Home

Nico's Cervical cancer Pathology reports

Notes on data structure with the help of Gemini 2.5 PRO

Normally we may treat data wrangling as a script, for example

text to indexed text rows

txt = await(await fetch('https://raw.githubusercontent.com/epiverse/nico/refs/heads/main/Electronic%20path%20data%20example(Sheet1).csv')).text()
rows=txt.split(/\r\n/).slice(0,-1) // blank tail removed
rows=rows.map(function(row){return {txt:row,report_id:row.match(/[\w]+/)[0]}})

But one can also make some attributes available simply by exporting them. Let's restart by loading the model first

nico = await import('https://epiverse.github.io/nico/nico.mjs')

Metadata

start with the JSON docs

docs = await (await fetch('https://raw.githubusercontent.com/epiverse/nico/refs/heads/main/extract.json')).json()

convert docs into tsv

We'll borrow nico's 75 docs

tsv = await cli.docs2meta()

Projection:

https://projector.tensorflow.org/?config=https://gist.githubusercontent.com/jonasalmeida/38c359da408f32dd76cf275d559682d9/raw/473828af4be74a9edee738163acb8e93cc301718/nicoConfig.json