VevestaX — Open source library to track features used and machine learning experiments with 2 lines of code
VevestaX is an open source initiative by Vevesta Labs. VevestaX helps manage experiments, features and EDA. The library generates an excel file to track the data and machine learning(ML) experiments. With approximately 2 lines of code, you can track both your ML experiments as well as the feature set.
Step 1 : How to install vevestaX
pip install vevestaX
Step 2: How to import the library and create an VevestaX object
Step 3 : How to extract features from the data source
Step 4: How to extract features engineered during the modelling process.
Step 5: Track the variables you wish to track by nesting it between V.start() and V.end(). These two functions can be called, as a block, multiple times within in the code. Note: writing V.start() and V.end() is optional. In case this code block is not used, all the variables in the code file are captured in the excel.
Step 6: Write the experiment to an output excel file by passing optional parameters, filename, message and version. vevesta.xlsx file is created when optional parameter filename is not passed.
Output file contains 4 tabs. The first tab, dataSourcing, has initial set of features in an experiments. A value = 1 means feature was present in that run and 0 means it was absent.
Similar to dataSourcing tab, tab for features engineered. This tab lists features captured with V.fe.
Sample output for tracked modelling parameters.
The output file has one more tab i.e. messages.
This repository is open sourced and can be accessed at following link:
You can access more details about the tool at www.vevesta.com. You can reach out with suggestions and feedback about the Vevestax at vevestax@vevesta.com.