[FIX] pipeline optimization paths fix + [FIX] predictions array shape…

… correction

setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = DeepMol
-version = 1.0.1
+version = 1.0.2
 description = DeepMol: a python-based machine and deep learning framework for drug discovery
 ;long_description = file: README.md
 keywords = machine-learning, deep-learning, cheminformatics, drug-discovery

src/deepmol/__init__.py

@@ -1,2 +1,2 @@
 
-__version__ = '0.0.6b0'
+__version__ = '1.0.2'

src/deepmol/models/deepchem_models.py

@@ -268,8 +268,13 @@ def predict_proba(self,
                 res)  # this works for all regression models (Keras and PyTorch) and is more general than the
             # commented code above
 
-        if not dataset.y.shape == np.array(new_res).shape:
+        if new_res.shape != (len(dataset.mols), dataset.n_tasks):
             new_res = normalize_labels_shape(new_res, dataset.n_tasks)
+
+        if len(new_res.shape) > 1:
+            if new_res.shape[1] == len(dataset.mols) and new_res.shape[0] == dataset.n_tasks:
+                new_res = new_res.T
+
         return new_res
 
     def predict_on_batch(self, dataset: Dataset) -> np.ndarray:

src/deepmol/models/keras_models.py

@@ -118,9 +118,6 @@ def predict(self, dataset: Dataset) -> np.ndarray:
           scikit-learn model has both methods, the value is always a return value of `predict_proba`.
         """
         predictions = self.predict_proba(dataset)
-        if not dataset.y.shape == np.array(predictions).shape:
-            predictions = normalize_labels_shape(predictions, dataset.n_tasks)
-
         y_pred_rounded = get_prediction_from_proba(dataset, predictions)
         return y_pred_rounded
 
@@ -146,9 +143,14 @@ def predict_proba(self, dataset: Dataset) -> np.ndarray:
             self.logger.info(str(type(self.model)))
             predictions = self.model.predict(dataset.X.astype('float32'))
 
-        if not dataset.y.shape == np.array(predictions).shape:
+        predictions = np.array(predictions)
+        if predictions.shape != (len(dataset.mols), dataset.n_tasks):
             predictions = normalize_labels_shape(predictions, dataset.n_tasks)
 
+        if len(predictions.shape) > 1:
+            if predictions.shape[1] == len(dataset.mols) and predictions.shape[0] == dataset.n_tasks:
+                predictions = predictions.T
+
         return predictions
 
     def predict_on_batch(self, dataset: Dataset) -> np.ndarray:

src/deepmol/models/sklearn_models.py

@@ -105,8 +105,9 @@ def predict(self, dataset: Dataset) -> np.ndarray:
         """
         predictions = self.model.predict(dataset.X)
 
-        if not dataset.y.shape == np.array(predictions).shape:
-            predictions = normalize_labels_shape(predictions, dataset.n_tasks)
+        if len(predictions.shape) > 1:
+            if predictions.shape != (len(dataset.mols), dataset.n_tasks):
+                predictions = normalize_labels_shape(predictions, dataset.n_tasks)
 
         return predictions
 
@@ -124,10 +125,13 @@ def predict_proba(self, dataset: Dataset) -> np.ndarray:
         np.ndarray
         """
         predictions = self.model.predict_proba(dataset.X)
-
-        if not dataset.y.shape == np.array(predictions).shape:
+        if predictions.shape != (len(dataset.mols), dataset.n_tasks):
             predictions = normalize_labels_shape(predictions, dataset.n_tasks)
 
+        if len(predictions.shape) > 1:
+            if predictions.shape != (len(dataset.mols), dataset.n_tasks):
+                predictions = normalize_labels_shape(predictions, dataset.n_tasks)
+
         return predictions
 
     def predict_on_batch(self, dataset: Dataset) -> np.ndarray:

src/deepmol/pipeline_optimization/objective_wrapper.py

@@ -44,7 +44,7 @@ def __init__(self, objective_steps, study, direction, train_dataset, test_datase
         self.test_dataset = test_dataset
         self.metric = metric
         self.save_top_n = save_top_n
-        self.save_dir = os.path.join(os.getcwd(), study.study_name)
+        self.save_dir = study.study_name
         self.kwargs = kwargs
 
     def __call__(self, trial: Trial):

src/deepmol/utils/utils.py

@@ -165,16 +165,22 @@ def normalize_labels_shape(y_pred: Union[List, np.ndarray], n_tasks: int) -> np.
     labels
         Array of predictions in the format [0, 1, 0, ...]/[[0, 1, 0, ...], [0, 1, 1, ...], ...]
     """
+    if not isinstance(y_pred, np.ndarray):
+        y_pred = np.array(y_pred)
+
     if n_tasks == 1:
         labels = _normalize_singletask_labels_shape(y_pred)
     else:
-        if isinstance(y_pred, np.ndarray):
-            if len(y_pred.shape) == 3:
-                y_pred = np.array([np.array([j[1] for j in i]) for i in y_pred]).T
+        if len(y_pred.shape) == 3:
+            if y_pred.shape[2] > 1:
+                y_pred = np.array([np.array([j[1] for j in i]) for i in y_pred])
+            else:
+                y_pred = y_pred.reshape(y_pred.shape[0], y_pred.shape[1])
         labels = []
         for task in y_pred:
             labels.append(_normalize_singletask_labels_shape(task))
-        labels = np.array(labels).T
+
+    labels = np.array(labels)
     return labels
 
 
@@ -196,6 +202,8 @@ def _normalize_singletask_labels_shape(y_pred: Union[List, np.ndarray]) -> np.nd
     # list of probabilities in the format [0.1, 0.9, 0.2, ...]
     if isinstance(y_pred[0], (np.floating, float)):
         return np.array(y_pred)
+    elif isinstance(y_pred[0], (np.integer, int)):
+        return np.array(y_pred)
     # list of lists of probabilities in the format [[0.1], [0.2], ...]
     elif len(y_pred[0]) == 1:
         return np.array([i[0] for i in y_pred])

tests/integration_tests/pipeline_optimization/test_pipeline_optimization.py

@@ -1,6 +1,6 @@
 import os
 import shutil
-from unittest import TestCase
+from unittest import TestCase, skip
 
 import optuna
 from sklearn.ensemble import RandomForestClassifier
@@ -10,6 +10,7 @@
 from deepmol.loaders import CSVLoader
 from deepmol.metrics import Metric
 from deepmol.models import SklearnModel
+from deepmol.pipeline import Pipeline
 from deepmol.pipeline_optimization import PipelineOptimization
 from deepmol.splitters import RandomSplitter
 
@@ -103,6 +104,11 @@ def objective(trial):
         df2 = po.trials_dataframe(cols=['number', 'value'])
         self.assertEqual(df2.shape, (5, 2))
 
+        best_pipeline = po.best_pipeline
+        new_predictions = best_pipeline.evaluate(test, [metric])[0][metric.name]
+        self.assertEqual(new_predictions, po.best_value)
+
+    @skip("This test is too slow to run on CI and can have different results on different trials")
     def test_classification_preset(self):
         storage_name = "sqlite:///test_pipeline.db"
         po = PipelineOptimization(direction='maximize', study_name='test_pipeline', storage=storage_name)
@@ -126,6 +132,7 @@ def test_classification_preset(self):
             for param in param_importance:
                 self.assertTrue(param in po.best_params.keys())
 
+    @skip("This test is too slow to run on CI and can have different results on different trials")
     def test_regression_preset(self):
         po = PipelineOptimization(direction='minimize', study_name='test_pipeline')
         metric = Metric(mean_squared_error)

tests/unit_tests/models/test_keras_model.py

@@ -1,6 +1,6 @@
 import os
 import shutil
-from unittest import TestCase
+from unittest import TestCase, skip
 
 import numpy as np
 from sklearn.metrics import roc_auc_score, precision_score, classification_report, accuracy_score, confusion_matrix
@@ -114,6 +114,7 @@ def test_baseline_models(self):
 
             shutil.rmtree("test_model")
 
+    @skip("This test is too slow for CI")
     def test_rnn_baseline_models(self):
         model_kwargs = {}
         keras_kwargs = {}