What data formats does the Data Profiler support?

The skill works with any data that can be loaded into a Pandas DataFrame, including CSV, Parquet, JSON, and SQL query results.

Is this skill suitable for large datasets?

It provides memory usage statistics and efficient summaries, though performance is ultimately dependent on the memory limits of the environment where the Python script is executed.

Does it identify missing data patterns?

Yes, it specifically profiles missing data patterns, including 'co-missing' columns where data tends to be absent across multiple fields simultaneously.

Can I customize the correlation threshold?

Yes, the correlation analysis function allows you to specify a threshold to filter for only the most significant relationships.

Data Profiler

Name: Data Profiler
Author: majesticlabs-dev

bymajesticlabs-dev

•

데이터 과학 및 ML

Generates detailed statistical profiles and correlation analysis for DataFrames to accelerate exploratory data analysis.

소개

The Data Profiler skill empowers Claude to perform automated, deep-dive explorations of datasets directly within your development environment. By leveraging specialized profiling scripts, it extracts comprehensive statistics, identifies missing data patterns, and analyzes feature correlations, providing data engineers and analysts with immediate insights into dataset health and characteristics. It is particularly useful during the initial stages of a project to understand data quality, distributions, and relationships without writing repetitive boilerplate code.

주요 기능

19 GitHub stars
Advanced missing data pattern recognition and co-occurrence analysis
Type-specific profiling including date ranges and string length analysis
Automated summary statistics for numeric, string, and datetime columns
High-correlation detection to identify redundant features
Memory usage and dataset shape reporting for performance optimization

사용 사례

Auditing data quality to identify unexpected null values or outliers
Performing rapid Exploratory Data Analysis (EDA) on newly acquired datasets
Preprocessing analysis to understand feature relationships before ML modeling

소개

주요 기능

19 GitHub stars
Advanced missing data pattern recognition and co-occurrence analysis
Type-specific profiling including date ranges and string length analysis
Automated summary statistics for numeric, string, and datetime columns
High-correlation detection to identify redundant features
Memory usage and dataset shape reporting for performance optimization

사용 사례

Auditing data quality to identify unexpected null values or outliers
Performing rapid Exploratory Data Analysis (EDA) on newly acquired datasets
Preprocessing analysis to understand feature relationships before ML modeling