Skip to main content

Visualize

Visualize lets you investigate columns and aggregates through charts and graphs.

Format​

Visualize has several formats depending on what you're visualizing:

Columns​

Visualize <dependent column> by <independent columns> (showing the top <top>) | (showing the bottom <bottom>) (with optimization)

Aggregations​

Visualize (<aggregation>) by (<column>) (excluding <predicate> | only including <predicate>)

Parameters​

Visualize uses the following parameters:

  • dependent column (required). The column you want to visualize against the independent columns.
  • independent columns (required). A list of columns you want to use to visualize the dependent column.
  • top (optional). The number of rows, starting from the top, in the independent column to restrict the output to.
  • bottom (optional). The number of rows, starting from the bottom, in the independent column to restrict the output to.
  • aggregation (required). The aggregation (created by the Define skill) to visualize.
  • predicate (optional). When visualizing an aggregation, you can include or exclude certain data from the chart using a predicate (created by the Define skill).
  • with optimization (optional). Whether to use machine learning to identify impactful features and create charts based on those findings. When this option is enabled:
    • If you didn't specify any independent columns in the independent columns parameter, DataChat uses machine learning to identify which features have the most impact on your chosen KPI. Then, Visualize creates several charts using the most impactful features as independent columns, in order from most impactful to least impactful.
    • If you did specify independent columns in the independent columns, DataChat uses machine learning to identify which features have the most impact on your chosen KPI along with your specified independent columns to create two groups of charts:
      • Charts based on your KPI and the independent variables you chose.
      • Charts based on the most impactful features identified by the machine learning process, in order from most impactful to least impactful.

Output​

If the column or aggregation is successfully visualized, the related chart appears in the Data tab. Otherwise, an error message is shown in the conversation history.

Examples​

To visualize the column Age in the "Titanic Dataset" against the Pclass and Gender columns using machine-learning-generated recommendations, enter Visualize Age by Pclass, Gender with optimization.

To visualize an aggregation called AvgAge, which is defined as the average of the values in the Age column, against the column PClass, excluding any data that satisfies a predicate called Adults (defined as passengers over the age of 18), enter Visualize AvgAge by PClass excluding Adults.

Feedback