idanmoradarthas / DataScienceUtils / 101

100%

push

travis-ci

feature/version_1.7 (#28)

* ### Added
- xai::plot_features_importance method that visualize into bar chart the feature importance.
### Changed
- deprecated xai::draw_tree. Use sklearn.tree.plot_tree instead.

* ### Added
- a new module named `unsupervised` was added. The module contains methods that calculate and/or visualize evaluation
performance of an unsupervised model.
- unsupervised::plot_cluster_cardinality method that plots the number of points per cluster as a bar chart.

* ### Added
- unsupervised::plot_cluster_magnitude method that plots the the Total Point-to-Centroid Distance per cluster as a bar chart.

* ### Added
- unsupervised::plot_magnitude_vs_cardinality method plots the cardinality vs. magnitude as a scatter plot.

* minor chages

* ### Added
- unsupervised::plot_loss_vs_cluster_number method that plots the graph which helps to find the optimum parameter ``k``
for KMeans.

* fix conda script

* fix tests

Co-authored-by: Idan Morad <idan.morad@elbitsystems.com>

89 of 89 new or added lines in 3 files covered. (100.0%)

392 of 394 relevant lines covered (99.49%)

2.98 hits per line