abacusai 0.77.0__tar.gz → 0.77.5__tar.gz

{abacusai-0.77.0/abacusai.egg-info → abacusai-0.77.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: abacusai
-Version: 0.77.0
+Version: 0.77.5
 Summary: Abacus.AI Python Client Library
 Home-page: https://github.com/abacusai/api-python
 Author: Abacus.AI

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/__init__.py

@@ -4,4 +4,4 @@ from .prediction_client import PredictionClient
 from .streaming_client import StreamingClient
 
 
-__version__ = "0.77.0"
+__version__ = "0.77.5"

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/api_class/__init__.py

@@ -5,6 +5,7 @@ from .document_retriever import *
 from .enums import *
 from .feature_group import *
 from .model import *
+from .monitor import *
 from .monitor_alert import *
 from .project import *
 from .python_functions import *

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/api_class/abstract.py

@@ -45,6 +45,14 @@ class ApiClass(ABC):
     def _get_builder(cls):
         return None
 
+    def __str__(self):
+        non_none_fields = {key: value for key, value in self.__dict__.items() if value is not None}
+        field_str = ', '.join([f'{key}={value!r}' for key, value in non_none_fields.items()])
+        return f'{self.__class__.__name__}({field_str})'
+
+    def _repr_html_(self):
+        return self.__str__()
+
     def to_dict(self):
         """
         Standardizes converting an ApiClass to dictionary.

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/api_class/batch_prediction.py

@@ -10,7 +10,6 @@ class BatchPredictionArgs(ApiClass):
 
     kwargs: dict = dataclasses.field(default_factory=dict)
     problem_type: enums.ProblemType = dataclasses.field(default=None)
-    name: str = 'batch_prediction_args'
 
     @classmethod
     def _get_builder(cls):

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/api_class/dataset.py

@@ -14,4 +14,7 @@ class ParsingConfig(ApiClass):
 class DocumentProcessingConfig(ApiClass):
     extract_bounding_boxes: bool = False
     convert_to_markdown: bool = False
-    use_doctr: bool = True
+    remove_header_footer: bool = False
+    use_doctr: bool = False
+    remove_watermarks: bool = None
+    use_full_ocr: bool = None

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/api_class/model.py

@@ -98,6 +98,8 @@ class PersonalizationTrainingConfig(TrainingConfig):
     add_time_features: bool = dataclasses.field(default=None)
     disable_timestamp_scalar_features: bool = dataclasses.field(default=None)
     compute_session_metrics: bool = dataclasses.field(default=None)
+    query_column: str = dataclasses.field(default=None)
+    item_query_column: str = dataclasses.field(default=None)
 
     # outliers
     max_user_history_len_percentile: int = dataclasses.field(default=None)
@@ -167,6 +169,7 @@ class RegressionTrainingConfig(TrainingConfig):
     test_splitting_timestamp: str = dataclasses.field(default=None)
     sampling_unit_keys: List[str] = dataclasses.field(default=None)
     test_row_indicator: str = dataclasses.field(default=None)
+    full_data_retraining: bool = dataclasses.field(default=None)
 
     # data augmentation
     rebalance_classes: bool = dataclasses.field(default=None)

abacusai-0.77.5/abacusai/api_class/monitor.py

@@ -0,0 +1,12 @@
+import dataclasses
+
+from .abstract import ApiClass
+
+
+@dataclasses.dataclass
+class ForecastingMonitorConfig(ApiClass):
+    id_column: str = dataclasses.field(default=None)
+    timestamp_column: str = dataclasses.field(default=None)
+    target_column: str = dataclasses.field(default=None)
+    start_time: str = dataclasses.field(default=None)
+    end_time: str = dataclasses.field(default=None)

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/app_user_group.py

@@ -10,17 +10,19 @@ class AppUserGroup(AbstractApiClass):
             client (ApiClient): An authenticated API Client instance
             name (str): The name of the user group.
             userGroupId (str): The unique identifier of the user group.
+            externalApplicationIds (list[str]): The ids of the external applications the group has access to.
             users (User): The users in the user group.
     """
 
-    def __init__(self, client, name=None, userGroupId=None, users={}):
+    def __init__(self, client, name=None, userGroupId=None, externalApplicationIds=None, users={}):
         super().__init__(client, None)
         self.name = name
         self.user_group_id = userGroupId
+        self.external_application_ids = externalApplicationIds
         self.users = client._build_class(User, users)
 
     def __repr__(self):
-        return f"AppUserGroup(name={repr(self.name)},\n  user_group_id={repr(self.user_group_id)},\n  users={repr(self.users)})"
+        return f"AppUserGroup(name={repr(self.name)},\n  user_group_id={repr(self.user_group_id)},\n  external_application_ids={repr(self.external_application_ids)},\n  users={repr(self.users)})"
 
     def to_dict(self):
         """
@@ -29,4 +31,4 @@ class AppUserGroup(AbstractApiClass):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        return {'name': self.name, 'user_group_id': self.user_group_id, 'users': self._get_attribute_as_dict(self.users)}
+        return {'name': self.name, 'user_group_id': self.user_group_id, 'external_application_ids': self.external_application_ids, 'users': self._get_attribute_as_dict(self.users)}

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/batch_prediction.py

@@ -37,7 +37,6 @@ class BatchPrediction(AbstractApiClass):
             batchInputs (PredictionInput): Inputs to the batch prediction.
             latestBatchPredictionVersion (BatchPredictionVersion): The latest batch prediction version.
             refreshSchedules (RefreshSchedule): List of refresh schedules that dictate the next time the batch prediction will be run.
-            globalPredictionArgs (BatchPredictionArgs): Argument(s) passed to every prediction call.
     """
 
     def __init__(self, client, batchPredictionId=None, createdAt=None, name=None, deploymentId=None, fileConnectorOutputLocation=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, featureGroupTableName=None, summaryFeatureGroupTableName=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorId=None, modelVersion=None, algorithm=None, batchInputs={}, latestBatchPredictionVersion={}, refreshSchedules={}, globalPredictionArgs={}):

{abacusai-0.77.0 → abacusai-0.77.5}/abacusai/batch_prediction_version.py

@@ -41,12 +41,12 @@ class BatchPredictionVersion(AbstractApiClass):
             modelMonitorVersion (str): The version of the model monitor
             algoName (str): The name of the algorithm used to train the model
             algorithm (str): The algorithm that is currently deployed.
+            outputFeatureGroupId (str): The BP output feature group if applicable
             outputFeatureGroupVersion (str): The BP output feature group version if applicable
             batchInputs (PredictionInput): Inputs to the batch prediction
-            globalPredictionArgs (BatchPredictionArgs): Argument(s) passed to every prediction call
     """
 
-    def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupVersion=None, batchInputs={}, globalPredictionArgs={}):
+    def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None, status=None, driftMonitorStatus=None, deploymentId=None, modelId=None, modelVersion=None, predictionsStartedAt=None, predictionsCompletedAt=None, databaseOutputError=None, totalPredictions=None, failedPredictions=None, databaseConnectorId=None, databaseOutputConfiguration=None, explanations=None, fileConnectorOutputLocation=None, fileOutputFormat=None, connectorType=None, legacyInputLocation=None, error=None, driftMonitorError=None, monitorWarnings=None, csvInputPrefix=None, csvPredictionPrefix=None, csvExplanationsPrefix=None, databaseOutputTotalWrites=None, databaseOutputFailedWrites=None, outputIncludesMetadata=None, resultInputColumns=None, modelMonitorVersion=None, algoName=None, algorithm=None, outputFeatureGroupId=None, outputFeatureGroupVersion=None, batchInputs={}, globalPredictionArgs={}):
         super().__init__(client, batchPredictionVersion)
         self.batch_prediction_version = batchPredictionVersion
         self.batch_prediction_id = batchPredictionId
@@ -80,13 +80,14 @@ class BatchPredictionVersion(AbstractApiClass):
         self.model_monitor_version = modelMonitorVersion
         self.algo_name = algoName
         self.algorithm = algorithm
+        self.output_feature_group_id = outputFeatureGroupId
         self.output_feature_group_version = outputFeatureGroupVersion
         self.batch_inputs = client._build_class(PredictionInput, batchInputs)
         self.global_prediction_args = client._build_class(
             BatchPredictionArgs, globalPredictionArgs)
 
     def __repr__(self):
-        return f"BatchPredictionVersion(batch_prediction_version={repr(self.batch_prediction_version)},\n  batch_prediction_id={repr(self.batch_prediction_id)},\n  status={repr(self.status)},\n  drift_monitor_status={repr(self.drift_monitor_status)},\n  deployment_id={repr(self.deployment_id)},\n  model_id={repr(self.model_id)},\n  model_version={repr(self.model_version)},\n  predictions_started_at={repr(self.predictions_started_at)},\n  predictions_completed_at={repr(self.predictions_completed_at)},\n  database_output_error={repr(self.database_output_error)},\n  total_predictions={repr(self.total_predictions)},\n  failed_predictions={repr(self.failed_predictions)},\n  database_connector_id={repr(self.database_connector_id)},\n  database_output_configuration={repr(self.database_output_configuration)},\n  explanations={repr(self.explanations)},\n  file_connector_output_location={repr(self.file_connector_output_location)},\n  file_output_format={repr(self.file_output_format)},\n  connector_type={repr(self.connector_type)},\n  legacy_input_location={repr(self.legacy_input_location)},\n  error={repr(self.error)},\n  drift_monitor_error={repr(self.drift_monitor_error)},\n  monitor_warnings={repr(self.monitor_warnings)},\n  csv_input_prefix={repr(self.csv_input_prefix)},\n  csv_prediction_prefix={repr(self.csv_prediction_prefix)},\n  csv_explanations_prefix={repr(self.csv_explanations_prefix)},\n  database_output_total_writes={repr(self.database_output_total_writes)},\n  database_output_failed_writes={repr(self.database_output_failed_writes)},\n  output_includes_metadata={repr(self.output_includes_metadata)},\n  result_input_columns={repr(self.result_input_columns)},\n  model_monitor_version={repr(self.model_monitor_version)},\n  algo_name={repr(self.algo_name)},\n  algorithm={repr(self.algorithm)},\n  output_feature_group_version={repr(self.output_feature_group_version)},\n  batch_inputs={repr(self.batch_inputs)},\n  global_prediction_args={repr(self.global_prediction_args)})"
+        return f"BatchPredictionVersion(batch_prediction_version={repr(self.batch_prediction_version)},\n  batch_prediction_id={repr(self.batch_prediction_id)},\n  status={repr(self.status)},\n  drift_monitor_status={repr(self.drift_monitor_status)},\n  deployment_id={repr(self.deployment_id)},\n  model_id={repr(self.model_id)},\n  model_version={repr(self.model_version)},\n  predictions_started_at={repr(self.predictions_started_at)},\n  predictions_completed_at={repr(self.predictions_completed_at)},\n  database_output_error={repr(self.database_output_error)},\n  total_predictions={repr(self.total_predictions)},\n  failed_predictions={repr(self.failed_predictions)},\n  database_connector_id={repr(self.database_connector_id)},\n  database_output_configuration={repr(self.database_output_configuration)},\n  explanations={repr(self.explanations)},\n  file_connector_output_location={repr(self.file_connector_output_location)},\n  file_output_format={repr(self.file_output_format)},\n  connector_type={repr(self.connector_type)},\n  legacy_input_location={repr(self.legacy_input_location)},\n  error={repr(self.error)},\n  drift_monitor_error={repr(self.drift_monitor_error)},\n  monitor_warnings={repr(self.monitor_warnings)},\n  csv_input_prefix={repr(self.csv_input_prefix)},\n  csv_prediction_prefix={repr(self.csv_prediction_prefix)},\n  csv_explanations_prefix={repr(self.csv_explanations_prefix)},\n  database_output_total_writes={repr(self.database_output_total_writes)},\n  database_output_failed_writes={repr(self.database_output_failed_writes)},\n  output_includes_metadata={repr(self.output_includes_metadata)},\n  result_input_columns={repr(self.result_input_columns)},\n  model_monitor_version={repr(self.model_monitor_version)},\n  algo_name={repr(self.algo_name)},\n  algorithm={repr(self.algorithm)},\n  output_feature_group_id={repr(self.output_feature_group_id)},\n  output_feature_group_version={repr(self.output_feature_group_version)},\n  batch_inputs={repr(self.batch_inputs)},\n  global_prediction_args={repr(self.global_prediction_args)})"
 
     def to_dict(self):
         """
@@ -95,7 +96,7 @@ class BatchPredictionVersion(AbstractApiClass):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        return {'batch_prediction_version': self.batch_prediction_version, 'batch_prediction_id': self.batch_prediction_id, 'status': self.status, 'drift_monitor_status': self.drift_monitor_status, 'deployment_id': self.deployment_id, 'model_id': self.model_id, 'model_version': self.model_version, 'predictions_started_at': self.predictions_started_at, 'predictions_completed_at': self.predictions_completed_at, 'database_output_error': self.database_output_error, 'total_predictions': self.total_predictions, 'failed_predictions': self.failed_predictions, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_connector_output_location': self.file_connector_output_location, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'error': self.error, 'drift_monitor_error': self.drift_monitor_error, 'monitor_warnings': self.monitor_warnings, 'csv_input_prefix': self.csv_input_prefix, 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'database_output_total_writes': self.database_output_total_writes, 'database_output_failed_writes': self.database_output_failed_writes, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_version': self.model_monitor_version, 'algo_name': self.algo_name, 'algorithm': self.algorithm, 'output_feature_group_version': self.output_feature_group_version, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
+        return {'batch_prediction_version': self.batch_prediction_version, 'batch_prediction_id': self.batch_prediction_id, 'status': self.status, 'drift_monitor_status': self.drift_monitor_status, 'deployment_id': self.deployment_id, 'model_id': self.model_id, 'model_version': self.model_version, 'predictions_started_at': self.predictions_started_at, 'predictions_completed_at': self.predictions_completed_at, 'database_output_error': self.database_output_error, 'total_predictions': self.total_predictions, 'failed_predictions': self.failed_predictions, 'database_connector_id': self.database_connector_id, 'database_output_configuration': self.database_output_configuration, 'explanations': self.explanations, 'file_connector_output_location': self.file_connector_output_location, 'file_output_format': self.file_output_format, 'connector_type': self.connector_type, 'legacy_input_location': self.legacy_input_location, 'error': self.error, 'drift_monitor_error': self.drift_monitor_error, 'monitor_warnings': self.monitor_warnings, 'csv_input_prefix': self.csv_input_prefix, 'csv_prediction_prefix': self.csv_prediction_prefix, 'csv_explanations_prefix': self.csv_explanations_prefix, 'database_output_total_writes': self.database_output_total_writes, 'database_output_failed_writes': self.database_output_failed_writes, 'output_includes_metadata': self.output_includes_metadata, 'result_input_columns': self.result_input_columns, 'model_monitor_version': self.model_monitor_version, 'algo_name': self.algo_name, 'algorithm': self.algorithm, 'output_feature_group_id': self.output_feature_group_id, 'output_feature_group_version': self.output_feature_group_version, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
 
     def download_batch_prediction_result_chunk(self, offset: int = 0, chunk_size: int = 10485760):
         """