fix(all): Multiple minor fixes

bin/hello_world.py

@@ -3,22 +3,20 @@
 Uses the main libraries to verify the environment installation.
 """
 
-import sys
-
+from datetime import datetime
 import matplotlib.pyplot as plt
 import numpy as np
-# import pydensecrf.densecrf as crf
 import pymia.evaluation.evaluator as pymia_eval
 import SimpleITK as sitk
 import sklearn.ensemble as sk_ensemble
 
 
 def main():
 
-    print('Welcome to MIALab 2020!')
+    print(f'Welcome to MIALab {datetime.now().year}!')
 
     # --- scikit-learn
-    clf = sk_ensemble.RandomForestClassifier(max_depth=2, random_state=0)
+    sk_ensemble.RandomForestClassifier(max_depth=2, random_state=0)
 
     # --- SimpleITK
     image = sitk.Image(256, 128, 64, sitk.sitkInt16)
@@ -36,11 +34,8 @@ def main():
 
     plt.show()
 
-    # --- pydensecrf
-    # d = crf.DenseCRF(1000, 2)
-
     # --- pymia
-    eval_ = pymia_eval.SegmentationEvaluator([], {})
+    pymia_eval.SegmentationEvaluator([], {})
 
     print('Everything seems to work fine!')
 

bin/prepare_data.py

@@ -109,12 +109,12 @@ def join_and_check_path(file_id, file_names):
         return files
 
     subject_files = {}
-    subdirs = glob.glob(data_dir + '/*')
-    for subdir in subdirs:
-        if not os.path.isdir(subdir):
+    sub_dirs = glob.glob(data_dir + '/*')
+    for sub_dir in sub_dirs:
+        if not os.path.isdir(sub_dir):
             continue
 
-        id_ = os.path.basename(subdir)
+        id_ = os.path.basename(sub_dir)
 
         image_files = join_and_check_path(id_, image_names)
         label_files = join_and_check_path(id_, label_names)
@@ -138,14 +138,14 @@ def split_dataset(train_split, subject_files):
     return train_subject, test_subject
 
 
-def transform_and_write(subject_files, image_tranform, label_transform, out_dir):
+def transform_and_write(subject_files, image_transform, label_transform, out_dir):
 
     for id_, subject_file in subject_files.items():
         print(' - {}'.format(id_))
 
         for in_image_file, out_image_file in subject_file['images']:
             image = sitk.ReadImage(in_image_file, sitk.sitkUInt16)
-            transformed_image = image_tranform(image)
+            transformed_image = image_transform(image)
             out_image_path = os.path.join(out_dir, out_image_file)
             if not os.path.exists(os.path.dirname(out_image_path)):
                 os.makedirs(os.path.dirname(out_image_path))
@@ -225,7 +225,8 @@ def __call__(self, img: sitk.Image) -> sitk.Image:
         merged_img = np.zeros_like(np_img)
 
         for new_label, labels_to_merge in self.to_combine.items():
-            merged_img[np.in1d(np_img.ravel(), labels_to_merge, assume_unique=True).reshape(np_img.shape)] = new_label
+            indices = np.reshape(np.in1d(np_img.ravel(), labels_to_merge, assume_unique=True), np_img.shape)
+            merged_img[indices] = new_label
 
         out_img = sitk.GetImageFromArray(merged_img)
         out_img.CopyInformation(img)

bin/toy_example.py

@@ -120,7 +120,8 @@ def get_test_data(grid_size: int):
 
         rng = np.linspace(0, grid_size - 1, grid_size)
         grid = np.meshgrid(rng, rng)
-        return np.append(grid[0].reshape(-1, 1), grid[1].reshape(-1, 1), axis=1).astype(np.float32, copy=False)
+        return np.append(np.reshape(grid[0], (-1, 1)),
+                         np.reshape(grid[1], (-1, 1)), axis=1).astype(np.float32, copy=False)
 
     @staticmethod
     def get_test_data_with_label(grid_size: int):
@@ -240,7 +241,6 @@ def main(result_dir: str, input_file: str):
 
     # apply the forest to test data
     print('Decision forest testing...')
-    predictions = forest.predict(test_data)
     probabilities = forest.predict_proba(test_data)
 
     # let's have a look at the feature importance

mialab/filtering/postprocessing.py

@@ -51,12 +51,12 @@ def __str__(self):
 #
 #         Args:
 #             img_t1 (sitk.Image): The T1-weighted image.
-#             img_t2 (sitk.Image): The T2-weigthed image.
-#             img_proba (sitk.Image): The posterior probability image.
+#             img_t2 (sitk.Image): The T2-weighted image.
+#             img_probability (sitk.Image): The posterior probability image.
 #         """
 #         self.img_t1 = img_t1
 #         self.img_t2 = img_t2
-#         self.img_proba = img_proba
+#         self.img_probability = img_probability
 #
 #
 # class DenseCRF(pymia_fltr.Filter):
@@ -86,25 +86,25 @@ def __str__(self):
 #
 #         img_t2 = sitk.GetArrayFromImage(params.img_t1)
 #         img_ir = sitk.GetArrayFromImage(params.img_t2)
-#         img_proba = sitk.GetArrayFromImage(params.img_proba)
+#         img_probability = sitk.GetArrayFromImage(params.img_probability)
 #
 #         # some variables
-#         x = img_proba.shape[2]
-#         y = img_proba.shape[1]
-#         z = img_proba.shape[0]
-#         no_labels = img_proba.shape[3]
+#         x = img_probability.shape[2]
+#         y = img_probability.shape[1]
+#         z = img_probability.shape[0]
+#         no_labels = img_probability.shape[3]
 #
-#         img_proba = np.rollaxis(img_proba, 3, 0)
+#         img_probability = np.rollaxis(img_probability, 3, 0)
 #
 #         d = crf.DenseCRF(x * y * z, no_labels)  # width, height, nlabels
-#         U = crf_util.unary_from_softmax(img_proba)
+#         U = crf_util.unary_from_softmax(img_probability)
 #         d.setUnaryEnergy(U)
 #
 #         stack = np.stack([img_t2, img_ir], axis=3)
 #
 #         # Create the pairwise bilateral term from the above images.
 #         # The two `s{dims,chan}` parameters are model hyper-parameters defining
-#         # the strength of the location and image content bilaterals, respectively.
+#         # the strength of the location and image content bi-laterals, respectively.
 #
 #         # higher weight equals stronger
 #         pairwise_energy = crf_util.create_pairwise_bilateral(sdims=(1, 1, 1), schan=(1, 1), img=stack, chdim=3)

mialab/utilities/file_access_utilities.py

@@ -146,7 +146,7 @@ class FileSystemDataCrawler:
         >>>
         >>> class MyFilePathGenerator(FilePathGenerator):
         >>>     @staticmethod
-        >>>     def get_full_file_path(id_: str, root_dir: str, file_key, file_extension: str) -> str:
+        >>>     def get_full_file_path(_id: str, root_dir: str, file_key, file_extension: str) -> str:
         >>>         if file_key == MyImgType.T1:
         >>>             file_name = 'Image'
         >>>         elif file_key == MyImgType.GroundTruth: