BioSample: ncbi, 2023-09

import pandas as pd

df = pd.read_xml("https://www.ncbi.nlm.nih.gov/biosample/docs/attributes/?format=xml")

df.columns = df.columns.str.lower()

df.rename(columns={"harmonizedname": "abbr", "synonym": "synonyms"}, inplace=True)

df

	name	abbr	synonyms	description	format	package
0	API gravity	api	api gravity	API gravity is a measure of how heavy or light...	{float} {unit}	MIUVIG.hydrocarbon-fluids_swabs.6.0
1	EDTA inhibitor tested	edta_inhibitor_tested	edta inhibitor tested	Was carbapenemase activity tested in the prese...	['', 'yes', 'no', 'missing', 'not applicable',...	Beta-lactamase.1.0
2	FAO classification	fao_class	soil taxonomic/fao classification	soil classification from the FAO World Referen...	{term}	MIUVIG.soil.6.0
3	FDA food industry class name	food_industry_class	food industry class	The US FDA Class is the second of five element...	{text}	OneHealthEnteric.1.0
4	FDA food industry code name	food_industry_code	food industry code	The US FDA Industry Code is the first of five ...	{text}	OneHealthEnteric.1.0
...	...	...	...	...	...	...
933	window signs of water/mold	window_water_mold	window water mold	Signs of the presence of mold or mildew on the...	{text}	MIUVIG.built.6.0
934	window status	window_status	None	Defines whether the windows were open or close...	{text}	MIUVIG.built.6.0
935	window type	window_type	None	The type of windows, e.g., single-hung sash wi...	{text}	MIUVIG.built.6.0
936	window vertical position	window_vert_pos	window vert pos	The vertical position of the window on the wal...	{text}	MIUVIG.built.6.0
937	xylene	xylene	None	Concentration of xylene in the sample	{float} {unit}	MIUVIG.hydrocarbon-fluids_swabs.6.0

938 rows × 6 columns

df.to_parquet("df_all__ncbi__2023-09__BioSample.parquet")

from bionty.dev._md5 import calculate_md5

calculate_md5("df_all__ncbi__2023-09__BioSample.parquet")

'918db9bd1734b97c596c67d9654a4126'