In DSCI-310/DSCI-310-Group-11-package: Data Preprocessing for Exploratory Data Analysis

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

projectPackage

The goal of projectPackage is to provide simplified functions to achieve the goal of data preprocessing for exploratory data analyses. The projectPackage makes the following steps quick and easy:

• Removing certain columns from a data set
• Creating a recipe
• Creating a ggpairs correlation plot

Installation

You can install the development version of projectPackage from Github like so:

# install.packages("devtools")
devtools::install_github("DSCI-310-Group-11-package")

Usage

Often when you work with large data sets, there will be columns that are redundant or not of interest. It can get monotonous writing and seeing the same lines of code over and over again across different projects, in that case, you can use projectPackage::data_cleaning()to drop those columns. This function differs from select and subsetin that it is more narrowed down to a specific usage which can be useful for learners who wish to work with simpler and straightforward functions.

library(projectPackage)

tidy_data <- data_cleaning(mtcars, c("drat","vs"))
head(tidy_data)

And if we want to create a recipe, we can easily accomplish that using projectPackage::recipe_scale_center(). This function scales and centers all the predictor variables as well as building a new model specification and recipe for the analysis. Therefore, the function saves tons of time as it minimizes the amount of coding that you have to write.

``` {r recipe} recipe_scale_center(mtcars, mpg ~ hp)

Lastly, if you want to create a `ggpairs` correlation matrix plot, this package also covers that! However, this function differs from the function `ggpairs()` in that it adds additional aesthetics which makes it prettier and more readable.

``` {r corr-plot}
correlation_graph(mtcars[1:3])

DSCI-310/DSCI-310-Group-11-package documentation built on April 9, 2022, 12:32 a.m.