Loading README.md +15 −1 Original line number Diff line number Diff line Loading @@ -260,8 +260,18 @@ Scaffold splitting |pdbbind(core) |MT-NN regression |Random |0.973 |0.494 | |pdbbind(refined)|MT-NN regression |Random |0.987 |0.503 | |pdbbind(full) |MT-NN regression |Random |0.983 |0.528 | |chembl |MT-NN regression |Index |0.443 |0.427 | | |MT-NN regression |Random |0.464 |0.434 | | |MT-NN regression |Scaffold |0.484 |0.361 | |gdb7 |MT-NN regression |Index |0.961 |0.011 | | |MT-NN regression |Random |0.742 |0.732 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | |Dataset |Model |Splitting |Train score/MAE(kcal/mol)|Valid score/MAE(kcal/mol)| |----------------|--------------------|------------|-------------------------|-------------------------| |gdb7 |MT-NN regression |Index |44.5 |185.6 | | |MT-NN regression |Random |86.1 |92.2 | * General features Number of tasks and examples in the datasets Loading @@ -279,6 +289,8 @@ Number of tasks and examples in the datasets |pdbbind(core) |1 |195 | |pdbbind(refined)|1 |3706 | |pdbbind(full) |1 |11908 | |chembl(5thresh) |691 |23871 | |gdb7 |1 |7165 | Loading Loading @@ -313,6 +325,8 @@ Time needed for benchmark test(~20h in total) |pdbbind(core) |MT-NN regression |0(featurized) |30 | |pdbbind(refined)|MT-NN regression |0(featurized) |40 | |pdbbind(full) |MT-NN regression |0(featurized) |60 | |chembl |MT-NN regression |200 |9000 | |gdb7 |MT-NN regression |10 |110 | |kaggle |MT-NN regression |2200 |3200 | Loading deepchem/splits/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -10,5 +10,6 @@ from deepchem.splits.splitters import * from deepchem.splits.splitters import ScaffoldSplitter from deepchem.splits.splitters import SpecifiedSplitter from deepchem.splits.splitters import IndexSplitter from deepchem.splits.splitters import IndiceSplitter from deepchem.splits.task_splitter import merge_fold_datasets from deepchem.splits.task_splitter import TaskSplitter deepchem/splits/splitters.py +39 −0 Original line number Diff line number Diff line Loading @@ -327,6 +327,45 @@ class IndexSplitter(Splitter): return (indices[:train_cutoff], indices[train_cutoff:valid_cutoff], indices[valid_cutoff:]) class IndiceSplitter(Splitter): """ Class for splits based on input order. """ def __init__(self, verbose=False, valid_indices=None, test_indices=None): """ Parameters ----------- valid_indices: list of int indices of samples in the valid set test_indices: list of int indices of samples in the test set """ self.verbose = verbose self.valid_indices = valid_indices self.test_indices = test_indices def split(self, dataset, seed=None, frac_train=.8, frac_valid=.1, frac_test=.1, log_every_n=None): """ Splits internal compounds into train/validation/test in designated order. """ num_datapoints = len(dataset) indices = np.arange(num_datapoints).tolist() if self.valid_indices is None: self.valid_indices = [] else: for indice in indices: if indice in self.valid_indices: indices.remove(indice) if self.test_indices is None: self.test_indices = [] else: for indice in indices: if indice in self.valid_indices: indices.remove(indice) return (indices, self.valid_indices, self.test_indices) class ScaffoldSplitter(Splitter): """ Loading deepchem/trans/transformers.py +1 −0 Original line number Diff line number Diff line Loading @@ -104,6 +104,7 @@ class NormalizationTransformer(Transformer): y_means, y_stds = dataset.get_statistics(X_stats=False, y_stats=True) self.y_means = y_means # Control for pathological case with no variance. y_stds = np.array(y_stds) y_stds[y_stds == 0] = 1. self.y_stds = y_stds self.transform_gradients = transform_gradients Loading deepchem/utils/save.py +2 −0 Original line number Diff line number Diff line Loading @@ -108,6 +108,8 @@ def load_from_disk(filename): except KeyError: # Try older joblib version for legacy files. return old_joblib.load(filename) except ValueError: return old_joblib.load(filename) elif os.path.splitext(name)[1] == ".csv": # First line of user-specified CSV *must* be header. df = pd.read_csv(filename, header=0) Loading Loading
README.md +15 −1 Original line number Diff line number Diff line Loading @@ -260,8 +260,18 @@ Scaffold splitting |pdbbind(core) |MT-NN regression |Random |0.973 |0.494 | |pdbbind(refined)|MT-NN regression |Random |0.987 |0.503 | |pdbbind(full) |MT-NN regression |Random |0.983 |0.528 | |chembl |MT-NN regression |Index |0.443 |0.427 | | |MT-NN regression |Random |0.464 |0.434 | | |MT-NN regression |Scaffold |0.484 |0.361 | |gdb7 |MT-NN regression |Index |0.961 |0.011 | | |MT-NN regression |Random |0.742 |0.732 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | |Dataset |Model |Splitting |Train score/MAE(kcal/mol)|Valid score/MAE(kcal/mol)| |----------------|--------------------|------------|-------------------------|-------------------------| |gdb7 |MT-NN regression |Index |44.5 |185.6 | | |MT-NN regression |Random |86.1 |92.2 | * General features Number of tasks and examples in the datasets Loading @@ -279,6 +289,8 @@ Number of tasks and examples in the datasets |pdbbind(core) |1 |195 | |pdbbind(refined)|1 |3706 | |pdbbind(full) |1 |11908 | |chembl(5thresh) |691 |23871 | |gdb7 |1 |7165 | Loading Loading @@ -313,6 +325,8 @@ Time needed for benchmark test(~20h in total) |pdbbind(core) |MT-NN regression |0(featurized) |30 | |pdbbind(refined)|MT-NN regression |0(featurized) |40 | |pdbbind(full) |MT-NN regression |0(featurized) |60 | |chembl |MT-NN regression |200 |9000 | |gdb7 |MT-NN regression |10 |110 | |kaggle |MT-NN regression |2200 |3200 | Loading
deepchem/splits/__init__.py +1 −0 Original line number Diff line number Diff line Loading @@ -10,5 +10,6 @@ from deepchem.splits.splitters import * from deepchem.splits.splitters import ScaffoldSplitter from deepchem.splits.splitters import SpecifiedSplitter from deepchem.splits.splitters import IndexSplitter from deepchem.splits.splitters import IndiceSplitter from deepchem.splits.task_splitter import merge_fold_datasets from deepchem.splits.task_splitter import TaskSplitter
deepchem/splits/splitters.py +39 −0 Original line number Diff line number Diff line Loading @@ -327,6 +327,45 @@ class IndexSplitter(Splitter): return (indices[:train_cutoff], indices[train_cutoff:valid_cutoff], indices[valid_cutoff:]) class IndiceSplitter(Splitter): """ Class for splits based on input order. """ def __init__(self, verbose=False, valid_indices=None, test_indices=None): """ Parameters ----------- valid_indices: list of int indices of samples in the valid set test_indices: list of int indices of samples in the test set """ self.verbose = verbose self.valid_indices = valid_indices self.test_indices = test_indices def split(self, dataset, seed=None, frac_train=.8, frac_valid=.1, frac_test=.1, log_every_n=None): """ Splits internal compounds into train/validation/test in designated order. """ num_datapoints = len(dataset) indices = np.arange(num_datapoints).tolist() if self.valid_indices is None: self.valid_indices = [] else: for indice in indices: if indice in self.valid_indices: indices.remove(indice) if self.test_indices is None: self.test_indices = [] else: for indice in indices: if indice in self.valid_indices: indices.remove(indice) return (indices, self.valid_indices, self.test_indices) class ScaffoldSplitter(Splitter): """ Loading
deepchem/trans/transformers.py +1 −0 Original line number Diff line number Diff line Loading @@ -104,6 +104,7 @@ class NormalizationTransformer(Transformer): y_means, y_stds = dataset.get_statistics(X_stats=False, y_stats=True) self.y_means = y_means # Control for pathological case with no variance. y_stds = np.array(y_stds) y_stds[y_stds == 0] = 1. self.y_stds = y_stds self.transform_gradients = transform_gradients Loading
deepchem/utils/save.py +2 −0 Original line number Diff line number Diff line Loading @@ -108,6 +108,8 @@ def load_from_disk(filename): except KeyError: # Try older joblib version for legacy files. return old_joblib.load(filename) except ValueError: return old_joblib.load(filename) elif os.path.splitext(name)[1] == ".csv": # First line of user-specified CSV *must* be header. df = pd.read_csv(filename, header=0) Loading
