Renamed DataFeaturizer to DataLoader

joe-nano · Jul 19, 2016 · 4018ef4 · 4018ef4
1 parent 3dd366c
commit 4018ef4
Show file tree

Hide file tree

Showing 25 changed files with 173 additions and 178 deletions.
diff --git a/deepchem/datasets/bace_datasets.py b/deepchem/datasets/bace_datasets.py
@@ -11,7 +11,7 @@
 from deepchem.utils.save import load_from_disk
 from deepchem.splits import SpecifiedSplitter
 from deepchem.featurizers import UserDefinedFeaturizer 
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.datasets import Dataset
 from deepchem.transformers import NormalizationTransformer
 from deepchem.transformers import ClippingTransformer
@@ -69,7 +69,7 @@ def load_bace(mode="regression", transform=True, split="20-80"):
   else:
     raise ValueError("Unknown mode %s" % mode)
   featurizer = UserDefinedFeaturizer(user_specified_features)
-  loader = DataFeaturizer(tasks=bace_tasks,
+  loader = DataLoader(tasks=bace_tasks,
                               smiles_field="mol",
                               id_field="CID",
                               featurizer=featurizer)

diff --git a/deepchem/datasets/muv_datasets.py b/deepchem/datasets/muv_datasets.py
@@ -10,7 +10,7 @@
 import shutil
 from deepchem.utils.save import load_from_disk
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import BalancingTransformer
 
@@ -49,10 +49,10 @@ def load_muv(base_dir, reload=True):
                           'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
                           'MUV-466', 'MUV-832'])
 
-  loader = DataFeaturizer(tasks=all_MUV_tasks,
-                          smiles_field="smiles",
-                          featurizer=featurizer,
-                          verbosity=verbosity)
+  loader = DataLoader(tasks=all_MUV_tasks,
+                      smiles_field="smiles",
+                      featurizer=featurizer,
+                      verbosity=verbosity)
   if not reload or not os.path.exists(data_dir):
     dataset = loader.featurize(dataset_file, data_dir)
     regen = True

diff --git a/deepchem/datasets/nci_datasets.py b/deepchem/datasets/nci_datasets.py
@@ -13,7 +13,7 @@
 import shutil
 from deepchem.utils.save import load_sharded_csv
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import NormalizationTransformer
 
@@ -65,10 +65,10 @@ def load_nci(base_dir, reload=True, force_transform=False):
                     'MDA-MB-231/ATCC', 'MDA-MB-468', 'HS 578T', 'BT-549',
                     'T-47D'])
 
-  loader = DataFeaturizer(tasks=all_nci_tasks,
-                          smiles_field="smiles",
-                          featurizer=featurizer,
-                          verbosity=verbosity)
+  loader = DataLoader(tasks=all_nci_tasks,
+                      smiles_field="smiles",
+                      featurizer=featurizer,
+                      verbosity=verbosity)
   if not reload or not os.path.exists(data_dir):
     dataset = loader.featurize(dataset_paths, data_dir)
     regen = True

diff --git a/deepchem/datasets/pcba_datasets.py b/deepchem/datasets/pcba_datasets.py
@@ -10,7 +10,7 @@
 import shutil
 from deepchem.utils.save import load_from_disk
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import BalancingTransformer
 
@@ -70,10 +70,10 @@ def load_pcba(base_dir, reload=True):
       'PCBA-902','PCBA-903','PCBA-904','PCBA-912','PCBA-914','PCBA-915',
       'PCBA-924','PCBA-925','PCBA-926','PCBA-927','PCBA-938','PCBA-995']
 
-  loader = DataFeaturizer(tasks=all_PCBA_tasks,
-                          smiles_field="smiles",
-                          featurizer=featurizer,
-                          verbosity=verbosity)
+  loader = DataLoader(tasks=all_PCBA_tasks,
+                      smiles_field="smiles",
+                      featurizer=featurizer,
+                      verbosity=verbosity)
   if not reload or not os.path.exists(data_dir):
     dataset = loader.featurize(dataset_file, data_dir)
     regen = True

diff --git a/deepchem/datasets/pdbbind_datasets.py b/deepchem/datasets/pdbbind_datasets.py
@@ -13,7 +13,6 @@
 from rdkit import Chem
 from deepchem.utils.save import load_from_disk
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import BalancingTransformer
 from deepchem.featurizers.nnscore import NNScoreComplexFeaturizer

diff --git a/deepchem/datasets/tests/__init__.py b/deepchem/datasets/tests/__init__.py
@@ -15,7 +15,7 @@
 import shutil
 import numpy as np
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import NormalizationTransformer
 from deepchem.models.tests import TestAPI
@@ -33,7 +33,7 @@ def load_solubility_data(self):
     tasks = ["log-solubility"]
     task_type = "regression"
     input_file = os.path.join(self.current_dir, "../../models/tests/example.csv")
-    featurizer = DataFeaturizer(
+    featurizer = DataLoader(
         tasks=tasks,
         smiles_field=self.smiles_field,
         featurizer=featurizer,
@@ -50,7 +50,7 @@ def load_classification_data(self):
     task_type = "classification"
     input_file = os.path.join(
         self.current_dir, "../../models/tests/example_classification.csv")
-    loader = DataFeaturizer(
+    loader = DataLoader(
         tasks=tasks,
         smiles_field=self.smiles_field,
         featurizer=featurizer,
@@ -67,7 +67,7 @@ def load_multitask_data(self):
              "task13", "task14", "task15", "task16"]
     input_file = os.path.join(
         self.current_dir, "../../models/tests/multitask_example.csv")
-    loader = DataFeaturizer(
+    loader = DataLoader(
         tasks=tasks,
         smiles_field=self.smiles_field,
         featurizer=featurizer,

diff --git a/deepchem/datasets/tests/test_datasets.py b/deepchem/datasets/tests/test_datasets.py
@@ -15,7 +15,7 @@
 import shutil
 import numpy as np
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.transformers import NormalizationTransformer
 from deepchem.datasets.tests import TestDatasetAPI

diff --git a/deepchem/datasets/tests/test_drop.py b/deepchem/datasets/tests/test_drop.py
@@ -4,7 +4,7 @@
 import numpy as np
 from deepchem.models.tests import TestAPI
 from deepchem.utils.save import load_from_disk
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.datasets import Dataset
 from sklearn.ensemble import RandomForestClassifier
 from deepchem.models.sklearn_models import SklearnModel
@@ -37,10 +37,10 @@ def test_drop(self):
     featurizer = CircularFingerprint(size=1024)
     emols_tasks = ['activity']
 
-    loader = DataFeaturizer(tasks=emols_tasks,
-                            smiles_field="smiles",
-                            featurizer=featurizer,
-                            verbosity=verbosity)
+    loader = DataLoader(tasks=emols_tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(dataset_file, data_dir, debug=True, logging=False)
 
     X, y, w, ids = dataset.to_numpy()

diff --git a/deepchem/datasets/tests/test_load.py b/deepchem/datasets/tests/test_load.py
@@ -16,7 +16,7 @@
 from deepchem.models.tests import TestAPI
 from deepchem.utils.save import load_from_disk
 from deepchem.featurizers.fingerprints import CircularFingerprint
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.datasets import Dataset
 
 ## task0: 1,1,0,-,0,-,1,-,-,1
@@ -37,10 +37,10 @@ def test_move_load(self):
 
     featurizer = CircularFingerprint(size=1024)
     tasks = ["log-solubility"]
-    loader = DataFeaturizer(tasks=tasks,
-                                smiles_field="smiles",
-                                featurizer=featurizer,
-                                verbosity=verbosity)
+    loader = DataLoader(tasks=tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(dataset_file, data_dir)
 
     X, y, w, ids = dataset.to_numpy()
@@ -92,10 +92,10 @@ def test_multiload(self):
     all_tasks = ["task%d"%i for i in range(17)] 
 
     ####### Do featurization
-    loader = DataFeaturizer(tasks=all_tasks,
-                                smiles_field="smiles",
-                                featurizer=featurizer,
-                                verbosity=verbosity)
+    loader = DataLoader(tasks=all_tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(
         dataset_file, data_dir)
 
@@ -160,10 +160,10 @@ def test_singletask_matches_multitask_load(self):
     tasks = all_tasks[0:n_tasks]
 
     ####### Do multitask load
-    loader = DataFeaturizer(tasks=tasks,
-                            smiles_field="smiles",
-                            featurizer=featurizer,
-                            verbosity=verbosity)
+    loader = DataLoader(tasks=tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(dataset_file, data_dir)
 
     # Do train/valid split.
@@ -176,10 +176,10 @@ def test_singletask_matches_multitask_load(self):
       print("Processing task %s" % task)
       if os.path.exists(data_dir):
         shutil.rmtree(data_dir)
-      loader = DataFeaturizer(tasks=[task],
-                              smiles_field="smiles",
-                              featurizer=featurizer,
-                              verbosity=verbosity)
+      loader = DataLoader(tasks=[task],
+                          smiles_field="smiles",
+                          featurizer=featurizer,
+                          verbosity=verbosity)
       dataset = loader.featurize(dataset_file, data_dir)
 
       X_task, y_task, w_task, ids_task = dataset.to_numpy()

diff --git a/deepchem/datasets/tests/test_merge.py b/deepchem/datasets/tests/test_merge.py
@@ -16,7 +16,7 @@
 from deepchem.models.tests import TestAPI
 from deepchem.utils.save import load_from_disk
 from deepchem.featurizers.fingerprints import CircularFingerprint
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.datasets import Dataset
 
 class TestMerge(TestAPI):
@@ -36,13 +36,13 @@ def test_merge(self):
 
     featurizer = CircularFingerprint(size=1024)
     tasks = ["log-solubility"]
-    featurizer = DataFeaturizer(tasks=tasks,
-                                smiles_field="smiles",
-                                featurizer=featurizer,
-                                verbosity=verbosity)
-    first_dataset = featurizer.featurize(
+    loader = DataLoader(tasks=tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
+    first_dataset = loader.featurize(
         dataset_file, first_data_dir)
-    second_dataset = featurizer.featurize(
+    second_dataset = loader.featurize(
         dataset_file, second_data_dir)
 
     merged_dataset = Dataset.merge(
@@ -62,11 +62,11 @@ def test_subset(self):
 
     featurizer = CircularFingerprint(size=1024)
     tasks = ["log-solubility"]
-    featurizer = DataFeaturizer(tasks=tasks,
-                                smiles_field="smiles",
-                                featurizer=featurizer,
-                                verbosity=verbosity)
-    dataset = featurizer.featurize(
+    loader = DataLoader(tasks=tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
+    dataset = loader.featurize(
         dataset_file, data_dir, shard_size=2)
 
     shard_nums = [1, 2]

diff --git a/deepchem/datasets/tests/test_reload.py b/deepchem/datasets/tests/test_reload.py
@@ -17,7 +17,7 @@
 from deepchem.models.tests import TestAPI
 from deepchem.utils.save import load_from_disk
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.splits import ScaffoldSplitter
 from deepchem.datasets import Dataset
@@ -45,10 +45,10 @@ def _run_muv_experiment(self, dataset_file, reload=False, verbosity=None):
                  'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712',
                  'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652',
                  'MUV-466', 'MUV-832']
-    loader = DataFeaturizer(tasks=MUV_tasks,
-                                smiles_field="smiles",
-                                featurizer=featurizer,
-                                verbosity=verbosity)
+    loader = DataLoader(tasks=MUV_tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(dataset_file, self.data_dir)
     assert len(dataset) == len(raw_dataset)
 

diff --git a/deepchem/datasets/tests/test_shuffle.py b/deepchem/datasets/tests/test_shuffle.py
@@ -16,7 +16,7 @@
 from deepchem.models.tests import TestAPI
 from deepchem.utils.save import load_from_disk
 from deepchem.featurizers.fingerprints import CircularFingerprint
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.datasets import Dataset
 
 class TestShuffle(TestAPI):
@@ -34,10 +34,10 @@ def test_shuffle(self):
 
     featurizer = CircularFingerprint(size=1024)
     tasks = ["log-solubility"]
-    loader = DataFeaturizer(tasks=tasks,
-                            smiles_field="smiles",
-                            featurizer=featurizer,
-                            verbosity=verbosity)
+    loader = DataLoader(tasks=tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(
         dataset_file, data_dir, shard_size=2)
 

diff --git a/deepchem/datasets/tox21_datasets.py b/deepchem/datasets/tox21_datasets.py
@@ -12,7 +12,7 @@
 from sklearn.ensemble import RandomForestClassifier
 from deepchem.utils.save import load_from_disk
 from deepchem.datasets import Dataset
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 from deepchem.splits import ScaffoldSplitter
 from deepchem.splits import RandomSplitter
@@ -62,10 +62,10 @@ def load_tox21(base_dir, reload=True):
                      'SR-HSE', 'SR-MMP', 'SR-p53']
 
   if not reload or not os.path.exists(data_dir):
-    loader = DataFeaturizer(tasks=all_tox21_tasks,
-                            smiles_field="smiles",
-                            featurizer=featurizer,
-                            verbosity=verbosity)
+    loader = DataLoader(tasks=all_tox21_tasks,
+                        smiles_field="smiles",
+                        featurizer=featurizer,
+                        verbosity=verbosity)
     dataset = loader.featurize(
         dataset_file, data_dir, shard_size=8192)
   else:

diff --git a/deepchem/featurizers/featurize.py b/deepchem/featurizers/featurize.py
@@ -124,7 +124,7 @@ def featurize_map_function(args):
 #  else:
 #    raise ValueError("Field of unrecognized type: %s" % str(val))
 
-class DataFeaturizer(object):
+class DataLoader(object):
   """
   Handles loading/featurizing of chemical samples (datapoints).
 

diff --git a/deepchem/featurizers/tests/test_data_featurizer.py b/deepchem/featurizers/tests/test_data_featurizer.py
@@ -1,5 +1,5 @@
 """
-Tests for DataFeaturizer class
+Tests for DataLoader class
 """
 from __future__ import print_function
 from __future__ import division
@@ -14,10 +14,10 @@
 import tempfile
 import shutil
 from deepchem.models.tests import TestAPI
-from deepchem.featurizers.featurize import DataFeaturizer
+from deepchem.featurizers.featurize import DataLoader
 from deepchem.featurizers.fingerprints import CircularFingerprint
 
-class TestDataFeaturizer(TestAPI):
+class TestDataLoader(TestAPI):
   """
   Test Data Featurizer class.
   """
@@ -29,10 +29,10 @@ def test_log_solubility_dataset(self):
 
     tasks = ["log-solubility"]
     smiles_field = "smiles"
-    loader = DataFeaturizer(tasks=tasks,
-                            smiles_field=self.smiles_field,
-                            featurizer=CircularFingerprint(size=1024),
-                            verbosity="low")
+    loader = DataLoader(tasks=tasks,
+                        smiles_field=self.smiles_field,
+                        featurizer=CircularFingerprint(size=1024),
+                        verbosity="low")
     dataset = loader.featurize(input_file, self.data_dir)
 
     assert len(dataset) == 10