Cleanup (c04f8f3c) · Commits · 钟慕尧 / deepchem

deepchem/featurizers/featurize.py

+0 −5

Original line number	Diff line number	Diff line
		@@ -163,9 +163,6 @@ class DataFeaturizer(object):
		input_type=input_type)


		################################### DEBUG
		#raw_df = raw_df.apply(process_raw_sample_helper_partial, axis=1, reduce=False)
		################################### DEBUG
		nb_sample = raw_df.shape[0]
		interval_points = np.linspace(
		0, nb_sample, np.ceil(float(nb_sample)/shard_size)+1, dtype=int)
		@@ -174,10 +171,8 @@ class DataFeaturizer(object):
		log("Sharding and standardizing into shard-%s / %s shards"
		% (str(j+1), len(interval_points)-1), self.verbosity)
		raw_df_shard = raw_df.iloc[range(interval_points[j], interval_points[j+1])]
		################################### DEBUG
		raw_df_shard = raw_df_shard.apply(
		process_raw_sample_helper_partial, axis=1, reduce=False)
		################################### DEBUG

		df = self._standardize_df(raw_df_shard)

deepchem/models/multitask.py

+3 −34

Original line number	Diff line number	Diff line
		@@ -25,10 +25,8 @@ class SingletaskToMultitask(Model):
		self.model_params = model_params
		self.models = {}
		self.model_dir = model_dir
		############################################### DEBUG
		self.task_model_dirs = {}
		self.model_builder = model_builder
		############################################### DEBUG
		self.verbosity = verbosity
		log("About to initialize singletask to multitask model",
		self.verbosity, "high")
		@@ -42,13 +40,7 @@ class SingletaskToMultitask(Model):
		os.makedirs(task_model_dir)
		log("Initializing model for task %s" % task,
		self.verbosity, "high")
		############################################### DEBUG
		self.task_model_dirs[task] = task_model_dir
		############################################### DEBUG
		#self.models[task] = model_builder([task], task_types, model_params,
		# task_model_dir,
		# verbosity=verbosity)
		############################################### DEBUG

		def fit(self, dataset):
		"""
		@@ -63,16 +55,11 @@ class SingletaskToMultitask(Model):
		w_task = w[:, ind]
		X_task = X[w_task != 0, :]
		y_task = y_task[w_task != 0]
		############################################### DEBUG
		task_model = self.model_builder([task], {task: self.task_types[task]}, self.model_params,
		self.task_model_dirs[task],
		verbosity=self.verbosity)
		############################################### DEBUG
		#self.models[task].raw_model.fit(X_task, y_task)
		task_model.raw_model.fit(X_task, y_task)
		############################################### DEBUG
		task_model.save()
		############################################### DEBUG

		def predict_on_batch(self, X):
		"""
		@@ -83,18 +70,14 @@ class SingletaskToMultitask(Model):
		y_pred = np.zeros((n_samples, n_tasks))
		for ind, task in enumerate(self.tasks):
		task_type = self.task_types[task]
		############################################### DEBUG
		task_model = self.model_builder([task], {task: self.task_types[task]}, self.model_params,
		self.task_model_dirs[task],
		verbosity=self.verbosity)
		task_model.reload()

		############################################### DEBUG
		if task_type == "classification":
		#y_pred[:, ind] = self.models[task].predict_on_batch(X)
		y_pred[:, ind] = task_model.predict_on_batch(X)
		elif task_type == "regression":
		#y_pred[:, ind] = self.models[task].predict_on_batch(X)
		y_pred[:, ind] = task_model.predict_on_batch(X)
		else:
		raise ValueError("Invalid task_type")
		@@ -109,34 +92,20 @@ class SingletaskToMultitask(Model):
		n_samples = X.shape[0]
		y_pred = np.zeros((n_samples, n_tasks, n_classes))
		for ind, task in enumerate(self.tasks):
		############################################### DEBUG
		task_model = self.model_builder([task], {task: self.task_types[task]}, self.model_params,
		self.task_model_dirs[task],
		verbosity=self.verbosity)
		task_model.reload()

		############################################### DEBUG
		#y_pred[:, ind] = self.models[task].predict_proba_on_batch(X)
		y_pred[:, ind] = task_model.predict_proba_on_batch(X)
		############################################### DEBUG
		return y_pred

		def save(self):
		"""Save all models"""
		############################################### DEBUG
		#for task in self.tasks:
		# log("Saving model for task %s" % task, self.verbosity, "high")
		# self.models[task].save()
		############################################### DEBUG
		# Saving is done on-the-fly
		pass
		############################################### DEBUG

		def load(self):
		def reload(self):
		"""Load all models"""
		############################################### DEBUG
		#for task in self.tasks:
		# log("Loading model for task %s" % task, self.verbosity, "high")
		# self.models[task].load()
		############################################### DEBUG
		# Loading is done on-the-fly
		pass
		############################################### DEBUG

examples/pcba/pcba_sklearn.py

+0 −3

Original line number	Diff line number	Diff line
		@@ -93,9 +93,6 @@ os.makedirs(model_dir)
		def model_builder(tasks, task_types, model_params, model_dir, verbosity=None):
		return SklearnModel(tasks, task_types, model_params, model_dir,
		model_instance=LogisticRegression(class_weight="balanced"),
		#model_instance=RandomForestClassifier(
		# class_weight="balanced",
		# n_estimators=500),
		verbosity=verbosity)
		model = SingletaskToMultitask(pcba_tasks, pcba_task_types, params_dict, model_dir,
		model_builder, verbosity=verbosity)

Admin message