Removed some print statements (e0e475c5) · Commits · 钟慕尧 / deepchem

deepchem/featurizers/featurize.py

+0 −3

Original line number	Diff line number	Diff line
		@@ -442,9 +442,6 @@ class FeaturizedSamples(object):
		raise ValueError("improper splittype.")
		train_samples, valid_samples, test_samples = None, None, None
		dataset_files = self.dataset_files
		print("FeaturizedSamples.train_valid_test_split")
		print("dataset_files")
		print(dataset_files)
		if train_dir is not None:
		train_samples = FeaturizedSamples(samples_dir=train_dir,
		dataset_files=dataset_files,

deepchem/hyperparameters/init.py

+0 −5

Original line number	Diff line number	Diff line
		@@ -70,11 +70,6 @@ class HyperparamOpt(object):
		valid_score = scores_df.iloc[0][metric.name]
		else:
		valid_score = multitask_scores[metric.name]
		print("hyperparameters.compute")
		print("valid_score")
		print(valid_score)
		print("hyperparameter_tuple")
		print(hyperparameter_tuple)
		all_scores[hyperparameter_tuple] = valid_score

		if (use_max and valid_score >= best_validation_score) or (

examples/Multitask Networks on MUV.ipynb

+8 −9

Original line number	Diff line number	Diff line
		%% Cell type:markdown id: tags:

		This notebook walks through the creation of multitask models on MUV. The goal is to demonstrate that multitask methods outperform singletask methods on MUV.

		%% Cell type:code id: tags:

		``` python
		%reload_ext autoreload
		%autoreload 2
		%pdb off
		reload = True
		```

		%% Output

		Automatic pdb calling has been turned OFF

		%% Cell type:code id: tags:

		``` python
		from deepchem.utils.save import load_from_disk
		from deepchem.datasets import Dataset

		dataset_file= "../datasets/muv.csv.gz"
		dataset = load_from_disk(dataset_file)
		print("Columns of dataset: %s" % str(dataset.columns.values))
		print("Number of examples in dataset: %s" % str(dataset.shape[0]))
		```

		%% Output

		Columns of dataset: ['mol_id' 'smiles' 'MUV-692' 'MUV-689' 'MUV-846' 'MUV-859' 'MUV-644'
		'MUV-548' 'MUV-852' 'MUV-600' 'MUV-810' 'MUV-712' 'MUV-737' 'MUV-858'
		'MUV-713' 'MUV-733' 'MUV-652' 'MUV-466' 'MUV-832']
		Number of examples in dataset: 93127

		%% Cell type:markdown id: tags:

		Now, let's visualize some compounds from our dataset

		%% Cell type:code id: tags:

		``` python
		from itertools import islice
		from rdkit import Chem
		from deepchem.utils.visualization import mols_to_pngs
		from deepchem.utils.visualization import display_images

		num_to_display = 12
		molecules = []
		for _, data in islice(dataset.iterrows(), num_to_display):
		molecules.append(Chem.MolFromSmiles(data["smiles"]))
		display_images(mols_to_pngs(molecules))
		```

		%% Output


		%% Cell type:code id: tags:

		``` python
		from deepchem.featurizers.fingerprints import CircularFingerprint

		featurizers = [CircularFingerprint(size=1024)]
		```

		%% Cell type:code id: tags:

		``` python
		MUV_tasks = ['MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644',
		'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',
		'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
		'MUV-466', 'MUV-832']
		```

		%% Cell type:code id: tags:

		``` python
		import os
		from deepchem.featurizers.featurize import DataFeaturizer

		# The base_dir holds the results of all analysis
		base_dir = "/scratch/users/rbharath/muv_multitask_analysis"
		#Make directories to store the raw and featurized datasets.
		feature_dir = os.path.join(base_dir, "features")
		samples_dir = os.path.join(base_dir, "samples")

		featurizer = DataFeaturizer(tasks=MUV_tasks,
		smiles_field="smiles",
		compound_featurizers=featurizers,
		verbosity="low")

		# Setting reload=True directs the featurizer to use existing featurization on disk if such exists.
		featurized_samples = featurizer.featurize(dataset_file, feature_dir, samples_dir, shard_size=4096,
		reload=reload)
		```

		%% Cell type:code id: tags:

		``` python
		splittype = "scaffold"
		train_dir = os.path.join(base_dir, "train_dataset")
		valid_dir = os.path.join(base_dir, "valid_dataset")
		test_dir = os.path.join(base_dir, "test_dataset")

		train_samples, valid_samples, test_samples = featurized_samples.train_valid_test_split(
		splittype, train_dir, valid_dir, test_dir, log_every_n=1000, reload=reload)
		```

		%% Output

		FeaturizedSamples.train_valid_test_split
		dataset_files
		[u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard0.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard1.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard2.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard3.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard4.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard5.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard6.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard7.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard8.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard9.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard10.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard11.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard12.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard13.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard14.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard15.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard16.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard17.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard18.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard19.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard20.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard21.joblib', u'/scratch/users/rbharath/muv_multitask_analysis/features/features_shard22.joblib']

		%% Cell type:code id: tags:

		``` python
		from deepchem.datasets import Dataset
		print("Creating train dataset")
		verbosity = None
		train_dataset = Dataset(data_dir=train_dir, samples=train_samples,
		featurizers=featurizers, tasks=MUV_tasks,
		verbosity=verbosity, reload=reload)
		print("Creating valid dataset")
		valid_dataset = Dataset(data_dir=valid_dir, samples=valid_samples,
		featurizers=featurizers, tasks=MUV_tasks,
		verbosity=verbosity, reload=reload)
		print("Creating test dataset")
		test_dataset = Dataset(data_dir=test_dir, samples=test_samples,
		featurizers=featurizers, tasks=MUV_tasks,
		verbosity=verbosity, reload=reload)
		```

		%% Output

		Creating train dataset
		Creating valid dataset
		Creating test dataset

		%% Cell type:code id: tags:

		``` python
		input_transformers = []
		output_transformers = []
		```

		%% Cell type:code id: tags:

		``` python
		from deepchem.hyperparameters import HyperparamOpt
		from deepchem.models.tensorflow_models import TensorflowModel
		from deepchem.models.tensorflow_models.fcnet import TensorflowMultiTaskClassifier
		from deepchem import metrics
		from deepchem.metrics import Metric
		import numpy as np
		import numpy.random
		model_dir = os.path.join(base_dir, "model")

		MUV_task_types = {task: "Classification" for task in MUV_tasks}
		params_dict = {"activation": ["relu"],
		"momentum": [.9],
		"batch_size": [50],
		"init": ["glorot_uniform"],
		"data_shape": [train_dataset.get_data_shape()],
		"learning_rate": [1e-3],
		"decay": [1e-6],
		"nb_hidden": [1000],
		"nb_epoch": [1],
		"nesterov": [False],
		"dropouts": [(.5,)],
		"nb_layers": [1],
		"batchnorm": [False],
		"layer_sizes": [(1000,)],
		"weight_init_stddevs": [(.1,)],
		"bias_init_consts": [(1.,)],
		"num_classes": [2],
		"penalty": [0.],
		"optimizer": ["sgd"],
		"num_classification_tasks": [len(MUV_task_types)]
		}

		def model_builder(task_types, params_dict, logdir, verbosity=None):
		return TensorflowModel(
		task_types, params_dict, logdir,
		tf_class=TensorflowMultiTaskClassifier,
		verbosity=verbosity)

		metric = Metric(metrics.roc_auc_score, np.mean)
		optimizer = HyperparamOpt(model_builder, MUV_task_types, verbosity="low")
		best_dnn, best_hyperparams, all_results = optimizer.hyperparam_search(
		params_dict, train_dataset, valid_dataset, output_transformers, metric, logdir=model_dir)
		```

		%% Output

		step 1669: 0.0102656
		Training for 1 epochs
		Ending epoch 0: loss 0.00714142
		ys[0]
		[0.0 0.0 0.0 ..., 0.0 0.0 0.0]
		y_preds[0]
		[0 0 0 ..., 0 0 0]
		Saving predictions to <open file '<fdopen>', mode 'w+b' at 0x7f280c626c00>

		/home/rbharath/deepchem/deepchem/metrics/__init__.py:151: UserWarning: Error calculating metric mean-roc_auc_score: unknown format is not supported
		% (self.name, e))

		Saving predictions to <open file '<fdopen>', mode 'w+b' at 0x7f3751586c00>
		Saving model performance scores to <open file '<fdopen>', mode 'w+b' at 0x7f3751586b70>
		Saving model performance scores to <open file '<fdopen>', mode 'w+b' at 0x7f280c626b70>
		hyperparameters.compute
		valid_score
		nan
		hyperparameter_tuple
		('sgd', 1e-06, (1024,), 1, 'relu', (1000,), 50, 0.0, False, 'glorot_uniform', (1.0,), (0.1,), 2, 1, 17, 1000, False, (0.5,), 0.001, 0.9)
		Model 0/1, Metric mean-roc_auc_score, Validation set 0: nan
		best_validation_score so far: -inf
		No models trained correctly.

		%% Cell type:code id: tags:

		``` python
		```

Admin message