data("mtcars")
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 2.812500
mtcars %>% 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 2.812500
mtcars %>% 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 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 2.6538462
mtcars %>% 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 2.6538462
mtcars %>% 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 21.4
mtcars %>% 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 21.4
Create your own function
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 2)
## [1] 20
mtcars %>% map_dfr(.x = ., .f = ~double_by_factor(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
## # … with 22 more rows
When you have a grouping variable (factor)
mtcars %>% lm(formula = mpg ~ wt, data = .)
##
## Call:
## lm(formula = mpg ~ wt, data = .)
##
## Coefficients:
## (Intercept) wt
## 37.285 -5.344
mtcars %>% distinct(cyl)
## cyl
## Mazda RX4 6
## Datsun 710 4
## Hornet Sportabout 8
re_coeff_tbl <- mtcars %>% split(.$cyl) %>% map(~lm(formula = mpg ~ wt, data = .x)) %>% map(broom::tidy, conf.int = TRUE) %>% bind_rows(id. = “cyl”) %>% filter(term == “wt”)
re_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, xmox = conf.high))
Choose either one of the two cases above and apply it to your data
data <- read_excel("Raisin_Dataset.xlsx")
data
## # A tibble: 900 × 7
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea Extent Perime…¹
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 87524 442. 253. 0.820 90546 0.759 1184.
## 2 75166 407. 243. 0.802 78789 0.684 1122.
## 3 90856 442. 266. 0.798 93717 0.638 1209.
## 4 45928 287. 209. 0.685 47336 0.700 844.
## 5 79408 352. 291. 0.564 81463 0.793 1073.
## 6 49242 318. 200. 0.777 51368 0.658 882.
## 7 42492 310. 176. 0.823 43904 0.666 824.
## 8 60952 332. 235. 0.706 62329 0.744 933.
## 9 42256 323. 173. 0.845 44743 0.698 850.
## 10 64380 367. 228. 0.784 66125 0.664 982.
## # … with 890 more rows, and abbreviated variable name ¹Perimeter
data %>% map_dbl(.x = ., .f = ~mean(x = .x))
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea
## 8.780413e+04 4.309300e+02 2.544881e+02 7.815422e-01 9.118609e+04
## Extent Perimeter
## 6.995079e-01 1.165907e+03
data %>% map_dbl(.f = ~mean(x = .x))
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea
## 8.780413e+04 4.309300e+02 2.544881e+02 7.815422e-01 9.118609e+04
## Extent Perimeter
## 6.995079e-01 1.165907e+03
data %>% map_dbl(mean)
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea
## 8.780413e+04 4.309300e+02 2.544881e+02 7.815422e-01 9.118609e+04
## Extent Perimeter
## 6.995079e-01 1.165907e+03
#adding argument
data %>% map_dbl(.x = ., .f = ~mean(x = .x, trim = 1))
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea
## 78902.000000 407.803951 247.848409 0.798846 81651.000000
## Extent Perimeter
## 0.707367 1119.509000
data %>% map_dbl(mean, trim = 1)
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexArea
## 78902.000000 407.803951 247.848409 0.798846 81651.000000
## Extent Perimeter
## 0.707367 1119.509000
data %>% select(.data = ., Area)
## # A tibble: 900 × 1
## Area
## <dbl>
## 1 87524
## 2 75166
## 3 90856
## 4 45928
## 5 79408
## 6 49242
## 7 42492
## 8 60952
## 9 42256
## 10 64380
## # … with 890 more rows
data %>% select(Area)
## # A tibble: 900 × 1
## Area
## <dbl>
## 1 87524
## 2 75166
## 3 90856
## 4 45928
## 5 79408
## 6 49242
## 7 42492
## 8 60952
## 9 42256
## 10 64380
## # … with 890 more rows
Create your own function
double_by_factor <- function(x, factor) {x * factor}
10 %>% double_by_factor(factor = 100)
## [1] 1000
data %>% map_dfr(.x = ., .f = ~double_by_factor(x = .x, factor = 100))
## # A tibble: 900 × 7
## Area MajorAxisLength MinorAxisLength Eccentricity ConvexA…¹ Extent Perim…²
## <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 8752400 44225. 25329. 82.0 9054600 75.9 118404
## 2 7516600 40669. 24303. 80.2 7878900 68.4 112179.
## 3 9085600 44227. 26633. 79.8 9371700 63.8 120858.
## 4 4592800 28654. 20876. 68.5 4733600 70.0 84416.
## 5 7940800 35219. 29083. 56.4 8146300 79.3 107325.
## 6 4924200 31813. 20012. 77.7 5136800 65.8 88184.
## 7 4249200 31015. 17613. 82.3 4390400 66.6 82380.
## 8 6095200 33246. 23543. 70.6 6232900 74.4 93337.
## 9 4225600 32319. 17258. 84.5 4474300 69.8 84973.
## 10 6438000 36696. 22777. 78.4 6612500 66.4 98154.
## # … with 890 more rows, and abbreviated variable names ¹ConvexArea, ²Perimeter