Index

A

add_edges() (in module tamr_toolbox.workflow.concurrent.Graph) apply_feedback() (in module tamr_toolbox.project.categorization.jobs) (in module tamr_toolbox.project.mastering.jobs)

apply_feedback_and_update_results() (in module tamr_toolbox.project.categorization.jobs) (in module tamr_toolbox.project.mastering.jobs)

B

BOOLEAN (in module tamr_toolbox.models.attribute_type) bootstrap_dataset() (in module tamr_toolbox.project.categorization.schema) (in module tamr_toolbox.project.mastering.schema) (in module tamr_toolbox.project.schema_mapping.schema)

C

CategorizationArtifacts (class in tamr_toolbox.models.project_artifacts) CategorizationSteps (class in tamr_toolbox.models.project_steps) classify_backups() (in module tamr_toolbox.workflow.backup) Client (class in tamr_toolbox.data_io.df_connect.client) convert_to_mappings() (in module tamr_toolbox.enrichment.dictionary) create() (in module tamr_toolbox.data_io.df_connect.client) (in module tamr_toolbox.data_io.df_connect.jdbc_info) (in module tamr_toolbox.dataset.manage) (in module tamr_toolbox.enrichment.dictionary) (in module tamr_toolbox.utils.client) (in module tamr_toolbox.utils.logger)

create_attributes() (in module tamr_toolbox.dataset.manage) create_directories() (in module tamr_toolbox.filesystem.bash) create_node() (in module tamr_toolbox.project.categorization.taxonomy) current() (in module tamr_toolbox.utils.version)

D

datasets() (in module tamr_toolbox.utils.downstream) (in module tamr_toolbox.utils.upstream) DEFAULT (in module tamr_toolbox.models.attribute_type) default() (tamr_toolbox.enrichment.dictionary.SetEncoder method) delete_attributes() (in module tamr_toolbox.dataset.manage)

delete_backups() (in module tamr_toolbox.workflow.backup) delete_node() (in module tamr_toolbox.project.categorization.taxonomy) delete_old_backups() (in module tamr_toolbox.workflow.backup) delete_old_files() (in module tamr_toolbox.filesystem.bash) delete_old_spark_event_logs() (in module tamr_toolbox.workflow.backup) DOUBLE (in module tamr_toolbox.models.attribute_type)

E

edit_attributes() (in module tamr_toolbox.dataset.manage) enable_package_logging() (in module tamr_toolbox.utils.logger) enable_toolbox_logging() (in module tamr_toolbox.utils.logger) encode() (tamr_toolbox.enrichment.dictionary.SetEncoder method) enforce_after_or_equal() (in module tamr_toolbox.utils.version) enforce_success() (in module tamr_toolbox.utils.operation) estimate_pair_counts() (in module tamr_toolbox.project.mastering.jobs)

execute() (in module tamr_toolbox.workflow.concurrent.Planner) execute_statement() (in module tamr_toolbox.data_io.df_connect.client) exists() (in module tamr_toolbox.dataset.manage) export_artifacts() (in module tamr_toolbox.project) export_dataset() (in module tamr_toolbox.data_io.df_connect.client) export_dataset_as_avro() (in module tamr_toolbox.data_io.df_connect.client) export_dataset_avro_schema() (in module tamr_toolbox.data_io.df_connect.client)

F

filename() (in module tamr_toolbox.enrichment.dictionary) flatten() (in module tamr_toolbox.data_io.dataframe) from_config() (in module tamr_toolbox.data_io.df_connect.client) (in module tamr_toolbox.data_io.df_connect.jdbc_info) from_dataset() (in module tamr_toolbox.data_io.csv) (in module tamr_toolbox.data_io.dataframe) (in module tamr_toolbox.enrichment.dictionary) from_edges() (in module tamr_toolbox.workflow.concurrent.Graph)

from_graph() (in module tamr_toolbox.workflow.concurrent.Planner) from_json() (in module tamr_toolbox.models.attribute_type) from_list() (in module tamr_toolbox.enrichment.translate) from_plan_node() (in module tamr_toolbox.workflow.concurrent.PlanNodeStatus) from_planner() (in module tamr_toolbox.workflow.concurrent.PlanStatus) from_project_list() (in module tamr_toolbox.workflow.concurrent.Graph) from_resource_id() (in module tamr_toolbox.utils.operation) from_taxonomy() (in module tamr_toolbox.data_io.csv) from_yaml() (in module tamr_toolbox.utils.config)

G

gcs_download() (in module tamr_toolbox.filesystem.cloud) gcs_upload() (in module tamr_toolbox.filesystem.cloud) generate_pairs() (in module tamr_toolbox.project.mastering.jobs) GEOSPATIAL (in module tamr_toolbox.models.attribute_type) get_active() (in module tamr_toolbox.utils.operation) get_all() (in module tamr_toolbox.project.categorization.transformations) (in module tamr_toolbox.project.mastering.transformations) (in module tamr_toolbox.project.schema_mapping.transformations) (in module tamr_toolbox.utils.operation) get_all_downstream_nodes() (in module tamr_toolbox.workflow.concurrent.Graph) get_all_unified() (in module tamr_toolbox.project.categorization.transformations) (in module tamr_toolbox.project.mastering.transformations) (in module tamr_toolbox.project.schema_mapping.transformations) get_backup_by_id() (in module tamr_toolbox.workflow.backup) get_config() (in module tamr_toolbox.sysadmin.instance) get_configs() (in module tamr_toolbox.sysadmin.instance) get_connect_session() (in module tamr_toolbox.data_io.df_connect.client)

get_details() (in module tamr_toolbox.utils.operation) get_end_nodes() (in module tamr_toolbox.workflow.concurrent.Graph) get_latest() (in module tamr_toolbox.utils.operation) get_phrases_to_translate() (in module tamr_toolbox.enrichment.translate) get_predecessors() (in module tamr_toolbox.workflow.concurrent.Graph) get_profile() (in module tamr_toolbox.dataset._dataset) get_project_output_datasets() (in module tamr_toolbox.workflow.jobs) get_projects_by_tier() (in module tamr_toolbox.workflow.concurrent.Graph) get_source_nodes() (in module tamr_toolbox.workflow.concurrent.Graph) get_successors() (in module tamr_toolbox.workflow.concurrent.Graph) get_taxonomy_as_dataframe() (in module tamr_toolbox.project.categorization.taxonomy) get_tier_confidence() (in module tamr_toolbox.project.categorization.metrics) get_upstream_projects() (in module tamr_toolbox.workflow.jobs) get_with_connection_retry() (in module tamr_toolbox.utils.client) GoldenRecordsArtifacts (class in tamr_toolbox.models.project_artifacts) GoldenRecordsSteps (class in tamr_toolbox.models.project_steps) Graph (class in tamr_toolbox.workflow.concurrent.Graph)

H

health_check() (in module tamr_toolbox.utils.client)

I

import_artifacts() (in module tamr_toolbox.project) ingest_dataset() (in module tamr_toolbox.data_io.df_connect.client) initiate_backup() (in module tamr_toolbox.workflow.backup) initiate_restore() (in module tamr_toolbox.workflow.backup) InputTransformation (class in tamr_toolbox.project.categorization.transformations) (class in tamr_toolbox.project.mastering.transformations) (class in tamr_toolbox.project.schema_mapping.transformations)

INT (in module tamr_toolbox.models.attribute_type) is_version_condition_met() (in module tamr_toolbox.utils.version) iterencode() (tamr_toolbox.enrichment.dictionary.SetEncoder method)

J

JdbcInfo (class in tamr_toolbox.data_io.df_connect.jdbc_info)

L

list_backups() (in module tamr_toolbox.workflow.backup)

load() (in module tamr_toolbox.enrichment.dictionary) LONG (in module tamr_toolbox.models.attribute_type)

M

map_attribute() (in module tamr_toolbox.project.categorization.schema) (in module tamr_toolbox.project.mastering.schema) (in module tamr_toolbox.project.schema_mapping.schema) MasteringArtifacts (class in tamr_toolbox.models.project_artifacts) MasteringSteps (class in tamr_toolbox.models.project_steps) match_query() (in module tamr_toolbox.realtime.matching) mock_api() (in module tamr_toolbox.utils.testing) module tamr_toolbox.data_io.csv tamr_toolbox.data_io.dataframe tamr_toolbox.data_io.df_connect.client tamr_toolbox.data_io.df_connect.jdbc_info tamr_toolbox.dataset._dataset tamr_toolbox.dataset.manage tamr_toolbox.enrichment.api_client.google tamr_toolbox.enrichment.dictionary tamr_toolbox.enrichment.translate tamr_toolbox.filesystem.bash tamr_toolbox.filesystem.cloud tamr_toolbox.models.operation_state tamr_toolbox.models.project_artifacts tamr_toolbox.models.project_steps tamr_toolbox.models.project_type tamr_toolbox.models.validation_check tamr_toolbox.notifications.emails tamr_toolbox.notifications.slack tamr_toolbox.project.categorization.jobs tamr_toolbox.project.categorization.metrics tamr_toolbox.project.categorization.taxonomy tamr_toolbox.project.golden_records.jobs tamr_toolbox.project.mastering.jobs tamr_toolbox.project.schema_mapping.jobs tamr_toolbox.realtime.matching tamr_toolbox.sysadmin.instance tamr_toolbox.utils.client tamr_toolbox.utils.config tamr_toolbox.utils.downstream tamr_toolbox.utils.logger tamr_toolbox.utils.operation tamr_toolbox.utils.testing tamr_toolbox.utils.upstream tamr_toolbox.utils.version tamr_toolbox.workflow.backup tamr_toolbox.workflow.concurrent.Graph tamr_toolbox.workflow.concurrent.Planner tamr_toolbox.workflow.concurrent.PlanNode tamr_toolbox.workflow.concurrent.PlanNodeStatus tamr_toolbox.workflow.concurrent.PlanStatus tamr_toolbox.workflow.jobs

monitor() (in module tamr_toolbox.utils.operation) (in module tamr_toolbox.workflow.concurrent.PlanNode) monitor_job() (in module tamr_toolbox.notifications.emails) (in module tamr_toolbox.notifications.slack) move_node() (in module tamr_toolbox.project.categorization.taxonomy)

O

OperationState (class in tamr_toolbox.models.operation_state)

P

Planner (class in tamr_toolbox.workflow.concurrent.Planner) PlanNode (class in tamr_toolbox.workflow.concurrent.PlanNode) PlanNodeStatus (class in tamr_toolbox.workflow.concurrent.PlanNodeStatus) PlanStatus (class in tamr_toolbox.workflow.concurrent.PlanStatus) poll() (in module tamr_toolbox.workflow.concurrent.PlanNode) poll_endpoint() (in module tamr_toolbox.utils.client) poll_realtime_match_status() (in module tamr_toolbox.realtime.matching)

profile() (in module tamr_toolbox.data_io.dataframe) profile_query_results() (in module tamr_toolbox.data_io.df_connect.client) ProjectArtifacts (class in tamr_toolbox.models.project_artifacts) projects() (in module tamr_toolbox.utils.downstream) (in module tamr_toolbox.utils.upstream) ProjectType (class in tamr_toolbox.models.project_type) publish_clusters() (in module tamr_toolbox.project.mastering.jobs) publish_golden_records() (in module tamr_toolbox.project.golden_records.jobs)

R

Record (class in tamr_toolbox.models.attribute_type) remove_directories() (in module tamr_toolbox.filesystem.bash) rename_node() (in module tamr_toolbox.project.categorization.taxonomy) requires_tamr_version() (in module tamr_toolbox.utils.version) restart_tamr() (in module tamr_toolbox.sysadmin.instance)

run() (in module tamr_toolbox.project.categorization.jobs) (in module tamr_toolbox.project.golden_records.jobs) (in module tamr_toolbox.project.mastering.jobs) (in module tamr_toolbox.project.schema_mapping.jobs) (in module tamr_toolbox.workflow.jobs) run_next_step() (in module tamr_toolbox.workflow.concurrent.PlanNode)

S

s3_download() (in module tamr_toolbox.filesystem.cloud) s3_upload() (in module tamr_toolbox.filesystem.cloud) safe_estimate_counts() (in module tamr_toolbox.utils.operation) save() (in module tamr_toolbox.enrichment.dictionary) SchemaMappingArtifacts (class in tamr_toolbox.models.project_artifacts) SchemaMappingSteps (class in tamr_toolbox.models.project_steps) send_email() (in module tamr_toolbox.notifications.emails) send_message() (in module tamr_toolbox.notifications.slack) set_all() (in module tamr_toolbox.project.categorization.transformations) (in module tamr_toolbox.project.mastering.transformations) (in module tamr_toolbox.project.schema_mapping.transformations)

set_all_unified() (in module tamr_toolbox.project.categorization.transformations) (in module tamr_toolbox.project.mastering.transformations) (in module tamr_toolbox.project.schema_mapping.transformations) set_config() (in module tamr_toolbox.sysadmin.instance) set_configs() (in module tamr_toolbox.sysadmin.instance) set_logging_level() (in module tamr_toolbox.utils.logger) SetEncoder (class in tamr_toolbox.enrichment.dictionary) standardize_phrases() (in module tamr_toolbox.enrichment.translate) start_tamr() (in module tamr_toolbox.sysadmin.instance) stop_tamr() (in module tamr_toolbox.sysadmin.instance) STRING (in module tamr_toolbox.models.attribute_type)

T

tamr_toolbox.data_io.csv module tamr_toolbox.data_io.dataframe module tamr_toolbox.data_io.df_connect.client module tamr_toolbox.data_io.df_connect.jdbc_info module tamr_toolbox.dataset._dataset module tamr_toolbox.dataset.manage module tamr_toolbox.enrichment.api_client.google module tamr_toolbox.enrichment.dictionary module tamr_toolbox.enrichment.translate module tamr_toolbox.filesystem.bash module tamr_toolbox.filesystem.cloud module tamr_toolbox.models.attribute_type.Array (class in tamr_toolbox.models.project_steps) tamr_toolbox.models.attribute_type.Map (class in tamr_toolbox.models.project_steps) tamr_toolbox.models.operation_state module tamr_toolbox.models.project_artifacts module tamr_toolbox.models.project_steps module tamr_toolbox.models.project_type module tamr_toolbox.models.validation_check module tamr_toolbox.notifications.emails module tamr_toolbox.notifications.slack module tamr_toolbox.project.categorization.jobs module tamr_toolbox.project.categorization.metrics module tamr_toolbox.project.categorization.taxonomy module tamr_toolbox.project.golden_records.jobs module tamr_toolbox.project.mastering.jobs module

tamr_toolbox.project.schema_mapping.jobs module tamr_toolbox.realtime.matching module tamr_toolbox.sysadmin.instance module tamr_toolbox.utils.client module tamr_toolbox.utils.config module tamr_toolbox.utils.downstream module tamr_toolbox.utils.logger module tamr_toolbox.utils.operation module tamr_toolbox.utils.testing module tamr_toolbox.utils.upstream module tamr_toolbox.utils.version module tamr_toolbox.workflow.backup module tamr_toolbox.workflow.concurrent.Graph module tamr_toolbox.workflow.concurrent.Planner module tamr_toolbox.workflow.concurrent.PlanNode module tamr_toolbox.workflow.concurrent.PlanNodeStatus module tamr_toolbox.workflow.concurrent.PlanStatus module tamr_toolbox.workflow.jobs module to_dataset() (in module tamr_toolbox.enrichment.dictionary) to_dict() (in module tamr_toolbox.enrichment.dictionary) to_json() (in module tamr_toolbox.enrichment.dictionary) (in module tamr_toolbox.models.attribute_type) (in module tamr_toolbox.workflow.concurrent.Planner) TransformationGroup (class in tamr_toolbox.project.categorization.transformations) (class in tamr_toolbox.project.mastering.transformations) (class in tamr_toolbox.project.schema_mapping.transformations) translate() (in module tamr_toolbox.enrichment.api_client.google) translation_client_from_json() (in module tamr_toolbox.enrichment.api_client.google) TranslationDictionary (class in tamr_toolbox.enrichment.dictionary)

U

unmap_attribute() (in module tamr_toolbox.project.categorization.schema) (in module tamr_toolbox.project.mastering.schema) (in module tamr_toolbox.project.schema_mapping.schema) unmap_dataset() (in module tamr_toolbox.project.categorization.schema) (in module tamr_toolbox.project.mastering.schema) (in module tamr_toolbox.project.schema_mapping.schema) update() (in module tamr_toolbox.dataset.manage) (in module tamr_toolbox.enrichment.dictionary) update_and_publish() (in module tamr_toolbox.project.golden_records.jobs) update_clusters() (in module tamr_toolbox.project.mastering.jobs)

update_golden_records() (in module tamr_toolbox.project.golden_records.jobs) update_pair_predictions() (in module tamr_toolbox.project.mastering.jobs) update_plan() (in module tamr_toolbox.workflow.concurrent.Planner) update_profiling_info() (in module tamr_toolbox.project.golden_records.jobs) update_realtime_match_data() (in module tamr_toolbox.realtime.matching) update_results_only() (in module tamr_toolbox.project.categorization.jobs) (in module tamr_toolbox.project.mastering.jobs) update_unified_dataset() (in module tamr_toolbox.project.categorization.jobs) (in module tamr_toolbox.project.mastering.jobs) (in module tamr_toolbox.project.schema_mapping.jobs)

V

validate() (in module tamr_toolbox.data_io.dataframe)

validate_backup() (in module tamr_toolbox.workflow.backup) ValidationCheck (class in tamr_toolbox.models.validation_check)

W

wait() (in module tamr_toolbox.utils.operation)