User_specified_features (2e1fa8eb) · Commits · 钟慕尧 / deepchem

datasets/gbd3k.pkl.gz

0 → 100644

+405 KiB

File added.

No diff preview for this file type.

deepchem/featurizers/featurize.py

+10 −11

Original line number	Diff line number	Diff line
		@@ -136,20 +136,19 @@ class DataFeaturizer(object):
		0, nb_sample, np.ceil(float(nb_sample)/shard_size)+1, dtype=int)
		shard_files = []
		for j in range(len(interval_points)-1):
		log("Sharding and standardizing into shard-%s / %s shards" % (str(j+1), len(interval_points)-1), self.verbose)
		#log("Sharding and standardizing into shard-%s / %s shards" % (str(j+1), len(interval_points)-1), self.verbose)
		raw_df_shard = raw_df.iloc[range(interval_points[j], interval_points[j+1])]

		df = self._standardize_df(raw_df_shard)
		log("Aggregating User-Specified Features", self.verbose)
		#log("Aggregating User-Specified Features", self.verbose)
		self._add_user_specified_features(df)

		for compound_featurizer in self.compound_featurizers:
		log("Currently feauturizing feature_type: %s"
		log("Currently featurizing feature_type: %s"
		% compound_featurizer.__class__.__name__, self.verbose)
		self._featurize_compounds(df, compound_featurizer)

		for complex_featurizer in self.complex_featurizers:
		log("Currently feauturizing feature_type: %s"
		log("Currently featurizing feature_type: %s"
		% complex_featurizer.__class__.__name__, self.verbose)
		self._featurize_complexes(df, complex_featurizer)

		@@ -159,8 +158,7 @@ class DataFeaturizer(object):

		featurizers = self.compound_featurizers + self.complex_featurizers
		samples = FeaturizedSamples(samples_dir=samples_dir, featurizers=featurizers,
		dataset_files=shard_files,
		reload_data=False)
		dataset_files=shard_files, reload_data=False)

		return samples

		@@ -190,7 +188,7 @@ class DataFeaturizer(object):
		df["smiles"] = ori_df[[self.smiles_field]]
		for task in self.tasks:
		df[task] = ori_df[[task]]
		if self.split_field is not None:
		if self.user_specified_features is not None:
		for feature in self.user_specified_features:
		df[feature] = ori_df[[feature]]
		if self.split_field is not None:
		@@ -235,15 +233,15 @@ class DataFeaturizer(object):
		into final features dataframe
		"""
		if self.user_specified_features is not None:
		log("Adding user-defined features.", self.verbose)
		#log("Adding user-defined features.", self.verbose)
		features_data = []
		for _, row in df.iterrows():
		# pandas rows are tuples (row_num, row_data)
		feature_list = []
		for feature_name in self.user_specified_features:
		feature_list.append(row[feature_name])
		features_data.append({"user-specified-features": np.array(feature_list)})
		df["user-specified-features"] = pd.DataFrame(features_data)
		features_data.append(np.array(feature_list))
		df["user-specified-features"] = features_data


		def map_function(data_tuple, featurizer):
		@@ -345,6 +343,7 @@ class FeaturizedSamples(object):
		"""Returns size of internal dataset."""
		return self.num_samples

		irint("feature types %s" % self.feature_types)
		def itersamples(self):
		"""Iterates over samples in this object."""
		compound_ids = set(list(self.compounds_df["mol_id"]))

deepchem/models/init.py

+4 −1

Original line number	Diff line number	Diff line
		@@ -77,7 +77,10 @@ class Model(object):
		"""
		Factory method that initializes model of requested type.
		"""
		if model_instance.__class__ in non_sklearn_models:
		print(model_instance.__class__)
		print(task_types)
		print(model_params)
		if model_instance.__class__ in Model.non_sklearn_models:
		model = model_instance(task_types, model_params, initialize_raw_model)
		else:
		model = Model.registered_model_classes["SklearnModel"](model_instance,

deepchem/utils/dataset.py

+5 −1

Original line number	Diff line number	Diff line
		@@ -30,9 +30,13 @@ class Dataset(object):
		os.makedirs(data_dir)
		self.data_dir = data_dir

		if featurizers is not None:
		feature_types = [featurizer.__class__.__name__ for featurizer in featurizers]
		else:
		feature_types = None

		if use_user_specified_features:
		feature_types += ["user-specified-features"]
		feature_types = ["user-specified-features"]

		if samples is not None and feature_types is not None:
		if not isinstance(feature_types, list):

deepchem/utils/test/gbd3k.pkl.gz

0 → 100644

+405 KiB

File added.

No diff preview for this file type.

View file

Admin message