exploratory-data-analysis

Generating an exploratory data analysis report involves detecting the scientific file format and extracting metadata using libraries like h5py and nd2reader. The skill outputs a comprehensive Markdown report summarizing data structure, quality metrics, and actionable insights for downstream processing.

Automatically extracting metadata from bioinformatics and microscopy files requires format-specific parsing using dependencies like biopython and Pillow. This skill identifies the file type across 200+ scientific formats and extracts relevant metadata into a structured data dictionary and analysis plan.

Using Python and pandas to create a data dictionary for cross-format scientific datasets is fully supported by this skill. It leverages pandas and numpy to assess data quality and produces a reproducible Markdown EDA report guiding downstream analysis.

This EDA tool supports file format detection for chemistry, proteomics, metabolomics, and spectroscopy data. It automatically maps the detected format to reference files, runs the analyzer script, and generates a detailed report with quality metrics and recommendations.

Limitations of automated EDA scripts for scientific data exploration include dependency on specific libraries like h5py and biopython for format support. The skill's depth is intermediate, meaning it provides metadata extraction and quality metrics but may require manual intervention for complex, non-standard file structures.