teradataml.store.feature_store.models.DataDomain.datasets

DESCRIPTION:
    Returns the list of Dataset objects associated with corresponding data domain.
 
PARAMETERS:
    None
 
RETURNS:
    list of Dataset.
 
RAISES:
    None
 
EXAMPLES:
    # Load data to be used.
    >>> from teradataml import load_example_data, DataFrame
    >>> load_example_data('dataframe', ['sales', 'admissions_train'])
    >>> df = DataFrame('sales')
    >>> admission_df = DataFrame('admissions_train')
 
    # Define repo and data doamin.
    >>> repo = 'vfs_test'
    >>> data_domain = 'sales'
 
    # Create a FeatureStore.
    >>> from teradataml import FeatureStore
    >>> fs = FeatureStore(repo=repo, data_domain=data_domain)
    Repo vfs_test does not exist. Run FeatureStore.setup() to create the repo and setup FeatureStore.
    >>> fs.setup()
    True
 
    # Run FeatureProcess to ingest features.
    >>> from teradataml import FeatureProcess
    >>> fp = FeatureProcess(repo=repo,
    ...                     data_domain=data_domain,
    ...                     object=df,
    ...                     entity='accounts',
    ...                     features=['Jan', 'Feb', 'Mar', 'Apr'])
    >>> fp.run()
    Process '4098c3ea-6c8d-11f0-837a-24eb16d15109' started.
    Process '4098c3ea-6c8d-11f0-837a-24eb16d15109' completed.
 
    # Build dataset.
    >>> from teradataml import DatasetCatalog
    >>> dataset_catalog = DatasetCatalog(repo=repo, data_domain=data_domain)
    >>> dataset_catalog.build_dataset(entity='accounts',
    ...                               selected_features={
    ...                                   'Jan': fp.process_id,
    ...                                   'Feb': fp.process_id,
    ...                                   'Mar': fp.process_id},
    ...                               view_name='dd_test_view',
    ...                               description='DataDomain Test')
         accounts    Jan    Feb    Mar
    0  Yellow Inc    NaN   90.0    NaN
    1    Alpha Co  200.0  210.0  215.0
    2   Jones LLC  150.0  200.0  140.0
    3    Blue Inc   50.0   90.0   95.0
    4  Orange Inc    NaN  210.0    NaN
    5     Red Inc  150.0  200.0  140.0
 
    # Run another FeatureProcess to ingest features into different dataframe.
    >>> fp2 = FeatureProcess(repo=repo,
    ...                      data_domain=data_domain,
    ...                      object=admission_df,
    ...                      entity='id',
    ...                      features=['masters', 'gpa', 'stats', 'admitted'])
    >>> fp2.run()
    Process '5129c4eb-7d9e-21f1-947b-35fb27e26210' started.
    Process '5129c4eb-7d9e-21f1-947b-35fb27e26210' completed.
 
    # Build dataset.
    >>> dataset_catalog.build_dataset(entity='id',
    ...                               selected_features={
    ...                                   'master': fp2.process_id,
    ...                                   'stats': fp2.process_id,
    ...                                   'gpa': fp2.process_id}
    ...                               view_name='dd_test_view_2',
    ...                               description='DataDomain Test 2')
       id masters   gpa     stats
    0  13      no  4.00  Advanced
    1  36      no  3.00  Advanced
    2  15     yes  4.00  Advanced
    3  38     yes  2.65  Advanced
    4   5      no  3.44    Novice
    5  40     yes  3.95    Novice
    6   7     yes  2.33    Novice
    7  22     yes  3.46    Novice
    8  26     yes  3.57  Advanced
    9  19     yes  1.98  Advanced
 
    # Example 1: Get the datasets in data domain.
    # Create DataDomain object.
    >>> from teradataml import DataDomain
    >>> dd = DataDomain(repo=repo,
    ...                 data_domain=data_domain)
 
    # List datasets.
    >>> dd.datasets
    [Dataset(repo=vfs_test, id=f4450459-6f17-4155-8b8a-01764701e4aa, data_domain=sales),
     Dataset(repo=vfs_test, id=75533508-74f4-40ca-bd63-8ea6710d9700, data_domain=sales)]