Exploratory data analysis (EDA) is the first step performed in a classical statistical data analysis or machine learning model development. The Statsomat/EDAPY app is a web-based application for automated EDA with Python and created with the Shiny technology in combination with the R
reticulate package. The Statsomat/EDAPY app is hosted on shinyapps.io and
is one of several apps which can be accessed via the webpage of Statsomat . You can also access the app directly https://statsomat.shinyapps.io/edapy/.
There is no need to install the Statsomat/EDAPY app since it runs in the browser. If you really want to run it locally, then download the repository and run the app from the project folder:
Before running the app locally, please consider to install required R and Python packages.
The dataset HolzingerSwineford1939.csv extracted from the R package
lavaan is contained in the repository and can be used as an example. Follow also the Instructions described directly on the webpage of the app https://statsomat.shinyapps.io/edapy/.
The user uploads the data as a CSV file. A PDF report is generated and finally downloaded. The PDF report contains the most important univariate EDA statistics and graphics. Moreover, the user can generate a file containing the Python code which can be used for learning or to reproduce results locally.
The app was tested and validated by a pool of datasets. Outputs were compared to outputs generated by the R packages for EDA
1) Contribute to the software:
You are welcome to improve and extend the functionality of the app. If you want to make a pull request, please check that you can run test cases locally without any errors or warnings.
Please consider to test your changes also on shinyapps.io. While uploading, ignore the
Error in eval(x, envir = envir), it is a non-fatal error, also related to related to https://github.com/rstudio/packrat/issues/385 and https://github.com/rstudio/rsconnect/issues/429.
2) Report issues or problems with the software: Please open an issue in this repository to report any bugs.
3) Seek support: We try to answer all questions in reasonable time but general support is limited.