yellowbrick
yellowbrick copied to clipboard
DistrictDataLabs
Visual analysis and diagnostic tools to facilitate machine learning model selection.
Create a TravisCI `after_failure` script that uploads actual images and diffs to S3 so we can diagnose TravisCI failures. ### Proposal/Issue It seems like every time we push a commit...
Create an Identify estimator to allow yellowbrick to use datasets that already contain predicted probabilities ``` from sklearn.base import BaseEstimator, ClassifierMixin class Identity(BaseEstimator, ClassifierMixin): def fit(self, X, y=None): return self...
While I was trying to use ParallelCoordinates with normalization on a dataset with missing value, I got the following error. ValueError: Input contains NaN, infinity or a value too large...
The concept is to create a visualizer utility / transformer method to create multiple plots that each have a focus on one element / class in a set of values....
Add labels with metrics such as recall, precision, tpr and etc to the DecisionBoundaryVisualizer As seen in as the visualizations in this blog post: https://medium.com/towards-data-science/what-metrics-should-we-use-on-imbalanced-data-set-precision-recall-roc-e2e79252aeba Example from the blog post:...
Create some kind of visualizer that enables the user to steer the outlier removal/pruning process through visualizations. For a single dimension, this would depict an iterative outlier pruning process, for...
The `AlphaSelection` visualizer, implemented in #103 has a slight bug: Right now the alphas and errors selection method uses a search to find the right attributes on the model (rather...
Ok, this is kind of a stretch goal, but @bbengfort and I have been thinking about possibly doing a 3D rendering with LEDs to add a dimension to our visualizers....
Add an option to the `PredictionError` Visualizer to add heteroscedasticity visual measures and bounds.
We want to be able to implement a `FeatureVisualizer` for distribution analysis, such as a violinplot (see [Seaborn implementation here](http://seaborn.pydata.org/generated/seaborn.violinplot.html?highlight=violinplot#seaborn.violinplot)).
Metadata
Owner
Metadata
Visual analysis and diagnostic tools to facilitate machine learning model selection.