R Notebook

Class 4.1

iris 

Boxplot

box_plot = ggplot(iris, aes(x = variety, y = sepal.length, fill = variety)) +
  #fill for default color 
  #aes foe axis
geom_boxplot() +
  labs(title = "Boxplot using ggplot2",
       x = "Class",
       y = "Length") +
  
  theme(legend.position = "right",
        text = element_text(color = "black", size = 10),
        axis.text.x = element_text(color = "blue", size = 9),
        axis.text.y = element_text(color = "red", size = 8))
  box_plot
#save as a variable
ggsave("box_plot_500dpi.png", dpi = 500)

Saving 4.17 x 2.57 in image

#here the dot sign is a outlier

Violin Plot

ggplot(data = iris, aes(x = variety, y = sepal.length, fill = variety))+
  geom_violin()+
  labs(title = "This plot is created using ggplot",
       x = "Class",
       Y = "Sepal Length",
       caption = "Source = iris dataset")

# middle wide area indicate mean

To get mean

summary(iris)

  sepal.length  
 Min.   :4.300  
 1st Qu.:5.100  
 Median :5.800  
 Mean   :5.843  
 3rd Qu.:6.400  
 Max.   :7.900  
  sepal.width   
 Min.   :2.000  
 1st Qu.:2.800  
 Median :3.000  
 Mean   :3.057  
 3rd Qu.:3.300  
 Max.   :4.400  
  petal.length  
 Min.   :1.000  
 1st Qu.:1.600  
 Median :4.350  
 Mean   :3.758  
 3rd Qu.:5.100  
 Max.   :6.900  
  petal.width   
 Min.   :0.100  
 1st Qu.:0.300  
 Median :1.300  
 Mean   :1.199  
 3rd Qu.:1.800  
 Max.   :2.500  
   variety         
 Length:150        
 Class :character  
 Mode  :character  
                   
                   
                   

##Correlaton

cor(iris$sepal.length, iris$sepal.width)

[1] -0.1175698

#correlation value range from -1 to +1

Correlation Matrix

cor_matrix = cor(iris[ ,1:4])
cor_matrix

             sepal.length
sepal.length    1.0000000
sepal.width    -0.1175698
petal.length    0.8717538
petal.width     0.8179411
             sepal.width
sepal.length  -0.1175698
sepal.width    1.0000000
petal.length  -0.4284401
petal.width   -0.3661259
             petal.length
sepal.length    0.8717538
sepal.width    -0.4284401
petal.length    1.0000000
petal.width     0.9628654
             petal.width
sepal.length   0.8179411
sepal.width   -0.3661259
petal.length   0.9628654
petal.width    1.0000000

#to see correlation from 1 to 4 column, it has to be numerical value

Heatmap

library(ggcorrplot)
ggcorrplot(cor_matrix)

#to understand correlation among variables

###Lower triangle

library(ggcorrplot)
ggcorrplot(cor_matrix, type = "lower")

###Upper triangle

library(ggcorrplot)
ggcorrplot(cor_matrix, type = "upper")

To Change Color

ggcorrplot(cor_matrix, type = "lower",
           color = c("blue", "purple","white"))

To Show plot with Value

ggcorrplot(cor_matrix, type = "lower",
           color = c("blue", "purple","white"),
           lab = TRUE)

Pairplot : To show all data in one plot

library(GGally)
ggpairs(iris, aes(color = variety))

Interractive plot

library(plotly)
#pipeline operator (%>%): to apply conditions
fig = iris %>%
  plot_ly(y= ~sepal.length, type = "violin")
  fig

library(plotly)
#pipeline operator (%>%): to apply conditions
fig = iris %>%
  plot_ly(y= ~sepal.length, type = "box")
  fig

library(plotly)
#pipeline operator (%>%): to apply conditions
fig = iris %>%
  plot_ly(x= ~sepal.length, type = "histogram")
  fig

To show plots

plot_ly(iris, x = ~variety, y = ~ sepal.length, type = "box")