0 / 0
Time plots
Last updated: Oct 09, 2024
Time plots
Time plots illustrate data points at successive intervals of time. The time series you plot must contain numeric values and are assumed to occur over a range of time in which the periods are uniform. Time plots provide a preliminary analysis of the characteristics of time series data on basic statistics and test, and thus generate useful insights about your data before modeling. Time plots include analysis methods such as decomposition, augmented Dickey-Fuller test (ADF), correlations (ACF/PACF), and spectral analysis.

Creating a simple time plot

  1. In the Chart Type section, click the Time plot icon.

    The canvas updates to display a time plot chart template.

  2. From the Values drop-down, select a value for the y-axis.
  3. Click the Save visualization in the project control to save the visualization to the project. You can select to also Create a new asset from the visualization, provide a visualization asset name, description, and chart name.
  4. Click Apply to save the visualization to the project. The new visualization asset is now available under the Assets tab.

Options

Values
Lists variables that are available for the time plot values.
Date
Select a date from the drop-down, if applicable. Each observation is separated by the same time interval. If you select a date variable, a resample option is shown. You can use this option to aggregate value fields to match the specified interval.
Time plot algorithm
The time plot algorithm to use for analyzing the time series data.
Decomposition
Decompose a time series as three components (trend-cycle, seasonal, and irregular). Decomposition is run in an additive fashion.
ADF test
Augmented Dickey–Fuller (ADF) tests the null hypothesis that a unit root exists in the series and the series is not stationary. If the test result rejects the null hypothesis, the series is stationary, or can be represented to be stationary with a difference model.
ACF/PACF
Correlations of series.
Spectral analysis
An analytic tool in the frequency domain. The highest frequency is marked as diamond.
Swap chart position
Reverses the positions of the charts on the planimetric rectangular coordinate system and the polar coordinate system.
Show the turning point
Shows or hides the turning points in the charts. The series is explored to determine whether it has an overall trend or has some turning points that change the direction of the trend pattern.
Show the outlier
Shows or hides any outliers. The outliers of the time series are analyzed from the irregular component of time series decomposition.
Primary title
The chart title.
Subtitle
The chart subtitle, which is placed directly beneath the chart title.
Footnote
The chart footnote, which is placed beneath the chart.
XAxis label
The x-axis label, which is placed beneath the x-axis.
YAxis label
The y-axis label, which is placed above the y-axis.
Generative AI search and answer
These answers are generated by a large language model in watsonx.ai based on content from the product documentation. Learn more