Predictive Hacks

How to Visualize Multivariate Data Analysis

multivariate-analysis-factoextra

In this tutorial, we will work with the factoextra R package and we will consider the Country dataset. Let’s start:

library(factoextra)

df<-read.csv("DataCountries.txt", sep="\t")

head(df)
How to Visualize Multivariate Data Analysis 1
How to Visualize Multivariate Data Analysis 2

PCA Analysis

Now we will run a PCA analysis on our dataset. Note that we need to include only the numeric variables. We will also set as row names the column Country.

# set as rownames the column Country
rownames(df)<-df$Country

# remove the Countrly columns
df$Country<-NULL

# run a PCA Analysis
dfPCA <- prcomp(df, center = TRUE, scale. = TRUE) 

Let’s get Scree plot which shows the percentage of explained variance by Principal Component.

fviz_eig (dfPCA)
How to Visualize Multivariate Data Analysis 3

Graph of Individual

Let’s plot all the countries into two dimensions by taking into consideration the quality of the individuals on the factor map.

# cos2 = the quality of the individuals on the factor map
# Select and visualize some individuals (ind) with select.ind argument.
 # - ind with cos2 >= 0.96: select.ind = list(cos2 = 0.96)
 # - Top 20 ind according to the cos2: select.ind = list(cos2 = 20)
 # - Top 20 contributing individuals: select.ind = list(contrib = 20)
 # - Select ind by names: select.ind = list(name = c("23", "42", "119") )

fviz_pca_ind(dfPCA, col.ind = "cos2" , repel = TRUE)    
How to Visualize Multivariate Data Analysis 4

Graph of Variables

Let’s see how we can represent the variables into two dimensions by taking into account their contribution.

#  select.var = list(contrib = 15)

fviz_pca_var(dfPCA, col.var = "contrib", repel = TRUE)
How to Visualize Multivariate Data Analysis 5

Graph of the Biplot

# Graph of the Biplot
fviz_pca_biplot(dfPCA, repel = TRUE)
How to Visualize Multivariate Data Analysis 6

Eigenvalues, Variables and Individuals

Let’s see how we can get the Eigenvalues and statistics for Variables and Individuals such as the Coordinates, the Contributions to the PCs and the Quality of representation

Eigenvalues

# Eigenvalues
eigens_vals <- get_eigenvalue(dfPCA)
eigens_vals 
How to Visualize Multivariate Data Analysis 7

Variables

# By Variable
by_var <- get_pca_var(dfPCA)
by_var$coord         
by_var$contrib        
by_var$cos2    
How to Visualize Multivariate Data Analysis 8

Individuals

# By ndividual
by_ind <- get_pca_ind(dfPCA)
by_ind$coord         
by_ind$contrib        
by_ind$cos2  

Share This Post

Share on facebook
Share on linkedin
Share on twitter
Share on email

1 thought on “How to Visualize Multivariate Data Analysis”

Leave a Comment

Subscribe To Our Newsletter

Get updates and learn from the best

More To Explore

snowflake
Miscellaneous

How to Schedule Tasks in Snowflake

We have started a series of Snowflake tutorials, like How to Get Data from Snowflake using Python, How to Load