Import multimember ensemble datasets when your source data is combined into one collective dataset that includes data for all members. This collective dataset can be any of the following:
An ensemble table containing
table arrays or matrices. Table rows represent individual
An ensemble cell array containing tables or matrices. Cell array rows represent individual members.
An ensemble datastore object that contains the information necessary to interact with files stored externally to the app. Use an ensemble datastore object especially when you have too much data to fit into app memory.
The members in the collective dataset must all contain the same independent variables, data variables, and condition variables.
All independent time variables must be of the same type — either all double or all
duration or all
datetime. If your original
data was uniformly sampled and timestamps were not recorded, the app prompts you to
construct a uniform timeline during the import process
Embedded matrices can contain only one independent variable, but can have any number of data variables tied to that independent variable.
Condition variables in a member dataset contain a single scalar. The form of the scalar can be numeric, string, cell, or categorical.
Before importing your data, it must already be clean, with preprocessing such as outlier and missing-value removal. For more information, see Data Preprocessing for Condition Monitoring and Predictive Maintenance.
Select a single dataset from Ensemble variable. You cannot import data incrementally.
Review and modify the variable types and units that Diagnostic Feature Designer associates with your imported variables.
If a table variable consists of a
timetable array or a
table array with its own variable names, then the imported variable name
combines these names. For example, if table variable
Vibration is a
variables, then the imported variable names are
The import process infers the variable type from its source and type. Sometimes, the type or the unit is ambiguous, and you must update the default setting.
Numeric scalars represent either condition variables or features. By default, when you import tables, the app treats numeric scalars as features. If the default type is incorrect, select the correct variable type.
Independent variable type is explicit in timetables, but not in tables or matrices. Select the correct independent variable type for any unidentified independent variables.
Update units for variables if necessary by selecting or entering alternatives within Units.
Uniformly sampled data does not always have explicitly recorded timestamps. The app detects when your imported data does not contain an explicit independent variable and allows you to create a uniform one. Specify the type, starting value, and sampling interval.
Review the ensemble variables that result from your import. Each of these variables is an ensemble variable that contains information from all your imported members. The app maintains these variables in Ensemble name. Update the default if you want to use a different ensemble name.
Click Import once you are confident your ensemble is complete. If, after completing the import, you find that you need additional data, you must perform a fresh import that includes everything you want. This fresh import deletes existing imported variables, derived variables, and features.
Consider saving your session immediately after you import if you plan to explore the data in multiple sessions. Saving your session after import provides you with an option for a clean start for new sessions without needing to import your ensemble dataset again. You can save additional sessions after you have generated derived variables and features.
For more information on:
Data ensembles — See Data Ensembles for Condition Monitoring and Predictive Maintenance.
Creating an ensemble table from member matrices — See Prepare Matrix Data for Diagnostic Feature Designer.