Module 13: Apply it to your data 12
Chapter 21 Iteration
Christa Imbriano
Import your data
data("mtcars")Repeat the same operation over different columns of a data frame
Case of numeric variables
mtcars %>% map_dbl(.x = ., .f = ~mean(x = .x))## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500mtcars %>% map_dbl(.f = ~mean(x = .x))## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500mtcars %>% map_dbl(.f = mean)## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500mtcars %>% map_dbl(mean)## mpg cyl disp hp drat wt qsec
## 20.090625 6.187500 230.721875 146.687500 3.596563 3.217250 17.848750
## vs am gear carb
## 0.437500 0.406250 3.687500 2.812500# Adding an argument
mtcars %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 0.1))## mpg cyl disp hp drat wt
## 19.6961538 6.2307692 222.5230769 141.1923077 3.5792308 3.1526923
## qsec vs am gear carb
## 17.8276923 0.4230769 0.3846154 3.6153846 2.6538462mtcars %>% map_dbl(mean, trim = 0.1)## mpg cyl disp hp drat wt
## 19.6961538 6.2307692 222.5230769 141.1923077 3.5792308 3.1526923
## qsec vs am gear carb
## 17.8276923 0.4230769 0.3846154 3.6153846 2.6538462mtcars %>% select(.data = ., mpg)## mpg
## Mazda RX4 21.0
## Mazda RX4 Wag 21.0
## Datsun 710 22.8
## Hornet 4 Drive 21.4
## Hornet Sportabout 18.7
## Valiant 18.1
## Duster 360 14.3
## Merc 240D 24.4
## Merc 230 22.8
## Merc 280 19.2
## Merc 280C 17.8
## Merc 450SE 16.4
## Merc 450SL 17.3
## Merc 450SLC 15.2
## Cadillac Fleetwood 10.4
## Lincoln Continental 10.4
## Chrysler Imperial 14.7
## Fiat 128 32.4
## Honda Civic 30.4
## Toyota Corolla 33.9
## Toyota Corona 21.5
## Dodge Challenger 15.5
## AMC Javelin 15.2
## Camaro Z28 13.3
## Pontiac Firebird 19.2
## Fiat X1-9 27.3
## Porsche 914-2 26.0
## Lotus Europa 30.4
## Ford Pantera L 15.8
## Ferrari Dino 19.7
## Maserati Bora 15.0
## Volvo 142E 21.4mtcars %>% select(mpg)## mpg
## Mazda RX4 21.0
## Mazda RX4 Wag 21.0
## Datsun 710 22.8
## Hornet 4 Drive 21.4
## Hornet Sportabout 18.7
## Valiant 18.1
## Duster 360 14.3
## Merc 240D 24.4
## Merc 230 22.8
## Merc 280 19.2
## Merc 280C 17.8
## Merc 450SE 16.4
## Merc 450SL 17.3
## Merc 450SLC 15.2
## Cadillac Fleetwood 10.4
## Lincoln Continental 10.4
## Chrysler Imperial 14.7
## Fiat 128 32.4
## Honda Civic 30.4
## Toyota Corolla 33.9
## Toyota Corona 21.5
## Dodge Challenger 15.5
## AMC Javelin 15.2
## Camaro Z28 13.3
## Pontiac Firebird 19.2
## Fiat X1-9 27.3
## Porsche 914-2 26.0
## Lotus Europa 30.4
## Ford Pantera L 15.8
## Ferrari Dino 19.7
## Maserati Bora 15.0
## Volvo 142E 21.4Create your own function
# Double values in columns
double_by_vector <- function(x, factor) {x * factor}
10 %>% double_by_vector(factor = 5)## [1] 50100 %>% double_by_vector(factor = 5)## [1] 500mtcars %>% map_dfr(.x = ., .f = ~double_by_vector(x = .x, factor = 10))## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 210 60 1600 1100 39 26.2 165. 0 10 40 40
## 2 210 60 1600 1100 39 28.8 170. 0 10 40 40
## 3 228 40 1080 930 38.5 23.2 186. 10 10 40 10
## 4 214 60 2580 1100 30.8 32.2 194. 10 0 30 10
## 5 187 80 3600 1750 31.5 34.4 170. 0 0 30 20
## 6 181 60 2250 1050 27.6 34.6 202. 10 0 30 10
## 7 143 80 3600 2450 32.1 35.7 158. 0 0 30 40
## 8 244 40 1467 620 36.9 31.9 200 10 0 40 20
## 9 228 40 1408 950 39.2 31.5 229 10 0 40 20
## 10 192 60 1676 1230 39.2 34.4 183 10 0 40 40
## # ℹ 22 more rowsmtcars %>% map_dfr(double_by_vector, factor = 10)## # A tibble: 32 × 11
## mpg cyl disp hp drat wt qsec vs am gear carb
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 210 60 1600 1100 39 26.2 165. 0 10 40 40
## 2 210 60 1600 1100 39 28.8 170. 0 10 40 40
## 3 228 40 1080 930 38.5 23.2 186. 10 10 40 10
## 4 214 60 2580 1100 30.8 32.2 194. 10 0 30 10
## 5 187 80 3600 1750 31.5 34.4 170. 0 0 30 20
## 6 181 60 2250 1050 27.6 34.6 202. 10 0 30 10
## 7 143 80 3600 2450 32.1 35.7 158. 0 0 30 40
## 8 244 40 1467 620 36.9 31.9 200 10 0 40 20
## 9 228 40 1408 950 39.2 31.5 229 10 0 40 20
## 10 192 60 1676 1230 39.2 34.4 183 10 0 40 40
## # ℹ 22 more rowsRepeat the same operation over different elements of a list
When you have a grouping variable (factor)
mtcars %>% lm(formula = mpg ~wt, data = .)##
## Call:
## lm(formula = mpg ~ wt, data = .)
##
## Coefficients:
## (Intercept) wt
## 37.285 -5.344mtcars %>% distinct(cyl)## cyl
## Mazda RX4 6
## Datsun 710 4
## Hornet Sportabout 8reg_coeff_tbl <- mtcars %>%
# Split it into a list of dataf rames
split(.$cyl) %>%
# Repeat regression over each group
map(~lm(formula = mpg ~ wt, data = .x)) %>%
# Extract coefficients from regression results
map(broom::tidy, conf.int = TRUE) %>%
# Convert to tibble
bind_rows(.id = "cyl") %>%
# Filter or wt coefficients
filter(term == "wt")
reg_coeff_tbl %>%
mutate(estimate = -estimate,
conf.low = -conf.low,
conf.high = -conf.high) %>%
ggplot(aes(x = estimate, y = cyl)) +
geom_point() +
geom_errorbar(aes(xmin = conf.low, xmax = conf.high))
Create your own
Choose either one of the two cases above and apply it to your data
data <- read_excel("../00_data/myData.xlsx")
data## # A tibble: 1,232 × 9
## Column1 state condition measure_id measure_name score footnote
## <dbl> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 1 AK Healthcare Personnel Va… HCP_COVID… Percentage … 7.3 NA
## 2 2 AK Healthcare Personnel Va… IMM_3 Healthcare … 80 NA
## 3 3 AK Emergency Department OP_18b Average (me… 140 25, 26
## 4 4 AK Emergency Department OP_18b_HI… Average tim… 157 25, 26
## 5 5 AK Emergency Department OP_18b_LO… Average tim… 136 25, 26
## 6 6 AK Emergency Department OP_18b_ME… Average tim… 136 25, 26
## 7 7 AK Emergency Department OP_18b_VE… Average tim… NA 25, 26
## 8 8 AK Emergency Department OP_18c Average (me… 196 25
## 9 9 AK Emergency Department OP_18c_HI… Average tim… 230 25
## 10 10 AK Emergency Department OP_18c_LO… Average tim… 182 25
## # ℹ 1,222 more rows
## # ℹ 2 more variables: start_date <dttm>, end_date <dttm>Own example
data <- na.omit(data[, c("state", "score", "condition")])
data## # A tibble: 1,232 × 3
## state score condition
## <chr> <chr> <chr>
## 1 AK 7.3 Healthcare Personnel Vaccination
## 2 AK 80 Healthcare Personnel Vaccination
## 3 AK 140 Emergency Department
## 4 AK 157 Emergency Department
## 5 AK 136 Emergency Department
## 6 AK 136 Emergency Department
## 7 AK NA Emergency Department
## 8 AK 196 Emergency Department
## 9 AK 230 Emergency Department
## 10 AK 182 Emergency Department
## # ℹ 1,222 more rowsMean of score with confidence levels
filtered_data <- data %>%
filter(state %in% c("AK", "AZ", "CA"))
# Step 2: Select only numeric columns for calculations
numeric_data <- filtered_data %>%
select(state, where(is.numeric)) # keeps 'state' and numeric columns
# Step 3: Calculate sum and standard deviation by state
standard_deviation <- numeric_data %>%
group_by(state) %>%
summarise(across(
.cols = where(is.numeric), # apply to all numeric columns
.fns = list(
total = ~sum(.x, na.rm = TRUE),
stddev = ~sd(.x, na.rm = TRUE)
),
.names = "{col}_{fn}" # output column names like score_total, score_stddev
))
# Step 4: View the results
print(standard_deviation)## # A tibble: 3 × 1
## state
## <chr>
## 1 AK
## 2 AZ
## 3 CA