def generate_pairs(session: Session, project: MasteringProject) -> Operation:
"""Generates pairs according to the binning model
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "recordPairs:refresh")
return operation._from_response(project.url.instance, r)
def update_pair_results(session: Session, project: MasteringProject) -> Operation:
"""Updates record pair predictions according to the latest pair-matching model
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "recordPairsWithPredictions:refresh")
return operation._from_response(project.url.instance, r)
def apply_feedback(session: Session, project: MasteringProject) -> Operation:
"""Trains the pair-matching model according to verified labels
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "recordPairsWithPredictions/model:refresh")
return operation._from_response(project.url.instance, r)
def update_high_impact_pairs(session: Session, project: MasteringProject) -> Operation:
"""Produces new high-impact pairs according to the latest pair-matching model
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "highImpactPairs:refresh")
return operation._from_response(project.url.instance, r)
def update_cluster_results(session: Session, project: MasteringProject) -> Operation:
"""Generates clusters based on the latest pair-matching model
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "recordClusters:refresh")
return operation._from_response(project.url.instance, r)
def estimate_pairs(session: Session, project: MasteringProject) -> Operation:
"""Updates the estimated pair counts
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "estimatedPairCounts:refresh")
return operation._from_response(project.url.instance, r)
def publish_clusters(session: Session, project: MasteringProject) -> Operation:
"""Publishes current record clusters
Args:
project: Tamr Mastering project
"""
r = session.post(str(project.url) + "publishedClustersWithData:refresh")
return operation._from_response(project.url.instance, r)
def _publish_async(session: Session,
project: GoldenRecordsProject) -> Operation:
r = session.post(
str(project.url) + "/publishedGoldenRecords:refresh",
params={
"validate": "true",
"version": "CURRENT"
},
)
return operation._from_response(project.url.instance, r)
def _apply_changes_async(
session: Session, unified_dataset: UnifiedDataset
) -> Operation:
"""Applies changes to the unified dataset
Args:
unified_dataset: The Unified Dataset which will be committed
"""
r = session.post(str(unified_dataset.url) + ":refresh")
return operation._from_response(unified_dataset.url.instance, r)
def _apply_changes_async(session: Session,
unified_dataset: UnifiedDataset) -> Operation:
"""Applies changes to the unified dataset
Args:
unified_dataset: The Unified Dataset which will be committed
"""
r = session.post(
str(unified_dataset.url) + ":refresh",
headers={
"Content-Type": "application/json",
"Accept": "application/json"
},
)
return operation._from_response(unified_dataset.url.instance, r)
def _update_cluster_results_async(
session: Session, project: MasteringProject
) -> Operation:
r = session.post(str(project.url) + "/recordClusters:refresh")
return operation._from_response(project.url.instance, r)
def _update_async(session: Session,
project: GoldenRecordsProject) -> Operation:
r = session.post(str(project.url) + "/goldenRecords:refresh")
return operation._from_response(project.url.instance, r)
def _materialize_async(session: Session, dataset: Dataset) -> Operation:
r = session.post(str(dataset.url) + ":refresh",)
return operation._from_response(dataset.url.instance, r)
def _generate_pairs_async(session: Session, project: MasteringProject) -> Operation:
r = session.post(str(project.url) + "/recordPairs:refresh")
return operation._from_response(project.url.instance, r)
def _apply_feedback_async(session: Session, project: MasteringProject) -> Operation:
r = session.post(str(project.url) + "/recordPairsWithPredictions/model:refresh")
return operation._from_response(project.url.instance, r)
def _update_high_impact_pairs_async(
session: Session, project: MasteringProject
) -> Operation:
r = session.post(str(project.url) + "/highImpactPairs:refresh")
return operation._from_response(project.url.instance, r)
def _apply_feedback_async(
session: Session, project: CategorizationProject
) -> Operation:
r = session.post(str(project.url) + "/categorizations/model:refresh")
return operation._from_response(project.url.instance, r)
def _update_results_async(
session: Session, project: CategorizationProject
) -> Operation:
r = session.post(str(project.url) + "/categorizations:refresh")
return operation._from_response(project.url.instance, r)
def _publish_clusters_async(session: Session, project: MasteringProject) -> Operation:
r = session.post(str(project.url) + "/publishedClustersWithData:refresh")
return operation._from_response(project.url.instance, r)
