GoldenMatch quickstart

goldenmatch dedupe customers.csv

import goldenmatch as gm

result = gm.dedupe("customers.csv")
print(result)  # DedupeResult(records=5000, clusters=847, match_rate=12.0%)
result.golden.write_csv("deduped.csv")

goldenmatch match prospects.csv --against customers.csv

import { dedupe } from "goldenmatch";

const rows = [
  { id: 1, name: "John Smith", email: "john@example.com", zip: "12345" },
  { id: 2, name: "Jon Smith",  email: "john@example.com", zip: "12345" },
  { id: 3, name: "Jane Doe",   email: "jane@example.com", zip: "54321" },
];

const result = dedupe(rows, {
  fuzzy: { name: 0.85 },
  blocking: ["zip"],
  threshold: 0.85,
});

console.log(result.stats);
for (const record of result.goldenRecords) {
  console.log(record);
}

import goldenmatch as gm

config = gm.GoldenMatchConfig(
    matchkeys=[
        gm.MatchkeyConfig(
            name="exact_email",
            type="exact",
            fields=[gm.MatchkeyField(field="email", transforms=["lowercase"])],
        ),
        gm.MatchkeyConfig(
            name="fuzzy_name",
            type="weighted",
            threshold=0.85,
            fields=[
                gm.MatchkeyField(field="name", scorer="jaro_winkler", weight=0.7),
                gm.MatchkeyField(field="zip", scorer="exact", weight=0.3),
            ],
        ),
    ],
    blocking=gm.BlockingConfig(strategy="learned"),
    llm_scorer=gm.LLMScorerConfig(enabled=True, mode="cluster"),
    backend="ray",
)

result = gm.dedupe_df(df, config=config)

matchkeys:
  - name: exact_email
    type: exact
    fields:
      - field: email
        transforms: [lowercase]
  - name: fuzzy_name
    type: weighted
    threshold: 0.85
    fields:
      - field: name
        scorer: jaro_winkler
        weight: 0.7
      - field: zip
        scorer: exact
        weight: 0.3

blocking:
  strategy: learned

golden_rules:
  default_strategy: most_complete
  auto_split: true

import goldenmatch

goldenmatch.add_correction(
    id_a=42, id_b=87,
    decision="reject",
    source="steward",
    reason="Different EIN despite name match",
    dataset="customers",
)

adjustments = goldenmatch.learn()
print(f"Adjusted {len(adjustments)} matchkey thresholds")
print(goldenmatch.memory_stats())

import goldenmatch as gm

metrics = gm.evaluate("data.csv", config="config.yaml", ground_truth="gt.csv")
print(f"F1: {metrics['f1']:.1%}, Precision: {metrics['precision']:.1%}")