class work 4
Data Visualization
- Bar
- Pie
- Line graph
- Box plot
- Different type of curves
- Heatmap
- scatter plot
- histogram
iris = read.csv("iris.csv")
iris## sepal.length sepal.width petal.length petal.width variety
## 1 5.1 3.5 1.4 0.2 Setosa
## 2 4.9 3.0 1.4 0.2 Setosa
## 3 4.7 3.2 1.3 0.2 Setosa
## 4 4.6 3.1 1.5 0.2 Setosa
## 5 5.0 3.6 1.4 0.2 Setosa
## 6 5.4 3.9 1.7 0.4 Setosa
## 7 4.6 3.4 1.4 0.3 Setosa
## 8 5.0 3.4 1.5 0.2 Setosa
## 9 4.4 2.9 1.4 0.2 Setosa
## 10 4.9 3.1 1.5 0.1 Setosa
## 11 5.4 3.7 1.5 0.2 Setosa
## 12 4.8 3.4 1.6 0.2 Setosa
## 13 4.8 3.0 1.4 0.1 Setosa
## 14 4.3 3.0 1.1 0.1 Setosa
## 15 5.8 4.0 1.2 0.2 Setosa
## 16 5.7 4.4 1.5 0.4 Setosa
## 17 5.4 3.9 1.3 0.4 Setosa
## 18 5.1 3.5 1.4 0.3 Setosa
## 19 5.7 3.8 1.7 0.3 Setosa
## 20 5.1 3.8 1.5 0.3 Setosa
## 21 5.4 3.4 1.7 0.2 Setosa
## 22 5.1 3.7 1.5 0.4 Setosa
## 23 4.6 3.6 1.0 0.2 Setosa
## 24 5.1 3.3 1.7 0.5 Setosa
## 25 4.8 3.4 1.9 0.2 Setosa
## 26 5.0 3.0 1.6 0.2 Setosa
## 27 5.0 3.4 1.6 0.4 Setosa
## 28 5.2 3.5 1.5 0.2 Setosa
## 29 5.2 3.4 1.4 0.2 Setosa
## 30 4.7 3.2 1.6 0.2 Setosa
## 31 4.8 3.1 1.6 0.2 Setosa
## 32 5.4 3.4 1.5 0.4 Setosa
## 33 5.2 4.1 1.5 0.1 Setosa
## 34 5.5 4.2 1.4 0.2 Setosa
## 35 4.9 3.1 1.5 0.2 Setosa
## 36 5.0 3.2 1.2 0.2 Setosa
## 37 5.5 3.5 1.3 0.2 Setosa
## 38 4.9 3.6 1.4 0.1 Setosa
## 39 4.4 3.0 1.3 0.2 Setosa
## 40 5.1 3.4 1.5 0.2 Setosa
## 41 5.0 3.5 1.3 0.3 Setosa
## 42 4.5 2.3 1.3 0.3 Setosa
## 43 4.4 3.2 1.3 0.2 Setosa
## 44 5.0 3.5 1.6 0.6 Setosa
## 45 5.1 3.8 1.9 0.4 Setosa
## 46 4.8 3.0 1.4 0.3 Setosa
## 47 5.1 3.8 1.6 0.2 Setosa
## 48 4.6 3.2 1.4 0.2 Setosa
## 49 5.3 3.7 1.5 0.2 Setosa
## 50 5.0 3.3 1.4 0.2 Setosa
## 51 7.0 3.2 4.7 1.4 Versicolor
## 52 6.4 3.2 4.5 1.5 Versicolor
## 53 6.9 3.1 4.9 1.5 Versicolor
## 54 5.5 2.3 4.0 1.3 Versicolor
## 55 6.5 2.8 4.6 1.5 Versicolor
## 56 5.7 2.8 4.5 1.3 Versicolor
## 57 6.3 3.3 4.7 1.6 Versicolor
## 58 4.9 2.4 3.3 1.0 Versicolor
## 59 6.6 2.9 4.6 1.3 Versicolor
## 60 5.2 2.7 3.9 1.4 Versicolor
## 61 5.0 2.0 3.5 1.0 Versicolor
## 62 5.9 3.0 4.2 1.5 Versicolor
## 63 6.0 2.2 4.0 1.0 Versicolor
## 64 6.1 2.9 4.7 1.4 Versicolor
## 65 5.6 2.9 3.6 1.3 Versicolor
## 66 6.7 3.1 4.4 1.4 Versicolor
## 67 5.6 3.0 4.5 1.5 Versicolor
## 68 5.8 2.7 4.1 1.0 Versicolor
## 69 6.2 2.2 4.5 1.5 Versicolor
## 70 5.6 2.5 3.9 1.1 Versicolor
## 71 5.9 3.2 4.8 1.8 Versicolor
## 72 6.1 2.8 4.0 1.3 Versicolor
## 73 6.3 2.5 4.9 1.5 Versicolor
## 74 6.1 2.8 4.7 1.2 Versicolor
## 75 6.4 2.9 4.3 1.3 Versicolor
## 76 6.6 3.0 4.4 1.4 Versicolor
## 77 6.8 2.8 4.8 1.4 Versicolor
## 78 6.7 3.0 5.0 1.7 Versicolor
## 79 6.0 2.9 4.5 1.5 Versicolor
## 80 5.7 2.6 3.5 1.0 Versicolor
## 81 5.5 2.4 3.8 1.1 Versicolor
## 82 5.5 2.4 3.7 1.0 Versicolor
## 83 5.8 2.7 3.9 1.2 Versicolor
## 84 6.0 2.7 5.1 1.6 Versicolor
## 85 5.4 3.0 4.5 1.5 Versicolor
## 86 6.0 3.4 4.5 1.6 Versicolor
## 87 6.7 3.1 4.7 1.5 Versicolor
## 88 6.3 2.3 4.4 1.3 Versicolor
## 89 5.6 3.0 4.1 1.3 Versicolor
## 90 5.5 2.5 4.0 1.3 Versicolor
## 91 5.5 2.6 4.4 1.2 Versicolor
## 92 6.1 3.0 4.6 1.4 Versicolor
## 93 5.8 2.6 4.0 1.2 Versicolor
## 94 5.0 2.3 3.3 1.0 Versicolor
## 95 5.6 2.7 4.2 1.3 Versicolor
## 96 5.7 3.0 4.2 1.2 Versicolor
## 97 5.7 2.9 4.2 1.3 Versicolor
## 98 6.2 2.9 4.3 1.3 Versicolor
## 99 5.1 2.5 3.0 1.1 Versicolor
## 100 5.7 2.8 4.1 1.3 Versicolor
## 101 6.3 3.3 6.0 2.5 Virginica
## 102 5.8 2.7 5.1 1.9 Virginica
## 103 7.1 3.0 5.9 2.1 Virginica
## 104 6.3 2.9 5.6 1.8 Virginica
## 105 6.5 3.0 5.8 2.2 Virginica
## 106 7.6 3.0 6.6 2.1 Virginica
## 107 4.9 2.5 4.5 1.7 Virginica
## 108 7.3 2.9 6.3 1.8 Virginica
## 109 6.7 2.5 5.8 1.8 Virginica
## 110 7.2 3.6 6.1 2.5 Virginica
## 111 6.5 3.2 5.1 2.0 Virginica
## 112 6.4 2.7 5.3 1.9 Virginica
## 113 6.8 3.0 5.5 2.1 Virginica
## 114 5.7 2.5 5.0 2.0 Virginica
## 115 5.8 2.8 5.1 2.4 Virginica
## 116 6.4 3.2 5.3 2.3 Virginica
## 117 6.5 3.0 5.5 1.8 Virginica
## 118 7.7 3.8 6.7 2.2 Virginica
## 119 7.7 2.6 6.9 2.3 Virginica
## 120 6.0 2.2 5.0 1.5 Virginica
## 121 6.9 3.2 5.7 2.3 Virginica
## 122 5.6 2.8 4.9 2.0 Virginica
## 123 7.7 2.8 6.7 2.0 Virginica
## 124 6.3 2.7 4.9 1.8 Virginica
## 125 6.7 3.3 5.7 2.1 Virginica
## 126 7.2 3.2 6.0 1.8 Virginica
## 127 6.2 2.8 4.8 1.8 Virginica
## 128 6.1 3.0 4.9 1.8 Virginica
## 129 6.4 2.8 5.6 2.1 Virginica
## 130 7.2 3.0 5.8 1.6 Virginica
## 131 7.4 2.8 6.1 1.9 Virginica
## 132 7.9 3.8 6.4 2.0 Virginica
## 133 6.4 2.8 5.6 2.2 Virginica
## 134 6.3 2.8 5.1 1.5 Virginica
## 135 6.1 2.6 5.6 1.4 Virginica
## 136 7.7 3.0 6.1 2.3 Virginica
## 137 6.3 3.4 5.6 2.4 Virginica
## 138 6.4 3.1 5.5 1.8 Virginica
## 139 6.0 3.0 4.8 1.8 Virginica
## 140 6.9 3.1 5.4 2.1 Virginica
## 141 6.7 3.1 5.6 2.4 Virginica
## 142 6.9 3.1 5.1 2.3 Virginica
## 143 5.8 2.7 5.1 1.9 Virginica
## 144 6.8 3.2 5.9 2.3 Virginica
## 145 6.7 3.3 5.7 2.5 Virginica
## 146 6.7 3.0 5.2 2.3 Virginica
## 147 6.3 2.5 5.0 1.9 Virginica
## 148 6.5 3.0 5.2 2.0 Virginica
## 149 6.2 3.4 5.4 2.3 Virginica
## 150 5.9 3.0 5.1 1.8 Virginicastr(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 ...
## $ variety : chr "Setosa" "Setosa" "Setosa" "Setosa" ...Box plot
library(ggplot2)## Warning: package 'ggplot2' was built under R version 4.3.3ggplot(data = iris, aes(x = variety, y=sepal.length, fill = variety)) +
geom_boxplot() +
scale_fill_manual(values = c("Setosa" = "orange", "Versicolor" = "purple", "Virginica" = "green"))+ # fix this later
labs(title = "Box plot of Iris dataset", y = "Sepal Length", x = "Species") +
theme_minimal()
Violin plot
ggplot(data = iris, aes(x = variety, y=sepal.length, fill = variety)) +
geom_violin()+
scale_fill_manual(values = c("Setosa" = "orange", "Versicolor" = "purple", "Virginica" = "green"))+ # fix this later
labs(title = "Box plot of Iris dataset", y = "Sepal Length", x = "Species") +
theme_minimal()
## scale point
ggplot(data = iris, aes(x = variety, y=sepal.length, color = variety)) +
geom_point() +
scale_color_manual(values = c("Setosa" = "orange", "Versicolor" = "purple", "Virginica" = "green"))+ # fix this later
theme_minimal()
ggplot(data = iris, aes(x = petal.length, y=sepal.length, color = variety)) +
geom_point() +
theme_minimal()
ggplot(data = iris, aes(x = sepal.width, y=sepal.length, color = variety)) +
geom_point() +
theme_minimal()
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
## variety
## Length:150
## Class :character
## Mode :character
##
##
## count
ggplot(data = iris, aes(x = variety, fill = variety) ) +
geom_bar() +
theme_minimal()
ggplot(data = iris, aes(x = "", fill = variety)) +
geom_bar(stat = "count") +
coord_polar(theta = "y") +
theme_minimal()
Heat map
cor_mat = cor(iris[ ,1:4])
cor_mat## sepal.length sepal.width petal.length petal.width
## sepal.length 1.0000000 -0.1175698 0.8717538 0.8179411
## sepal.width -0.1175698 1.0000000 -0.4284401 -0.3661259
## petal.length 0.8717538 -0.4284401 1.0000000 0.9628654
## petal.width 0.8179411 -0.3661259 0.9628654 1.0000000library(ggcorrplot)## Warning: package 'ggcorrplot' was built under R version 4.3.3ggcorrplot(cor_mat)
ggcorrplot(cor_mat, type="lower")
ggcorrplot(cor_mat, type="lower", lab = TRUE)
ggcorrplot(cor_mat, type="upper", lab = TRUE)
ggcorrplot(cor_mat, type="upper", lab = TRUE, colors = c("red", "white", "skyblue"))
## time series data visulization - curve graph
time = seq(1, 150)
time## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
## [19] 19 20 21 22 23 24 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 50 51 52 53 54
## [55] 55 56 57 58 59 60 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 86 87 88 89 90
## [91] 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108
## [109] 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126
## [127] 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
## [145] 145 146 147 148 149 150iris = cbind(iris, time)
head(iris)## sepal.length sepal.width petal.length petal.width variety time
## 1 5.1 3.5 1.4 0.2 Setosa 1
## 2 4.9 3.0 1.4 0.2 Setosa 2
## 3 4.7 3.2 1.3 0.2 Setosa 3
## 4 4.6 3.1 1.5 0.2 Setosa 4
## 5 5.0 3.6 1.4 0.2 Setosa 5
## 6 5.4 3.9 1.7 0.4 Setosa 6ggplot(iris, aes(x = time, y = sepal.length, color = variety)) +
geom_line() + theme_minimal()
##time
time50 = seq(1, 50)
time150 = c(time50, time50, time50)
time150## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [26] 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
## [51] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [76] 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50
## [101] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
## [126] 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50iris = cbind(iris, time150)
head(iris)## sepal.length sepal.width petal.length petal.width variety time time150
## 1 5.1 3.5 1.4 0.2 Setosa 1 1
## 2 4.9 3.0 1.4 0.2 Setosa 2 2
## 3 4.7 3.2 1.3 0.2 Setosa 3 3
## 4 4.6 3.1 1.5 0.2 Setosa 4 4
## 5 5.0 3.6 1.4 0.2 Setosa 5 5
## 6 5.4 3.9 1.7 0.4 Setosa 6 6ggplot(iris, aes(x = time150, y = sepal.length, color = variety)) +
geom_line() +
theme_minimal()
ggplot(iris, aes(x = sepal.length)) +
geom_histogram(fill = "lightblue", color="black", binwidth = 0.2)
##
library(GGally)## Warning: package 'GGally' was built under R version 4.3.3## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2ggpairs(iris[ , 1:5], aes(color=variety))## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
iris_violin = ggplot(data = iris, aes(x = variety, y=sepal.length, fill = variety)) +
geom_violin()+
labs(title = "Box plot of Iris dataset", y = "Sepal Length", x = "Species") +
theme_minimal()
iris_violin
interactive graph
library(plotly)## Warning: package 'plotly' was built under R version 4.3.3##
## Attaching package: 'plotly'## The following object is masked from 'package:ggplot2':
##
## last_plot## The following object is masked from 'package:stats':
##
## filter## The following object is masked from 'package:graphics':
##
## layoutggplotly(iris_violin)scatter_iris = ggplot(data = iris, aes(x = sepal.width, y=sepal.length, color = variety)) +
geom_point() +
theme_minimal()
ggplotly(scatter_iris)line_iris = ggplot(iris, aes(x = time, y = sepal.length, color = variety)) +
geom_line() +
theme_minimal()
ggplotly(line_iris)chord diagram global map plot