Automate record linkage with configurable match rules and fuzzy matching.
npx skills add https://github.com/TrevorMann/AIDataCleansing --skill record-linker
Please help me install this Agent Skill. Skill: Record Linker Source: https://github.com/TrevorMann/AIDataCleansing/tree/main/skills/_common/record_linker Command: npx skills add https://github.com/TrevorMann/AIDataCleansing --skill record-linker
This Skill automates the process of finding records that refer to the same real-world entity, streamlining entity resolution and record grouping across batches of data.
Use the Record Linker skill to link records from the 'customer_data.csv' file and identify duplicate or linked records.
High-intent search queries and answers about installing and using this skill.
You can automate record linkage by applying configurable match rules to batch data, identifying and linking records that refer to the same real-world entity. This creates a unified view across scattered databases.
Fuzzy matching for record grouping works by comparing character bigrams and calculating Levenshtein similarity between records. This identifies records with similar attributes, automatically linking them even when data isn't perfectly exact.
The best way to group scattered customer data is through batch record linkage. By applying configurable match rules, the system links matching records and outputs metadata identifying grouped duplicates for a unified dataset.
Yes, entity resolution handles batch processing to group records in bulk. It processes the data using match rules and provides metadata on linked records, indicating which entries refer to the same entity.
Yes, record linkage supports configurable match rules for processing CSV files. You can apply these rules to batch data to identify and group duplicate or linked records automatically.
Fuzzy matching relies on character bigrams and Levenshtein similarity, which may require tuning match rules for optimal accuracy. It is designed for batch entity resolution rather than real-time streaming data linkage.
h4vzzClean raw datasets into analysis-ready tables using pandas, pyjanitor, and great_expectations.
duany049Convert research papers into indexed wiki pages with cross-references and graph edges.
zilliztechDetect exact and near-duplicate records using hash checks and semantic similarity.
puyanguvicMatch non-identical strings using Levenshtein distance and similarity metrics.
