from __future__ import unicode_literals import os import numpy as np import tempfile import shutil import deepchem as dc from sklearn.ensemble import RandomForestRegressor from MERCK_datasets import load_uv ###Load data### shard_size = 2000 num_cores = 1 num_shards_per_batch = 4 print("About to load UV data.") UV_tasks, datasets, transformers = load_uv( shard_size=shard_size, num_shards_per_batch=num_shards_per_batch) train_dataset, valid_dataset, test_dataset = datasets print("Number of compounds in train set") print(len(train_dataset)) print("Number of compounds in validation set") print(len(valid_dataset)) print("Number of compounds in test set") print(len(test_dataset)) num_features = train_dataset.get_data_shape()[0] print("Num features: %d" % num_features) def task_model_builder(model_dir): sklearn_model = RandomForestRegressor(n_estimators=100,
import os import tempfile import shutil import numpy as np import deepchem as dc from MERCK_datasets import load_uv # Set numpy seed np.random.seed(123) ###Load data### shard_size = 2000 num_shards_per_batch = 4 print("About to load MERCK data.") UV_tasks, datasets, transformers = load_uv( shard_size=shard_size, num_shards_per_batch=num_shards_per_batch) train_dataset, valid_dataset, test_dataset = datasets print("Number of compounds in train set") print(len(train_dataset)) print("Number of compounds in validation set") print(len(valid_dataset)) print("Number of compounds in test set") print(len(test_dataset)) ###Create model### n_layers = 3 nb_epoch = 50 model = dc.models.ProgressiveMultitaskRegressor( len(UV_tasks), train_dataset.get_data_shape()[0],