Jakub Adamczyk

Results 39 comments of Jakub Adamczyk

The dataset used was [Codon Usage](https://archive.ics.uci.edu/ml/datasets/Codon+usage). Interestingly enough, it has only nonnegative values (codon percentages), so regular cosine is always nonnegative as well. Exact code: ``` import pandas as pd...

I found it - query() method returns indices of nearest neighbors. It would be nice to have a semantic search example on the docs, though. I couls make a PR...

Any way for turning off warnings would be very useful. For cleaning large corpora of email texts, I get incredibly large logs due to those warnings

I mean that if you run exactly the same code twice, you will get two different results. This applies also when conformers are already calculated, as you can see from...

@thegodone the code is, indeed, nondeterministic, as commented here: https://github.com/rdkit/rdkit/blob/a8d4912f88ae2ea9ea7afa366ba5b9c0be09cb79/Code/GraphMol/Descriptors/GETAWAY.cpp#L216 This should be fixed, and this is what this issue concerns.

@greglandrum sure. I used HIV dataset from MoleculeNet, and smallest molecules from it (shortest SMILES, to be precise). I first generate conformers (with 1000 attempts), and then perform 2 GETAWAY...

@thegodone to be precise, I first generate the conformations, and only then I calculate GETAWAY descriptors multiple times. So I get different descriptor values for the same conformation. You can...

Root cause: this error happens because there is no radius N for atoms in a molecule with diameter lower than N. This function returns an environment of radius exactly N,...

@sethmlarson any news on this? If this library is indeed deprecated, or there is no capability to officially support this, maybe select and pass this to other maintainers. This is...