Available deduplicators

KeepFirst

class optunaz.utils.preprocessing.deduplicator.KeepFirst(name='KeepFirst')[source]: Keep first.

KeepLast

class optunaz.utils.preprocessing.deduplicator.KeepLast(name='KeepLast')[source]: Keep last.

KeepRandom

class optunaz.utils.preprocessing.deduplicator.KeepRandom(name='KeepRandom', seed=None)[source]: Keep random.

KeepMin

class optunaz.utils.preprocessing.deduplicator.KeepMin(name='KeepMin')[source]: Keep min.

KeepMax

class optunaz.utils.preprocessing.deduplicator.KeepMax(name='KeepMax')[source]: Keep max.

KeepAvg

class optunaz.utils.preprocessing.deduplicator.KeepAvg(name='KeepAvg')[source]

Keep average. Classification will threshold at 0.5.

This deduplicator converts input SMILES to canonical SMILES.

dedup(df, smiles_col)[source]: For regression, keep mean value.

KeepMedian

class optunaz.utils.preprocessing.deduplicator.KeepMedian(name='KeepMedian')[source]

Keep median. Classification will threshold at 0.5.

This deduplicator converts input SMILES to canonical SMILES.

dedup(df, smiles_col)[source]: For regression, keep median value.

KeepKeepAllNoDeduplication

class optunaz.utils.preprocessing.deduplicator.KeepAllNoDeduplication(name='KeepAllNoDeduplication')[source]

Keep all.

Do not perform any deduplication.