyselect},
- .fns = {some function},
- {additional arguments}
+ {vector or tidyselect},
+ {some function}
))ces %>%
summarize(across(
- .cols = contains("Water") & ends_with("Pctl"),
- .fns = sum
+ contains("Water") & ends_with("Pctl"),
+ sum
))## # A tibble: 1 × 3
## DrinkingWaterPctl GroundwaterThreatsPctl ImpWaterBodiesPctl
@@ -459,21 +456,9 @@ 2.2
## 1 NA 304029. 256802.ces %>%
summarize(across(
- .cols = contains("Water") & ends_with("Pctl"),
- .fns = sum,
- na.rm = TRUE
+ contains("Water") & ends_with("Pctl"),
+ function(x) sum(x, na.rm = T)
))## Warning: There was 1 warning in `summarize()`.
-## ℹ In argument: `across(...)`.
-## Caused by warning:
-## ! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
-## Supply arguments directly to `.fns` through an anonymous function instead.
-##
-## # Previously
-## across(a:b, mean, na.rm = TRUE)
-##
-## # Now
-## across(a:b, \(x) mean(x, na.rm = TRUE))## # A tibble: 1 × 3
## DrinkingWaterPctl GroundwaterThreatsPctl ImpWaterBodiesPctl
## <dbl> <dbl> <dbl>
@@ -484,20 +469,20 @@ 2.3
Use across and mutate to convert all
columns containing the word “Pctl” into proportions (i.e., divide that
value by 100). Hint: use contains() to
-select the right columns within across(). Use a “function
-on the fly” to divide by 100 (function(x) x / 100). It will
-also be easier to check your work if you select() columns
-that match “Pctl”.
+select the right columns within across(). Use an anonymous
+function (“function on the fly”) to divide by 100
+(function(x) x / 100). It will also be easier to check your
+work if you select() columns that match “Pctl”.
# General format
data %>%
mutate(across(
- .cols = {vector or tidyselect},
- .fns = {some function}
+ {vector or tidyselect},
+ {some function}
))
ces %>%
mutate(across(
- .cols = contains("Pctl"),
- .fns = function(x) x / 100
+ contains("Pctl"),
+ function(x) x / 100
)) %>%
select(contains("Pctl"))
## # A tibble: 8,035 × 23
@@ -530,12 +515,12 @@ P.2
columns starting with the string “PM” into a binary variable: TRUE if
the value is greater than 10 and FALSE if less than or equal to 10.
Hint: use starts_with() to select the
-columns that start with “PM”. Use a “function on the fly” to do a
-logical test if the value is greater than 10.
+columns that start with “PM”. Use an anonymous function (“function on
+the fly”) to do a logical test if the value is greater than 10.
ces %>%
mutate(across(
- .cols = starts_with("PM"),
- .fns = function(x) x > 10
+ starts_with("PM"),
+ function(x) x > 10
))
## # A tibble: 8,035 × 68
## ...1 CensusTract CaliforniaCounty ZIP Longitude Latitude ApproxLocation
@@ -575,8 +560,8 @@ P.3
ces_dat <-
ces %>%
mutate(across(
- .cols = starts_with("PM"),
- .fns = function(x) x > 10
+ starts_with("PM"),
+ function(x) x > 10
)) %>%
filter(ApproxLocation != "Oakland")