exploratory-data-analysis

Exploratory data analysis on scientific formats is automated by auto-detecting the file extension, loading the corresponding format reference, and running domain-aware analysis to generate a detailed markdown report with metadata, quality assessments, and recommendations.

Extracting metadata and assessing data quality across bioinformatics and omics files is handled by running a domain-aware EDA process that outputs format-specific metadata, data analysis results, and structured quality assessments in a comprehensive markdown report.

Analyzing chemistry and spectroscopy data requires dependencies including numpy, pandas, biopython, pillow, and h5py to load format references and execute the domain-aware analysis, with clear error messages provided when libraries or formats are unavailable.

Generating an automatic EDA report across 200+ formats is supported by auto-detecting the file type, extracting basic and format-specific metadata, and running domain-aware analysis for chemistry, bioinformatics, imaging, spectroscopy, and omics data.

File type detection works by automatically checking the file extension to determine the category, loading the corresponding format reference, and applying fallbacks to deliver a structured object containing basic_info, file_type, reference_info, and data_analysis.

If a required library is unavailable when processing proteomics or metabolomics files, the analysis provides clear error messages and applies fallbacks to ensure the structured output object still contains basic_info, file_type, reference_info, and data_analysis.