radMLBench 1.0__tar.gz → 1.2__tar.gz

{radmlbench-1.0 → radmlbench-1.2}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: radMLBench
-Version: 1.0
+Version: 1.2
 Summary: A Python wrapper for the radMLBench data repository.
 Home-page: https://github.com/aydindemircioglu/radMLBench
 Author: Aydin Demircioglu
@@ -19,6 +19,18 @@ Requires-Dist: pyyaml>=5.2
 Requires-Dist: joblib>=0.12.0
 Requires-Dist: numpy>=1.18.0
 Requires-Dist: scikit-learn>=0.20.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 
 A Python wrapper for the radMLBench data repository.

{radmlbench-1.0 → radmlbench-1.2}/README.md

@@ -30,13 +30,13 @@ The complete list of datasets is
 | Dataset                     |   Year | Modality   |   #Instances |   #Features |   Dimensionality |   ClassBalance | DOI                                          |
 |:----------------------------|-------:|:-----------|-------------:|------------:|-----------------:|---------------:|:---------------------------------------------|
 | Ahn2021                     |   2021 | MRI        |          114 |         108 |             0.96 |             55 | https://doi.org/10.1016/j.ejrad.2019.108642  |
-| Arita2018                   |   2018 | MRI        |          168 |         684 |             4.08 |             66 | https://doi.org/10.1038/s41598-018-30273-4   |
+| Arita2018                   |   2018 | MRI        |          168 |         683 |             4.08 |             66 | https://doi.org/10.1038/s41598-018-30273-4   |
 | BraTS-2021                  |   2021 | MRI        |          577 |        4060 |             7.04 |             52 | https://doi.org/10.48550/arXiv.2107.02314    |
 | Brancato2023                |   2023 | MRI        |           58 |        2380 |            41.07 |             60 | https://doi.org/10.3390/jcm12010140          |
 | C4KC-KiTS                   |   2021 | CT         |           70 |         315 |             4.53 |             66 | https://doi.org/10.1016/j.media.2020.101821  |
 | Colorectal-Liver-Metastases |   2024 | CT         |           90 |         525 |             5.86 |             84 | https://doi.org/10.1038/s41597-024-02981-2   |
 | Dai2023                     |   2023 | CT         |          119 |         851 |             7.17 |             26 | https://doi.org/10.7717/peerj.16230          |
-| Deng2023                    |   2023 | MRI        |          261 |         224 |             0.87 |             36 | https://doi.org/10.1007/s13246-023-01300-0   |
+| Deng2023                    |   2023 | MRI        |          261 |         225 |             0.87 |             36 | https://doi.org/10.1007/s13246-023-01300-0   |
 | Dong2022                    |   2022 | CT         |          279 |         851 |             3.06 |             49 | https://doi.org/10.7717/peerj.14127          |
 | Fusco2022                   |   2022 | MRI        |           54 |         192 |             3.59 |             61 | https://doi.org/10.3390/curroncol29030159    |
 | Granata2021                 |   2021 | CT         |           88 |         580 |             6.61 |             47 | https://doi.org/10.3390/cancers13163992      |
@@ -124,6 +124,9 @@ contain the data and y the labels.
 The decorrelation example can be found in `examples/decorrelation`,
 to execute it, start `./examples/decorrelation/decorrelation.py`.
 
+**NOTE**: Due to size problems, it is not possible to upload the .csv result files to github for the time being. Thus, to recreate the results, please rerun the experiment.
+ 
+
 The other example, TabFPN, can be found in `examples/tebpfn`.
 However, before executing this, one must install TabFPN (which in turn
 will install things like torch). One must also execute TabFPN once
@@ -136,15 +139,11 @@ put downloadFirst to False again to execute the experiment.
 
 
 
-
 ## Citing radMLBench
 
 If you use radMLBench in a scientific publication, please consider citing the paper:
 
-Aydin Demircioglu.
-[radMLBench: A radiomics dataset collection for benchmarking in radiomics](TBD).
-_TBD_ (2024).
-
-(This will update as soon as the manuscript is submitted).
-
-```
+Aydin Demircioglu.  
+[radMLBench: A radiomics dataset collection for benchmarking in radiomics](https://doi.org/10.1016/j.compbiomed.2024.109140).  
+_Computers in Biology and Medicine_, Volume 182, 2024, 109140.  
+ISSN 0010-4825.

{radmlbench-1.0 → radmlbench-1.2}/radMLBench/metadata.yaml

@@ -26,7 +26,7 @@ Arita2018:
   dataset: Arita2018
   download_source: https://www.nature.com/articles/s41598-018-30273-4#Sec18
   modality: MRI
-  nFeatures: 684
+  nFeatures: 683
   nInstances: 168
   outcome: IDH mutation status
   pathology: Glioma
@@ -142,7 +142,7 @@ Deng2023:
   dataset: Deng2023
   download_source: https://github.com/BboyT/BM_NSCLC_subpathology
   modality: MRI
-  nFeatures: 224
+  nFeatures: 225
   nInstances: 261
   outcome: Pathological diagnosis
   pathology: NSCLC

{radmlbench-1.0 → radmlbench-1.2}/radMLBench/radMLBench.py

@@ -25,7 +25,12 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 import pandas as pd
 import numpy as np
 import os
-from pkg_resources import resource_filename
+
+try:
+    from importlib.resources import files
+except ImportError: # Python <3.9
+    from importlib_resources import files
+    
 import requests
 import warnings
 import subprocess
@@ -167,24 +172,16 @@ def getCVSplits(dataset, num_splits=10, num_repeats=10):
 
 def readMetaData ():
     """Internal. Reads metadata into variable"""
-    def read_yaml(file_path):
-        try:
-            with open(file_path, 'r') as stream:
-                data = yaml.safe_load(stream)
-                return data
-        except Exception as e:
-            print ('Unable to read metadata file for all dataset!')
-            print ('Error', e)
-            return None
-
     global metaData
     if metaData is None:
-        #print ("Reading metadata.")
-        package_dir = resource_filename('radMLBench', '')
-        metadata_path = os.path.join(package_dir, 'metadata.yaml')
-        metaData = read_yaml(metadata_path)
-    pass
-
+        try:
+            ref = files('radMLBench').joinpath('metadata.yaml')
+            with ref.open('r') as stream:
+                metaData = yaml.safe_load(stream)
+        except Exception as e:
+            print('Unable to read metadata file for all dataset!')
+            print('Error', e)
+            metaData = None
 
 
 

{radmlbench-1.0 → radmlbench-1.2}/radMLBench.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: radMLBench
-Version: 1.0
+Version: 1.2
 Summary: A Python wrapper for the radMLBench data repository.
 Home-page: https://github.com/aydindemircioglu/radMLBench
 Author: Aydin Demircioglu
@@ -19,6 +19,18 @@ Requires-Dist: pyyaml>=5.2
 Requires-Dist: joblib>=0.12.0
 Requires-Dist: numpy>=1.18.0
 Requires-Dist: scikit-learn>=0.20.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
 
 
 A Python wrapper for the radMLBench data repository.

{radmlbench-1.0 → radmlbench-1.2}/setup.py

@@ -5,11 +5,12 @@ from setuptools import setup, find_packages
 
 setup(
     name='radMLBench',
-    version='1.0',
+    version='1.2',
     author='Aydin Demircioglu',
     author_email=('aydin.demircioglu@uk-essen.de'),
     packages=find_packages(),
-    package_data={'radMLBench': ['./metadata.yaml']},
+    package_data={'radMLBench': ['metadata.yaml']},
+    python_required=">=3.9",
     include_package_data=True,
     url='https://github.com/aydindemircioglu/radMLBench',
     license="MIT",