Index

A

algorithm (preclink.score.comparisons.StringComparison attribute) (preclink.score.StringComparison attribute) (preclink.score.TFIDFStringComparison attribute)

ambiguous_pairs (preclink.inspect.InspectionReport attribute) apply() (preclink.block.Crosswalk method)

B

block() (preclink.block.Blocker method) (preclink.block.FieldBlocker method) (preclink.block.FullBlocker method) (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method)

BlockConfig (class in preclink.core) Blocker (class in preclink.block) build() (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method)

C

candidate_pairs (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute) ClusterDeduplicator (class in preclink.deduplicate) collapse_whitespace (preclink.core.PreprocessConfig attribute) column (preclink.score.Comparison attribute) (preclink.score.comparisons.DateComparison attribute) (preclink.score.comparisons.ExactComparison attribute) (preclink.score.comparisons.NumericComparison attribute) (preclink.score.comparisons.StringComparison attribute) (preclink.score.DateComparison attribute) (preclink.score.ExactComparison attribute) (preclink.score.NumericComparison attribute) (preclink.score.StringComparison attribute) (preclink.score.TFIDFStringComparison attribute) columns (preclink.core.PreprocessConfig attribute) compare() (preclink.score.Comparison method) (preclink.score.comparisons.DateComparison method) (preclink.score.comparisons.ExactComparison method) (preclink.score.comparisons.NumericComparison method) (preclink.score.comparisons.StringComparison method) (preclink.score.DateComparison method) (preclink.score.ExactComparison method) (preclink.score.NumericComparison method) (preclink.score.StringComparison method) (preclink.score.TFIDFStringComparison method)

Comparison (class in preclink.score) comparisons (preclink.core.ScoreConfig attribute) completeness_scores (preclink.preprocess.CompletenessReport attribute) CompletenessFilter (class in preclink.preprocess) CompletenessReport (class in preclink.preprocess) compute_diagnostics() (in module preclink.inspect) Crosswalk (class in preclink.block) crosswalk (preclink.core.BlockConfig attribute)

D

DateComparison (class in preclink.score) (class in preclink.score.comparisons) decide() (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method) (preclink.decide.DecisionRule method) (preclink.decide.GreedyDecision method) (preclink.decide.HungarianDecision method) (preclink.decide.RowSequentialDecision method) DecideConfig (class in preclink.core) DecisionRule (class in preclink.decide) deduplicate() (preclink.deduplicate.ClusterDeduplicator method) (preclink.deduplicate.Deduplicator method) (preclink.deduplicate.ExactDeduplicator method)

DeduplicationReport (class in preclink.deduplicate) Deduplicator (class in preclink.deduplicate) diagnostics (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute) (preclink.inspect.InspectionReport attribute) drop_rate (preclink.preprocess.CompletenessReport property) dropped_as_duplicate (preclink.deduplicate.DeduplicationReport attribute) dropped_as_indistinguishable (preclink.deduplicate.DeduplicationReport attribute) dropped_count (preclink.preprocess.CompletenessReport attribute) dropped_indices (preclink.preprocess.CompletenessReport attribute)

E

ExactComparison (class in preclink.score) (class in preclink.score.comparisons)

ExactDeduplicator (class in preclink.deduplicate)

F

FieldBlocker (class in preclink.block) Filter (class in preclink.filter) filter() (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method) (preclink.filter.Filter method) (preclink.filter.MarginFilter method) (preclink.filter.ThresholdFilter method) (preclink.preprocess.CompletenessFilter method)

FilterConfig (class in preclink.core) filtered_pairs (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute) FullBlocker (class in preclink.block)

G

generate_report() (in module preclink.inspect)

GreedyDecision (class in preclink.decide) groups_found (preclink.deduplicate.DeduplicationReport attribute)

H

HungarianDecision (class in preclink.decide)

I

inspect() (preclink.core.LinkageResult method) (preclink.core.result.LinkageResult method)

InspectionReport (class in preclink.inspect)

K

keep (preclink.deduplicate.ExactDeduplicator attribute)

kept_count (preclink.deduplicate.DeduplicationReport attribute)

L

largest_group_size (preclink.deduplicate.DeduplicationReport attribute) left (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute) link() (preclink.core.Pipeline method) (preclink.core.pipeline.Pipeline method)

LinkageDiagnostics (class in preclink.inspect) LinkageResult (class in preclink.core) (class in preclink.core.result) lowercase (preclink.core.PreprocessConfig attribute)

M

margin (preclink.core.FilterConfig attribute) (preclink.multipass.PassConfig attribute) MarginFilter (class in preclink.filter) match_rate_left (preclink.inspect.LinkageDiagnostics attribute) match_rate_right (preclink.inspect.LinkageDiagnostics attribute) matches (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute) merge_left() (preclink.core.LinkageResult method) (preclink.core.result.LinkageResult method) merge_right() (preclink.core.LinkageResult method) (preclink.core.result.LinkageResult method) method (preclink.core.DecideConfig attribute) (preclink.multipass.PassConfig attribute) min_completeness (preclink.core.PreprocessConfig attribute)

min_score (preclink.core.FilterConfig attribute) (preclink.multipass.PassConfig attribute) missing_policy (preclink.core.PreprocessConfig attribute) MissingHandler (class in preclink.preprocess) module preclink.block preclink.core preclink.decide preclink.deduplicate preclink.filter preclink.inspect preclink.multipass preclink.preprocess preclink.score MultiPassOrchestrator (class in preclink.multipass)

N

n_candidate_pairs (preclink.inspect.LinkageDiagnostics attribute) n_filtered_pairs (preclink.inspect.LinkageDiagnostics attribute) n_left (preclink.inspect.LinkageDiagnostics attribute) n_matches (preclink.inspect.LinkageDiagnostics attribute)

n_right (preclink.inspect.LinkageDiagnostics attribute) normalize_unicode (preclink.core.PreprocessConfig attribute) NumericComparison (class in preclink.score) (class in preclink.score.comparisons)

O

on (preclink.core.BlockConfig attribute)

original_count (preclink.deduplicate.DeduplicationReport attribute)

P

PairwiseScorer (class in preclink.score) PassConfig (class in preclink.multipass) Pipeline (class in preclink.core) (class in preclink.core.pipeline) PipelineBuilder (class in preclink.core) (class in preclink.core.pipeline) precision_first() (in module preclink.multipass) preclink.block module preclink.core module preclink.decide module preclink.deduplicate module preclink.filter module

preclink.inspect module preclink.multipass module preclink.preprocess module preclink.score module preprocess() (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method) (preclink.preprocess.MissingHandler method) (preclink.preprocess.Preprocessor method) (preclink.preprocess.TextNormalizer method) PreprocessConfig (class in preclink.core) Preprocessor (class in preclink.preprocess)

R

required_columns (preclink.core.PreprocessConfig attribute) retained_count (preclink.preprocess.CompletenessReport property) right (preclink.core.LinkageResult attribute) (preclink.core.result.LinkageResult attribute)

RowSequentialDecision (class in preclink.decide) run() (preclink.multipass.MultiPassOrchestrator method)

S

scale (preclink.score.comparisons.NumericComparison attribute) (preclink.score.NumericComparison attribute) score() (preclink.core.pipeline.PipelineBuilder method) (preclink.core.PipelineBuilder method) (preclink.score.PairwiseScorer method) score_stats (preclink.inspect.LinkageDiagnostics attribute)

ScoreConfig (class in preclink.core) set_idf_weights() (preclink.score.TFIDFStringComparison method) strict_then_relaxed() (in module preclink.multipass) StringComparison (class in preclink.score) (class in preclink.score.comparisons) strip_whitespace (preclink.core.PreprocessConfig attribute) summary() (preclink.inspect.InspectionReport method)

T

TextNormalizer (class in preclink.preprocess) TFIDFStringComparison (class in preclink.score) ThresholdFilter (class in preclink.filter) tolerance (preclink.score.comparisons.NumericComparison attribute) (preclink.score.NumericComparison attribute)

tolerance_days (preclink.score.comparisons.DateComparison attribute) (preclink.score.DateComparison attribute) total_count (preclink.preprocess.CompletenessReport attribute)

U

unmatched_left (preclink.inspect.InspectionReport attribute)

unmatched_right (preclink.inspect.InspectionReport attribute)

V

validate() (preclink.block.Crosswalk method)

W

weight (preclink.score.Comparison attribute) (preclink.score.comparisons.DateComparison attribute) (preclink.score.comparisons.ExactComparison attribute) (preclink.score.comparisons.NumericComparison attribute) (preclink.score.comparisons.StringComparison attribute) (preclink.score.DateComparison attribute) (preclink.score.ExactComparison attribute) (preclink.score.NumericComparison attribute) (preclink.score.StringComparison attribute) (preclink.score.TFIDFStringComparison attribute)