Version 0.78.0

Author: Brandon Lefore

abacusai/__init__.py

@@ -4,4 +4,4 @@
 from .streaming_client import StreamingClient
 
 
-__version__ = "0.77.8"
+__version__ = "0.78.0"

abacusai/api_class/model.py

@@ -55,7 +55,7 @@ class PersonalizationTrainingConfig(TrainingConfig):
         compute_session_metrics (bool): Evaluate models based on how well they are able to predict the next session of interactions.
         max_user_history_len_percentile (int): Filter out users with history length above this percentile.
         downsample_item_popularity_percentile (float): Downsample items more popular than this percentile.
-
+        allow_duplicate_action_types (List[str]): event types which will not be deduplicated.
     """
     # top-level params
     objective: enums.PersonalizationObjective = dataclasses.field(default=None)
@@ -67,6 +67,7 @@ class PersonalizationTrainingConfig(TrainingConfig):
     target_action_types: List[str] = dataclasses.field(default=None)
     target_action_weights: Dict[str, float] = dataclasses.field(default=None)
     session_event_types: List[str] = dataclasses.field(default=None)
+    allow_duplicate_action_types: List[str] = dataclasses.field(default=None)
 
     # data split
     test_split: int = dataclasses.field(default=None)
@@ -270,6 +271,7 @@ class ForecastingTrainingConfig(TrainingConfig):
         use_log_transforms (bool): Apply logarithmic transformations to input data.
         smooth_history (float): Smooth (low pass filter) the timeseries.
         local_scale_target (bool): Using per training/prediction window target scaling.
+        use_clipping (bool): Apply clipping to input data to stabilize the training.
         timeseries_weight_column (str): If set, we use the values in this column from timeseries data to assign time dependent item weights during training and evaluation.
         item_attributes_weight_column (str): If set, we use the values in this column from item attributes data to assign weights to items during training and evaluation.
         use_timeseries_weights_in_objective (bool): If True, we include weights from column set as "TIMESERIES WEIGHT COLUMN" in objective functions.
@@ -334,6 +336,7 @@ class ForecastingTrainingConfig(TrainingConfig):
     use_log_transforms: bool = dataclasses.field(default=None)
     smooth_history: float = dataclasses.field(default=None)
     local_scale_target: bool = dataclasses.field(default=None)
+    use_clipping: bool = dataclasses.field(default=None)
     # Item weights
     timeseries_weight_column: str = dataclasses.field(default=None)
     item_attributes_weight_column: str = dataclasses.field(default=None)

abacusai/batch_prediction_version.py

@@ -44,10 +44,11 @@ class BatchPredictionVersion(AbstractApiClass):
             outputFeatureGroupId (str): The BP output feature group id if applicable
             outputFeatureGroupVersion (str): The BP output feature group version if applicable
             outputFeatureGroupTableName (str): The BP output feature group name if applicable
+            batchPredictionWarnings (str): Relevant warnings if any issues are found
             batchInputs (PredictionInput): Inputs to the batch prediction
     """
 
-    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, outputFeatureGroupTableName=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, outputFeatureGroupTableName=None, batchPredictionWarnings=None, batchInputs={}, globalPredictionArgs={}):
         super().__init__(client, batchPredictionVersion)
         self.batch_prediction_version = batchPredictionVersion
         self.batch_prediction_id = batchPredictionId
@@ -84,13 +85,14 @@ def __init__(self, client, batchPredictionVersion=None, batchPredictionId=None,
         self.output_feature_group_id = outputFeatureGroupId
         self.output_feature_group_version = outputFeatureGroupVersion
         self.output_feature_group_table_name = outputFeatureGroupTableName
+        self.batch_prediction_warnings = batchPredictionWarnings
         self.batch_inputs = client._build_class(PredictionInput, batchInputs)
         self.global_prediction_args = client._build_class(
             BatchPredictionArgs, globalPredictionArgs)
 
     def __repr__(self):
-        repr_dict = {f'batch_prediction_version': repr(self.batch_prediction_version), f'batch_prediction_id': repr(self.batch_prediction_id), f'status': repr(self.status), f'drift_monitor_status': repr(self.drift_monitor_status), f'deployment_id': repr(self.deployment_id), f'model_id': repr(self.model_id), f'model_version': repr(self.model_version), f'predictions_started_at': repr(self.predictions_started_at), f'predictions_completed_at': repr(self.predictions_completed_at), f'database_output_error': repr(self.database_output_error), f'total_predictions': repr(self.total_predictions), f'failed_predictions': repr(self.failed_predictions), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_connector_output_location': repr(self.file_connector_output_location), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(
-            self.legacy_input_location), f'error': repr(self.error), f'drift_monitor_error': repr(self.drift_monitor_error), f'monitor_warnings': repr(self.monitor_warnings), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'database_output_total_writes': repr(self.database_output_total_writes), f'database_output_failed_writes': repr(self.database_output_failed_writes), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_version': repr(self.model_monitor_version), f'algo_name': repr(self.algo_name), f'algorithm': repr(self.algorithm), f'output_feature_group_id': repr(self.output_feature_group_id), f'output_feature_group_version': repr(self.output_feature_group_version), f'output_feature_group_table_name': repr(self.output_feature_group_table_name), f'batch_inputs': repr(self.batch_inputs), f'global_prediction_args': repr(self.global_prediction_args)}
+        repr_dict = {f'batch_prediction_version': repr(self.batch_prediction_version), f'batch_prediction_id': repr(self.batch_prediction_id), f'status': repr(self.status), f'drift_monitor_status': repr(self.drift_monitor_status), f'deployment_id': repr(self.deployment_id), f'model_id': repr(self.model_id), f'model_version': repr(self.model_version), f'predictions_started_at': repr(self.predictions_started_at), f'predictions_completed_at': repr(self.predictions_completed_at), f'database_output_error': repr(self.database_output_error), f'total_predictions': repr(self.total_predictions), f'failed_predictions': repr(self.failed_predictions), f'database_connector_id': repr(self.database_connector_id), f'database_output_configuration': repr(self.database_output_configuration), f'explanations': repr(self.explanations), f'file_connector_output_location': repr(self.file_connector_output_location), f'file_output_format': repr(self.file_output_format), f'connector_type': repr(self.connector_type), f'legacy_input_location': repr(self.legacy_input_location), f'error': repr(
+            self.error), f'drift_monitor_error': repr(self.drift_monitor_error), f'monitor_warnings': repr(self.monitor_warnings), f'csv_input_prefix': repr(self.csv_input_prefix), f'csv_prediction_prefix': repr(self.csv_prediction_prefix), f'csv_explanations_prefix': repr(self.csv_explanations_prefix), f'database_output_total_writes': repr(self.database_output_total_writes), f'database_output_failed_writes': repr(self.database_output_failed_writes), f'output_includes_metadata': repr(self.output_includes_metadata), f'result_input_columns': repr(self.result_input_columns), f'model_monitor_version': repr(self.model_monitor_version), f'algo_name': repr(self.algo_name), f'algorithm': repr(self.algorithm), f'output_feature_group_id': repr(self.output_feature_group_id), f'output_feature_group_version': repr(self.output_feature_group_version), f'output_feature_group_table_name': repr(self.output_feature_group_table_name), f'batch_prediction_warnings': repr(self.batch_prediction_warnings), f'batch_inputs': repr(self.batch_inputs), f'global_prediction_args': repr(self.global_prediction_args)}
         class_name = "BatchPredictionVersion"
         repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
         ) if getattr(self, key, None) is not None])
@@ -103,8 +105,8 @@ def to_dict(self):
         Returns:
             dict: The dict value representation of the class parameters
         """
-        resp = {'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, 'output_feature_group_table_name': self.output_feature_group_table_name, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
+        resp = {'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, 'output_feature_group_table_name': self.output_feature_group_table_name, 'batch_prediction_warnings': self.batch_prediction_warnings, 'batch_inputs': self._get_attribute_as_dict(self.batch_inputs), 'global_prediction_args': self._get_attribute_as_dict(self.global_prediction_args)}
         return {key: value for key, value in resp.items() if value is not None}
 
     def download_batch_prediction_result_chunk(self, offset: int = 0, chunk_size: int = 10485760):
@@ -148,6 +150,18 @@ def describe(self):
         """
         return self.client.describe_batch_prediction_version(self.batch_prediction_version)
 
+    def get_logs(self):
+        """
+        Retrieves the batch prediction logs.
+
+        Args:
+            batch_prediction_version (str): The unique version ID of the batch prediction version.
+
+        Returns:
+            BatchPredictionVersionLogs: The logs for the specified batch prediction version.
+        """
+        return self.client.get_batch_prediction_version_logs(self.batch_prediction_version)
+
     def download_result_to_file(self, file):
         """
         Downloads the batch prediction version in a local file.

abacusai/batch_prediction_version_logs.py

@@ -0,0 +1,35 @@
+from .return_class import AbstractApiClass
+
+
+class BatchPredictionVersionLogs(AbstractApiClass):
+    """
+        Logs from batch prediction version.
+
+        Args:
+            client (ApiClient): An authenticated API Client instance
+            logs (list[str]): List of logs from batch prediction version.
+            warnings (list[str]): List of warnings from batch prediction version.
+    """
+
+    def __init__(self, client, logs=None, warnings=None):
+        super().__init__(client, None)
+        self.logs = logs
+        self.warnings = warnings
+
+    def __repr__(self):
+        repr_dict = {f'logs': repr(
+            self.logs), f'warnings': repr(self.warnings)}
+        class_name = "BatchPredictionVersionLogs"
+        repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
+        ) if getattr(self, key, None) is not None])
+        return f"{class_name}({repr_str})"
+
+    def to_dict(self):
+        """
+        Get a dict representation of the parameters in this class
+
+        Returns:
+            dict: The dict value representation of the class parameters
+        """
+        resp = {'logs': self.logs, 'warnings': self.warnings}
+        return {key: value for key, value in resp.items() if value is not None}

abacusai/chat_message.py

@@ -12,19 +12,21 @@ class ChatMessage(AbstractApiClass):
             timestamp (str): The timestamp at which the message was sent
             isUseful (bool): Whether this message was marked as useful or not
             feedback (str): The feedback provided for the message
+            docId (str): Id of the uploaded document if the message has
     """
 
-    def __init__(self, client, role=None, text=None, timestamp=None, isUseful=None, feedback=None):
+    def __init__(self, client, role=None, text=None, timestamp=None, isUseful=None, feedback=None, docId=None):
         super().__init__(client, None)
         self.role = role
         self.text = text
         self.timestamp = timestamp
         self.is_useful = isUseful
         self.feedback = feedback
+        self.doc_id = docId
 
     def __repr__(self):
         repr_dict = {f'role': repr(self.role), f'text': repr(self.text), f'timestamp': repr(
-            self.timestamp), f'is_useful': repr(self.is_useful), f'feedback': repr(self.feedback)}
+            self.timestamp), f'is_useful': repr(self.is_useful), f'feedback': repr(self.feedback), f'doc_id': repr(self.doc_id)}
         class_name = "ChatMessage"
         repr_str = ',\n  '.join([f'{key}={value}' for key, value in repr_dict.items(
         ) if getattr(self, key, None) is not None])
@@ -38,5 +40,5 @@ def to_dict(self):
             dict: The dict value representation of the class parameters
         """
         resp = {'role': self.role, 'text': self.text, 'timestamp': self.timestamp,
-                'is_useful': self.is_useful, 'feedback': self.feedback}
+                'is_useful': self.is_useful, 'feedback': self.feedback, 'doc_id': self.doc_id}
         return {key: value for key, value in resp.items() if value is not None}