boxuancui / DataExplorer

Automate Data Exploration and Treatment
http://boxuancui.github.io/DataExplorer/
Other
512 stars 88 forks source link

introduce, plot_intro, plot_bar is not working with integer discrete values(Read as continuous value) #110

Closed mdumer closed 5 years ago

mdumer commented 5 years ago

Hi, Hope you are doing well. I tried this thing and find this issue.

head(df) Churn VoiceMail 1 0 1 2 0 1 3 0 0 4 0 0 5 0 0 6 0 0

introduce(df) rows | 599 columns | 2 discrete_columns | 0 continuous_columns | 2 all_missing_columns | 0 total_missing_values | 0 complete_rows | 599 total_observations | 1198 memory_usage | 6152

plot_intro(df) plot

Thanks

boxuancui commented 5 years ago

The package can only detect feature types by guessing. If you would like to set them as discrete values, you can simply do update_columns(df, names(df), as.factor), and then run these functions again. I don't think it is possible to force define feature class outside its generic type. Hope this helps.