Getting started with Orange tool
Introduction
Data has become a powerful source of earning and predict future and people will seek to utilize it even if they don’t know exactly how. Nowadays people prefer GUI based tools instead of more coding stuff. Orange is one of the popular open source machine learning and data visualization tool for beginners. People who don’t know more about coding and willing to visualize pattern and other stuff can easily work with Orange.
Why Orange?
Orange is an open-source software package released under GPL that powers Python scripts with its rich compilation of mining and machine learning algorithms for data pre-processing, classification, modeling, regression, clustering and other miscellaneous functions.
Orange also comes with a visual programming environment and its workbench consists of tools for importing data, dragging and dropping widgets, and links to connect different widgets for completing the workflow.
Widgets are orange components that span from simple data presentation, subset selection, and preprocessing to empirical evaluation and predictive modeling of learning algorithms.
How to use workflows in orange?
I have created a simple workflow wherein the inbuilt Iris dataset provided by Orange is being used. The workflow is such that data from the dataset is sent to the data table, to Distributions for creating a distribution and a Scatter Plot is plotted from the dataset. To create this workflow we load the dataset using the File widget, and then flow between File-Data Info, File-Data Table, File-Distributions and File-Scatter Plot is created.
For the data to be loaded in the Canvas, select the File widget from the left pane and place it in the canvas. Double click on the File widget and select the iris.tab file.
How to do basic data exploration (like data distribution, data information).
Data Information
To get the information about the data loaded in the file widget we can create a flow between the File widget and use the Data Info Widget which shows the name, description, row count, column count, features and target values in the dataset in File widget.
Then to view the data in Orange Canvas in the table form, select the Data Table widget from the left pane, place it in the canvas and connect the link between File and Data Table widget. On double clicking on the the Data Table widget the entire data can be seen in the tabular form, where Orange itself decides the Target Variable based on the data received.
Data Distribution
Use the Data Distribution widget to get the graphical representation of the dataset values. Here I got the distribution for various features from dataset.
We can also use the widget of Scatter Plot for plotting for different kinds of feature pairs.
How to load your data in Orange and how to load external data from API in Orange?
To load your data in Orange select the File Widget and from there in you can either select the dataset provided by Orange or else browse to the dataset file in your local machine to load the data. If you want load external data use can select the URL option in the file widget, where one can paste the external dataset link to load the data.
That’s it for the introduction part of the orange tool we will explore this tool in detail in the next blogs.. You can explore more about the Orange tool here.
Thank You!!
