How it works ?

This website intends to generate descriptives datas for a given excel file: mean, median, standard deviation, minimum, maximum, number of missing values in each column, boxplot, histograms...

Just upload a file with all your database, then let the algorithm works on your datas.

All your column names will be displayed. If you select one or 2 columns, descriptive datas will be generated, grouped according to your selection. If you don't select anything, descriptive datas will be generated on the whole table. This option is faster if you just want to have an overview of your datas.

It is usually more readable by user to use yes/no instead or 1/0. There might be confusions depending 1 stands for yes or no...For instance, an event can be set as 1 (myocardial infarction), but a "negative column" (like "no amputation"), can also be set as 1... All "Yes/Y/y/yes/Oui/O/oui/o" will be replaced by "1". "No" values by "0". It might sound confusing, but the most important point is to keep the same rule all over your excel file. If you prefer the reverse, then your free to make your own classification system.

Eventually, download the zip file...!

That's it :)

For more informations about organizing your datas in an excel file, check out this very short tutorial, and/or download the demonstration file...

One more thing...Absolutely NONE of your data are kept on the server...(all data are deleted when you click on "download") If you don't click on download, or an error occurs, a script delete every previous file every day... And if you really concerned about privacy, which you have to, and you don't trust me, what i fully understand, you are free to delete all possible identification columns before submitting the file...!

Check out the upcoming features on Github