fastMONAI 0.3.1__py3-none-any.whl → 0.3.3__py3-none-any.whl

fastMONAI/__init__.py

@@ -1 +1 @@
-__version__ = "0.3.1"
+__version__ = "0.3.3"

fastMONAI/_modidx.py

@@ -29,16 +29,18 @@ d = { 'settings': { 'branch': 'master',
                                                                                                'fastMONAI/external_data.py'),
                                          'fastMONAI.external_data._process_ixi_xls': ( 'external_data.html#_process_ixi_xls',
                                                                                        'fastMONAI/external_data.py'),
-                                         'fastMONAI.external_data._process_nodule_img': ( 'external_data.html#_process_nodule_img',
-                                                                                          'fastMONAI/external_data.py'),
-                                         'fastMONAI.external_data.download_NoduleMNIST3D': ( 'external_data.html#download_nodulemnist3d',
-                                                                                             'fastMONAI/external_data.py'),
+                                         'fastMONAI.external_data._process_medmnist_img': ( 'external_data.html#_process_medmnist_img',
+                                                                                            'fastMONAI/external_data.py'),
+                                         'fastMONAI.external_data.download_example_endometrial_cancer_data': ( 'external_data.html#download_example_endometrial_cancer_data',
+                                                                                                               'fastMONAI/external_data.py'),
                                          'fastMONAI.external_data.download_example_spine_data': ( 'external_data.html#download_example_spine_data',
                                                                                                   'fastMONAI/external_data.py'),
                                          'fastMONAI.external_data.download_ixi_data': ( 'external_data.html#download_ixi_data',
                                                                                         'fastMONAI/external_data.py'),
                                          'fastMONAI.external_data.download_ixi_tiny': ( 'external_data.html#download_ixi_tiny',
                                                                                         'fastMONAI/external_data.py'),
+                                         'fastMONAI.external_data.download_medmnist3d_dataset': ( 'external_data.html#download_medmnist3d_dataset',
+                                                                                                  'fastMONAI/external_data.py'),
                                          'fastMONAI.external_data.download_spine_test_data': ( 'external_data.html#download_spine_test_data',
                                                                                                'fastMONAI/external_data.py')},
             'fastMONAI.research_utils': { 'fastMONAI.research_utils.pred_postprocess': ( 'research_utils.html#pred_postprocess',
@@ -131,22 +133,6 @@ d = { 'settings': { 'branch': 'master',
                                                                                                           'fastMONAI/vision_augmentation.py'),
                                                'fastMONAI.vision_augmentation.ZNormalization.encodes': ( 'vision_augment.html#znormalization.encodes',
                                                                                                          'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_biasfield': ( 'vision_augment.html#_do_rand_biasfield',
-                                                                                                     'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_blur': ( 'vision_augment.html#_do_rand_blur',
-                                                                                                'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_gamma': ( 'vision_augment.html#_do_rand_gamma',
-                                                                                                 'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_ghosting': ( 'vision_augment.html#_do_rand_ghosting',
-                                                                                                    'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_motion': ( 'vision_augment.html#_do_rand_motion',
-                                                                                                  'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_noise': ( 'vision_augment.html#_do_rand_noise',
-                                                                                                 'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_rand_spike': ( 'vision_augment.html#_do_rand_spike',
-                                                                                                 'fastMONAI/vision_augmentation.py'),
-                                               'fastMONAI.vision_augmentation._do_z_normalization': ( 'vision_augment.html#_do_z_normalization',
-                                                                                                      'fastMONAI/vision_augmentation.py'),
                                                'fastMONAI.vision_augmentation.do_pad_or_crop': ( 'vision_augment.html#do_pad_or_crop',
                                                                                                  'fastMONAI/vision_augmentation.py')},
             'fastMONAI.vision_core': { 'fastMONAI.vision_core.MedBase': ('vision_core.html#medbase', 'fastMONAI/vision_core.py'),

fastMONAI/dataset_info.py

@@ -14,18 +14,23 @@ import torch
 import glob
 
 # %% ../nbs/08_dataset_info.ipynb 4
-class MedDataset():
-    '''A class to extract and present information about the dataset.'''
-
-    def __init__(self, path=None, # Path to the image folder
-                 postfix:str='', # Specify the file type if there are different files in the folder
-                 img_list:list=None, # Alternatively pass in a list with image paths
-                 reorder:bool=False, # Whether to reorder the data to be closest to canonical (RAS+) orientation
-                 dtype:(MedImage, MedMask)=MedImage, # Load data as datatype
-                 max_workers:int=1 #  The number of worker threads
-                ):
-        '''Constructs all the necessary attributes for the MedDataset object.'''
+class MedDataset:
+    """A class to extract and present information about the dataset."""
 
+    def __init__(self, path=None, postfix: str = '', img_list: list = None,
+                 reorder: bool = False, dtype: (MedImage, MedMask) = MedImage,
+                 max_workers: int = 1):
+        """Constructs MedDataset object.
+
+        Args:
+            path (str, optional): Path to the image folder.
+            postfix (str, optional): Specify the file type if there are different files in the folder.
+            img_list (List[str], optional): Alternatively, pass in a list with image paths.
+            reorder (bool, optional): Whether to reorder the data to be closest to canonical (RAS+) orientation.
+            dtype (Union[MedImage, MedMask], optional): Load data as datatype. Default is MedImage.
+            max_workers (int, optional): The number of worker threads. Default is 1.
+        """
+                     
         self.path = path
         self.postfix = postfix
         self.img_list = img_list
@@ -35,48 +40,43 @@ class MedDataset():
         self.df = self._create_data_frame()
 
     def _create_data_frame(self):
-        '''Private method that returns a dataframe with information about the dataset
-
-        Returns:
-            DataFrame: A DataFrame with information about the dataset.
-        '''
+        """Private method that returns a dataframe with information about the dataset."""
 
         if self.path:
             self.img_list = glob.glob(f'{self.path}/*{self.postfix}*')
             if not self.img_list: print('Could not find images. Check the image path')
-        
+
         with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
             data_info_dict = list(executor.map(self._get_data_info, self.img_list))
-        
+
         df = pd.DataFrame(data_info_dict)
-        if df.orientation.nunique() > 1: print('The volumes in this dataset have different orientations. Recommended to pass in the argument reorder=True when creating a MedDataset object for this dataset')
+        
+        if df.orientation.nunique() > 1:
+            print('The volumes in this dataset have different orientations. '
+                  'Recommended to pass in the argument reorder=True when creating a MedDataset object for this dataset')
+
         return df
 
     def summary(self):
-        '''Summary DataFrame of the dataset with example path for similar data.'''
-
+        """Summary DataFrame of the dataset with example path for similar data."""
+        
         columns = ['dim_0', 'dim_1', 'dim_2', 'voxel_0', 'voxel_1', 'voxel_2', 'orientation']
-        return self.df.groupby(columns,as_index=False).agg(example_path=('path', 'min'), total=('path', 'size')).sort_values('total', ascending=False)
+        
+        return self.df.groupby(columns, as_index=False).agg(
+            example_path=('path', 'min'), total=('path', 'size')
+        ).sort_values('total', ascending=False)
 
     def suggestion(self):
-        '''Voxel value that appears most often in dim_0, dim_1 and dim_2, and wheter the data should be reoriented.'''
+        """Voxel value that appears most often in dim_0, dim_1 and dim_2, and whether the data should be reoriented."""
+        
         resample = [self.df.voxel_0.mode()[0], self.df.voxel_1.mode()[0], self.df.voxel_2.mode()[0]]
-
         return resample, self.reorder
 
-    def _get_data_info(self, fn:str):
-        '''Private method to collect information about an image file.
+    def _get_data_info(self, fn: str):
+        """Private method to collect information about an image file."""
+        _, o, _ = med_img_reader(fn, dtype=self.dtype, reorder=self.reorder, only_tensor=False)
 
-        Args:
-            fn: Image file path.
-
-        Returns:
-            dict: A dictionary with information about the image file
-        '''
-
-        _,o,_ = med_img_reader(fn, dtype=self.dtype, reorder=self.reorder, only_tensor=False)
-
-        info_dict = {'path': fn,  'dim_0': o.shape[1],  'dim_1': o.shape[2],  'dim_2' :o.shape[3],
+        info_dict = {'path': fn, 'dim_0': o.shape[1], 'dim_1': o.shape[2], 'dim_2': o.shape[3],
                      'voxel_0': round(o.spacing[0], 4), 'voxel_1': round(o.spacing[1], 4), 'voxel_2': round(o.spacing[2], 4),
                      'orientation': f'{"".join(o.orientation)}+'}
 
@@ -87,28 +87,36 @@ class MedDataset():
 
         return info_dict
 
-    def get_largest_img_size(self,
-                             resample:list=None # A list with voxel spacing [dim_0, dim_1, dim_2]
-                            ) -> list:
-        '''Get the largest image size in the dataset.'''
-        dims = None 
+    def get_largest_img_size(self, resample: list = None) -> list:
+        """Get the largest image size in the dataset."""
         
-        if resample is not None: 
-            
+        dims = None
+
+        if resample is not None:
             org_voxels = self.df[["voxel_0", "voxel_1", 'voxel_2']].values
             org_dims = self.df[["dim_0", "dim_1", 'dim_2']].values
-            
+
             ratio = org_voxels/resample
             new_dims = (org_dims * ratio).T
             dims = [new_dims[0].max().round(), new_dims[1].max().round(), new_dims[2].max().round()]
-        
-        else: dims = [df.dim_0.max(), df.dim_1.max(), df.dim_2.max()]
-        
+
+        else:
+            dims = [df.dim_0.max(), df.dim_1.max(), df.dim_2.max()]
+
         return dims
 
 # %% ../nbs/08_dataset_info.ipynb 5
-def get_class_weights(train_labels:(np.array, list), class_weight='balanced'): 
-    '''calculate class weights.'''
+def get_class_weights(labels: (np.array, list), class_weight: str = 'balanced') -> torch.Tensor: 
+    """Calculates and returns the class weights.
+
+    Args:
+        labels: An array or list of class labels for each instance in the dataset.
+        class_weight: Defaults to 'balanced'.
+
+    Returns:
+        A tensor of class weights.
+    """
+    
+    class_weights =  compute_class_weight(class_weight=class_weight, classes=np.unique(labels), y=labels)
     
-    class_weights =  compute_class_weight(class_weight=class_weight, classes=np.unique(train_labels), y=train_labels)
     return torch.Tensor(class_weights)

fastMONAI/external_data.py

@@ -2,9 +2,9 @@
 
 # %% auto 0
 __all__ = ['MURLs', 'download_ixi_data', 'download_ixi_tiny', 'download_spine_test_data', 'download_example_spine_data',
-           'download_NoduleMNIST3D']
+           'download_medmnist3d_dataset', 'download_example_endometrial_cancer_data']
 
-# %% ../nbs/09_external_data.ipynb 2
+# %% ../nbs/09_external_data.ipynb 1
 from pathlib import Path
 from glob import glob
 from numpy import load 
@@ -15,27 +15,36 @@ from torchio import ScalarImage
 import multiprocessing as mp
 from functools import partial
 
-# %% ../nbs/09_external_data.ipynb 4
+# %% ../nbs/09_external_data.ipynb 3
 class MURLs():
-    '''A class with external medical dataset URLs.'''
+    """A class with external medical dataset URLs."""
 
     IXI_DATA = 'http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI-T1.tar'
     IXI_DEMOGRAPHIC_INFORMATION = 'http://biomedic.doc.ic.ac.uk/brain-development/downloads/IXI/IXI.xls'
     CHENGWEN_CHU_SPINE_DATA = 'https://drive.google.com/uc?id=1rbm9-KKAexpNm2mC9FsSbfnS8VJaF3Kn&confirm=t'
     EXAMPLE_SPINE_DATA = 'https://drive.google.com/uc?id=1Ms3Q6MYQrQUA_PKZbJ2t2NeYFQ5jloMh'
-    NODULE_MNIST_DATA = 'https://zenodo.org/record/6496656/files/nodulemnist3d.npz?download=1'
+    MEDMNIST_DICT = {'OrganMNIST3D': 'https://zenodo.org/record/6496656/files/organmnist3d.npz?download=1',	
+                     'NoduleMNIST3D': 'https://zenodo.org/record/6496656/files/nodulemnist3d.npz?download=1',
+                     'AdrenalMNIST3D': 'https://zenodo.org/record/6496656/files/adrenalmnist3d.npz?download=1',	
+                     'FractureMNIST3D': 'https://zenodo.org/record/6496656/files/fracturemnist3d.npz?download=1',
+                     'VesselMNIST3D': 'https://zenodo.org/record/6496656/files/vesselmnist3d.npz?download=1', 
+                     'SynapseMNIST3D': 'https://zenodo.org/record/6496656/files/synapsemnist3d.npz?download=1'}
+    EXAMPLE_EC_DATA = 'https://drive.google.com/uc?id=1cjOBhkdRsoX3unxHiL377R5j8ottN4An'
 
-# %% ../nbs/09_external_data.ipynb 5
-def _process_ixi_xls(xls_path:(str, Path), img_path: Path):
-    '''Private method to process the demographic information for the IXI dataset.
+# %% ../nbs/09_external_data.ipynb 4
+def _process_ixi_xls(xls_path: (str, Path), img_path: Path) -> pd.DataFrame:
+    """Private method to process the demographic information for the IXI dataset.
 
     Args:
         xls_path: File path to the xls file with the demographic information.
-        img_path: Folder path to the images
+        img_path: Folder path to the images.
 
     Returns:
-        DataFrame: A processed dataframe with image path and demographic information.
-    '''
+        A processed dataframe with image path and demographic information.
+
+    Raises:
+        ValueError: If xls_path or img_path do not exist.
+    """
 
     print('Preprocessing ' + str(xls_path))
 
@@ -45,14 +54,14 @@ def _process_ixi_xls(xls_path:(str, Path), img_path: Path):
 
     for subject_id in duplicate_subject_ids:
         age = df.loc[df.IXI_ID == subject_id].AGE.nunique()
-        if age != 1: df = df.loc[df.IXI_ID != subject_id] #Remove duplicates with two different age values
+        if age != 1: df = df.loc[df.IXI_ID != subject_id]  # Remove duplicates with two different age values
 
     df = df.drop_duplicates(subset='IXI_ID', keep='first').reset_index(drop=True)
 
     df['subject_id'] = ['IXI' + str(subject_id).zfill(3) for subject_id in df.IXI_ID.values]
     df = df.rename(columns={'SEX_ID (1=m, 2=f)': 'gender'})
     df['age_at_scan'] = df.AGE.round(2)
-    df = df.replace({'gender': {1:'M', 2:'F'}})
+    df = df.replace({'gender': {1: 'M', 2: 'F'}})
 
     img_list = list(img_path.glob('*.nii.gz'))
     for path in img_list:
@@ -61,50 +70,58 @@ def _process_ixi_xls(xls_path:(str, Path), img_path: Path):
 
     df = df.dropna()
     df = df[['t1_path', 'subject_id', 'gender', 'age_at_scan']]
+    
     return df
 
-# %% ../nbs/09_external_data.ipynb 7
-def download_ixi_data(path:(str, Path)='../data' # Path to the directory where the data will be stored
-                     ):
-    '''Download T1 scans and demographic information from the IXI dataset, then process the demographic 
-        information for each subject and save the information as a CSV file.
-    Returns path to the stored CSV file.
-    '''
-    path = Path(path)/'IXI'
-    img_path = path/'T1_images' 
+# %% ../nbs/09_external_data.ipynb 6
+def download_ixi_data(path: (str, Path) = '../data') -> Path:
+    """Download T1 scans and demographic information from the IXI dataset.
+    
+    Args:
+        path: Path to the directory where the data will be stored. Defaults to '../data'.
+
+    Returns:
+        The path to the stored CSV file.
+    """
+
+    path = Path(path) / 'IXI'
+    img_path = path / 'T1_images'
 
     # Check whether image data already present in img_path:
-    is_extracted=False
+    is_extracted = False
     try:
-        if len(list(img_path.iterdir())) >= 581: # 581 imgs in the IXI dataset
-            is_extracted=True
+        if len(list(img_path.iterdir())) >= 581:  # 581 imgs in the IXI dataset
+            is_extracted = True
             print(f"Images already downloaded and extracted to {img_path}")
     except:
-        is_extracted=False
-
-    # Download and extract images
-    if not is_extracted: 
-        download_and_extract(url=MURLs.IXI_DATA, filepath=path/'IXI-T1.tar', output_dir=img_path)
-        (path/'IXI-T1.tar').unlink()
+        is_extracted = False
 
+    if not is_extracted:
+        download_and_extract(url=MURLs.IXI_DATA, filepath=path / 'IXI-T1.tar', output_dir=img_path)
+        (path / 'IXI-T1.tar').unlink()
 
-    # Download demographic info
-    download_url(url=MURLs.IXI_DEMOGRAPHIC_INFORMATION, filepath=path/'IXI.xls')
+    download_url(url=MURLs.IXI_DEMOGRAPHIC_INFORMATION, filepath=path / 'IXI.xls')
 
-    processed_df = _process_ixi_xls(xls_path=path/'IXI.xls', img_path=img_path)
-    processed_df.to_csv(path/'dataset.csv',index=False)
+    processed_df = _process_ixi_xls(xls_path=path / 'IXI.xls', img_path=img_path)
+    processed_df.to_csv(path / 'dataset.csv', index=False)
 
     return path
 
-# %% ../nbs/09_external_data.ipynb 9
-def download_ixi_tiny(path:(str, Path)='../data'):
-    ''' Download tiny version of IXI provided by TorchIO, containing 566 T1 brain MR scans and their corresponding brain segmentations.'''
+# %% ../nbs/09_external_data.ipynb 8
+def download_ixi_tiny(path: (str, Path) = '../data') -> Path:
+    """Download the tiny version of the IXI dataset provided by TorchIO.
+
+    Args:
+        path: The directory where the data will be 
+            stored. If not provided, defaults to '../data'.
+
+    Returns:
+        The path to the directory where the data is stored.
+    """
     
-    path = Path(path)/'IXITiny'
+    path = Path(path) / 'IXITiny'
     
-    #Download MR scans and segmentation masks
     IXITiny(root=str(path), download=True)
-    # Download demographic info
     download_url(url=MURLs.IXI_DEMOGRAPHIC_INFORMATION, filepath=path/'IXI.xls')
     
     processed_df = _process_ixi_xls(xls_path=path/'IXI.xls', img_path=path/'image')
@@ -115,96 +132,169 @@ def download_ixi_tiny(path:(str, Path)='../data'):
     return path
 
 # %% ../nbs/09_external_data.ipynb 10
-def _create_spine_df(test_dir:Path):
-    # Get a list of the image files in the 'img' directory
-    img_list = glob(str(test_dir/'img/*.nii.gz'))
+def _create_spine_df(dir: Path) -> pd.DataFrame:
+    """Create a pandas DataFrame containing information about spinal images.
 
-    # Create a list of the corresponding mask files in the 'seg' directory
-    mask_list = [str(fn).replace('img', 'seg') for fn in img_list]
+    Args:
+        dir: Directory path where data (image and segmentation 
+            mask files) are stored.
 
-    # Create a list of the subject IDs for each image file
+    Returns:
+         A DataFrame containing the paths to the image files and their 
+            corresponding mask files, the subject IDs, and a flag indicating that 
+            these are test data.
+    """
+    
+    img_list = glob(str(dir / 'img/*.nii.gz'))
+    mask_list = [str(fn).replace('img', 'seg') for fn in img_list]
     subject_id_list = [fn.split('_')[-1].split('.')[0] for fn in mask_list]
     
-    # Create a dictionary containing the test data
-    test_data = {'t2_img_path':img_list, 't2_mask_path':mask_list, 'subject_id':subject_id_list, 'is_test':True}
+    test_data = {
+        't2_img_path': img_list,
+        't2_mask_path': mask_list,
+        'subject_id': subject_id_list,
+        'is_test': True,
+    }
 
-    # Create a DataFrame from the example data dictionary
     return pd.DataFrame(test_data)
 
-# %% ../nbs/09_external_data.ipynb 12
-def download_spine_test_data(path:(str, Path)='../data'):
+# %% ../nbs/09_external_data.ipynb 11
+def download_spine_test_data(path: (str, Path) = '../data') -> pd.DataFrame:
+    """Downloads T2w scans from the study 'Fully Automatic Localization and 
+    Segmentation of 3D Vertebral Bodies from CT/MR Images via a Learning-Based 
+    Method' by Chu et. al. 
+
+    Args:
+        path: Directory where the downloaded data 
+            will be stored and extracted. Defaults to '../data'.
+
+    Returns:
+        Processed dataframe containing image paths, label paths, and subject IDs.
+    """
     
-    ''' Download T2w scans from 'Fully Automatic Localization and Segmentation of 3D Vertebral Bodies from CT/MR Images via a Learning-Based Method' study by Chu et. al. 
-    Returns a processed dataframe with image path, label path and subject IDs. 
-    '''
     study = 'chengwen_chu_2015'
     
-    download_and_extract(url=MURLs.CHENGWEN_CHU_SPINE_DATA, filepath=f'{study}.zip', output_dir=path)
+    download_and_extract(
+        url=MURLs.CHENGWEN_CHU_SPINE_DATA, 
+        filepath=f'{study}.zip', 
+        output_dir=path
+    )
     Path(f'{study}.zip').unlink()
     
-    return _create_spine_df(Path(path)/study)
+    return _create_spine_df(Path(path) / study)
 
-# %% ../nbs/09_external_data.ipynb 13
-def download_example_spine_data(path:(str, Path)='../data'): 
+# %% ../nbs/09_external_data.ipynb 12
+def download_example_spine_data(path: (str, Path) = '../data') -> Path:
+    """Downloads example T2w scan and corresponding predicted mask.
+    
+    Args:
+        path: Directory where the downloaded data 
+            will be stored and extracted. Defaults to '../data'.
+
+    Returns:
+        Path to the directory where the example data has been extracted.
+    """
     
-    '''Download example T2w scan and predicted mask.'''
     study = 'example_data'
     
-    download_and_extract(url=MURLs.EXAMPLE_SPINE_DATA, filepath='example_data.zip', output_dir=path);
+    download_and_extract(
+        url=MURLs.EXAMPLE_SPINE_DATA, 
+        filepath='example_data.zip', 
+        output_dir=path
+    )
     Path('example_data.zip').unlink()
     
-    return Path(path/study)
+    return Path(path) / study
 
-# %% ../nbs/09_external_data.ipynb 15
-def _process_nodule_img(path, idx_arr):
-    '''Save tensor as NIfTI.'''
+# %% ../nbs/09_external_data.ipynb 14
+def _process_medmnist_img(path, idx_arr):
+    """Save tensor as NIfTI."""
+    
     idx, arr = idx_arr
     img = ScalarImage(tensor=arr[None, :])
     fn = path/f'{idx}_nodule.nii.gz'
     img.save(fn)
     return str(fn)
 
-# %% ../nbs/09_external_data.ipynb 16
+# %% ../nbs/09_external_data.ipynb 15
 def _df_sort_and_add_columns(df, label_list, is_val):
-    '''Sort the dataframe based on img_idx and add labels and if it is validation data column'''
+    """Sort the dataframe based on img_idx and add labels and if it is validation data column."""
+    
     df = df.sort_values(by='img_idx').reset_index(drop=True)
     df['labels'], df['is_val'] = label_list, is_val     
-    df = df.replace({"labels": {0:'b', 1:'m'}})
+    #df = df.replace({"labels": {0:'b', 1:'m'}})
     df = df.drop('img_idx', axis=1)
     
     return df 
 
-# %% ../nbs/09_external_data.ipynb 17
+# %% ../nbs/09_external_data.ipynb 16
 def _create_nodule_df(pool, output_dir, imgs, labels, is_val=False): 
-    '''Create dataframe for NoduleMNIST3D data.'''
-    img_path_list = pool.map(partial(_process_nodule_img, output_dir), enumerate(imgs))
+    """Create dataframe for MedMNIST data."""
+    
+    img_path_list = pool.map(partial(_process_medmnist_img, output_dir), enumerate(imgs))
     img_idx = [float(Path(fn).parts[-1].split('_')[0]) for fn in img_path_list]
     
     df = pd.DataFrame(list(zip(img_path_list, img_idx)), columns=['img_path','img_idx'])        
     return  _df_sort_and_add_columns(df, labels, is_val)
 
-# %% ../nbs/09_external_data.ipynb 18
-def download_NoduleMNIST3D(path:(str, Path)='../data', max_workers=1): 
-    
-    '''Download ....'''
-    study = 'NoduleMNIST3D'
-    path = Path(path)/study
-    
-    download_url(url=MURLs.NODULE_MNIST_DATA, filepath=path/f'{study}.npz');
-    data = load(path/f'{study}.npz')
-    key_fn = ['train_images', 'val_images', 'test_images']    
-    for fn in key_fn: (path/fn).mkdir(exist_ok=True)
-    
-    
-    train_imgs, val_imgs, test_imgs = data[key_fn[0]], data[key_fn[1]], data[key_fn[2]]
+# %% ../nbs/09_external_data.ipynb 17
+def download_medmnist3d_dataset(study: str, path: (str, Path) = '../data',
+                                max_workers: int = 1):
+    """Downloads and processes a particular MedMNIST3D dataset.
 
+    Args:
+        study: MedMNIST dataset ('OrganMNIST3D', 'NoduleMNIST3D', 
+               'AdrenalMNIST3D', 'FractureMNIST3D', 'VesselMNIST3D', 'SynapseMNIST3D')
+        path: Directory to store and extract downloaded data. Defaults to '../data'.
+        max_workers: Maximum number of worker processes for data processing. 
+                     Defaults to 1.
+
+    Returns:
+        Two pandas DataFrames. The first DataFrame combines training and validation 
+        data, and the second DataFrame contains the testing data.
+    """
+    path = Path(path) / study
+    dataset_file_path = path / f'{study}.npz'
+
+    try:
+        #todo: check if dataset is downloaded
+        download_url(url=MURLs.MEDMNIST_DICT[study], filepath=dataset_file_path)
+    except:
+        raise ValueError(f"Dataset '{study}' does not exist.")
+
+    data = load(dataset_file_path)
+    keys = ['train_images', 'val_images', 'test_images']
+
+    for key in keys:
+        (path / key).mkdir(exist_ok=True)
+
+    train_imgs = data[keys[0]]
+    val_imgs = data[keys[1]]
+    test_imgs = data[keys[2]]
 
     with mp.Pool(processes=max_workers) as pool:
-        
-        train_df = _create_nodule_df(pool, path/key_fn[0], train_imgs, data['train_labels'])
-        val_df = _create_nodule_df(pool, path/key_fn[1], val_imgs, data['val_labels'], is_val=True)
-        test_df = _create_nodule_df(pool, path/key_fn[2], test_imgs, data['test_labels'])
-        
+        train_df = _create_nodule_df(pool, path / keys[0], train_imgs, 
+                                     data['train_labels'])
+        val_df = _create_nodule_df(pool, path / keys[1], val_imgs, 
+                                   data['val_labels'], is_val=True)
+        test_df = _create_nodule_df(pool, path / keys[2], test_imgs, 
+                                    data['test_labels'])
+
     train_val_df = pd.concat([train_df, val_df], ignore_index=True)
-    
+
+    dataset_file_path.unlink()
+
     return train_val_df, test_df
+
+# %% ../nbs/09_external_data.ipynb 19
+def download_example_endometrial_cancer_data(path: (str, Path) = '../data') -> Path:
+    study = 'ec'
+    
+    download_and_extract(
+        url=MURLs.EXAMPLE_EC_DATA, 
+        filepath='ec.zip', 
+        output_dir=path
+    )
+    Path('ec.zip').unlink()
+    
+    return Path(path) / study

fastMONAI/utils.py

@@ -9,12 +9,8 @@ import torch
 from pathlib import Path
 
 # %% ../nbs/07_utils.ipynb 3
-def store_variables(pkl_fn:(str, Path),
-                    size:list,
-                    reorder:bool,
-                    resample:(int,list),
-                   ) -> None:
-    '''Save variable values in a pickle file.'''
+def store_variables(pkl_fn: (str, Path), size: list, reorder: bool, resample: (int, list)):
+    """Save variable values in a pickle file."""
     
     var_vals = [size, reorder, resample]
     
@@ -22,19 +18,21 @@ def store_variables(pkl_fn:(str, Path),
         pickle.dump(var_vals, f)
 
 # %% ../nbs/07_utils.ipynb 4
-def load_variables(pkl_fn # Filename of the pickle file
-                  ):
-    '''Load stored variable values from a pickle file.
+def load_variables(pkl_fn: (str, Path)):
+    """Loads stored variable values from a pickle file.
 
-    Returns: A list of variable values.
-    '''
+    Args:
+        pkl_fn: File path of the pickle file to be loaded.
 
+    Returns:
+        The deserialized value of the pickled data.
+    """
     with open(pkl_fn, 'rb') as f:
         return pickle.load(f)
 
 # %% ../nbs/07_utils.ipynb 5
 def print_colab_gpu_info(): 
-    '''Check if we have a GPU attached to the runtime.'''
+    """Check if we have a GPU attached to the runtime."""
     
     colab_gpu_msg =(f"{'#'*80}\n"
                     "Remember to attach a GPU to your Colab Runtime:"