Python machine learning library based on Object Oriented design principles; the goal is to allow users to quickly explore data and search for top machine learning algorithm candidates for a given dataset
MIT License
1
stars
0
forks
source link
Documentation & Examples in Jupyter Notebook(s) #6
[x] NOTE: I don’t think Kappaor F1 makes sense to use as Scores when Searching/Tuning models, because they are affected by the threshold, which is 0.5, why not use AUC ROC and AUC Precision/Recall? Then, when choosing among thresholds, can use cross validation to find best threshold. (Get for free in Resampler using decorator, right?)
shane-kercheval
commented
6 years ago
Need to go through the project and document the classes, while adding examples via Jupyter Notebook(s)
Possible ideas & datasets:
Other:
KappaorF1makes sense to use as Scores when Searching/Tuning models, because they are affected by the threshold, which is0.5, why not use AUC ROC and AUC Precision/Recall? Then, when choosing among thresholds, can use cross validation to find best threshold. (Get for free in Resampler using decorator, right?)