AutoMlForecastingInputs(mapping=None, *, ignore_unknown_fields=False, **kwargs)
The name of the column that the model is to predict.
The name of the column that identifies the time series.
The name of the column that identifies time order in the time series.
Each transformation will apply transform function to given input column. And the result will be used for training. When creating transformation for BigQuery Struct column, the column should be flattened using "." as the delimiter.
Objective function the model is optimizing towards. The training process creates a model that optimizes the value of the objective function over the validation set. The supported optimization objectives: "minimize-rmse" (default) - Minimize root- mean-squared error (RMSE). "minimize-mae" - Minimize mean-absolute error (MAE). "minimize- rmsle" - Minimize root-mean-squared log error (RMSLE). "minimize-rmspe" - Minimize root- mean-squared percentage error (RMSPE). "minimize-wape-mae" - Minimize the combination of weighted absolute percentage error (WAPE) and mean-absolute-error (MAE).
Required. The train budget of creating this model, expressed in milli node hours i.e. 1,000 value in this field means 1 node hour. The training cost of the model will not exceed this budget. The final cost will be attempted to be close to the budget, though may end up being (even) noticeably smaller - at the backend's discretion. This especially may happen when further model training ceases to provide any improvements. If the budget is set to a value known to be insufficient to train a model for the given dataset, the training won't be attempted and will error. The train budget must be between 1,000 and 72,000 milli node hours, inclusive.
Column name that should be used as the weight column. Higher values in this column give more importance to the row during model training. The column must have numeric values between 0 and 10000 inclusively; 0 means the row is ignored for training. If weight column field is not set, then all rows are assumed to have equal weight of 1.
Column names that should be used as static columns. The value of these columns are static per time series.
Column names that should be used as time variant past only columns. This column contains information for the given entity (identified by the time_series_identifier_column) that is known for the past but not the future (e.g. population of a city in a given year, or weather on a given day).
Column names that should be used as time variant past and future columns. This column contains information for the given entity (identified by the key column) that is known for the past and the future
Expected difference in time granularity between rows in the data. If it is not set, the period is inferred from data.
The number of periods offset into the future as the start of the forecast window (the window of future values to predict, relative to the present.), where each period is one unit of granularity as defined by the ``period`` field above. Default to 0. Inclusive.
The number of periods offset into the future as the end of the forecast window (the window of future values to predict, relative to the present.), where each period is one unit of granularity as defined by the ``period`` field above. Inclusive.
The number of periods offset into the past to restrict past sequence, where each period is one unit of granularity as defined by the ``period``. Default value 0 means that it lets algorithm to define the value. Inclusive.
Configuration for exporting test set predictions to a BigQuery table. If this configuration is absent, then the export is not performed.
Inheritancebuiltins.object > proto.message.Message > AutoMlForecastingInputs
Period(mapping=None, *, ignore_unknown_fields=False, **kwargs)
A duration of time expressed in time granularity units.
Transformation(mapping=None, *, ignore_unknown_fields=False, **kwargs)