Update reference-automated-ml-forecasting.md

ssalgadodev · web-flow · commit 040a16e8ceff · 2023-03-08T13:27:32.000-08:00
diff --git a/articles/machine-learning/reference-automated-ml-forecasting.md b/articles/machine-learning/reference-automated-ml-forecasting.md
@@ -58,7 +58,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 
 | Key | Type | Description | Allowed values | Default value |
 | --- | ---- | ----------- | -------------- | ------------- |
-| `enable_early_termination` | boolean | Represents whether to enable of experiment termination if the loss score doesn't improve after 'x' number of iterations.<br>In a Automated ML job, no early stopping is applied on first 20 iterations. The early stopping window starts only after first 20 iterations. | `true`, `false` | `true` |
+| `enable_early_termination` | boolean | Represents whether to enable of experiment termination if the loss score doesn't improve after 'x' number of iterations.<br>In an Automated ML job, no early stopping is applied on first 20 iterations. The early stopping window starts only after first 20 iterations. | `true`, `false` | `true` |
 | `max_concurrent_trials` | integer | The maximum number of trials (children jobs) that would be executed in parallel. It's highly recommended to set the number of concurrent runs to the number of nodes in the cluster (aml compute defined in `compute`). | | `1` |
 | `max_trials` | integer | Represents the maximum number of trials an Automated ML job can try to run a training algorithm with different combination of hyperparameters. Its default value is set to 1000. If `enable_early_termination` is defined, then the number of trials used to run training algorithms can be smaller.| | `1000` |
 | `max_cores_per_trial` | integer | Represents the maximum number of cores per that are available to be used by each trial. Its default value is set to -1, which means all cores are used in the process.| | `-1` |
@@ -77,7 +77,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 | `frequency` | string | The frequency at which the forecast generation is desired, for example daily, weekly, yearly, etc. <br>If it isn't specified or set to None, then its default value is inferred from the dataset time index. The user can set its value greater than dataset's inferred frequency, but not less than it. For example, if dataset's frequency is daily, it can take values like daily, weekly, monthly, but not hourly as hourly is less than daily(24 hours).<br> Refer to [pandas documentation](https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#dateoffset-objects) for more information.|  | `None` |
 | `time_series_id_column_names` | string or list(strings) | The names of columns in the data to be used to group data into multiple time series. If time_series_id_column_names is not defined or set to None, the Automated ML uses auto-detection logic to detect the columns.|  | `None` |
 | `feature_lags` | string | Represents if user wants to generate lags automatically for the provided numeric features. The default is set to `auto`, meaning that Automated ML uses autocorrelation-based heuristics to automatically select lag orders and generate corresponding lag features for all numeric features. "None" means no lags are generated for any numeric features.| `'auto'`, `None` | `None` |
-| `country_or_region_for_holidays` | string | The country or region to be used to generate holiday features. These characters should be represented in ISO 3166 two-letter country/region codes, for example 'US' or 'GB'. The list of the ISO codes can be found here : https://en.wikipedia.org/wiki/List_of_ISO_3166_country_codes|  | `None` |
+| `country_or_region_for_holidays` | string | The country or region to be used to generate holiday features. These characters should be represented in ISO 3166 two-letter country/region codes, for example 'US' or 'GB'. The list of the ISO codes can be found here: https://en.wikipedia.org/wiki/List_of_ISO_3166_country_codes|  | `None` |
 | `cv_step_size` | string or integer | The number of periods between the origin_time of one CV fold and the next fold. For example, if it is set to 3 for daily data, the origin time for each fold is three days apart. If it set to None or not specified, then it's set to `auto` by default. If it is of integer type, minimum value it can take is 1 else it raises an error. | `auto`, [int] | `auto` |
 | `seasonality` | string or integer | The time series seasonality as an integer multiple of the series frequency. If seasonality is not specified, its value is set to `'auto'`, meaning it is inferred automatically by Automated ML. If this parameter is not set to `None`, the Automated ML assumes time series as non-seasonal, which is equivalent to setting it as integer value 1. | `'auto'`, [int] | `auto` | 
 | `short_series_handling_config` | string | Represents how Automated ML should handle short time series if specified. It takes following values: <br><ul><li>`'auto'` : short series is padded if there are no long series, otherwise short series is dropped.</li><li>`'pad'`: all the short series is padded with zeros.</li><li>`'drop'`: all the short series is dropped.</li><li> `None`: the short series is not modified.</li><ul>| `'auto'`, `'pad'`, `'drop'`, `None` | `auto` |
@@ -108,7 +108,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 | `enable_dnn_training` | boolean | A flag to turn on or off the inclusion of DNN based models to try out during model selection.| `True`, `False` | `False` |
 | `enable_model_explainability` | boolean |  Represents a flag to turn on model explainability like feature importance, of best model evaluated by Automated ML system. | `True`, `False` | `True` |
 | `enable_vote_ensemble` | boolean | A flag to enable or disable the ensembling of some base models using Voting algorithm. For more information about ensembles, see [Set up Auto train](./how-to-configure-auto-train.md). | `true`, `false` | `true` |
-| `enable_stack_ensemble` | boolean | A flag to enable or disable ensembling of some base models using Stacking algorithm. In forecasting tasks, this flag is turned off by default, to avoid risks of overfitting due to small training set used in fitting the meta learner. For more information about ensembles, see [Set up Auto trai](./how-to-configure-auto-train.md). | `true`, `false` | `false` |
+| `enable_stack_ensemble` | boolean | A flag to enable or disable ensembling of some base models using Stacking algorithm. In forecasting tasks, this flag is turned off by default, to avoid risks of overfitting due to small training set used in fitting the meta learner. For more information about ensembles, see [Set up Auto train](./how-to-configure-auto-train.md). | `true`, `false` | `false` |
 
 
 
@@ -150,4 +150,4 @@ az ml job create --file [YOUR_CLI_YAML_FILE] --workspace-name [YOUR_AZURE_WORKSP
 1. [Install and use the CLI (v2)](how-to-configure-cli.md)
 2. [How to run AutoML job via CLI]()
 2. [How to auto train forecasts](./how-to-auto-train-forecast.md)
-3. CLI Forecasting examples:<br><ul><li>[Orange Juice Sale Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-orange-juice-sales)</li><li>[Energy Demand Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-task-energy-demand)</li><li>[Bike Share Demand Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-bike-share)</li><li>[Github Daily Active Users Forecast](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-task-github-dau)
+3. CLI Forecasting examples:<br><ul><li>[Orange Juice Sale Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-orange-juice-sales)</li><li>[Energy Demand Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-task-energy-demand)</li><li>[Bike Share Demand Forecasting](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-bike-share)</li><li>[GitHub Daily Active Users Forecast](https://github.com/Azure/azureml-examples/tree/main/cli/jobs/automl-standalone-jobs/cli-automl-forecasting-task-github-dau)
