Loading README.md +6 −0 Original line number Diff line number Diff line Loading @@ -274,6 +274,9 @@ Scaffold splitting | |graphconv regression|Random |0.996 |0.873 | | |MT-NN regression |Scaffold |0.782 |0.426 | | |graphconv regression|Scaffold |0.994 |0.606 | |nci |MT-NN regression |Index |0.890 |0.890 | | |MT-NN regression |Random |0.891 |0.888 | | |MT-NN regression |Scaffold |0.912 |0.020 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | * General features Loading @@ -289,6 +292,7 @@ Number of tasks and examples in the datasets |toxcast |617 |8615 | |delaney |1 |1128 | |kaggle |15 |173065 | |nci |60 |1057371 | Time needed for benchmark test(~20h in total) Loading @@ -315,6 +319,8 @@ Time needed for benchmark test(~20h in total) | |robust MT-NN |80 |4000 | | |graph convolution |80 |900 | |delaney |MT-NN regression |10 |40 | | |graphconv regression|10 |40 | |nci |MT-NN regression |2000 |30000 | |kaggle |MT-NN regression |2200 |3200 | Loading deepchem/models/tf_keras_models/multitask_regressor.py +5 −5 Original line number Diff line number Diff line Loading @@ -21,9 +21,9 @@ class MultitaskGraphRegressor(Model): def __init__(self, sess, model, n_tasks, logdir=None, batch_size=50, final_loss='weighted_L2', learning_rate=.001, optimizer_type="adam", learning_rate_decay_time=1000, beta1=.9, beta2=.999, verbosity=None): beta1=.9, beta2=.999, verbose=True): self.verbosity = verbosity self.verbose = verbose self.sess = sess self.n_tasks = n_tasks self.final_loss = final_loss Loading Loading @@ -148,15 +148,15 @@ class MultitaskGraphRegressor(Model): def fit(self, dataset, nb_epoch=10, max_checkpoints_to_keep=5, log_every_N_batches=50, **kwargs): # Perform the optimization log("Training for %d epochs" % nb_epoch, self.verbosity) log("Training for %d epochs" % nb_epoch, self.verbose) # TODO(rbharath): Disabling saving for now to try to debug. for epoch in range(nb_epoch): log("Starting epoch %d" % epoch, self.verbosity) log("Starting epoch %d" % epoch, self.verbose) for batch_num, (X_b, y_b, w_b, ids_b) in enumerate(dataset.iterbatches( self.batch_size, pad_batches=True)): if batch_num % log_every_N_batches == 0: log("On batch %d" % batch_num, self.verbosity) log("On batch %d" % batch_num, self.verbose) self.sess.run( self.train_op, feed_dict=self.construct_feed_dict(X_b, y_b, w_b)) Loading examples/benchmark.py +16 −13 Original line number Diff line number Diff line Loading @@ -36,6 +36,7 @@ import deepchem as dc import tensorflow as tf import argparse from keras import backend as K import csv from sklearn.ensemble import RandomForestClassifier Loading Loading @@ -135,23 +136,25 @@ def benchmark_loading_datasets(hyper_parameters, model=model) time_finish_fitting = time.time() with open(os.path.join(out_path, 'results.csv'),'a') as f: f.write('\n'+str(count)+',') f.write(dataset+','+str(split)+','+mode+',train,') with open(os.path.join(out_path, 'results.csv'),'ab') as f: writer = csv.writer(f) if mode == 'classification': for i in train_score: f.write(i+','+str(train_score[i]['mean-roc_auc_score'])+',') f.write('valid,') for i in valid_score: f.write(i+','+str(valid_score[i]['mean-roc_auc_score'])+',') output_line = [count, dataset, str(split), mode, 'train', i, train_score[i]['mean-roc_auc_score'], 'valid', i, valid_score[i]['mean-roc_auc_score'], 'time_for_running', time_finish_fitting-time_start_fitting] writer.writerow(output_line) else: for i in train_score: f.write(i+','+str(train_score[i]['mean-pearson_r2_score'])+',') f.write('valid,') for i in valid_score: f.write(i+','+str(valid_score[i]['mean-pearson_r2_score'])+',') f.write('time_for_running,'+ str(time_finish_fitting-time_start_fitting)+',') output_line = [count, dataset, str(split), mode, 'train', i, train_score[i]['mean-pearson_r2_score'], 'valid', i, valid_score[i]['mean-pearson_r2_score'], 'time_for_running', time_finish_fitting-time_start_fitting] writer.writerow(output_line) def benchmark_classification(train_dataset, valid_dataset, tasks, transformers, hyper_parameters, Loading Loading
README.md +6 −0 Original line number Diff line number Diff line Loading @@ -274,6 +274,9 @@ Scaffold splitting | |graphconv regression|Random |0.996 |0.873 | | |MT-NN regression |Scaffold |0.782 |0.426 | | |graphconv regression|Scaffold |0.994 |0.606 | |nci |MT-NN regression |Index |0.890 |0.890 | | |MT-NN regression |Random |0.891 |0.888 | | |MT-NN regression |Scaffold |0.912 |0.020 | |kaggle |MT-NN regression |User-defined|0.748 |0.452 | * General features Loading @@ -289,6 +292,7 @@ Number of tasks and examples in the datasets |toxcast |617 |8615 | |delaney |1 |1128 | |kaggle |15 |173065 | |nci |60 |1057371 | Time needed for benchmark test(~20h in total) Loading @@ -315,6 +319,8 @@ Time needed for benchmark test(~20h in total) | |robust MT-NN |80 |4000 | | |graph convolution |80 |900 | |delaney |MT-NN regression |10 |40 | | |graphconv regression|10 |40 | |nci |MT-NN regression |2000 |30000 | |kaggle |MT-NN regression |2200 |3200 | Loading
deepchem/models/tf_keras_models/multitask_regressor.py +5 −5 Original line number Diff line number Diff line Loading @@ -21,9 +21,9 @@ class MultitaskGraphRegressor(Model): def __init__(self, sess, model, n_tasks, logdir=None, batch_size=50, final_loss='weighted_L2', learning_rate=.001, optimizer_type="adam", learning_rate_decay_time=1000, beta1=.9, beta2=.999, verbosity=None): beta1=.9, beta2=.999, verbose=True): self.verbosity = verbosity self.verbose = verbose self.sess = sess self.n_tasks = n_tasks self.final_loss = final_loss Loading Loading @@ -148,15 +148,15 @@ class MultitaskGraphRegressor(Model): def fit(self, dataset, nb_epoch=10, max_checkpoints_to_keep=5, log_every_N_batches=50, **kwargs): # Perform the optimization log("Training for %d epochs" % nb_epoch, self.verbosity) log("Training for %d epochs" % nb_epoch, self.verbose) # TODO(rbharath): Disabling saving for now to try to debug. for epoch in range(nb_epoch): log("Starting epoch %d" % epoch, self.verbosity) log("Starting epoch %d" % epoch, self.verbose) for batch_num, (X_b, y_b, w_b, ids_b) in enumerate(dataset.iterbatches( self.batch_size, pad_batches=True)): if batch_num % log_every_N_batches == 0: log("On batch %d" % batch_num, self.verbosity) log("On batch %d" % batch_num, self.verbose) self.sess.run( self.train_op, feed_dict=self.construct_feed_dict(X_b, y_b, w_b)) Loading
examples/benchmark.py +16 −13 Original line number Diff line number Diff line Loading @@ -36,6 +36,7 @@ import deepchem as dc import tensorflow as tf import argparse from keras import backend as K import csv from sklearn.ensemble import RandomForestClassifier Loading Loading @@ -135,23 +136,25 @@ def benchmark_loading_datasets(hyper_parameters, model=model) time_finish_fitting = time.time() with open(os.path.join(out_path, 'results.csv'),'a') as f: f.write('\n'+str(count)+',') f.write(dataset+','+str(split)+','+mode+',train,') with open(os.path.join(out_path, 'results.csv'),'ab') as f: writer = csv.writer(f) if mode == 'classification': for i in train_score: f.write(i+','+str(train_score[i]['mean-roc_auc_score'])+',') f.write('valid,') for i in valid_score: f.write(i+','+str(valid_score[i]['mean-roc_auc_score'])+',') output_line = [count, dataset, str(split), mode, 'train', i, train_score[i]['mean-roc_auc_score'], 'valid', i, valid_score[i]['mean-roc_auc_score'], 'time_for_running', time_finish_fitting-time_start_fitting] writer.writerow(output_line) else: for i in train_score: f.write(i+','+str(train_score[i]['mean-pearson_r2_score'])+',') f.write('valid,') for i in valid_score: f.write(i+','+str(valid_score[i]['mean-pearson_r2_score'])+',') f.write('time_for_running,'+ str(time_finish_fitting-time_start_fitting)+',') output_line = [count, dataset, str(split), mode, 'train', i, train_score[i]['mean-pearson_r2_score'], 'valid', i, valid_score[i]['mean-pearson_r2_score'], 'time_for_running', time_finish_fitting-time_start_fitting] writer.writerow(output_line) def benchmark_classification(train_dataset, valid_dataset, tasks, transformers, hyper_parameters, Loading
