Update reference-automated-ml-forecasting.md

Author: ssalgadodev

articles/machine-learning/reference-automated-ml-forecasting.md

@@ -61,7 +61,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 | `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` |
-| `timeout_minutes ` | integer | The maximum amount of time in minutes that the submitted Automated ML job can take to run. After the specified amount of time, the job is terminated. This timeout includes setup, featurization, training runs, ensembling and model explainability (if provided) of all trials. Note that it doesn't include the ensembling and model explainability runs at the end of the process if the job fails to get completed within provided `timeout_minutes` since these features are available once all the trials (children jobs) are done. Its default value is set to 360 minutes (6 hours). To specify a timeout less than or equal to 1 hour (60 minutes), the user should make sure dataset's size isn't greater than 10,000,000 (rows times column) or an error results. | | `360` |
+| `timeout_minutes ` | integer | The maximum amount of time in minutes that the submitted Automated ML job can take to run. After the specified amount of time, the job is terminated. This timeout includes setup, featurization, training runs, ensembling and model explainability (if provided) of all trials. <br> Note that it doesn't include the ensembling and model explainability runs at the end of the process if the job fails to get completed within provided `timeout_minutes` since these features are available once all the trials (children jobs) are done. <br> Its default value is set to 360 minutes (6 hours). To specify a timeout less than or equal to 1 hour (60 minutes), the user should make sure dataset's size isn't greater than 10,000,000 (rows times column) or an error results. | | `360` |
 | `trial_timeout_minutes ` | integer | The maximum amount of time in minutes that each trial (child job) in the submitted Automated ML job can take run. After the specified amount of time, the child job will get terminated. | |`30`|
 | `exit_score` | float | The score to achieve by an experiment. The experiment terminates after the specified score is reached. If not specified (no criteria), the experiment runs until no further progress is made on the defined `primary metric`. | | |
 
@@ -115,7 +115,7 @@ The source JSON schema can be found at https://azuremlschemas.azureedge.net/late
 
 | Key | Type | Description | Allowed values | Default value |
 | --- | ---- | ----------- | -------------- | ------------- |
-| `mode` | string | The featurization mode to be used by Automated ML job.<br>Setting it to: <br> `'auto'` indicates whether featurization step should be done automatically<br>`'off'` indicates no featurization<`'custom'` indicates whether customized featurization should be used. <br> Note: If the input data is sparse, featurization cannot be turned on. | `'auto'`, `'off'`, `'custom'` | `None` |
+| `mode` | string | The featurization mode to be used by Automated ML job.<br>Setting it to: <br> `'auto'` indicates whether featurization step should be done automatically<br>`'off'` indicates no featurization<`'custom'` indicates whether customized featurization should be used. <br><br> Note: If the input data is sparse, featurization cannot be turned on. | `'auto'`, `'off'`, `'custom'` | `None` |
 | `blocked_transformers` | list(string) | A list of transformer names to be blocked during featurization step by Automated ML, if featurization `mode` is set to 'custom'. | `'text_target_encoder'`, `'one_hot_encoder'`, `'cat_target_encoder'`, `'tf_idf'`, `'wo_e_target_encoder'`, `'label_encoder'`, `'word_embedding'`, `'naive_bayes'`, `'count_vectorizer'`, `'hash_one_hot_encoder'` | `None` |
 | `column_name_and_types` | object | A dictionary object consisting of column names as dict key and feature types used to update column purpose as associated value, if featurization `mode` is set to 'custom'.|  |  |
 | `transformer_params` | object | A nested dictionary object consisting of transformer name as key and corresponding customization parameters on dataset columns for featurization, if featurization `mode` is set to 'custom'.<br>The forecasting only supports `imputer` transformer for customization.<br> Check out [column_transformers](#column_transformers) to find out how to create customization parameters. |  | `None` |