hvPlot 0.8.0 Release

Release announcement for hvPlot 0.8.0

What is hvPlot?

hvPlot is an open-source library that offers powerful high-level functionality for data exploration and visualization that doesn’t require you to learn a new API. For instance, if you have a Pandas or Xarray data pipeline already, you can turn it into a simple data-exploration app by starting the pipeline with .interactive and replacing method arguments with widgets. Or you can get powerful interactive and compositional Bokeh, Plotly, or Matplotlib plots by simply replacing .plot with .hvplot. hvPlot makes all the analytical power of the HoloViz ecosystem available, using the APIs you already know.

import hvplot.pandas
from bokeh.sampledata import penguins

df = penguins.data
df.hvplot.scatter(x='bill_length_mm', y='bill_depth_mm', by='species')

Check out the hvPlot’s website to find out more!

New release!

We are very pleased to announce the 0.8.0 and 0.8.1 releases of hvPlot! The 0.8.0 release focused on adding a number of powerful features requested by our users, including:

• In addition to Bokeh, hvPlot now supports Matplotlib and Plotly plotting extensions, so that the results of your exploratory analysis can be used alongside highly customized plots from your favorite library.
• .interactive() pipelines can now start with functions as inputs, not just from an existing data structure, so that you can make fully self-contained data apps from using hvPlot alone.
• The new hvPlot Explorer is a UI component designed to easily explore data without having to write any code; just drop it in your notebook or app and start exploring!

@sophiamyang has created an awesome video that introduces you to the new features of hvPlot, check it out!

While this blog post will focus on those three big features, hvPlot 0.8 includes a number of other enhancements and bug fixes that are of almost equal importance. For a detailed list of the changes, check out the release notes for hvPlot 0.8.0 and 0.8.1.

Many, many thanks to everyone who filed issues or contributed to this release. In particular we would like to thank @jbednar, @FabianHofmann, @jomey, @ablythed, @jlstevens, @MarcSkovMadsen, @Hoxbro, @michaelaye, @MridulS, @ppwadhwa, @maximlt, @philippjfr for contributing various fixes and improvements!

---

If you are using conda, you can get the latest hvPlot with conda install -c pyviz hvplot , and using pip you can install it with pip install hvplot.

---

New plotting extensions: Matplotlib and Plotly

You may be surprised that despite its name, hvPlot is actually not a plotting library! Instead, it is a high-level interface that delegates the actual “plotting” work, i.e. how to display lines, points, etc. on a screen, to lower-level libraries. Until now, hvPlot was only able to delegate that work to Bokeh, one particular interactive plotting library. However, hvPlot happens to be built on top of HoloViews, which for years has had support for Matplotlib and Plotly as well. hvPlot now exposes those capabilities of HoloViews, which opens up new opportunities of hvPlot usage. For instance, you can now explore plots interactively using hvPlot, export them as Matplotlib figures, and then combine the output with other custom Matplotlib figures for a publication-ready workflow.

While Bokeh is still the default plotting backend of hvPlot, with the new hvplot.extension() utility you can now declare, usually at the start of a notebook, the plotting backend you would like to use.

hvplot.extension('matplotlib')