Merge pull request #31 from MolecularAI/3.1.3

Init 3.1.3

docs/sphinx-source/algorithms.rst

@@ -14,13 +14,13 @@ Lasso
 
 
 KNeighborsClassifier
-#####
+####################
 ..  autoclass:: optunaz.config.optconfig.KNeighborsClassifier
     :members:
 
 
 KNeighborsRegressor
-#####
+###################
 ..  autoclass:: optunaz.config.optconfig.KNeighborsRegressor
     :members:
 
@@ -103,8 +103,8 @@ ChemPropHyperoptRegressor
     :members:
 
 
-ChemPropRegressorPretrained
-#########################
+ChemPropHyperoptRegressorPretrained
+###################################
 ..  autoclass:: optunaz.config.optconfig.ChemPropRegressorPretrained
     :members:
 

docs/sphinx-source/conf.py

@@ -22,7 +22,7 @@
 author = 'MAI'
 
 # The full version, including alpha/beta/rc tags
-release = '3.1.2'
+release = '3.1.3'
 
 
 # -- General configuration ---------------------------------------------------

docs/sphinx-source/descriptors.rst

@@ -19,7 +19,7 @@ ECFP_counts
 
 
 PathFP
-###########
+######
 ..  autoclass:: optunaz.descriptors.PathFP
     :members:
 
@@ -37,13 +37,13 @@ UnscaledPhyschemDescriptors
 
 
 UnscaledJazzyDescriptors
-###########################
+########################
 ..  autoclass:: optunaz.descriptors.UnscaledJazzyDescriptors
     :members:
 
 
 UnscaledZScalesDescriptors
-###########
+##########################
 ..  autoclass:: optunaz.descriptors.UnscaledZScalesDescriptors
     :members:
 
@@ -67,7 +67,7 @@ PrecomputedDescriptorFromFile
 
 
 ZScales
-###########
+#######
 ..  autoclass:: optunaz.descriptors.ZScalesDescriptors
     :members:
 
@@ -94,3 +94,39 @@ CompositeDescriptor
 ###################
 ..  autoclass:: optunaz.descriptors.CompositeDescriptor
     :members:
+
+
+AmorProtDescriptors
+###################
+..  autoclass:: optunaz.descriptors.AmorProtDescriptors
+    :members:
+
+
+PathFP
+######
+..  autoclass:: optunaz.descriptors.PathFP
+    :members:
+
+
+UnscaledMAPC
+############
+..  autoclass:: optunaz.descriptors.UnscaledMAPC
+    :members:
+
+
+UnscaledZScalesDescriptors
+##########################
+..  autoclass:: optunaz.descriptors.UnscaledZScalesDescriptors
+    :members:
+
+
+MAPC
+####
+..  autoclass:: optunaz.descriptors.MAPC
+    :members:
+
+
+ZScalesDescriptors
+##################
+..  autoclass:: optunaz.descriptors.ZScalesDescriptors
+    :members:

docs/sphinx-source/transform.rst

@@ -24,3 +24,10 @@ ZScales
 #######
 ..  autoclass:: optunaz.utils.preprocessing.transform.ZScales
     :members:
+
+
+AmorProt
+########
+..  autoclass:: optunaz.utils.preprocessing.transform.AmorProt
+    :members:
+

optunaz/__init__.py

@@ -1,5 +1,5 @@
 import os
 
-__version__ = "3.1.2"
+__version__ = "3.1.3"
 
 os.environ["TQDM_DISABLE"] = "1"

optunaz/algorithms/chem_prop.py

@@ -97,6 +97,21 @@ def __exit__(self, *args):
         del self._stringio
         sys.stdout = self._stdout
 
+class CaptureStdOutErr(list):
+    def __enter__(self):
+        self._stdout = sys.stdout
+        self._stderr = sys.stderr
+        sys.stdout = self._stringio = StringIO()
+        sys.stderr = self._stringioerr = StringIO()
+        return self
+
+    def __exit__(self, *args):
+        self.extend(self._stringio.getvalue().splitlines())
+        self.extend(self._stringioerr.getvalue().splitlines())
+        del self._stringio
+        del self._stringioerr
+        sys.stdout = self._stdout
+        sys.stderr = self._stderr
 
 def save_model_memory(model_dir):
     tarblob = io.BytesIO()
@@ -316,7 +331,7 @@ def fit(self, X, y):
                     ).to_csv(x_aux_path.name, index=False)
                     # arguments += ["--features_path", f"{x_aux_path.name}"] TODO: allow features once ChemProp is updated
 
-                with CaptureStdOut() as _:
+                with CaptureStdOutErr() as _:
                     args = QSARtunaTrainArgs().parse_args(arguments)
                     chemprop.train.cross_validate(
                         args=args, train_func=chemprop.train.run_training
@@ -365,7 +380,7 @@ def predict_proba(self, X):
             else:
                 X = np.array(X).reshape(len(X), 1)
 
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = QSARtunaPredictArgs().parse_args(arguments)
                 model_objects = chemprop.train.load_model(args=args)
                 preds = np.array(
@@ -444,7 +459,7 @@ def predict_uncert(self, X):
             else:
                 X = np.array(X[:, 0].reshape(len(X), 1))
 
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = QSARtunaPredictArgs().parse_args(arguments)
                 if uncertainty_method == "dropout":
                     model_objects = list(chemprop.train.load_model(args=args))
@@ -505,7 +520,7 @@ def interpret(self, X, prop_delta=0.75):
                     X = np.array(X[:, 0].reshape(len(X), 1))
                 X = pd.DataFrame(X, columns=["smiles"])
                 X.to_csv(data_path.name, index=False)
-                with CaptureStdOut() as _:
+                with CaptureStdOutErr() as _:
                     args = chemprop.args.InterpretArgs().parse_args(intrprt_args)
                 with CaptureStdOut() as intrprt:
                     interpret(args=args)
@@ -565,7 +580,7 @@ def chemprop_fingerprint(self, X, fingerprint_type="MPN"):
             ]
             # if self.x_aux_ is not None:
             # fprnt_args += ["--features_path", f"{x_aux_path.name}"] TODO: allow features once ChemProp is updated
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = chemprop.args.FingerprintArgs().parse_args(fprnt_args)
                 try:
                     fps = chemprop.train.molecule_fingerprint.molecule_fingerprint(
@@ -861,7 +876,7 @@ def fit(self, X, y):
                         arguments += ["--frzn_ffn_layers", "1"]
                     if self.frzn == "mpnn_last_ffn":
                         arguments += ["--frzn_ffn_layers", f"{self.ffn_num_layers - 1}"]
-                    with CaptureStdOut() as _:
+                    with CaptureStdOutErr() as _:
                         args = QSARtunaTrainArgs().parse_args(arguments)
                         chemprop.train.cross_validate(
                             args=args, train_func=chemprop.train.run_training

optunaz/algorithms/chem_prop_hyperopt.py

@@ -37,16 +37,21 @@
 chemprop.interpret.MoleculeDataLoader = MoleculeDataLoader
 
 
-class CaptureStdOut(list):
+class CaptureStdOutErr(list):
     def __enter__(self):
         self._stdout = sys.stdout
+        self._stderr = sys.stderr
         sys.stdout = self._stringio = StringIO()
+        sys.stderr = self._stringioerr = StringIO()
         return self
 
     def __exit__(self, *args):
         self.extend(self._stringio.getvalue().splitlines())
+        self.extend(self._stringioerr.getvalue().splitlines())
         del self._stringio
+        del self._stringioerr
         sys.stdout = self._stdout
+        sys.stderr = self._stderr
 
 
 def save_model_memory(model_dir):
@@ -294,7 +299,7 @@ def fit(self, X, y):
                     ).to_csv(x_aux_path.name, index=False)
                     # arguments += ["--features_path", f"{x_aux_path.name}"] TODO: allow features once ChemProp is updated
 
-                with CaptureStdOut() as _:
+                with CaptureStdOutErr() as _:
                     if self.num_iters > 1:
                         with tempfile.NamedTemporaryFile(
                             delete=True, mode="w+"
@@ -375,7 +380,7 @@ def predict_proba(self, X):
             else:
                 X = np.array(X[:, 0].reshape(len(X), 1))
 
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = chemprop.args.PredictArgs().parse_args(arguments)
                 model_objects = chemprop.train.load_model(args=args)
                 preds = np.array(
@@ -450,7 +455,7 @@ def predict_uncert(self, X):
             else:
                 X = np.array(X[:, 0].reshape(len(X), 1))
 
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = chemprop.args.PredictArgs().parse_args(arguments)
                 if uncertainty_method == "dropout":
                     model_objects = list(chemprop.train.load_model(args=args))
@@ -512,7 +517,7 @@ def interpret(self, X, prop_delta=0.75):
                 X = pd.DataFrame(X, columns=["smiles"])
                 X.to_csv(data_path.name, index=False)
                 args = chemprop.args.InterpretArgs().parse_args(intrprt_args)
-                with CaptureStdOut() as intrprt:
+                with CaptureStdOutErr() as intrprt:
                     interpret(args=args)
         intrprt = [
             line.split(",")
@@ -560,7 +565,7 @@ def chemprop_fingerprint(self, X, fingerprint_type="MPN"):
             # if self.x_aux_ is not None:
             # fprnt_args += ["--features_path", f"{x_aux_path.name}"] TODO: allow features once ChemProp is updated
             # load_model returns pred&train arguments, object models & tasks info - but we only need TrainArgs here
-            with CaptureStdOut() as _:
+            with CaptureStdOutErr() as _:
                 args = chemprop.args.FingerprintArgs().parse_args(fprnt_args)
                 _, trainargs, _, _, _, _ = chemprop.train.load_model(args=args)
                 if fingerprint_type == "MPN":

optunaz/builder.py

@@ -17,8 +17,27 @@ def build(
     estimator = buildconfig.algorithm.estimator()
     if merge_train_and_test_data:
         train_smiles, train_y, train_aux = buildconfig.data.get_merged_sets()
+        test_smiles, test_y, test_aux, test_X = None, None, None, None
     else:
-        train_smiles, train_y, train_aux, _, _, _ = buildconfig.data.get_sets()
+        (
+            train_smiles,
+            train_y,
+            train_aux,
+            test_smiles,
+            test_y,
+            test_aux,
+        ) = buildconfig.data.get_sets()
+        if test_smiles is not None and len(test_smiles) > 0:
+            test_X, failed_idx = descriptor_from_config(
+                test_smiles, buildconfig.descriptor, cache=cache
+            )
+            test_y, test_smiles, test_aux = remove_failed_idx(
+                failed_idx, test_y, test_smiles, test_aux
+            )
+            if test_aux is not None:
+                test_X = np.hstack((test_X, test_aux))
+        else:
+            test_X = None
 
     train_X, failed_idx = descriptor_from_config(
         train_smiles, buildconfig.descriptor, cache=cache
@@ -35,13 +54,20 @@ def build(
     estimator.X_ = train_X
     estimator.y_ = train_y
     estimator.aux_ = train_aux
+    estimator.test_smiles_ = test_smiles
+    estimator.test_X_ = test_X
+    estimator.test_y_ = test_y
+    estimator.test_aux_ = test_aux
 
-    if merge_train_and_test_data:
-        train_scores = get_merged_train_score(estimator, buildconfig, cache=cache)
-        test_scores = None
-    else:
+    if (
+        not merge_train_and_test_data
+        and test_smiles is not None
+        and len(test_smiles) > 0
+    ):
         train_scores, test_scores = get_train_test_scores(
-            estimator, buildconfig, cache=cache
+            estimator, buildconfig, train_X, train_y, test_X, test_y
         )
-
+    else:
+        train_scores = get_merged_train_score(estimator, buildconfig, train_X, train_y)
+        test_scores = None
     return estimator, train_scores, test_scores

optunaz/config/buildconfig.py

@@ -42,8 +42,8 @@ def estimator(self) -> BaseEstimator:
 class AdaBoostClassifier(Algorithm):
     @dataclass
     class AdaBoostClassifierParameters:
-        n_estimators: int = field(metadata=schema(min=1))
-        learning_rate: float = field(metadata=schema(min=0.0001))
+        n_estimators: int = field(default=1, metadata=schema(min=1))
+        learning_rate: float = field(default=0.1, metadata=schema(min=0.0001))
 
     name: Literal["AdaBoostClassifier"]
     parameters: AdaBoostClassifierParameters
@@ -116,7 +116,7 @@ class LogisticRegression(Algorithm):
     @dataclass
     class LogisticRegressionParameters:
         solver: str
-        C: float = field(metadata=schema(min=0.001, max=1000))
+        C: float = field(default=1.0, metadata=schema(min=0.001, max=1000))
 
     name: Literal["LogisticRegression"]
     parameters: LogisticRegressionParameters
@@ -137,7 +137,7 @@ def estimator(self):
 class PLSRegression(Algorithm):
     @dataclass
     class PLSParameters:
-        n_components: int = field(metadata=schema(min=1))
+        n_components: int = field(default=2, metadata=schema(min=1))
 
     name: Literal["PLSRegression"]
     parameters: PLSParameters
@@ -152,9 +152,9 @@ def estimator(self):
 class RandomForestClassifier(Algorithm):
     @dataclass
     class RandomForestParameters:
-        max_depth: int = field(metadata=schema(min=1))
-        n_estimators: int = field(metadata=schema(min=1))
         max_features: str
+        max_depth: int = field(default=None, metadata=schema(min=1))
+        n_estimators: int = field(default=100, metadata=schema(min=1))
 
     name: Literal["RandomForestClassifier"]
     parameters: RandomForestParameters

optunaz/descriptors.py

@@ -33,7 +33,6 @@
 
 from rdkit.ML.Descriptors.MoleculeDescriptors import MolecularDescriptorCalculator
 from jazzy.api import molecular_vector_from_smiles
-from jazzy.exception import JazzyError
 from sklearn import preprocessing
 from joblib import Parallel, delayed, effective_n_jobs
 from optunaz.config import NameParameterDataclass