nci-cidc-schemas 0.27.27__tar.gz → 0.28.0__tar.gz

{nci_cidc_schemas-0.27.27/nci_cidc_schemas.egg-info → nci_cidc_schemas-0.28.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.27
+Version: 0.28.0
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -12,23 +12,20 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3.9
-Requires-Python: >=3.9,<3.11
+Requires-Python: >=3.13,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: dateparser==1.1.4
-Requires-Dist: xlsxwriter==1.1.6
-Requires-Dist: argparse==1.1
-Requires-Dist: pyyaml==6.0.1
-Requires-Dist: jsonschema==3.0.1
-Requires-Dist: openpyxl==3.0.7
+Requires-Dist: argparse==1.4.0
+Requires-Dist: dateparser==1.2.2
+Requires-Dist: deepdiff==4.3.0
+Requires-Dist: jinja2==3.1.6
 Requires-Dist: jsonmerge==1.6.1
-Requires-Dist: deepdiff~=4.3.0
-Requires-Dist: jsonpointer==2.0
-Requires-Dist: pandas==1.5.3
-Requires-Dist: jinja2~=3.1.3
-Requires-Dist: nci-cidc-ngs-pipeline-api==0.1.25
-Requires-Dist: markupsafe==2.1.5
-Requires-Dist: regex==2022.3.2
+Requires-Dist: jsonpointer==3.0.0
+Requires-Dist: jsonschema==3.2.0
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: pandas==2.3.1
+Requires-Dist: pyyaml==6.0.2
+Requires-Dist: xlsxwriter==3.2.5
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -130,6 +127,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/README.md

@@ -86,6 +86,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/cidc_schemas/__init__.py

@@ -2,4 +2,4 @@
 
 __author__ = """NCI"""
 __email__ = "nci-cidc-tools-admin@mail.nih.gov"
-__version__ = "0.27.27"
+__version__ = "0.28.0"

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/cidc_schemas/json_validation.py

@@ -273,8 +273,7 @@ def _map_refs(node: dict, on_refs: Callable[[str], dict]) -> dict:
                     # So we raise on that, to notify schema creator that s/he should not
                     # expect those additional keys to be verified by schema validator.
                     raise Exception(
-                        f"Schema node with '$ref' should not contain anything else besides 'description' for public docs (or '$comment' for dev docs). \
-                        \nOn: {node} \nOffending keys {extra_keys}"
+                        f"Schema node with '$ref' should not contain anything else besides 'description' for public docs (or '$comment' for dev docs). \nOn: {node} \nOffending keys {extra_keys}"
                     )
 
             # We found a ref, so return it mapped through `on_refs`

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/cidc_schemas/prism/extra_metadata.py

@@ -98,7 +98,7 @@ def parse_npx(xlsx: BinaryIO) -> dict:
 
         # simplify.
         worksheet = workbook[worksheet_name]
-        seen_onlinkid = False
+        seen_id_column = False
         for i, row in enumerate(worksheet.iter_rows()):
 
             # extract values from row
@@ -110,8 +110,8 @@ def parse_npx(xlsx: BinaryIO) -> dict:
             if len(vals) == 0 or first_cell is None:
                 continue
 
-            # find OlinkID to locate the first data row
-            if not seen_onlinkid:
+            # find Cimac ID column to locate the first data row
+            if not seen_id_column:
                 # check that this is actually an NPX file
                 if i == 1 and first_cell != "NPX data":
                     raise ValueError("parse_npx got a file that is not in NPX format")
@@ -119,8 +119,10 @@ def parse_npx(xlsx: BinaryIO) -> dict:
                 # check if we are starting ids
                 # use this to capture cases where the column name changes in spacing / capitalization
                 ## needed because some data has 'OlinkID' while the standard seems to call for 'Olink ID'
-                if str(first_cell).lower().replace(" ", "") == "olinkid":
-                    seen_onlinkid = True
+                # Data is starting to come in with 'Sample ID' column instead - accepting that too
+                lower_first_cell = str(first_cell).lower().replace(" ", "")
+                if lower_first_cell in ["olinkid", "sampleid"]:
+                    seen_id_column = True
                     continue
 
             # once it's found keep getting ids until we're done

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/cidc_schemas/template.py

@@ -25,7 +25,7 @@ from .constants import ANALYSIS_TEMPLATE_DIR, SCHEMA_DIR, TEMPLATE_DIR
 from .json_validation import _load_dont_validate_schema
 from .util import get_file_ext, get_logger
 
-from cidc_ngs_pipeline_api import OUTPUT_APIS
+from .ngs_pipeline_api import OUTPUT_APIS
 
 logger = get_logger("cidc_schemas.template")
 

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0/nci_cidc_schemas.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nci_cidc_schemas
-Version: 0.27.27
+Version: 0.28.0
 Summary: The CIDC data model and tools for working with it.
 Home-page: https://github.com/NCI-CIDC/cidc-schemas
 Author: NCI
@@ -12,23 +12,20 @@ Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Natural Language :: English
 Classifier: Programming Language :: Python :: 3.9
-Requires-Python: >=3.9,<3.11
+Requires-Python: >=3.13,<3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: dateparser==1.1.4
-Requires-Dist: xlsxwriter==1.1.6
-Requires-Dist: argparse==1.1
-Requires-Dist: pyyaml==6.0.1
-Requires-Dist: jsonschema==3.0.1
-Requires-Dist: openpyxl==3.0.7
+Requires-Dist: argparse==1.4.0
+Requires-Dist: dateparser==1.2.2
+Requires-Dist: deepdiff==4.3.0
+Requires-Dist: jinja2==3.1.6
 Requires-Dist: jsonmerge==1.6.1
-Requires-Dist: deepdiff~=4.3.0
-Requires-Dist: jsonpointer==2.0
-Requires-Dist: pandas==1.5.3
-Requires-Dist: jinja2~=3.1.3
-Requires-Dist: nci-cidc-ngs-pipeline-api==0.1.25
-Requires-Dist: markupsafe==2.1.5
-Requires-Dist: regex==2022.3.2
+Requires-Dist: jsonpointer==3.0.0
+Requires-Dist: jsonschema==3.2.0
+Requires-Dist: openpyxl==3.1.5
+Requires-Dist: pandas==2.3.1
+Requires-Dist: pyyaml==6.0.2
+Requires-Dist: xlsxwriter==3.2.5
 Dynamic: author
 Dynamic: author-email
 Dynamic: classifier
@@ -130,6 +127,18 @@ If you're making changes to the module and want those changes to be reflected in
 python3 -m cidc_schemas.cli [args]
 ```
 
+### Creating a new assay or analysis type ###
+
+In order to create a new assay type, your best bet is to just search for an existing assay and copy it.
+
+Preferably, look at visium and copy exactly what it does. Make changes in the assay schema and template for your
+particular assay and/or analysis schema.
+
+There are a lot of gotchas and hidden parsing going on behind the scenes. Listing them all would be hard, so this is the best
+practical advice.
+
+Be sure to regenerate the docs after creating your schema, so the new schema is added to the reference docs.
+
 ### Generate templates
 
 Create a template for a given template configuration.

nci_cidc_schemas-0.28.0/nci_cidc_schemas.egg-info/requires.txt

@@ -0,0 +1,11 @@
+argparse==1.4.0
+dateparser==1.2.2
+deepdiff==4.3.0
+jinja2==3.1.6
+jsonmerge==1.6.1
+jsonpointer==3.0.0
+jsonschema==3.2.0
+openpyxl==3.1.5
+pandas==2.3.1
+pyyaml==6.0.2
+xlsxwriter==3.2.5

nci_cidc_schemas-0.28.0/requirements.txt

@@ -0,0 +1,11 @@
+argparse==1.4.0
+dateparser==1.2.2
+deepdiff==4.3.0
+jinja2==3.1.6
+jsonmerge==1.6.1 # TODO: 1.9.2
+jsonpointer==3.0.0
+jsonschema==3.2.0 # TODO: 4.25.0
+openpyxl==3.1.5
+pandas==2.3.1
+pyyaml==6.0.2
+xlsxwriter==3.2.5

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/setup.py

@@ -24,7 +24,7 @@ setup(
         "Programming Language :: Python :: 3.9",
     ],
     description="The CIDC data model and tools for working with it.",
-    python_requires=">=3.9,<3.11",
+    python_requires=">=3.13,<3.14",
     install_requires=requirements,
     license="MIT license",
     long_description=readme,

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/tests/prism/test_core.py

@@ -1,6 +1,6 @@
 """Tests for generic prismification functionality.
 
-TODO: some of these tests currently use the CIDC data model, but they 
+TODO: some of these tests currently use the CIDC data model, but they
 should probably use an unrelated test data model instead.
 """
 

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/tests/prism/test_extra_metadata.py

@@ -6,8 +6,9 @@ from cidc_schemas.prism.extra_metadata import parse_elisa, parse_npx, parse_clin
 
 from ..constants import TEST_DATA_DIR
 
-# Single NPX file and metadata
-npx_file_path = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_1_NPX.xlsx")
+# NPX files in differing acceptable formats and metadata
+npx_file_path_olink = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_1_NPX.xlsx")
+npx_file_path_sample = os.path.join(TEST_DATA_DIR, "olink", "olink_assay_2_NPX.xlsx")
 single_npx_metadata = {
     "number_of_samples": 4,
     "samples": ["CTTTP01A1.00", "CTTTP02A1.00", "CTTTP03A1.00", "CTTTP04A1.00"],
@@ -88,7 +89,8 @@ def test_parse_binaryio_only(parser):
 @pytest.mark.parametrize(
     "parser,file_path,target",
     [
-        (parse_npx, npx_file_path, single_npx_metadata),
+        (parse_npx, npx_file_path_olink, single_npx_metadata),
+        (parse_npx, npx_file_path_sample, single_npx_metadata),
         (parse_npx, npx_combined_file_path, combined_npx_metadata),
         # differ in column order and capitalization/spacing of cimac_id column
         # testing both to prevent unnecessary assumptions in formatting as this is hand generated

{nci_cidc_schemas-0.27.27 → nci_cidc_schemas-0.28.0}/tests/prism/test_merger.py

@@ -12,7 +12,8 @@ from cidc_schemas.prism.core import LocalFileUploadEntry
 from cidc_schemas.prism.constants import PROTOCOL_ID_FIELD_NAME
 
 from .test_extra_metadata import (
-    npx_file_path,
+    npx_file_path_olink,
+    npx_file_path_sample,
     npx_combined_file_path,
     invalid_npx_file_path,
     elisa_file_path_1,
@@ -381,7 +382,14 @@ def olink_ct_metadata():
 def olink_file_infos():
     return [
         LocalFileUploadEntry(
-            local_path=npx_file_path,
+            local_path=npx_file_path_olink,
+            gs_key="",
+            upload_placeholder="npx_1",
+            metadata_availability=True,
+            allow_empty=False,
+        ),
+        LocalFileUploadEntry(
+            local_path=npx_file_path_sample,
             gs_key="",
             upload_placeholder="npx_1",
             metadata_availability=True,

nci_cidc_schemas-0.27.27/nci_cidc_schemas.egg-info/requires.txt

@@ -1,14 +0,0 @@
-dateparser==1.1.4
-xlsxwriter==1.1.6
-argparse==1.1
-pyyaml==6.0.1
-jsonschema==3.0.1
-openpyxl==3.0.7
-jsonmerge==1.6.1
-deepdiff~=4.3.0
-jsonpointer==2.0
-pandas==1.5.3
-jinja2~=3.1.3
-nci-cidc-ngs-pipeline-api==0.1.25
-markupsafe==2.1.5
-regex==2022.3.2

nci_cidc_schemas-0.27.27/requirements.txt

@@ -1,14 +0,0 @@
-dateparser==1.1.4
-xlsxwriter==1.1.6
-argparse==1.1
-pyyaml==6.0.1
-jsonschema==3.0.1
-openpyxl==3.0.7
-jsonmerge==1.6.1
-deepdiff~=4.3.0
-jsonpointer==2.0
-pandas==1.5.3
-jinja2~=3.1.3
-nci-cidc-ngs-pipeline-api==0.1.25
-markupsafe==2.1.5
-regex==2022.3.2