georgian-io-archive / foreshadow

An automatic machine learning system
https://foreshadow.readthedocs.io
Apache License 2.0
29 stars 2 forks source link

Data summarization step #159

Closed jzhang-gp closed 5 years ago

jzhang-gp commented 5 years ago

Description

We want to add a step to summarize the dataset after the intent resolving step, just like version 0.1.0 so that users can see why the column is categorized into an intent based on the stats.

This is done by adding a FeatureSummarizationStep into the DataPreparer and its only functionality is to spit out stats. No transformation is done on the data.