oddt.scoring package¶
Subpackages¶
Module contents¶
-
oddt.scoring.cross_validate(model, cv_set, cv_target, n=10, shuffle=True, n_jobs=1)[source]¶ Perform cross validation of model using provided data
- Parameters
- model: object
Model to be tested
- cv_set: array-like of shape = [n_samples, n_features]
Estimated target values.
- cv_target: array-like of shape = [n_samples] or [n_samples, n_outputs]
Estimated target values.
- n: integer (default = 10)
How many folds to be created from dataset
- shuffle: bool (default = True)
Should data be shuffled before folding.
- n_jobs: integer (default = 1)
How many CPUs to use during cross validation
- Returns
- r2: array of shape = [n]
R^2 score for each of generated folds
-
class
oddt.scoring.ensemble_descriptor(descriptor_generators)[source]¶ Bases:
objectProxy class to build an ensemble of destriptors with an API as one
- Parameters
- models: array
An array of models
Methods
build
set_protein
-
class
oddt.scoring.ensemble_model(models)[source]¶ Bases:
objectProxy class to build an ensemble of models with an API as one
- Parameters
- models: array
An array of models
Methods
fit
predict
score
-
class
oddt.scoring.scorer(model_instance, descriptor_generator_instance, score_title='score')[source]¶ Bases:
objectScorer class is parent class for scoring functions.
- Parameters
- model_instance: model
Medel compatible with sklearn API (fit, predict and score methods)
- descriptor_generator_instance: array of descriptors
Descriptor generator object
- score_title: string
Title of score to be used.
Methods
fit(ligands, target, *args, **kwargs)Trains model on supplied ligands and target values
load(filename)Loads scoring function from a pickle file.
predict(ligands, *args, **kwargs)Predicts values (eg.
predict_ligand(ligand)Local method to score one ligand and update it’s scores.
predict_ligands(ligands)Method to score ligands in a lazy fashion.
save(filename)Saves scoring function to a pickle file.
score(…)- Parameters
set_protein(protein)Proxy method to update protein in all relevant places.
-
fit(ligands, target, *args, **kwargs)[source]¶ Trains model on supplied ligands and target values
- Parameters
- ligands: array-like of ligands
Molecules to featurize and feed into the model
- target: array-like of shape = [n_samples] or [n_samples, n_outputs]
Ground truth (correct) target values.
-
classmethod
load(filename)[source]¶ Loads scoring function from a pickle file.
- Parameters
- filename: string
Pickle filename
- Returns
- sf: scorer-like object
Scoring function object loaded from a pickle
-
predict(ligands, *args, **kwargs)[source]¶ Predicts values (eg. affinity) for supplied ligands.
- Parameters
- ligands: array-like of ligands
Molecules to featurize and feed into the model
- Returns
- predicted: np.array or array of np.arrays of shape = [n_ligands]
Predicted scores for ligands
-
predict_ligand(ligand)[source]¶ Local method to score one ligand and update it’s scores.
- Parameters
- ligand: oddt.toolkit.Molecule object
Ligand to be scored
- Returns
- ligand: oddt.toolkit.Molecule object
Scored ligand with updated scores
-
predict_ligands(ligands)[source]¶ Method to score ligands in a lazy fashion.
- Parameters
- ligands: iterable of oddt.toolkit.Molecule objects
Ligands to be scored
- Returns
- ligand: iterator of oddt.toolkit.Molecule objects
Scored ligands with updated scores
-
save(filename)[source]¶ Saves scoring function to a pickle file.
- Parameters
- filename: string
Pickle filename
-
score(accuracy for classification or R^2 for regression)[source]¶ - Parameters
- ligands: array-like of ligands
Molecules to featurize and feed into the model
- target: array-like of shape = [n_samples] or [n_samples, n_outputs]
Ground truth (correct) target values.
- Returns
- s: float
Quality score (accuracy or R^2) for prediction