Please enable JavaScript.
Coggle requires JavaScript to display documents.
Chapter 19: Interpret Model (19.3 The Overall Impact of a Feature Adjusted…
Chapter 19: Interpret Model
19.1 Feature Impacts on Target
four kinds of relationships
The overall impact of a feature adjusted for the impact of other features
The directional impact of a feature
The overall impact of a feature without consideration of the impact of other features
The partial impact of a feature
19.3 The Overall Impact of a Feature Adjusted for the Impact of other Features
This high importance score occurred despite the fact that some of the blended models did not have access to text information
the most important feature is scaled to a score of 100%, and the other features are scaled relative to it
initiate a calculation of the value of each feature in the context of this model
by randomly shuffling the values of one feature within the validation data segment
The Feature Impact pane uses information from any tree-based model to show yet another view of feature importance
19.2 The Overall Impact of Features on the Target Without Consideration of other Features
The overall impact of a feature without consideration for the impact of other features treats each feature as a standalone effect on the target
A full green bar indicates that the feature explains at least 30% of the target value
score allows a data scientist to focus attention on the features most likely to yield additional predictive value
importance scores should not be relied on for feature selection and model interpretation
19.4 The Directional Impact of Features on Target
knowing how to rerun a regression model at a greater data quantity may prove valuable in future projects
provide what are commonly known as coefficients (labeled here as Effect) for the most important feature characteristics that drive a prediction decision
the directional impact of the feature, or whether the presence of a value helps the model by assisting it
red bars indicate feature values that make positive cases more likely, blue bars: negative cases
19.5 The Partial Impact of Features on Target
same as used to rank features under Data tab, but displays 100% of the bar
The left Y-axis contains the frequency of cases in the validation set. The X-axis contains the values of the most predictive feature
The Model X-Ray constructs a list of features ranked by their influence on the target as denoted by the size of the green line under each feature name in the left pane
focus on the last two features showing large differences between predicted and actual
19.6 The Power of Language
access to a subject matter expert (SME) will be important during evaluation of the text model
word cloud
represents the words that have the highest coefficients
intensity of red or blue colors indicates the size of their coefficient
19.7 Hotspots
this visualization uses the RuleFit Classifier, which is an immediate red flag, considering that this is one of the algorithms that was stalled at 16% of the data during model creation
the deeper the tone of the blue and the red, the more of an impact that particular combination of features that specifies a sub-group of patients has on the targe
shows the most relevant (up to four) combinations of features and their effect on the target