First run-through to completion. (0917ec2e) · Commits · 钟慕尧 / deepchem

deep_chem/scripts/launch_models.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -21,7 +21,7 @@ from deep_chem.utils.preprocess import train_test_random_split
		from deep_chem.utils.preprocess import train_test_scaffold_split
		from deep_chem.utils.preprocess import scaffold_separate
		from deep_chem.utils.preprocess import multitask_to_singletask
		from deep_chem.utils.preprocess import get_default_task_types_and_transforms
		from deep_chem.utils.load import get_default_task_types_and_transforms
		from deep_chem.utils.preprocess import get_default_descriptor_transforms

		def parse_args(input_args=None):

+2 −0

Original line number	Diff line number	Diff line
		@@ -5,6 +5,8 @@ __author__ = "Bharath Ramsundar"
		__copyright__ = "Copyright 2015, Stanford University"
		__license__ = "LGPL"

		import numpy as np

		def summarize_distribution(y):
		"""Analyzes regression dataset.

+5 −0

Original line number	Diff line number	Diff line
		@@ -5,6 +5,11 @@ __author__ = "Bharath Ramsundar"
		__copyright__ = "Copyright 2015, Stanford University"
		__license__ = "LGPL"

		import numpy as np
		from deep_chem.utils.preprocess import dataset_to_numpy
		from deep_chem.utils.preprocess import labels_to_weights
		from sklearn.metrics import roc_auc_score

		def model_predictions(test_set, model, n_targets, n_descriptors=0,
		add_descriptors=False, modeltype="sklearn"):
		"""Obtains predictions of provided model on test_set.

+23 −0

Original line number	Diff line number	Diff line
		@@ -11,6 +11,29 @@ import os
		import cPickle as pickle
		from deep_chem.utils.preprocess import transform_outputs

		def get_default_task_types_and_transforms(dataset_specs):
		"""Provides default task transforms for provided datasets.

		Parameters
		----------
		dataset_specs: dict
		Maps name of datasets to filepath.
		"""
		task_types, task_transforms = {}, {}
		for name, path in dataset_specs.iteritems():
		targets = get_target_names([path])
		if name == "muv" or name == "dude" or name == "pcba":
		for target in targets:
		task_types[target] = "classification"
		task_transforms[target] = []
		elif name == "pfizer":
		for target in targets:
		task_types[target] = "regression"
		task_transforms[target] = ["log", "normalize"]
		elif name == "pdbbind":
		raise ValueError("pdbbind not yet supported!")
		return task_types, task_transforms

		def load_descriptors(paths, descriptor_dir_name="descriptors"):
		"""Load dataset descriptors and return.

+1 −24

Original line number	Diff line number	Diff line
		@@ -6,7 +6,7 @@ __copyright__ = "Copyright 2015, Stanford University"
		__license__ = "LGPL"

		import numpy as np
		from deep_chem.utils.load import get_target_names
		from deep_chem.utils.analysis import summarize_distribution

		def get_default_descriptor_transforms():
		"""Provides default descriptor transforms for rdkit descriptors."""
		@@ -17,29 +17,6 @@ def get_default_descriptor_transforms():
		desc_transforms[desc] = ["normalize"]
		return desc_transforms

		def get_default_task_types_and_transforms(dataset_specs):
		"""Provides default task transforms for provided datasets.

		Parameters
		----------
		dataset_specs: dict
		Maps name of datasets to filepath.
		"""
		task_types, task_transforms = {}, {}
		for name, path in dataset_specs.iteritems():
		targets = get_target_names([path])
		if name == "muv" or name == "dude" or name == "pcba":
		for target in targets:
		task_types[target] = "classification"
		task_transforms[target] = []
		elif name == "pfizer":
		for target in targets:
		task_types[target] = "regression"
		task_transforms[target] = ["log", "normalize"]
		elif name == "pdbbind":
		raise ValueError("pdbbind not yet supported!")
		return task_types, task_transforms

		def transform_outputs(dataset, task_transforms, desc_transforms={},
		add_descriptors=False):
		"""Tranform the provided outputs