skills.rest
gracefullight
gracefullightCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

exploratory-data-analysis

Analyze scientific data files across 200+ formats and generate markdown EDA reports.

4|Updated May 6, 2025
Search Tags:#data quality#bioinformatics#scientific data#exploratory data analysis#eda#markdown report#file format detection
One-click install
npx skills add https://github.com/gracefullight/py-starter --skill exploratory-data-analysis-gracefullight
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: exploratory-data-analysis
Source: https://github.com/gracefullight/py-starter/tree/main/.agents/skills/exploratory-data-analysis
Command: npx skills add https://github.com/gracefullight/py-starter --skill exploratory-data-analysis-gracefullight

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, h5py, biopython, pillow, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve? Scientific data arrives in hundreds of specialized formats, and understanding a file's structure, quality, and content before analysis requires format-specific expertise and tedious manual inspection. ## Core Features & Use Cases - Automatic Format Detection: Identifies 200+ scientific file types across chemistry, bioinformatics, microscopy, spectroscopy, proteomics, and general scientific data, then applies format-appropriate analysis. - Format-Specific Analysis: Extracts metadata, computes statistical summaries, assesses data quality, and detects issues using reference guides and the eda_analyzer.py script. - Markdown Report Generation: Produces comprehensive EDA reports with key findings, quality metrics, and downstream analysis recommendations. - Use Case: A researcher receives a FASTQ sequencing file and asks to explore it. The skill detects the format, computes read counts, length distributions, and quality scores, then saves a detailed report as reads_eda_report.md. ## Quick Start Analyze the structure and quality of my data file experiment_results.csv and generate a full EDA report.

Frequently Asked Questions about exploratory-data-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I analyze a scientific data file in Python?▼

Run the eda_analyzer.py script with your file path to auto-detect the format and generate a markdown report. Alternatively, load the file with format-specific libraries like pandas, Biopython, or h5py and compute statistics directly.

What file formats does exploratory data analysis support?▼

It supports over 200 formats across six categories: chemistry (PDB, SDF, MOL2), bioinformatics (FASTQ, BAM, VCF), microscopy (TIFF, ND2, CZI), spectroscopy (mzML, FID, JCAMP), proteomics (mzid, pepXML), and general data (CSV, HDF5, Parquet).

Which Python libraries read FASTQ and BAM sequencing files?▼

Biopython's SeqIO parses FASTA and FASTQ files, while pysam handles SAM, BAM, and CRAM alignments with indexing support. For quality metrics, compute per-base Phred score distributions and GC content from parsed reads.

Why does analysis fail with an import error for my file type?▼

Many scientific formats require specialized libraries that are not installed by default. Install the relevant package for your format, such as biopython for sequences, tifffile for microscopy images, or pymzml for mass spectrometry data.

How do I analyze very large scientific data files?▼

Sample a representative subset, such as the first 10,000 records, or use memory-mapped access for NPY and HDF5 files. For CSV and FASTQ files, process data in chunks and extrapolate estimates from the sample.

Related Skills

Explore More Data & Analytics Skills→
doctordukedoctorduke

life-sciences-connector

Query PubMed and analyze biological sequences with Biopython.

Official
Intermediate
robotlearning123robotlearning123

pathml

Load whole-slide images, preprocess, and construct spatial graphs for pathology.

Community
Advanced
dailycafidailycafi
7

bio-metabolomics-normalization-qc

Normalize metabolomics feature tables with QC-RSC, TIC, PQN, and ComBat.

Community
Advanced
TianGzlabTianGzlab
155

genomics-qc

Perform quality control on genomic sequencing data with FastQC and fastp.

Official
Intermediate