Be the first to read our first Ebook!

In the Age of AutoML, we are all Data Scientists! | Artificial Intelligence (AI) has become increasingly essential to our daily routine lives.

Data profiling: Get an exhaustive results in matter of minutes with SmartPredict's Data Visualizer module.

Published on May 25, 2021 by Haingomanitra H. F.

SmartPredict is an AI platform that allows users to save a huge amount of time in completing a production-ready AI project. This is due in part to the fact that time-consuming tasks can be performed with a simple drag and drop and module configuration. 

There are over a hundred configurable modules you can use to build your AI workflow on this platform. Among them is the Data Visualizer module, which allows you to get data profiling, before and after its processing, without having to code or install any packages. So, keep reading to learn more about how easy it is to get comprehensive data profiling with the Data Visualizer module.

Data profiling with Data visualizer module

Data Visualizer module built-in module based on Pandas libraries in the SmartPredict AI platform, which generates a profile report of a dataset before and after its processing.

As a result, you get the following statistics for each column of your dataset :

  • Essentials: type, unique values, missing values
  • Quantile statistics like minimum value, Q1, median, Q3, maximum, range, interquartile range
  • Descriptive statistics like mean, mode, standard deviation, sum, median absolute deviation, coefficient of variation, kurtosis, skewness
  • Most frequent values
  • Histogram
  • Correlations highlighting highly correlated variables, Spearman and Pearson matrixes as shown in the figures below

How to use it?

This module can be used anywhere in a flowchart to see the profiling of a dataset before and after its processing. Just drag and drop it from the module menu and connect it to either : 

-(a)  the dataset module’s output

- (b) or the data processing pipeline’s output,

as shown in the following images.

Note that only one Data visualizer module can be computed in a flowchart. So be sure to disable the others if there are several in your flowchart.

This module can be also used in Autoflow as the generated flowchart is customizable.

Steps on getting a data profiling with the Data Visualizer module

1-Create a new project in Manualflow

2-Upload (or create) your dataset 

2-Drag and drop the dataset module into the build workspace 

3-Look for the Data visualizer in the module menu and drag and drop

4-Link it to the dataset then run the flowchart

5-Double click on it to see the result in the processing and profiling tab.

This tutorial video shows you more about these steps.

You have now seen how to use the Data Visualizer module to gain valuable insights from your data exploration in a few minutes.

Now start using it to brilliantly present your reports