This project uses several machine learning models to predict reservation cancellation. Among them, DART in LightGBM beats other competitors with highest testing accuracy (table) and also other metrics.

This issue is related to Sklearn, one solution is to state a eligible Solver .

For .reindex , from 0.21.0, .loc or [] are not allowed to index with a list with one or more missing labels in Pandas。

This is a lecture note of mine.