added helper function to list all available datasets

Author: ymahlich

coderdata/__init__.py

@@ -17,4 +17,5 @@
 except ImportError:
     __version_tuple__ = (0, 1, 40)
 
-from .utils.utils import version
+from .utils.utils import version
+from .utils.utils import list_datasets

coderdata/datasets.yml

@@ -0,0 +1,10 @@
+datasets:
+  beataml:
+    description: "Beat acute myeloid leukemia (BeatAML) focuses on acute myeloid leukemia tumor data. Data includes drug response, proteomics, and transcriptomics datasets."
+    doi: "https://doi.org/10.1016/j.ccell.2022.07.002"
+  cptac:
+    description: "The Clinical Proteomic Tumor Analysis Consortium (CPTAC) project is a collaborative network funded by the National Cancer Institute (NCI) focused on improving our understanding of cancer biology through the integration of transcriptomic, proteomic, and genomic data."
+  hcmi:
+    description: "Human Cancer Models Initiative (HCMI) encompasses numerous cancer types and includes cell line, organoid, and tumor data. Data includes the transcriptomics, somatic mutation, and copy number datasets."
+  mpnst:
+    description: "Malignant Peripheral Nerve Sheath Tumor is a rare, agressive sarcoma that affects peripheral nerves throughout the body."

coderdata/utils/__init__.py

@@ -1 +1,2 @@
-from .utils import version
+from .utils import version
+from .utils import list_datasets

coderdata/utils/utils.py

@@ -1,13 +1,53 @@
 """
 Collection of small utility and helper functions. 
 """
+
+from importlib import resources
+import yaml
+
 from .. import __version__
 from .. import __version_tuple__
 
-def version():
+
+def version() -> dict:
+    """
+    Helper function that returns the version strings for the package and
+    the dataset build.
+
+    Returns
+    -------
+    dict
+        Contains package and dataset build version.
+    """
     return {
         'package' : __version__,
         'dataset' : f"{__version_tuple__[0]}.{__version_tuple__[1]}"
         }
 
 
+def list_datasets(raw: bool=False) -> dict | None:
+    """
+    Hepler function that returns a list of available datasets including 
+    a short description and additional information available.
+
+    Parameters
+    ----------
+    raw : bool, default=False
+        If set to True returns a yaml dictionary containing all 
+        available datasets including additional information. If set to 
+        false prints information to stdout and returns None.
+
+    Returns
+    -------
+    dict | None
+        Returns a dict containing the information if ``raw==True``,
+        otherwise prints information to stdout and returns `None`.
+    """
+    with resources.open_text('coderdata', 'datasets.yml') as f:
+        datasets = yaml.load(f, Loader=yaml.FullLoader)
+    if raw:
+        return datasets
+    else:
+        datasets = datasets['datasets']
+        for dataset in datasets:
+            print(f'{dataset}: "{datasets[dataset]['description']}"')