Bộ dữ liệu Iris
data("iris")
setosa <- iris[iris$Species == 'setosa',]
notsetosa <- iris[!iris$Species == 'setosa',]summary(iris$Sepal.Length)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.300 5.100 5.800 5.843 6.400 7.900iris$slcoded <- cut(iris$Sepal.Length, breaks = c(4.3,4.8,7.2,7.9),labels = c('ngắn','vừa','dài'))
table(iris$slcoded)##
## ngắn vừa dài
## 15 126 8mean(iris$Sepal.Length)## [1] 5.843333var(iris$Sepal.Length)## [1] 0.6856935sd(iris$Sepal.Length)## [1] 0.8280661sum(iris$Sepal.Length)## [1] 876.5quantile(iris$Sepal.Length, .3)## 30%
## 5.27table(iris$Species)##
## setosa versicolor virginica
## 50 50 50aggregate(iris$Sepal.Length, list(iris$Species), FUN = 'mean')## Group.1 x
## 1 setosa 5.006
## 2 versicolor 5.936
## 3 virginica 6.588aggregate(iris$Sepal.Length, list(iris$Species), FUN = 'var')## Group.1 x
## 1 setosa 0.1242490
## 2 versicolor 0.2664327
## 3 virginica 0.4043429aggregate(iris$Sepal.Length, list(iris$Species), FUN = 'sd')## Group.1 x
## 1 setosa 0.3524897
## 2 versicolor 0.5161711
## 3 virginica 0.6358796aggregate(iris$Sepal.Length, list(iris$Species), FUN = 'sum')## Group.1 x
## 1 setosa 250.3
## 2 versicolor 296.8
## 3 virginica 329.4aggregate(iris$Sepal.Length, list(iris$slcoded), FUN = 'mean')## Group.1 x
## 1 ngắn 4.633333
## 2 vừa 5.886508
## 3 dài 7.625000aggregate(iris$Sepal.Length, list(iris$Species), FUN = 'summary')## Group.1 x.Min. x.1st Qu. x.Median x.Mean x.3rd Qu. x.Max.
## 1 setosa 4.300 4.800 5.000 5.006 5.200 5.800
## 2 versicolor 4.900 5.600 5.900 5.936 6.300 7.000
## 3 virginica 4.900 6.225 6.500 6.588 6.900 7.900library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ purrr 1.0.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsiris %>% group_by(Species)## # A tibble: 150 × 6
## # Groups: Species [3]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species slcoded
## <dbl> <dbl> <dbl> <dbl> <fct> <fct>
## 1 5.1 3.5 1.4 0.2 setosa vừa
## 2 4.9 3 1.4 0.2 setosa vừa
## 3 4.7 3.2 1.3 0.2 setosa ngắn
## 4 4.6 3.1 1.5 0.2 setosa ngắn
## 5 5 3.6 1.4 0.2 setosa vừa
## 6 5.4 3.9 1.7 0.4 setosa vừa
## 7 4.6 3.4 1.4 0.3 setosa ngắn
## 8 5 3.4 1.5 0.2 setosa vừa
## 9 4.4 2.9 1.4 0.2 setosa ngắn
## 10 4.9 3.1 1.5 0.1 setosa vừa
## # ℹ 140 more rowspoi2 <- rpois(10,2)
poi2## [1] 2 0 1 3 0 3 1 1 1 3is.vector(poi2)## [1] TRUEpoi2 <- as.data.frame(poi2)
tg <- seq(2, length = 10)
tg <- seq(2,2, length = 10)
tg## [1] 2 2 2 2 2 2 2 2 2 2tg <- seq(1,1, length = 10)
poi2$tg <- tg
d1 <- rpois(10,6)
d2 <- rnorm(10,6,2)
d3 <- rnorm(10,15,2)
d1 <- as.data.frame(d1)
d1$tg <- seq(1,1, length = 10)
d2 <- as.data.frame(d2)
d2$tg <- seq(2,2, length = 10)
d3 <- as.data.frame(d3)
d3$tg <- seq(3,3, length = 10)Thao tác trên dataset
data(trees)
d <-trees
str(d)## 'data.frame': 31 obs. of 3 variables:
## $ Girth : num 8.3 8.6 8.8 10.5 10.7 10.8 11 11 11.1 11.2 ...
## $ Height: num 70 65 63 72 81 83 66 75 80 75 ...
## $ Volume: num 10.3 10.3 10.2 16.4 18.8 19.7 15.6 18.2 22.6 19.9 ...names(d) <- c('G','H','V')Tới đây đã xong một số việc.
head(d)## G H V
## 1 8.3 70 10.3
## 2 8.6 65 10.3
## 3 8.8 63 10.2
## 4 10.5 72 16.4
## 5 10.7 81 18.8
## 6 10.8 83 19.7Vol <- d$V
Vol## [1] 10.3 10.3 10.2 16.4 18.8 19.7 15.6 18.2 22.6 19.9 24.2 21.0 21.4 21.3 19.1
## [16] 22.2 33.8 27.4 25.7 24.9 34.5 31.7 36.3 38.3 42.6 55.4 55.7 58.3 51.5 51.0
## [31] 77.0Vol15 <- Vol[Vol>15 & Vol<50]
Vol15## [1] 16.4 18.8 19.7 15.6 18.2 22.6 19.9 24.2 21.0 21.4 21.3 19.1 22.2 33.8 27.4
## [16] 25.7 24.9 34.5 31.7 36.3 38.3 42.6Voll <- d[d$V > 15 |d$H < 60,]
Voll## G H V
## 4 10.5 72 16.4
## 5 10.7 81 18.8
## 6 10.8 83 19.7
## 7 11.0 66 15.6
## 8 11.0 75 18.2
## 9 11.1 80 22.6
## 10 11.2 75 19.9
## 11 11.3 79 24.2
## 12 11.4 76 21.0
## 13 11.4 76 21.4
## 14 11.7 69 21.3
## 15 12.0 75 19.1
## 16 12.9 74 22.2
## 17 12.9 85 33.8
## 18 13.3 86 27.4
## 19 13.7 71 25.7
## 20 13.8 64 24.9
## 21 14.0 78 34.5
## 22 14.2 80 31.7
## 23 14.5 74 36.3
## 24 16.0 72 38.3
## 25 16.3 77 42.6
## 26 17.3 81 55.4
## 27 17.5 82 55.7
## 28 17.9 80 58.3
## 29 18.0 80 51.5
## 30 18.0 80 51.0
## 31 20.6 87 77.0d$logV <- log(d$V)
d$logH <- log(d$H)
d$Tong <- d$G + d$H + d$V
cut(Vol,4)## [1] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9]
## [7] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9]
## [13] (10.1,26.9] (10.1,26.9] (10.1,26.9] (10.1,26.9] (26.9,43.6] (26.9,43.6]
## [19] (10.1,26.9] (10.1,26.9] (26.9,43.6] (26.9,43.6] (26.9,43.6] (26.9,43.6]
## [25] (26.9,43.6] (43.6,60.3] (43.6,60.3] (43.6,60.3] (43.6,60.3] (43.6,60.3]
## [31] (60.3,77.1]
## Levels: (10.1,26.9] (26.9,43.6] (43.6,60.3] (60.3,77.1]table(cut(Vol,4))##
## (10.1,26.9] (26.9,43.6] (43.6,60.3] (60.3,77.1]
## 18 7 5 1Bộ dữ liệu Iris
data("iris")
cut(iris$Petal.Length,4)## [1] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [6] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [11] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [16] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [21] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [26] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [31] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [36] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [41] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [46] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48] (0.994,2.48]
## [51] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43]
## [56] (3.95,5.43] (3.95,5.43] (2.48,3.95] (3.95,5.43] (2.48,3.95]
## [61] (2.48,3.95] (3.95,5.43] (3.95,5.43] (3.95,5.43] (2.48,3.95]
## [66] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (2.48,3.95]
## [71] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43]
## [76] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (2.48,3.95]
## [81] (2.48,3.95] (2.48,3.95] (2.48,3.95] (3.95,5.43] (3.95,5.43]
## [86] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43]
## [91] (3.95,5.43] (3.95,5.43] (3.95,5.43] (2.48,3.95] (3.95,5.43]
## [96] (3.95,5.43] (3.95,5.43] (3.95,5.43] (2.48,3.95] (3.95,5.43]
## [101] (5.43,6.91] (3.95,5.43] (5.43,6.91] (5.43,6.91] (5.43,6.91]
## [106] (5.43,6.91] (3.95,5.43] (5.43,6.91] (5.43,6.91] (5.43,6.91]
## [111] (3.95,5.43] (3.95,5.43] (5.43,6.91] (3.95,5.43] (3.95,5.43]
## [116] (3.95,5.43] (5.43,6.91] (5.43,6.91] (5.43,6.91] (3.95,5.43]
## [121] (5.43,6.91] (3.95,5.43] (5.43,6.91] (3.95,5.43] (5.43,6.91]
## [126] (5.43,6.91] (3.95,5.43] (3.95,5.43] (5.43,6.91] (5.43,6.91]
## [131] (5.43,6.91] (5.43,6.91] (5.43,6.91] (3.95,5.43] (5.43,6.91]
## [136] (5.43,6.91] (5.43,6.91] (5.43,6.91] (3.95,5.43] (3.95,5.43]
## [141] (5.43,6.91] (3.95,5.43] (3.95,5.43] (5.43,6.91] (5.43,6.91]
## [146] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43] (3.95,5.43]
## Levels: (0.994,2.48] (2.48,3.95] (3.95,5.43] (5.43,6.91]table(cut(iris$Petal.Length,4))##
## (0.994,2.48] (2.48,3.95] (3.95,5.43] (5.43,6.91]
## 50 11 61 28table(cut(iris$Petal.Length,4),iris$Species)##
## setosa versicolor virginica
## (0.994,2.48] 50 0 0
## (2.48,3.95] 0 11 0
## (3.95,5.43] 0 39 22
## (5.43,6.91] 0 0 28