Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapter 19 (Hotspots (under insights, uses the RuleFit Classifier which is…
Chapter 19
Hotspots
under insights
uses the RuleFit Classifier which is a red flag
shows the most relevant combinations of features and their effect on the target
Power of Language
insight screen--> text mining
effects in this case are just relabeling of the word coefficient
Word Cloud
Feature Impacts on Target
4 types of relationships a feature can have with a target
overall impact of a feature without consideration of the impact of other features
treats each feature as a standalone effect on the target
importance score allows you to focus attention on the features most likely to yield additional predictive value if misinterpreted by the AutoML
not fully reliable indicators of the value of a feature
overall impact of a feature adjusted for the impact of other features
calculation of the value of each feature in the context of this model
examines models performance relative to the model that retained all the features
tree-based variable importance screen in the insights area does not demand a high degree of scrutiny
minimal processing power, only applies to tree-based models and contains less accurate info
directional impact of a feature
whether the presence of a value helps the model by assisting it in predicting the targer
variable effect screen doesnt provide all the info to recreate a model
partial impact of a feature
model x-ray constructs a list of features ranked by theri influence on the target as denoted by the size of green line under each feature name
Reason Codes
understanding data is important
Reason Codes Screen
thresholds allow for the specification of the probability cutoffs to be used in this view
powerful feature that can supplement business decisions