Iris Data Set
2025-08-21
library(datasets)
data(iris)
summary(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
## ir3<- kmeans(iris[,-5], center=3, iter.max=200)
ir3## K-means clustering with 3 clusters of sizes 38, 62, 50
##
## Cluster means:
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 1 6.850000 3.073684 5.742105 2.071053
## 2 5.901613 2.748387 4.393548 1.433871
## 3 5.006000 3.428000 1.462000 0.246000
##
## Clustering vector:
## [1] 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3
## [38] 3 3 3 3 3 3 3 3 3 3 3 3 3 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2
## [75] 2 2 2 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 2 1 1 1 1 2 1 1 1 1
## [112] 1 1 2 2 1 1 1 1 2 1 2 1 2 1 1 2 2 1 1 1 1 1 2 1 1 1 1 2 1 1 1 2 1 1 1 2 1
## [149] 1 2
##
## Within cluster sum of squares by cluster:
## [1] 23.87947 39.82097 15.15100
## (between_SS / total_SS = 88.4 %)
##
## Available components:
##
## [1] "cluster" "centers" "totss" "withinss" "tot.withinss"
## [6] "betweenss" "size" "iter" "ifault"table(ir3$cluster, iris$Species)##
## setosa versicolor virginica
## 1 0 2 36
## 2 0 48 14
## 3 50 0 0cm<-table(ir3$cluster,iris$Species)
1-sum(diag(cm))/sum(cm)## [1] 0.68str(iris)## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...row.names(iris)## [1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10" "11" "12"
## [13] "13" "14" "15" "16" "17" "18" "19" "20" "21" "22" "23" "24"
## [25] "25" "26" "27" "28" "29" "30" "31" "32" "33" "34" "35" "36"
## [37] "37" "38" "39" "40" "41" "42" "43" "44" "45" "46" "47" "48"
## [49] "49" "50" "51" "52" "53" "54" "55" "56" "57" "58" "59" "60"
## [61] "61" "62" "63" "64" "65" "66" "67" "68" "69" "70" "71" "72"
## [73] "73" "74" "75" "76" "77" "78" "79" "80" "81" "82" "83" "84"
## [85] "85" "86" "87" "88" "89" "90" "91" "92" "93" "94" "95" "96"
## [97] "97" "98" "99" "100" "101" "102" "103" "104" "105" "106" "107" "108"
## [109] "109" "110" "111" "112" "113" "114" "115" "116" "117" "118" "119" "120"
## [121] "121" "122" "123" "124" "125" "126" "127" "128" "129" "130" "131" "132"
## [133] "133" "134" "135" "136" "137" "138" "139" "140" "141" "142" "143" "144"
## [145] "145" "146" "147" "148" "149" "150"## Data Preprocess
sum(!complete.cases(iris))## [1] 0 ## Remove or impute missing objects
df <-na.omit(iris)
## Rescale (or normalization, etc.)
## Rescale (or normalization, etc.)
##df <-scale(df,center=T,scale = T)
summary(df)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. :4.300 Min. :2.000 Min. :1.000 Min. :0.100
## 1st Qu.:5.100 1st Qu.:2.800 1st Qu.:1.600 1st Qu.:0.300
## Median :5.800 Median :3.000 Median :4.350 Median :1.300
## Mean :5.843 Mean :3.057 Mean :3.758 Mean :1.199
## 3rd Qu.:6.400 3rd Qu.:3.300 3rd Qu.:5.100 3rd Qu.:1.800
## Max. :7.900 Max. :4.400 Max. :6.900 Max. :2.500
## Species
## setosa :50
## versicolor:50
## virginica :50
##
##
## apply(iris, 2, sd)## Warning in var(if (is.vector(x) || is.factor(x)) x else as.double(x), na.rm =
## na.rm): NAs introduced by coercion## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 0.8280661 0.4358663 1.7652982 0.7622377 NA apply(iris, 2, mean)## Warning in mean.default(newX[, i], ...): argument is not numeric or logical:
## returning NA## Warning in mean.default(newX[, i], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(newX[, i], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(newX[, i], ...): argument is not numeric or logical:
## returning NA
## Warning in mean.default(newX[, i], ...): argument is not numeric or logical:
## returning NA## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## NA NA NA NA NA apply(df, 2, sd)## Warning in var(if (is.vector(x) || is.factor(x)) x else as.double(x), na.rm =
## na.rm): NAs introduced by coercion## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 0.8280661 0.4358663 1.7652982 0.7622377 NA library(factoextra)## Warning: package 'factoextra' was built under R version 4.5.1## Loading required package: ggplot2## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa distance<-get_dist(df)## Warning in stats::dist(x, method = method, ...): NAs introduced by coercion library(mlr3)## Warning: package 'mlr3' was built under R version 4.5.1 library(mlr3cluster)## Warning: package 'mlr3cluster' was built under R version 4.5.1 library(mlr3viz)## Warning: package 'mlr3viz' was built under R version 4.5.1 library(devtools)## Warning: package 'devtools' was built under R version 4.5.1## Loading required package: usethis## Warning: package 'usethis' was built under R version 4.5.1 fviz_dist(distance, gradient = list(low = "#00AFBB",mid = "white", high = "green"))
## R Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see <http://rmarkdown.rstudio.com>.
When you click the **Knit** button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
```