First commit of completed model. Will rerun on GPU before final commit. (5337e9dc) · Commits · 钟慕尧 / deepchem

deepchem/featurizers/featurize.py

+14 −2

Original line number	Diff line number	Diff line
		@@ -342,10 +342,22 @@ class FeaturizedSamples(object):
		"""Returns size of internal dataset."""
		return self.num_samples

		# TODO(rbharath): Might this be inefficient?
		def itersamples(self):
		"""Iterates over samples in this object."""
		compound_ids = set(list(self.compounds_df["mol_id"]))
		for df_file in self.dataset_files:
		df = load_from_disk(df_file)
		visible_inds = []
		for ind, row in df.iterrows():
		if row["mol_id"] in compound_ids:
		visible_inds.append(ind)
		for visible_ind in visible_inds:
		yield df.loc[visible_ind]

		# TODO(rbharath): Might this be inefficient?
		def iterdataframes(self):
		"""
		Provides an iterator over samples.
		Provides a bulk iterator over data.

		Each sample from the iterator is a dataframe of samples.
		"""

deepchem/models/init.py

+9 −5

Original line number	Diff line number	Diff line
		@@ -22,12 +22,14 @@ class Model(object):
		registered_model_classes = {}
		non_sklearn_models = ["SingleTaskDNN", "MultiTaskDNN", "DockingDNN"]
		def __init__(self, task_types, model_params, model_instance=None,
		initialize_raw_model=True, verbose=True):
		initialize_raw_model=True, verbosity="low"):
		self.model_class = model_instance.__class__
		self.task_types = task_types
		self.model_params = model_params
		self.raw_model = None
		self.verbose = verbose
		assert verbosity in [None, "low", "high"]
		self.low_verbosity = (verbosity == "low")
		self.high_verbosity = (verbosity == "high")

		def fit_on_batch(self, X, y, w):
		"""
		@@ -133,14 +135,16 @@ class Model(object):
		# memory overflows.
		batch_size = self.model_params["batch_size"]
		for epoch in range(self.model_params["nb_epoch"]):
		log("Starting epoch %s" % str(epoch+1), self.verbose)
		log("Starting epoch %s" % str(epoch+1), self.low_verbosity)
		for i, (X, y, w, _) in enumerate(dataset.itershards()):
		log("Training on shard-%s/epoch-%s" % (str(i+1), str(epoch+1)), self.verbose)
		log("Training on shard-%s/epoch-%s" % (str(i+1), str(epoch+1)),
		self.high_verbosity)
		nb_sample = np.shape(X)[0]
		interval_points = np.linspace(
		0, nb_sample, np.ceil(float(nb_sample)/batch_size)+1, dtype=int)
		for j in range(len(interval_points)-1):
		log("Training on batch-%s/shard-%s/epoch-%s" % (str(j+1), str(i+1), str(epoch+1)), self.verbose)
		log("Training on batch-%s/shard-%s/epoch-%s" %
		(str(j+1), str(i+1), str(epoch+1)), self.high_verbosity)
		indices = range(interval_points[j], interval_points[j+1])
		X_batch = X[indices, :]
		y_batch = y[indices]

deepchem/models/deep.py

+0 −4

Original line number	Diff line number	Diff line
		@@ -150,10 +150,6 @@ class MultiTaskDNN(KerasModel):
		# output the most likely class.
		y_pred_task = np.squeeze(np.argmax(y_pred_dict[taskname], axis=1))
		else:
		print("taskname")
		print(taskname)
		print("y_pred_dict.keys()")
		print(y_pred_dict.keys())
		y_pred_task = np.squeeze(y_pred_dict[taskname])
		y_pred[:, ind] = y_pred_task
		y_pred = np.squeeze(y_pred)

deepchem/utils/dataset.py

+1 −1

Original line number	Diff line number	Diff line
		@@ -44,7 +44,7 @@ class Dataset(object):

		metadata_rows = []
		# TODO(rbharath): Still a bit of information leakage.
		for df_file, df in zip(samples.dataset_files, samples.itersamples()):
		for df_file, df in zip(samples.dataset_files, samples.iterdataframes()):
		retval = write_dataset_single_partial((df_file, df))
		if retval is not None:
		metadata_rows.append(retval)

docs/solubility.html

0 → 100644

+1956 −0

File added.

Preview size limit exceeded, changes collapsed.

Admin message