AutoViz: A New Tool For Automated Visualization in Data Science

Short Article

0
2247
Image by 200 Degrees from Pixabay

If you are looking for a tool that can perform automated visualization, AutoViz could be good one to try. It performs automatic visualization with one line of code for any dataset. If you input any data file, either pandas dataframe or CSV, AutoViz will visualize it.

If the observations are large, then AutoViz takes random samples from the file. If the number of variables is large (decided by user), AutoViz can select features that are important and plot impactful visualizations only using those automatically selected features.

AutoViz can be used in 4 simple steps:

  1. Installation by using “pip install autoviz”
  2. Import via “from autoviz.AutoViz_Class import AutoViz_Class”
  3. Instantiate a class “AV = AutoViz_Class()”
  4. Try running an experiment in the following line with our data set:
dft = AV.AutoViz("filename", sep="sep", depVar="target", dfte="pandasDF", header=0, verbose=2, lowess=False, chart_format="svg", max_rows_analyzed=1500, max_cols_analyzed=30)

Github: https://github.com/AutoViML/AutoViz

Notebook: https://github.com/DanRothDataScience/autoviz_test/blob/master/AutoViz_test.ipynb

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.