Closed arnabbiswas1 closed 6 years ago
I want to work on this. Thanks Aparna
@aparnack Here you go. However, if any one else is interested, please let us know. We can have multiple members owning the same issue.
i would like to contribute to this task as well
@githubssn Here you go! 👍
This has been addressed as a part of https://github.com/DataKind-BLR/PrathamBooks-Sprint-2018/pull/11
stories_pages.csv consists of different attributes associated with each stories such as language, reading levels, number of reads, whether publisher created or community created. Basic EDA may be helpful to better understand the data. Following could be some interesting features to visualize:
"is_child_created_story","stories_status","ancestry","is_recommended_story","reads","language_name","organization_name""story_derivation_type","story_publishing_type","reading_level_cat"
The end result should be a notebook.
Considering the generic nature of the solution, multiple contributors can be involved. Please add a comment if you are working on it.