Data visualisation

Lecture 6: Data visualisation

-be able to explain the motivation for data visualisation

• Converting data into a visual format
  • Reveals characteristics of the data, relationships between objects or relationships between features
  • Simplifies the data
• Humans are very good at analysing information in a visual format
  • Spot trends, patterns, outliers
  • Visualisation can help show data quality
  • Visualisation helps tell a story ….

-be able to draw and interpret a 2-D scatter plot

• Plotting points in 2D or 3D space, using colours to indicate classes/segments
• Plotting points in 2D / 3D space
• Take two columns from a dataset
• Can show some clustering
• Could be losing some information due to 2D nature
• Can find the cluster
• Can find how data are related, for example, positive related.

-be able to draw and interpret a histogram

• Usually shows the distribution of values of a single variable
• Divide the values into bins and show a bar plot of the number of objects in each bin.
• The height of each bar indicates the number of objects
• Shape of histogram depends on the number of bins

-be able to interpret a heat map visualisation of a dataset

• Plot the data matrix
• This can be useful when objects are sorted according to class/type
• Typically, features are normalized to prevent one attribute from dominating the plot
• This can be useful when objects are sorted according to class
• Typically, features are normalized to prevent one attribute from dominating the plot
• can find some pattern of data, for example, the busiest time of a supermarket.

-understand the advantages and disadvantages of using parallel coordinates to visualise a dataset

• Parallel Coordinates
  • Used to plot the feature values of high-dimensional data
  • Instead of using perpendicular axes, use a set of parallel axes
  • The feature values of each object are plotted as a point on each corresponding coordinate axis and the points are connected by a line
  • Thus, each object is represented as a line
  • Often, the lines representing a distinct class of objects group
  • together, at least for some features
  • Ordering of attributes is important in seeing such groupings
• Issue
• Scaling axes
  • Affects the visualisation. May choose to scale all features into the range [0,1] via a pre-processing step
• Ordering of axes
  • Influences the relationships that can be seen. Correlations between pairs of features may only be visible in certain orderings
• Advantages: easier to find similar and different items
• Disadvantages: the ordering is very important, bad ordering may results in hard to find difference or similarity between items. (see the lecture example of iris species)

-be able to interpret a parallel coordinates plot and understand why the ordering of the feature axes is important

• Scaling axes
  • Affects the visualisation. May choose to scale all features into the range [0,1] via a pre-processing step

-understand why it can be useful to normalise each feature into the range [0, 1] before computing Euclidean distance between vectors

• Ordering of axes
  • Influences the relationships that can be seen. Correlations between pairs of features may only be visible in certain orderings