Create a model that can learn how to accurately predict a label from a set of numeric values (train model).

Example: Consider a table with columns longitude, latitude, and a city name. Create a model that can predict a city name (or the closest city) from the given longitude and latitude.

29°45′46", 95°22′59″ => Houston, TX, USA

Operator Usage in Easy Mode

Click + on the parent node.
Enter Create Model from Numeric Values operator in the search field and select the operator from the Results to open the operator form.
In the Table drop-down, enter or select the table to create a model.
In the Model Name field, enter the name of the model to store it in a particular location.
In the Label Column Name drop-down, select the column name that contains the labels. The drop-down list displays the data based on the selected table name.
Optional. Click Add More to add a list of column names used to create the model.
Click Run to view the result.
Click Save to add the operator to the playbook.
Click Cancel to discard the operator form.

Usage Details

LQL Command

createModelFromNumericValues(table, outputModelName, label, listOfColumns)

Input
table: Input table to train a model.
outputModelName: Model name to store trained model. Trained models are not displayed in the UI, so remember the name of the model that was created. If a model with the same name exists, this operation overwrites it without notification.
label: Label column name.
listOfColumns: List of columns to train a model to learn label, such as "col1", "col2", "col3".

Output
A message saying that the model (name) was successfully created.

Example

Input
table = github_logs

id	height	weight	gender
1	70	190	male
2	63	120	female

LQL command

createModelFromNumericValues(table,"genderFromHeightWeight", "gender", "height_in", "weight_lb")

Output

If the operation is successful, a message that the model was successfully created. To use in prediction, see the predictLabelFromNumericValues operator.

Browser not supported