Debugging more tests (ca10e0f5) · Commits · 钟慕尧 / deepchem

deepchem/data/init.py

+2 −0

Original line number	Diff line number	Diff line
		@@ -11,6 +11,8 @@ from deepchem.data.datasets import pad_batch
		from deepchem.data.datasets import Dataset
		from deepchem.data.datasets import NumpyDataset
		from deepchem.data.datasets import DiskDataset
		from deepchem.data.datasets import sparsify_features
		from deepchem.data.datasets import densify_features
		from deepchem.data.supports import *
		from deepchem.data.data_loader import DataLoader
		from deepchem.data.data_loader import CSVLoader

deepchem/data/data_loader.py

+18 −1

Original line number	Diff line number	Diff line
		@@ -57,6 +57,10 @@ def featurize_smiles_df(df, featurizer, field, log_every_N=1000, verbose=True):
		or macromolecules, compute & add features for that compound to the
		features dataframe
		"""
		######################################################## DEBUG
		print("field")
		print(field)
		######################################################## DEBUG
		sample_elems = df[field].tolist()

		features = []
		@@ -144,6 +148,10 @@ class DataLoader(object):
		self.user_specified_features = featurizer.feature_fields
		self.featurizer = featurizer
		self.log_every_n = log_every_n
		##################################################### DEBUG
		print("self.smiles_field")
		print(self.smiles_field)
		##################################################### DEBUG

		def featurize(self, input_files, data_dir=None, shard_size=8192):
		"""Featurize provided files and write to specified location."""
		@@ -155,6 +163,10 @@ class DataLoader(object):
		def shard_generator():
		for shard_num, shard in enumerate(self.get_shards(input_files, shard_size)):
		time1 = time.time()
		##################################################### DEBUG
		print("self.smiles_field")
		print(self.smiles_field)
		##################################################### DEBUG
		X, valid_inds = self.featurize_shard(shard)
		ids, y, w = convert_df_to_numpy(shard, self.tasks, self.id_field)
		# Filter out examples where featurization failed.
		@@ -184,8 +196,13 @@ class CSVLoader(DataLoader):

		def featurize_shard(self, shard):
		"""Featurizes a shard of an input dataframe."""
		######################################################### DEBUG
		print("self.smiles_field")
		print(self.smiles_field)
		######################################################### DEBUG
		return featurize_smiles_df(shard, self.featurizer,
		field=self.smiles_field)

		class UserCSVLoader(DataLoader):
		"""
		Handles loading of CSV files with user-defined featurizers.
		@@ -198,7 +215,7 @@ class UserCSVLoader(DataLoader):
		"""Featurizes a shard of an input dataframe."""
		assert isinstance(self.featurizer, UserDefinedFeaturizer)
		X = get_user_specified_features(shard, self.featurizer)
		return (X, np.ones(len(X)))
		return (X, np.ones(len(X), dtype=bool))

		class SDFLoader(DataLoader):
		"""

deepchem/data/datasets.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -608,7 +608,7 @@ class DiskDataset(Dataset):
		for shard_num, row in self.metadata_df.iterrows():
		X, y, w, ids = self.get_shard(shard_num)
		newx, newy, neww = fn(X, y, w)
		yield (X, y, w, ids)
		yield (newx, newy, neww, ids)
		return DiskDataset(generator(), data_dir=out_dir)

		@staticmethod

deepchem/data/tests/init.py

+9 −4

Original line number	Diff line number	Diff line
		@@ -23,9 +23,14 @@ def load_solubility_data():
		tasks = ["log-solubility"]
		task_type = "regression"
		input_file = os.path.join(current_dir, "../../models/tests/example.csv")
		featurizer = dc.data.CSVLoader(
		loader = dc.data.CSVLoader(
		tasks=tasks, smiles_field="smiles", featurizer=featurizer)
		return featurizer.featurize(input_file)
		##################################################### DEBUG
		print("loader.smiles_field")
		print(loader.smiles_field)
		##################################################### DEBUG

		return loader.featurize(input_file)

		def load_multitask_data():
		"""Load example multitask data."""
		@@ -73,7 +78,7 @@ def load_feat_multitask_data():
		tasks = ["task0", "task1", "task2", "task3", "task4", "task5"]
		input_file = os.path.join(
		current_dir, "../../models/tests/feat_multitask_example.csv")
		loader = dc.data.CSVLoader(
		loader = dc.data.UserCSVLoader(
		tasks=tasks, featurizer=featurizer, id_field="id")
		return loader.featurize(input_file)

		@@ -87,6 +92,6 @@ def load_gaussian_cdf_data():
		tasks = ["task0","task1"]
		input_file = os.path.join(
		current_dir, "../../models/tests/gaussian_cdf_example.csv")
		loader = dc.data.CSVLoader(
		loader = dc.data.UserCSVLoader(
		tasks=tasks, featurizer=featurizer, id_field="id")
		return loader.featurize(input_file)

deepchem/data/tests/test_datasets.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -16,7 +16,7 @@ import shutil
		import numpy as np
		import deepchem as dc

		class TestBasicDatasets(unittest.TestCase):
		class TestDatasets(unittest.TestCase):
		"""
		Test basic top-level API for dataset objects.
		"""

Admin message