Visualizers are scikit-learn Estimator objects and have a similar interface along with methods for drawing. The primary interface is therefore a Visualizer – an object that learns from data to produce a visualization. The Yellowbrick API is specifically designed to play nicely with scikit-learn. Note that because of matplotlib, Yellowbrick does not work inside of a virtual environment on macOS without jumping through some hoops. Once installed, you should be able to import Yellowbrick without an error, both in Python and inside of Jupyter notebooks. If you’re having trouble with installation, please let us know on GitHub. If you’re having trouble with this, please consult matplotlib’s backends documentation.Ĭonda install -c districtdatalabs yellowbrick Notebooks make it especially easy to coordinate code and visualizations however, you can also use Yellowbrick inside of regular Python scripts, either saving figures to disk or showing figures in a GUI window.
Yellowbrick is also commonly used inside of a Jupyter Notebook alongside Pandas data frames. If you’re having trouble, try using a distribution of Python that includes these packages like Anaconda. Both of these packages require some C code to be compiled, which can be difficult on some systems, like Windows.
Note that Yellowbrick works best with scikit-learn version 0.20 or later and matplotlib version 3.0.1 or later. If you do not have these Python packages, they will be installed alongside Yellowbrick. Yellowbrick has two primary dependencies: scikit-learn and matplotlib. Before we begin, however, there are several notes about development environments that you should consider. If you’re new to Yellowbrick, this guide will get you started and help you include visualizers in your machine learning workflow.
0 kommentar(er)
