data/pcdigitizer
1
0
Fork 0
Code Issues 19 Pull Requests Actions Packages Releases Activity

docs: replace "toolkit" to "package"

Browse Source
This commit is contained in:
Alex Maldonado
2026-04-15 10:39:10 -04:00
parent 09bd3df5ce
commit 588004bf0d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -2,7 +2,7 @@
<h4 align="center">Turn raw PubChem data into clean, ML-ready chemical datasets</h4> <h4 align="center">Turn raw PubChem data into clean, ML-ready chemical datasets</h4>
`pcdigitizer` is a Python toolkit for building ML-ready chemical datasets from [PubChem](https://pubchem.ncbi.nlm.nih.gov/). `pcdigitizer` is a Python package for building ML-ready chemical datasets from [PubChem](https://pubchem.ncbi.nlm.nih.gov/).
It handles the full pipeline: downloading raw data through PubChem's [PUG-REST API](https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest), parsing nested and inconsistent response formats, and cleaning the results into structured [Polars](https://pola.rs/) DataFrames ready for analysis or model training. It handles the full pipeline: downloading raw data through PubChem's [PUG-REST API](https://pubchem.ncbi.nlm.nih.gov/docs/pug-rest), parsing nested and inconsistent response formats, and cleaning the results into structured [Polars](https://pola.rs/) DataFrames ready for analysis or model training.
PubChem is the largest open chemical database in the world, but its data comes from thousands of depositors with varying formats, conventions, and quality levels. PubChem is the largest open chemical database in the world, but its data comes from thousands of depositors with varying formats, conventions, and quality levels.