The goal of EDA is to:
- Save Time
- Improve Efficiency
- Improve Project Analysis Quality
- Priduce Artifacts for Export Internally and Externally to Excel, PowerPoint, and Word
Since EDA is a private repository make sure you have a GitHub PAT (personal access token) setup and have permission before attempting to install the package. See Usethis Setup Guide for more details on setting this up.
You can install from GitHub with:
remotes::install_github("jimbrig2011/EDA")
# or
require(devtools)
devtools::install_github("jimbrig2011/EDA")After installing the package, you can run the app simply with:
EDA::run_app()EDA desires to provide the following features:
-
Data Upload Management:
- Support easy data upload for a various number of possible data types (xlsx, csv, txt, etc).
- Support advanced settings to upload different types of data (i.e. merge across excel tabs, headers, lines to skip, etc.)
- Implement a “control totals” feature which allows user to preview the sums of numeric columns and validate / reconcile.
- Allow user to create their own datasets from uploaded files via merging and transforming them
- Provide initial summary statistics on data and preview data itself
-
Data Diagnostics
-
Data Dictionary
-
Data Validation Report
-
Data Summaries
-
Data Visualization
-
Export to PDF, PowerPoint, CSV, Excel, and Email
-
Multivariate Analysis
-
Feature Engineering / Variable Importance
-
Record Linkage