Module `tripleblind.regression_asset`

Classes

class PSIVerticalRegressionModel (uuid: UUID)

PSIVerticalRegressionModel(uuid: 'UUID', _accesspoint_filename: 'Optional[str]' = None, _filename: 'Optional[str]' = None, _hash: 'Optional[str]' = None, _name: 'Optional[str]' = None, _namespace: 'Optional[UUID]' = None, _metadata: 'Optional[dict]' = None, _activate_date: 'Optional[dt.datetime]' = None, _deactivate_date: 'Optional[dt.datetime]' = None, _desc: 'Optional[str]' = None, _team: 'Optional[str]' = None, _team_id: 'Optional[str]' = None, _is_discoverable: 'bool' = False, _k_grouping: 'Optional[int]' = None)

Ancestors

Static methods

def train(datasets: Union[Asset, List[Asset]], match_column: Union[str, List[str]], regression_type: tb_shared_objects.enums.RegressionType, target: str, preprocessor: Union[preprocessor.tabular.TabularPreprocessor, List[preprocessor.tabular.TabularPreprocessor], preprocessor.tabular.TabularPreprocessorBuilder, List[preprocessor.tabular.TabularPreprocessorBuilder], ForwardRef(None)] = None, learning_rate: Optional[float] = 0.1, job_name: Optional[str] = None, session: Optional[Session] = None) -> Asset

Create a PSIVerticalRegression model trained on the provided dataset(s).

Args

datasets : Union[Asset, List[Asset]]: A dataset Asset (or a list of Assets) to be used in the psi prior to the regression.
match_column : Union[str, List[str]]: Name of the column to match. If not the same in all datasets, a list of the matching column names, starting with the initiator asset and then listing a name in each dataset.
regression_type : RegressionType: Type of regression to be run. Either tb.RegressionType.LINEAR or tb.RegressionType.LOGISTIC
target : str: The name of the target column for the training
preprocessor : Union[TabularPreprocessor, List[TabularPreprocessor]], optional: The preprocessor(s) to use against the datasets. When no preprocessor is specified, the default preprocessor selects all columns.
learning_rate : float, optional: Learning rate for training.
job_name : str, optional: Reference name for this process. This name will appear in the Access Request, Process History, and Audit Reports.
session : Session, optional: A connection session. If not specified, the default session is used.

Raises

TripleblindTrainingError: Model training failed

Returns

Regression Asset: The trained model, or None if training fails.

Inherited members

Regression:
- accesspoint_filename
- activate_date
- add_agreement
- archive
- cast
- deactivate_date
- delete
- desc
- download
- filename
- find
- find_all
- hash
- infer
- is_active
- is_discoverable
- is_valid
- k_grouping
- list_agreements
- metadata
- name
- namespace
- position
- psi_infer
- publish_to_team
- retrieve
- team
- team_id
- upload
- uuid

class Regression (uuid: UUID)

An abstract Regression class for representing a regression model.

Ancestors

Static methods

def cast(asset: Asset) -> Regression

Convert a generic Asset into a Regression

This should only be used on an asset known to be a Regression asset, no validation occurs during the cast.

Args

asset : Asset: A generic Asset

Returns

Regression: A Regression asset object

def find(search: Union[str, re.Pattern, ForwardRef(None)], namespace: Optional[uuid.UUID] = None, owned: Optional[bool] = False, owned_by: Optional[int] = None, session: Optional[Session] = None, exact_match: Optional[bool] = True) -> Optional[Regression]

Search the Router index for an asset matching the given search

Args

search : str or re.Pattern, optional: The search pattern applied to asset names. A simple string will be used as a substring search if exact_match is False, otherwise it will only return exact matches.
namespace : UUID, optional: The UUID of the user to which this asset belongs. None indicates any user, NAMESPACE_DEFAULT_USER indicates the current API user.
owned : bool, optional: Only return owned assets (either personally or by the current user's team)
owned_by : int, optional: Only return owned assets owned by the given team ID
session : Session, optional: A connection session. If not specified, the default session is used.
exact_match : bool, optional: When the 'search' is a string, setting this to True will perform an exact match. Ignored for regex patterns, defaults to True.

Raises

TripleblindAssetError: Thrown when multiple assets are found which match the search.

Returns

Regression: A single Regression asset, or None if no match found

Inherited members

ModelAsset:
- accesspoint_filename
- activate_date
- add_agreement
- archive
- deactivate_date
- delete
- desc
- download
- filename
- find_all
- hash
- infer
- is_active
- is_discoverable
- is_valid
- k_grouping
- list_agreements
- metadata
- name
- namespace
- position
- psi_infer
- publish_to_team
- retrieve
- team
- team_id
- upload
- uuid

class RegressionModel (uuid: UUID)

RegressionModel(uuid: 'UUID', _accesspoint_filename: 'Optional[str]' = None, _filename: 'Optional[str]' = None, _hash: 'Optional[str]' = None, _name: 'Optional[str]' = None, _namespace: 'Optional[UUID]' = None, _metadata: 'Optional[dict]' = None, _activate_date: 'Optional[dt.datetime]' = None, _deactivate_date: 'Optional[dt.datetime]' = None, _desc: 'Optional[str]' = None, _team: 'Optional[str]' = None, _team_id: 'Optional[str]' = None, _is_discoverable: 'bool' = False, _k_grouping: 'Optional[int]' = None)

Ancestors

Static methods

def train(datasets: Union[Asset, List[Asset]], regression_type: tb_shared_objects.enums.RegressionType, target: str, model_params: Optional[dict] = None, preprocessor: Union[preprocessor.tabular.TabularPreprocessor, List[preprocessor.tabular.TabularPreprocessor], preprocessor.tabular.TabularPreprocessorBuilder, List[preprocessor.tabular.TabularPreprocessorBuilder], ForwardRef(None)] = None, job_name: Optional[str] = None, test_size: Optional[float] = 0.0, data_scale_factor: Optional[int] = 1, weight_scale_factor: Optional[int] = 1, minimum_data_value: Optional[int] = 1, minimum_weight_value: Optional[int] = 1, session: Optional[Session] = None) -> Asset

Create a Regression model trained on the provided horizontal dataset(s).

Args

datasets : Union[Asset, List[Asset]]

A dataset Asset (or a list of Assets) used to train the regression.

regression_type : RegressionType

Type of regression to be run. One of: tb.RegressionType.LINEAR, LOGISTIC, LASSO, RIDGE

target : str

The name of the target column for the training

model_params : dict, optional

Model parameters specific to regression_type used. Available regression algorithms with usable params:

LinearRegression - https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LinearRegression.html

LogisticRegression - https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html

Lasso - https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Lasso.html

Ridge - https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html

preprocessor : Union[TabularPreprocessor, List[TabularPreprocessor]], optional

The preprocessor(s) to use against the datasets. When no preprocessor is specified, the default preprocessor selects all columns.

job_name : str, optional

Reference name for this process. This name will appear in the Access Request, Process History, and Audit Reports.

test_size : float, optional

test size used for training

data_scale_factor : int, optional

data scale factor used for training

weight_scale_factor : int, optional

weight scale factor used for training

minimum_data_value : int, optional

minimum data value used for training

minimum_weight_value : int, optional

minimum weight value used for training

session : Session, optional

A connection session. If not specified, the default session is used.

Raises

TripleblindTrainingError: Model training failed

Returns

Regression Asset: The trained model.

Inherited members

Regression:
- accesspoint_filename
- activate_date
- add_agreement
- archive
- cast
- deactivate_date
- delete
- desc
- download
- filename
- find
- find_all
- hash
- infer
- is_active
- is_discoverable
- is_valid
- k_grouping
- list_agreements
- metadata
- name
- namespace
- position
- psi_infer
- publish_to_team
- retrieve
- team
- team_id
- upload
- uuid