Loading deepchem/models/tensorgraph/models/graph_models.py +3 −3 Original line number Diff line number Diff line Loading @@ -139,7 +139,7 @@ class WeaveTensorGraph(TensorGraph): feed_dict[label] = to_one_hot(y_b[:, index]) if self.mode == "regression": feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b atom_feat = [] Loading Loading @@ -289,7 +289,7 @@ class DTNNTensorGraph(TensorGraph): if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b distance = [] atom_membership = [] Loading Loading @@ -440,7 +440,7 @@ class DAGTensorGraph(TensorGraph): feed_dict[label] = to_one_hot(y_b[:, index]) if self.mode == "regression": feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b atoms_per_mol = [mol.get_num_atoms() for mol in X_b] Loading examples/benchmark.py +35 −1022 File changed.Preview size limit exceeded, changes collapsed. Show changes examples/benchmark2.pydeleted 100644 → 0 +0 −110 Original line number Diff line number Diff line #!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Tue Oct 18 15:53:27 2016 @author: Michael Wu Benchmark test: Giving classification performances of: Random forest(rf), MultitaskDNN(tf), RobustMultitaskDNN(tf_robust), Logistic regression(logreg), IRV(irv) Graph convolution(graphconv), xgboost(xgb), Directed acyclic graph(dag), Weave(weave) on datasets: bace_c, bbbp, clintox, hiv, muv, pcba, sider, tox21, toxcast Giving regression performances of: MultitaskDNN(tf_regression), Fit Transformer MultitaskDNN(tf_regression_ft), Random forest(rf_regression), Graph convolution regression(graphconvreg), xgboost(xgb_regression), Deep tensor neural net(dtnn), Directed acyclic graph(dag_regression), Weave(weave_regression) on datasets: bace_r, chembl, clearance, delaney(ESOL), hopv, kaggle, lipo, nci, pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl(FreeSolv) time estimation listed in README file """ from __future__ import print_function from __future__ import division from __future__ import unicode_literals import os import numpy as np import deepchem as dc import argparse parser = argparse.ArgumentParser( description='Deepchem benchmark: ' + 'giving performances of different learning models on datasets') parser.add_argument( '-s', action='append', dest='splitter_args', default=[], help='Choice of splitting function: index, random, scaffold, stratified') parser.add_argument( '-m', action='append', dest='model_args', default=[], help='Choice of model: tf, tf_robust, logreg, rf, irv, graphconv, xgb,' + \ ' dag, weave, tf_regression, tf_regression_ft, rf_regression, ' + \ 'graphconvreg, xgb_regression, dtnn, dag_regression, weave_regression') parser.add_argument( '-d', action='append', dest='dataset_args', default=[], help='Choice of dataset: bace_c, bace_r, bbbp, chembl, clearance, ' + 'clintox, delaney, hiv, hopv, kaggle, lipo, muv, nci, pcba, ' + 'pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl, sider, tox21, toxcast') parser.add_argument( '-t', action='store_true', dest='test', default=False, help='Evalute performance on test set') parser.add_argument( '--seed', action='append', dest='seed_args', default=[], help='Choice of random seed') args = parser.parse_args() #Datasets and models used in the benchmark test splitters = args.splitter_args models = args.model_args datasets = args.dataset_args test = args.test if len(args.seed_args) > 0: seed = int(args.seed_args[0]) else: seed = 123 if len(splitters) == 0: splitters = ['index', 'random', 'scaffold'] if len(models) == 0: models = [ 'tf', 'tf_robust', 'logreg', 'graphconv', 'tf_regression', 'tf_regression_ft', 'graphconvreg' ] #irv, rf, rf_regression should be assigned manually if len(datasets) == 0: datasets = [ 'bace_c', 'bace_r', 'bbbp', 'clearance', 'clintox', 'delaney', 'hiv', 'hopv', 'lipo', 'muv', 'pdbbind', 'ppb', 'qm7b', 'qm8', 'qm9', 'sampl', 'sider', 'tox21', 'toxcast' ] for dataset in datasets: for split in splitters: for model in models: np.random.seed(seed) dc.molnet.run_benchmark( [dataset], str(model), split=split, test=test, seed=seed) Loading
deepchem/models/tensorgraph/models/graph_models.py +3 −3 Original line number Diff line number Diff line Loading @@ -139,7 +139,7 @@ class WeaveTensorGraph(TensorGraph): feed_dict[label] = to_one_hot(y_b[:, index]) if self.mode == "regression": feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b atom_feat = [] Loading Loading @@ -289,7 +289,7 @@ class DTNNTensorGraph(TensorGraph): if y_b is not None and not predict: for index, label in enumerate(self.labels_fd): feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b distance = [] atom_membership = [] Loading Loading @@ -440,7 +440,7 @@ class DAGTensorGraph(TensorGraph): feed_dict[label] = to_one_hot(y_b[:, index]) if self.mode == "regression": feed_dict[label] = y_b[:, index:index + 1] if w_b is not None and not predict: if w_b is not None: feed_dict[self.weights] = w_b atoms_per_mol = [mol.get_num_atoms() for mol in X_b] Loading
examples/benchmark.py +35 −1022 File changed.Preview size limit exceeded, changes collapsed. Show changes
examples/benchmark2.pydeleted 100644 → 0 +0 −110 Original line number Diff line number Diff line #!/usr/bin/env python3 # -*- coding: utf-8 -*- """ Created on Tue Oct 18 15:53:27 2016 @author: Michael Wu Benchmark test: Giving classification performances of: Random forest(rf), MultitaskDNN(tf), RobustMultitaskDNN(tf_robust), Logistic regression(logreg), IRV(irv) Graph convolution(graphconv), xgboost(xgb), Directed acyclic graph(dag), Weave(weave) on datasets: bace_c, bbbp, clintox, hiv, muv, pcba, sider, tox21, toxcast Giving regression performances of: MultitaskDNN(tf_regression), Fit Transformer MultitaskDNN(tf_regression_ft), Random forest(rf_regression), Graph convolution regression(graphconvreg), xgboost(xgb_regression), Deep tensor neural net(dtnn), Directed acyclic graph(dag_regression), Weave(weave_regression) on datasets: bace_r, chembl, clearance, delaney(ESOL), hopv, kaggle, lipo, nci, pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl(FreeSolv) time estimation listed in README file """ from __future__ import print_function from __future__ import division from __future__ import unicode_literals import os import numpy as np import deepchem as dc import argparse parser = argparse.ArgumentParser( description='Deepchem benchmark: ' + 'giving performances of different learning models on datasets') parser.add_argument( '-s', action='append', dest='splitter_args', default=[], help='Choice of splitting function: index, random, scaffold, stratified') parser.add_argument( '-m', action='append', dest='model_args', default=[], help='Choice of model: tf, tf_robust, logreg, rf, irv, graphconv, xgb,' + \ ' dag, weave, tf_regression, tf_regression_ft, rf_regression, ' + \ 'graphconvreg, xgb_regression, dtnn, dag_regression, weave_regression') parser.add_argument( '-d', action='append', dest='dataset_args', default=[], help='Choice of dataset: bace_c, bace_r, bbbp, chembl, clearance, ' + 'clintox, delaney, hiv, hopv, kaggle, lipo, muv, nci, pcba, ' + 'pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl, sider, tox21, toxcast') parser.add_argument( '-t', action='store_true', dest='test', default=False, help='Evalute performance on test set') parser.add_argument( '--seed', action='append', dest='seed_args', default=[], help='Choice of random seed') args = parser.parse_args() #Datasets and models used in the benchmark test splitters = args.splitter_args models = args.model_args datasets = args.dataset_args test = args.test if len(args.seed_args) > 0: seed = int(args.seed_args[0]) else: seed = 123 if len(splitters) == 0: splitters = ['index', 'random', 'scaffold'] if len(models) == 0: models = [ 'tf', 'tf_robust', 'logreg', 'graphconv', 'tf_regression', 'tf_regression_ft', 'graphconvreg' ] #irv, rf, rf_regression should be assigned manually if len(datasets) == 0: datasets = [ 'bace_c', 'bace_r', 'bbbp', 'clearance', 'clintox', 'delaney', 'hiv', 'hopv', 'lipo', 'muv', 'pdbbind', 'ppb', 'qm7b', 'qm8', 'qm9', 'sampl', 'sider', 'tox21', 'toxcast' ] for dataset in datasets: for split in splitters: for model in models: np.random.seed(seed) dc.molnet.run_benchmark( [dataset], str(model), split=split, test=test, seed=seed)
