Getting Started with Orange

7 min readAug 23, 2021

How to use workflows in orange?

How to do basic data exploration


The File widget reads the input data file (data table with data instances) and sends the dataset to its output channel. The history of most recently opened files is maintained in the widget. The widget also includes a directory with sample datasets that come pre-installed with Orange.

The widget reads data from Excel (.xlsx), simple tab-delimited (.txt), comma-separated files (.csv) or URLs.

Loaded the Datasets that is Heart Diseases.

Data Table

The Data Table widget receives one or more datasets in its input and presents them as a spreadsheet. Data instances may be sorted by attribute values. The widget also supports manual selection of data instances.


The Distributions widget displays the value distribution of discrete or continuous attributes. If the data contains a class variable, distributions may be conditioned on the class.

The graph shows how many times (e.g., in how many instances) each attribute value appears in the data. If the data contains a class variable, class distributions for each of the attribute values will be displayed (like in the snapshot below). To create this graph, we used the Zoo dataset.

Scatter Plot

The Scatter Plot widget provides a 2-dimensional scatter plot visualization for continuous attributes. The data is displayed as a collection of points, each having the value of the x-axis attribute determining the position on the horizontal axis and the value of the y-axis attribute determining the position on the vertical axis. Various properties of the graph, like color, size and shape of the points, axis titles, maximum point size and jittering can be adjusted on the left side of the widget. A snapshot below shows the scatter plot of the Iris dataset with the coloring matching of the class attribute.

Scatter Plot with Data Table

Silhouette Plot

The Silhouette Plot widget offers a graphical representation of consistency within clusters of data and provides the user with the means to visually assess cluster quality. The silhouette score is a measure of how similar an object is to its own cluster in comparison to other clusters and is crucial in the creation of a silhouette plot. The silhouette score close to 1 indicates that the data instance is close to the center of the cluster and instances possessing the silhouette scores close to 0 are on the border between two clusters.

Mosaic Display

The Mosaic plot is a graphical representation of a two-way frequency table or a contingency table. It is used for visualizing data from two or more qualitative variables and was introduced in 1981 by Hartigan and Kleiner and expanded and refined by Friendly in 1994. It provides the user with the means to more efficiently recognize relationships between different variables.

Heat Map

Heat map is a graphical method for visualizing attribute values by class in a two-way matrix. It only works on datasets containing continuous variables. The values are represented by color: the higher a certain value is, the darker the represented color. By combining class and attributes on x and y axes, we see where the attribute values are the strongest and where the weakest, thus enabling us to find typical features (discrete) or value range (continuous) for each class.

Data Info

Displays information on a selected dataset.

A simple widget that presents information on dataset size, features, targets, meta attributes, and location.

Select Columns

The Select Columns widget is used to manually compose your data domain. The user can decide which attributes will be used and how. Orange distinguishes between ordinary attributes, (optional) class attributes and meta attributes. For instance, for building a classification model, the domain would be composed of a set of attributes and a discrete class attribute. Meta attributes are not used in modeling, but several widgets can use them as instance labels.


The Rank widget scores variables according to their correlation with discrete or numeric target variable, based on applicable internal scorers (like information gain, chi-square and linear regression) and any connected external models that supports scoring, such as linear regression, logistic regression, random forest, SGD, etc. The widget can also handle unsupervised data, but only by external scorers, such as PCA.

Paint Data

The widget supports the creation of a new dataset by visually placing data points on a two-dimension plane. Data points can be placed on the plane individually (Put) or in a larger number by brushing (Brush). Data points can belong to classes if the data is intended to be used in supervised learning.

Aggregate Columns

Aggregate Columns outputs an aggregation of selected columns, for example a sum, min, max, etc.

Data Sampler

The Data Sampler widget implements several data sampling methods. It outputs a sampled and a complementary dataset (with instances from the input set that are not included in the sampled dataset). The output is processed after the input dataset is provided and Sample Data is pressed.

Pivot Table

Pivot Table summarizes the data of a more extensive table into a table of statistics. The statistics can include sums, averages, counts, etc. The widget also allows selecting a subset from the table and grouping by row values, which have to be a discrete variable. Data with only numeric variables cannot be displayed in the table.


Correlations computes Pearson or Spearman correlation scores for all pairs of features in a dataset. These methods can only detect monotonic relationship.

How to load your data from explorer:

How to load external data from API in Orange?

The Guardian

Fetching data from The Guardian Open Platform.

Guardian retrieves articles from the Guardian newspaper via their API. For the widget to work, you need to provide the API key, which you can get at their access platform.