Update model configuration

models_patch(id, table_name = NULL, database_id = NULL,
  credential_id = NULL, model_name = NULL, description = NULL,
  interaction_terms = NULL, box_cox_transformation = NULL,
  model_type_id = NULL, primary_key = NULL,
  dependent_variable = NULL, dependent_variable_order = NULL,
  excluded_columns = NULL, limiting_sql = NULL,
  active_build_id = NULL, cross_validation_parameters = NULL,
  number_of_folds = NULL, notifications = NULL, schedule = NULL,
  parent_id = NULL, time_zone = NULL)

Arguments

id

integer required. The ID of the model.

table_name

string optional. The qualified name of the table containing the training set from which to build the model.

database_id

integer optional. The ID of the database holding the training set table used to build the model.

credential_id

integer optional. The ID of the credential used to read the target table. Defaults to the user's default credential.

model_name

string optional. The name of the model.

description

string optional. A description of the model.

interaction_terms

boolean optional. Whether to search for interaction terms.

box_cox_transformation

boolean optional. Whether to transform data so that it assumes a normal distribution. Valid only with continuous models.

model_type_id

integer optional. The ID of the model's type.

primary_key

string optional. The unique ID (primary key) of the training dataset.

dependent_variable

string optional. The dependent variable of the training dataset.

dependent_variable_order

array optional. The order of dependent variables, especially useful for Ordinal Modeling.

excluded_columns

array optional. A list of columns which will be considered ineligible to be independent variables.

limiting_sql

string optional. A custom SQL WHERE clause used to filter the rows used to build the model. (e.g., "id > 105").

active_build_id

integer optional. The ID of the current active build, the build used to score predictions.

cross_validation_parameters

list optional. Cross validation parameter grid for tree methods, e.g. "n_estimators": [100, 200, 500], "learning_rate": [0.01, 0.1], "max_depth": [2, 3].

number_of_folds

integer optional. Number of folds for cross validation. Default value is 5.

notifications

list optional. A list containing the following elements:

  • urls array, URLs to receive a POST request at job completion

  • successEmailSubject string, Custom subject line for success e-mail.

  • successEmailBody string, Custom body text for success e-mail, written in Markdown.

  • successEmailAddresses array, Addresses to notify by e-mail when the job completes successfully.

  • successEmailFromName string, Name from which success emails are sent; defaults to "Civis."

  • successEmailReplyTo string, Address for replies to success emails; defaults to the author of the job.

  • failureEmailAddresses array, Addresses to notify by e-mail when the job fails.

  • stallWarningMinutes integer, Stall warning emails will be sent after this amount of minutes.

  • successOn boolean, If success email notifications are on.

  • failureOn boolean, If failure email notifications are on.

schedule

list optional. A list containing the following elements:

  • scheduled boolean, If the item is scheduled.

  • scheduledDays array, Day based on numeric value starting at 0 for Sunday.

  • scheduledHours array, Hours of the day it is scheduled on.

  • scheduledMinutes array, Minutes of the day it is scheduled on.

  • scheduledRunsPerHour integer, Alternative to scheduled minutes, number of times to run per hour.

parent_id

integer optional. The ID of the parent job that will trigger this model.

time_zone

string optional. The time zone of this model.

Value

An empty HTTP response