exploratory-data-analysis

Exploratory data analysis on heterogeneous scientific files is performed by automatically detecting file types and routing them through a modular analyzer. The skill generates a detailed markdown report with quality metrics and downstream recommendations for each file.

Automated EDA supports 200+ scientific formats across chemistry, bioinformatics, microscopy, spectroscopy, proteomics, and metabolomics. The analyzer loads format-specific references to execute targeted checks and extract metadata for the report.

Yes, bioinformatics and proteomics data can be analyzed without manual format specification via automatic file-type detection. The system identifies the format, applies format-aware checks, and outputs a markdown report with summaries and quality metrics.

Yes, this EDA tool processes HDF5, microscopy, and spectroscopy formats using dependencies like h5py and Pillow. It performs format-aware analysis to reveal data structure, content, and quality across these scientific file types.

The best way to generate a markdown report with data quality metrics is to use an automated EDA skill that examines scientific datasets. It produces a shareable report containing summaries, quality metrics, and downstream guidance for each analyzed file.

To analyze scientific data files and detect formats, you need numpy, pandas, biopython, h5py, and Pillow. These dependencies enable loading format references, executing format-specific checks, and generating the final markdown analysis report.