EDA is critical to every Data Analytics engagement. The intent is to:
install.packages("devtools")
devtools::install_github("gramener/eda")
library(eda)
help(package = eda)
help(metadata)
help(univariate)
help(bivariate)
meta <- metadata$new(path = "Specify path to the file you want to conduct EDA on")
meta$output()
meta$columns$age$type <- "discrete"
meta$save(savepath = "path to the existing excel file or a new excel file to be created",sheet = "Metadata Analysis")
Binning: https://en.wikipedia.org/wiki/Freedman%E2%80%93Diaconis_rule
uni <- univariate$new(metadata = meta,k = 3)
uni$output()
uni$save(path = "path to the existing excel file or a new excel file to be created",sheet = "Univariate Analysis")
uni$saveplot(path = "path to the existing excel file or a new excel file to be created")
uni$saveplot(path = "path to the existing excel file or a new excel file to be created")
- Categorical - Categorical Variable : Cross Tab of Count and Proportion of Records
- Numeric - Categorical Variable : Sum, Average, Min, Max of Records
- Numeric - Categorical Variable : Bar Plot for Sum, Average, Min, Max Records
- Numeric - Numeric : Scatter Plot and Correlation Plot
bi <- bivariate$new(metadata = meta)
bi$output()
bi$save(path = "path to the existing excel file or a new excel file to be created")
bi$saveplot(path = "path to the existing excel file or a new excel file to be created",method = "pearson")
This is a basic example which shows you how to solve a common problem:
##Install the eda package
install_github("gramener/eda")
##Load the eda package
library(eda)
##To compute the metadata for the iris dataset do:
meta <- metadata$new(data = iris)
##To view the metadata output onto the console:
meta$output()
##To save the metadata output into a xlsx file:
meta$save(savepath = "C:/Users/Admin/Desktop/Output.xlsx")
##To compute the univariate analysis do:
uni <- univariate$new(metadata = meta)
##To view the univariate analysis onto the console:
uni$output()
##To save the univariate analysis into a xlsx file do:
uni$save(savepath = "C:/Users/Admin/Desktop/Output.xlsx")
##To save the univariate plots into a xlsx file do:
uni$saveplot(savepath = "C:/Users/Admin/Desktop/Output.xlsx")
##To compute the bivariate analysis do:
bi <- bivariate$new(metadata = meta)
##To view the bivariate analysis onto the console:
bi$output()
##To save the bivariate analysis into a xlsx file do:
bi$save(savepath = "C:/Users/Admin/Desktop/Output.xlsx")
##To save the bivariate plots into a xlsx file do:
bi$saveplot(savepath = "C:/Users/Admin/Desktop/Output.xlsx",method = "pearson")
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.