cdapython 2.0.13__tar.gz → 2.1.0__tar.gz

cdapython-2.1.0/CHANGELOG.md

@@ -0,0 +1,25 @@
+2026-04-07: 2.1.0: add `search_terms` support; obsolesce `disease_slims` POC in deference to upcoming full version
+
+2025-12-09: 2.0.14: add sort postproc to POC `disease_slims` return column
+
+2025-12-09: 2.0.13: add POC `include_disease_slims` Boolean flag to `get_data()`
+
+2025-10-31: 2.0.12: standardize debug-layer SQL echo; adjust `column_values()` to handle known pathologies
+
+2025-10-27: 2.0.11: _cough_ bugfix for previous
+
+2025-10-27: 2.0.10: integrate `column_values()` parameter validation with shared validation library; expand support for `column_values( data_source )` to accept list values in addition to single strings
+
+2025-10-22: 2.0.9: parametrize `data_source` check in `column_values()`
+
+2025-10-20: 2.0.8: rename CDS to GC throughout
+
+2025-10-08: 2.0.7: fix malformed column metadata selector inside `collate=True` provenance management in `get_data()`
+
+2025-09-17: 2.0.6: update ternary numeric comparison handling for latest API ternary operator syntax support
+
+2025-08-18: 2.0.2: update PyYAML build dependency
+
+2025-08-18: 2.0.1: update default API URL
+
+2025-08-18: 2.0.0: initial public release to PyPI

{cdapython-2.0.13 → cdapython-2.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cdapython
-Version: 2.0.13
+Version: 2.1.0
 Summary: NCI CRDC CDA front-end user interface library
 License-File: LICENSE
 Requires-Python: >=3.9,<4.0
@@ -11,8 +11,8 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
-Requires-Dist: cda-client (>=2.0.0)
-Requires-Dist: pandas (>=2.2.3)
+Requires-Dist: cda-client (>=2.1.0)
+Requires-Dist: pandas (>=2.2.3,<3.0.0)
 Requires-Dist: pyyaml (>=6.0.0)
 Requires-Dist: tabulate (>=0.9.0)
 Description-Content-Type: text/markdown

{cdapython-2.0.13 → cdapython-2.1.0}/cdapython/discover.py

@@ -866,6 +866,7 @@ def column_values(
             cached_column_metadata=cached_column_metadata,
             valid_data_sources=valid_data_sources,
             table=None,
+            search_list=list(),
             column=column,
             match_from_file=None,
             data_source=data_source,
@@ -888,7 +889,7 @@ def column_values(
     # Set default sort_by value.
     if sort_by == '':
         if return_data_as in [ '', 'dataframe', 'tsv' ]:
-            sort_by = 'count'
+            sort_by = 'count:desc'
         elif return_data_as in [ 'list' ]:
             sort_by = 'value'
         else:

{cdapython-2.0.13 → cdapython-2.1.0}/cdapython/get_data.py

@@ -34,7 +34,7 @@ from cda_client.models.data_request_body import DataRequestBody
 #############################################################################################################################
 
 def get_file_data(
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -43,13 +43,19 @@ def get_file_data(
     exclude_columns=None,
     collate_results=False,
     return_data_as='dataframe',
-    output_file='',
-    include_disease_slims=False
+    output_file=''
 ):
     """
     Get CDA file rows ('result rows') that match user-specified criteria.
 
     Arguments:
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Users can add a wildcard character * to
+            either or both ends of each search term to enable partial matches
+            to longer values. Example:
+                get_file_data( 'kidney', 'adeno*', 'hispanic or latino' )
+
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
             ALL of which must be met by all result rows.
@@ -142,7 +148,7 @@ def get_file_data(
 
     """
 
-    return get_data( table='file', match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, collate_results=collate_results, include_external_refs=False, return_data_as=return_data_as, output_file=output_file, include_disease_slims=include_disease_slims )
+    return get_data( *search_terms, match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, collate_results=collate_results, include_external_refs=False, return_data_as=return_data_as, output_file=output_file, table='file' )
 
 #############################################################################################################################
 #
@@ -151,7 +157,7 @@ def get_file_data(
 #############################################################################################################################
 
 def get_subject_data(
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -161,13 +167,19 @@ def get_subject_data(
     collate_results=False,
     include_external_refs=False,
     return_data_as='dataframe',
-    output_file='',
-    include_disease_slims=False
+    output_file=''
 ):
     """
     Get CDA subject rows ('result rows') that match user-specified criteria.
 
     Arguments:
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Users can add a wildcard character * to
+            either or both ends of each search term to enable partial matches
+            to longer values. Example:
+                get_subject_data( 'kidney', 'adeno*', 'hispanic or latino' )
+
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
             ALL of which must be met by all result rows.
@@ -265,7 +277,7 @@ def get_subject_data(
 
     """
 
-    return get_data( table='subject', match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, collate_results=collate_results, include_external_refs=include_external_refs, return_data_as=return_data_as, output_file=output_file, include_disease_slims=include_disease_slims )
+    return get_data( *search_terms, match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, collate_results=collate_results, include_external_refs=include_external_refs, return_data_as=return_data_as, output_file=output_file, table='subject' )
 
 #############################################################################################################################
 #
@@ -274,8 +286,7 @@ def get_subject_data(
 #############################################################################################################################
 
 def get_data(
-    table=None,
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -286,14 +297,18 @@ def get_data(
     include_external_refs=False,
     return_data_as='dataframe',
     output_file='',
-    include_disease_slims=False
+    table=None
 ):
     """
     Get CDA data rows ('result rows') from `table` that match user-specified criteria.
 
     Arguments:
-        table ( string; required: 'file' or 'subject' ):
-            The CDA table whose rows are to be filtered and retrieved.
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Users can add a wildcard character * to
+            either or both ends of each search term to enable partial matches
+            to longer values. Example:
+                get_data( 'kidney', 'adeno*', 'hispanic or latino', table='subject' )
 
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
@@ -347,6 +362,9 @@ def get_data(
             resolvable path to a file into which get_data() will write
             tab-delimited results.
 
+        table ( string; required: 'file' or 'subject' ):
+            The CDA table whose rows are to be filtered and retrieved.
+
     Filter strings:
         Filter strings are expressions of the form 'COLUMN_NAME OP VALUE'
         (note in particular that the whitespace surrounding OP is required),
@@ -376,13 +394,13 @@ def get_data(
         the filters specified just above in the `match_all` argument, when querying
         the `subject` table, we can write:
 
-            get_data( table='subject', match_all=[ 'diagnosis = *duct*', 'sex = F*' ] )
+            get_data( match_all=[ 'diagnosis = *duct*', 'sex = F*' ], table='subject' )
 
         NULL is a special VALUE which can be used to match missing data. For
         example, to get `subject` rows where the `cause_of_death` field
         is missing data, we can write:
 
-            get_data( table='subject', match_all=[ 'cause_of_death = NULL' ] )
+            get_data( match_all=[ 'cause_of_death = NULL' ], table='subject' )
 
     Returns:
         (Default) A pandas.DataFrame containing CDA `table` rows matching the user-specified
@@ -401,6 +419,13 @@ def get_data(
     # Validate parameter inputs.
     #############################################################################################################################
 
+    search_list = list()
+    if len( search_terms ) > 0:
+        for search_string in search_terms:
+            # Let's not _immediately_ break our downstream processing with funky characters or evadable anomalies. Also,
+            # strip leading and trailing whitespace.
+            search_list.append( json.dumps( search_string ).strip( '"' ).strip() )
+
     # Normalize user-supplied parameter data so we can assume from here on out that these are always lists of values:
     # convert any of the following that come in as single values (instead of lists of values) into one-element lists,
     # and leave the rest unmodified. Also convert everything to lowercase.
@@ -460,6 +485,7 @@ def get_data(
             cached_column_metadata=cached_column_metadata,
             valid_data_sources=valid_data_sources,
             table=table,
+            search_list=search_list,
             column=None,
             match_from_file=match_from_file,
             data_source=data_source,
@@ -691,6 +717,7 @@ def get_data(
     # Build an object to represent our upcoming API query.
 
     query_object = DataRequestBody()
+    query_object.search_list = search_list
     query_object.match_all = queries_for_match_all
     query_object.match_some = queries_for_match_any
     query_object.add_columns = columns_to_add
@@ -861,631 +888,6 @@ def get_data(
                 if result_record[ f"{table}_data_at_{upstream_data_source.lower()}" ] == True:
                     result_dataframe['data_source'].iloc[row_index].append( upstream_data_source )
 
-    # BEGIN :: REMOVE ME AFTER SLIM DB INFRASTRUCTURE UPDATE
-    disease_slim_map = {
-        'Abdominal fibromatosis': 'Fibromatous neoplasms',
-        'Acinar cell adenoma': 'Acinar cell neoplasms',
-        'Acinar cell carcinoma': 'Acinar cell neoplasms',
-        'Acinar cell tumor': 'Acinar cell neoplasms',
-        'Acral melanoma': 'Nevi and melanomas',
-        'Acute erythroid leukemia': 'Leukemias',
-        'Acute leukemia, NOS': 'Leukemias',
-        'Acute megakaryoblastic leukemia': 'Leukemias',
-        'Acute monocytic leukemia': 'Leukemias',
-        'Acute myeloid leukemia with abnormal marrow eosinophils': 'Leukemias',
-        'Acute myeloid leukemia with biallelic mutation of CEBPA': 'Leukemias',
-        'Acute myeloid leukemia with inv(3)(q21;q26.2) or t(3;3)(q21;q26.2); RPN1-EVI1': 'Leukemias',
-        'Acute myeloid leukemia with maturation': 'Leukemias',
-        'Acute myeloid leukemia with mutated NPM1': 'Leukemias',
-        'Acute myeloid leukemia with myelodysplasia-related changes': 'Leukemias',
-        'Acute myeloid leukemia with t(6;9)(p23;q34); DEK-NUP214': 'Leukemias',
-        'Acute myeloid leukemia without maturation': 'Leukemias',
-        'Acute myeloid leukemia, 11q23 abnormalities': 'Leukemias',
-        'Acute myeloid leukemia, NOS': 'Leukemias',
-        'Acute myeloid leukemia, minimal differentiation': 'Leukemias',
-        'Acute myeloid leukemia, t(8;21)(q22;q22)': 'Leukemias',
-        'Acute myelomonocytic leukemia, NOS': 'Leukemias',
-        'Acute promyelocytic leukemia, t(15;17)(q22;q11-12)': 'Leukemias',
-        'Adenocarcinoma in adenomatous polyposis coli': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma in situ in adenomatous polyp': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma in situ, NOS': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma in tubulovillous adenoma': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma in villous adenoma': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma of anal glands': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma of the lung, mucinous': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma with mixed subtypes': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma with neuroendocrine differentiation': 'Complex epithelial neoplasms',
-        'Adenocarcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma, endocervical type': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma, intestinal type': 'Adenomas and adenocarcinomas',
-        'Adenocarcinoma, metastatic, NOS': 'Adenomas and adenocarcinomas',
-        'Adenoid basal carcinoma': 'Basal cell neoplasms',
-        'Adenoid cystic carcinoma': 'Adenomas and adenocarcinomas',
-        'Adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Adenomatous polyp, NOS': 'Adenomas and adenocarcinomas',
-        'Adenomatous polyposis coli': 'Adenomas and adenocarcinomas',
-        'Adenomyoepithelioma, NOS': 'Complex mixed and stromal neoplasms',
-        'Adenosarcoma': 'Complex mixed and stromal neoplasms',
-        'Adenosquamous carcinoma': 'Complex epithelial neoplasms',
-        'Adnexal adenocarcinoma, NOS': 'Adnexal and skin appendage neoplasms',
-        'Adnexal and skin appendage neoplasms': 'Adnexal and skin appendage neoplasms',
-        'Adrenal cortical adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Adrenal cortical carcinoma': 'Adenomas and adenocarcinomas',
-        'Adult T-cell leukemia/lymphoma (HTLV-1 positive)': 'Leukemias',
-        'Adult granulosa cell tumor of ovary': 'Specialized gonadal neoplasms',
-        'Adult granulosa cell tumor of testis': 'Specialized gonadal neoplasms',
-        'Aggressive fibromatosis': 'Fibromatous neoplasms',
-        'Alveolar rhabdomyosarcoma': 'Myomatous neoplasms',
-        'Alveolar soft part sarcoma': 'Granular cell tumors and alveolar soft part sarcomas',
-        'Amelanotic melanoma': 'Nevi and melanomas',
-        'Anaplastic large cell lymphoma, T-cell and Null-cell type': 'Hodgkin and non-Hodgkin lymphomas',
-        'Angiocentric glioma': 'Gliomas',
-        'Angioimmunoblastic T-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Angiomatoid fibrous histiocytoma': 'Fibromatous neoplasms',
-        'Angiomyofibroblastoma': 'Fibromatous neoplasms',
-        'Angiomyolipoma': 'Lipomatous neoplasms',
-        'Angiomyosarcoma': 'Myomatous neoplasms',
-        'Aortic body tumor': 'Paragangliomas and glomus tumors',
-        'Apocrine adenocarcinoma': 'Adnexal and skin appendage neoplasms',
-        'Astroblastoma': 'Gliomas',
-        'Astrocytoma, NOS': 'Gliomas',
-        'Astrocytoma, anaplastic': 'Gliomas',
-        'Atypical adenoma': 'Adenomas and adenocarcinomas',
-        'Atypical choroid plexus papilloma': 'Gliomas',
-        'Atypical chronic myeloid leukemia, BCR/ABL negative': 'Leukemias',
-        'Atypical meningioma': 'Meningiomas',
-        'Atypical teratoid/rhabdoid tumor': 'Neuroepitheliomatous neoplasms',
-        'B lymphoblastic leukemia/lymphoma with hyperdiploidy': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma with hypodiploidy(Hypodiploid ALL)': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma with t(12;21)(p13;q22); TEL-AML1(ETV6-RUNX1)': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma with t(1;19)(q23;p13.3); E2A-PBX1(TCF3-PBX1)': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma with t(9;22)(q34;q11.2); BCR-ABL1': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma with t(v;11q23); MLL rearranged': 'Leukemias',
-        'B lymphoblastic leukemia/lymphoma, NOS': 'Leukemias',
-        'B-cell chronic lymphocytic leukemia/small lymphocytic lymphoma': 'Leukemias',
-        'Basal cell adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Basal cell carcinoma, NOS': 'Basal cell neoplasms',
-        'Basal cell carcinoma, nodular': 'Basal cell neoplasms',
-        'Basal cell neoplasms': 'Basal cell neoplasms',
-        'Basaloid carcinoma': 'Transitional cell papillomas and carcinomas',
-        'Basaloid squamous cell carcinoma': 'Squamous cell neoplasms',
-        'Benign cystic nephroma': 'Complex mixed and stromal neoplasms',
-        'Blood vessel tumors': 'Blood vessel tumors',
-        'Blue nevus, malignant': 'Nevi and melanomas',
-        'Borderline Intraductal carcinoma and lobular': 'Ductal and lobular neoplasms',
-        'Brenner tumor, NOS': 'Fibroepithelial neoplasms',
-        'Bronchiolo-alveolar carcinoma, non-mucinous': 'Adenomas and adenocarcinomas',
-        'Burkitt lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'CNS embryonal tumor, NOS': 'Gliomas',
-        'Carcinoma in situ, NOS': 'Epithelial neoplasms',
-        'Carcinoma with osteoclast-like giant cells': 'Epithelial neoplasms',
-        'Carcinoma, NOS': 'Epithelial neoplasms',
-        'Carcinoma, anaplastic, NOS': 'Epithelial neoplasms',
-        'Carcinoma, diffuse type': 'Adenomas and adenocarcinomas',
-        'Carcinoma, metastatic, NOS': 'Epithelial neoplasms',
-        'Carcinoma, undifferentiated, NOS': 'Epithelial neoplasms',
-        'Carcinosarcoma, NOS': 'Complex mixed and stromal neoplasms',
-        'Cavernous hemangioma': 'Blood vessel tumors',
-        'Central neurocytoma': 'Neuroepitheliomatous neoplasms',
-        'Central osteosarcoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Cholangiocarcinoma': 'Adenomas and adenocarcinomas',
-        'Chondroblastic osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Chondroblastoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Chondroid chordoma': 'Miscellaneous tumors',
-        'Chondrosarcoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Chordoma, NOS': 'Miscellaneous tumors',
-        'Choriocarcinoma combined with other germ cell elements': 'Trophoblastic neoplasms',
-        'Choriocarcinoma, NOS': 'Trophoblastic neoplasms',
-        'Choroid plexus carcinoma': 'Gliomas',
-        'Choroid plexus papilloma, NOS': 'Gliomas',
-        'Chronic eosinophilic leukemia': 'Chronic myeloproliferative disorders',
-        'Chronic myelogenous leukemia, BCR/ABL positive': 'Leukemias',
-        'Chronic myeloid leukemia, NOS': 'Leukemias',
-        'Chronic myelomonocytic leukemia, NOS': 'Leukemias',
-        'Chronic neutrophilic leukemia': 'Chronic myeloproliferative disorders',
-        'Clear cell adenocarcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Clear cell adenoma': 'Adenomas and adenocarcinomas',
-        'Clear cell meningioma': 'Meningiomas',
-        'Clear cell odontogenic carcinoma': 'Odontogenic tumors',
-        'Clear cell sarcoma of kidney': 'Complex mixed and stromal neoplasms',
-        'Clear cell sarcoma, NOS': 'Synovial-like neoplasms',
-        'Collecting duct carcinoma': 'Adenomas and adenocarcinomas',
-        'Combined hepatocellular carcinoma and cholangiocarcinoma': 'Adenomas and adenocarcinomas',
-        'Combined small cell carcinoma': 'Epithelial neoplasms',
-        'Comedocarcinoma, noninfiltrating': 'Ductal and lobular neoplasms',
-        'Complex epithelial neoplasms': 'Complex epithelial neoplasms',
-        'Complex mixed and stromal neoplasms': 'Complex mixed and stromal neoplasms',
-        'Composite Hodgkin and non-Hodgkin lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Craniopharyngioma': 'Miscellaneous tumors',
-        'Craniopharyngioma, adamantinomatous': 'Miscellaneous tumors',
-        'Craniopharyngioma, papillary': 'Miscellaneous tumors',
-        'Cribriform carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Cutaneous T-cell lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Cystadenocarcinoma, NOS': 'Cystic, mucinous and serous neoplasms',
-        'Cystic, mucinous and serous neoplasms': 'Cystic, mucinous and serous neoplasms',
-        'Dedifferentiated chondrosarcoma': 'Osseous and chondromatous neoplasms',
-        'Dedifferentiated liposarcoma': 'Lipomatous neoplasms',
-        'Dermatofibroma, NOS': 'Fibromatous neoplasms',
-        'Dermatofibrosarcoma protuberans, NOS': 'Fibromatous neoplasms',
-        'Dermatofibrosarcoma protuberans, fibrosarcomatous': 'Fibromatous neoplasms',
-        'Dermoid cyst, NOS': 'Germ cell neoplasms',
-        'Desmoplastic infantile astrocytoma': 'Gliomas',
-        'Desmoplastic melanoma': 'Nevi and melanomas',
-        'Desmoplastic nodular medulloblastoma': 'Gliomas',
-        'Desmoplastic small round cell tumor': 'Soft tissue tumors and sarcomas',
-        'Diffuse large B-cell lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Diffuse midline glioma, H3 K27M-mutant': 'Gliomas',
-        'Ductal and lobular neoplasms': 'Ductal and lobular neoplasms',
-        'Dysembryoplastic neuroepithelial tumor': 'Gliomas',
-        'Dysgerminoma': 'Germ cell neoplasms',
-        'Embryonal carcinoma, NOS': 'Germ cell neoplasms',
-        'Embryonal rhabdomyosarcoma, NOS': 'Myomatous neoplasms',
-        'Embryonal sarcoma': 'Complex mixed and stromal neoplasms',
-        'Embryonal tumor with multilayered rosettes with C19MC alteration': 'Gliomas',
-        'Endometrial stromal sarcoma, NOS': 'Complex mixed and stromal neoplasms',
-        'Endometrial stromal sarcoma, low grade': 'Complex mixed and stromal neoplasms',
-        'Endometrioid adenocarcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Endometrioid adenocarcinoma, secretory variant': 'Adenomas and adenocarcinomas',
-        'Endometrioid adenoma, borderline malignancy': 'Adenomas and adenocarcinomas',
-        'Ependymoma, NOS': 'Gliomas',
-        'Ependymoma, RELA fusion-positive': 'Gliomas',
-        'Ependymoma, anaplastic': 'Gliomas',
-        'Epithelial tumor, benign': 'Epithelial neoplasms',
-        'Epithelial-myoepithelial carcinoma': 'Complex epithelial neoplasms',
-        'Epithelioid cell melanoma': 'Nevi and melanomas',
-        'Epithelioid cell nevus': 'Nevi and melanomas',
-        'Epithelioid hemangioendothelioma, NOS': 'Blood vessel tumors',
-        'Epithelioid leiomyosarcoma': 'Myomatous neoplasms',
-        'Epithelioid mesothelioma, malignant': 'Mesothelial neoplasms',
-        'Epithelioid sarcoma': 'Soft tissue tumors and sarcomas',
-        'Essential thrombocythemia': 'Chronic myeloproliferative disorders',
-        'Ewing sarcoma': 'Miscellaneous tumors',
-        'Extra-adrenal paraganglioma, NOS': 'Paragangliomas and glomus tumors',
-        'Fibrillary astrocytoma': 'Gliomas',
-        'Fibroblastic osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Fibroepithelial neoplasms': 'Fibroepithelial neoplasms',
-        'Fibrolipoma': 'Lipomatous neoplasms',
-        'Fibroma, NOS': 'Fibromatous neoplasms',
-        'Fibromatous neoplasms': 'Fibromatous neoplasms',
-        'Fibrosarcoma, NOS': 'Fibromatous neoplasms',
-        'Fibrous mesothelioma, malignant': 'Mesothelial neoplasms',
-        'Follicular adenocarcinoma, well differentiated': 'Adenomas and adenocarcinomas',
-        'Follicular carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Follicular carcinoma, minimally invasive': 'Adenomas and adenocarcinomas',
-        'Follicular dendritic cell sarcoma': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Follicular lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Gangliocytoma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Ganglioglioma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Ganglioglioma, anaplastic': 'Neuroepitheliomatous neoplasms',
-        'Ganglioneuroblastoma': 'Neuroepitheliomatous neoplasms',
-        'Ganglioneuroma': 'Neuroepitheliomatous neoplasms',
-        'Gastrointestinal stromal tumor': 'Complex mixed and stromal neoplasms',
-        'Gastrointestinal stromal tumor, NOS': 'Complex mixed and stromal neoplasms',
-        'Gastrointestinal stromal tumor, benign': 'Complex mixed and stromal neoplasms',
-        'Genital rhabdomyoma': 'Myomatous neoplasms',
-        'Germ cell neoplasms': 'Germ cell neoplasms',
-        'Germ cell tumor, nonseminomatous': 'Germ cell neoplasms',
-        'Germinoma': 'Germ cell neoplasms',
-        'Giant cell carcinoma': 'Epithelial neoplasms',
-        'Giant cell glioblastoma': 'Gliomas',
-        'Giant cell sarcoma': 'Soft tissue tumors and sarcomas',
-        'Giant cell tumor of bone, NOS': 'Giant cell tumors',
-        'Giant cell tumor of bone, malignant': 'Giant cell tumors',
-        'Giant cell tumor of soft parts, NOS': 'Giant cell tumors',
-        'Giant pigmented nevus, NOS': 'Nevi and melanomas',
-        'Glassy cell carcinoma': 'Epithelial neoplasms',
-        'Glioblastoma, IDH-mutant': 'Gliomas',
-        'Glioblastoma, NOS': 'Gliomas',
-        'Glioma, malignant': 'Gliomas',
-        'Gliomatosis cerebri': 'Gliomas',
-        'Gliosarcoma': 'Gliomas',
-        'Glomangiosarcoma': 'Paragangliomas and glomus tumors',
-        'Glomus tumor, NOS': 'Paragangliomas and glomus tumors',
-        'Glomus tumor, malignant': 'Paragangliomas and glomus tumors',
-        'Goblet cell carcinoid': 'Adenomas and adenocarcinomas',
-        'Granular cell tumor, NOS': 'Granular cell tumors and alveolar soft part sarcomas',
-        'Granulosa cell tumor, juvenile': 'Specialized gonadal neoplasms',
-        'HHV8-positive diffuse large B-cell lymphoma': 'Plasma Cell Tumors',
-        'Hairy cell leukemia, NOS': 'Leukemias',
-        'Hemangioblastoma': 'Blood vessel tumors',
-        'Hemangioendothelioma, NOS': 'Blood vessel tumors',
-        'Hemangioendothelioma, malignant': 'Blood vessel tumors',
-        'Hemangioma, NOS': 'Blood vessel tumors',
-        'Hemangiosarcoma': 'Blood vessel tumors',
-        'Hepatoblastoma, NOS': 'Complex mixed and stromal neoplasms',
-        'Hepatocellular carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Hepatocellular carcinoma, clear cell type': 'Adenomas and adenocarcinomas',
-        'Hepatocellular carcinoma, fibrolamellar': 'Adenomas and adenocarcinomas',
-        'Hepatocellular carcinoma, spindle cell variant': 'Adenomas and adenocarcinomas',
-        'Hepatoid adenocarcinoma': 'Complex epithelial neoplasms',
-        'Hepatosplenic T-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Hereditary leiomyomatosis and renal cell carcinoma (HRCC)-associated renal cell carcinoma': 'Adenomas and adenocarcinomas',
-        'Hibernoma': 'Lipomatous neoplasms',
-        'High grade serous carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'High grade surface osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Histiocytic sarcoma': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Hodgkin lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Hodgkin lymphoma, nodular lymphocyte predominant': 'Hodgkin and non-Hodgkin lymphomas',
-        'Hodgkin lymphoma, nodular sclerosis, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Hyalinizing trabecular tumor': 'Adenomas and adenocarcinomas',
-        'Hydatidiform mole, NOS': 'Trophoblastic neoplasms',
-        'Indolent systemic mastocytosis': 'Mast Cell Tumors',
-        'Infantile fibrosarcoma': 'Fibromatous neoplasms',
-        'Infiltrating duct and lobular carcinoma': 'Ductal and lobular neoplasms',
-        'Infiltrating duct carcinoma, NOS': 'Ductal and lobular neoplasms',
-        'Infiltrating duct mixed with other types of carcinoma': 'Ductal and lobular neoplasms',
-        'Infiltrating ductular carcinoma': 'Ductal and lobular neoplasms',
-        'Infiltrating ductular carcinoma, borderline malignancy': 'Ductal and lobular neoplasms',
-        'Infiltrating lobular mixed with other types of carcinoma': 'Ductal and lobular neoplasms',
-        'Inflammatory carcinoma': 'Ductal and lobular neoplasms',
-        'Interdigitating dendritic cell sarcoma': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Intimal sarcoma': 'Blood vessel tumors',
-        'Intraductal Papillary mucinous adenoma': 'Cystic, mucinous and serous neoplasms',
-        'Intraductal Papillary mucinous neoplasm with an associated invasive carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Intraductal Papillary mucinous neoplasm with high grade dysplasia': 'Cystic, mucinous and serous neoplasms',
-        'Intraductal carcinoma, noninfiltrating, NOS': 'Ductal and lobular neoplasms',
-        'Intraductal micropapillary carcinoma': 'Ductal and lobular neoplasms',
-        'Intraductal papillary adenocarcinoma with invasion': 'Ductal and lobular neoplasms',
-        'Intravascular large B-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Invasive micropapillary carcinoma of breast': 'Ductal and lobular neoplasms',
-        'Juvenile myelomonocytic leukemia, NOS': 'Leukemias',
-        'Kaposi sarcoma': 'Blood vessel tumors',
-        'Kupffer cell sarcoma': 'Blood vessel tumors',
-        'Lactotroph adenoma': 'Adenomas and adenocarcinomas',
-        'Langerhans cell histiocytosis, NOS': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Langerhans cell histiocytosis, disseminated': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Large cell carcinoma, NOS': 'Epithelial neoplasms',
-        'Large cell medulloblastoma': 'Gliomas',
-        'Large cell neuroendocrine carcinoma': 'Epithelial neoplasms',
-        'Leiomyoma, NOS': 'Myomatous neoplasms',
-        'Leiomyosarcoma, NOS': 'Myomatous neoplasms',
-        'Lentiginous melanocytic nevus': 'Nevi and melanomas',
-        'Lentigo maligna': 'Nevi and melanomas',
-        'Lentigo maligna melanoma': 'Nevi and melanomas',
-        'Lepidic adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Leukemia, NOS': 'Leukemias',
-        'Leydig cell tumor of the ovary, NOS': 'Specialized gonadal neoplasms',
-        'Leydig cell tumor of the testis, NOS': 'Specialized gonadal neoplasms',
-        'Lipid cell tumor of ovary': 'Specialized gonadal neoplasms',
-        'Lipoblastomatosis': 'Lipomatous neoplasms',
-        'Lipoma, NOS': 'Lipomatous neoplasms',
-        'Liposarcoma, NOS': 'Lipomatous neoplasms',
-        'Liposarcoma, well differentiated, NOS': 'Lipomatous neoplasms',
-        'Lobular carcinoma in situ, NOS': 'Ductal and lobular neoplasms',
-        'Lobular carcinoma, NOS': 'Ductal and lobular neoplasms',
-        'Low cumulative sun damage melanoma': 'Nevi and melanomas',
-        'Low grade central osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Low grade serous carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Lymphangioleiomyomatosis': 'Lymphatic vessel tumors',
-        'Lymphangioma, NOS': 'Lymphatic vessel tumors',
-        'Lymphoepithelial carcinoma': 'Squamous cell neoplasms',
-        'Lymphoid leukemia, NOS': 'Leukemias',
-        'Lymphoproliferative disorder, NOS': 'Other hematologic disorders',
-        'Malignant Spitz tumor': 'Nevi and melanomas',
-        'Malignant fibrous histiocytoma': 'Fibromatous neoplasms',
-        'Malignant histiocytosis': 'Neoplasms of histiocytes and accessory lymphoid cells',
-        'Malignant lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Malignant lymphoma, non-Hodgkin, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Malignant lymphoma, small B lymphocytic, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Malignant mastocytosis': 'Mast Cell Tumors',
-        'Malignant melanoma, NOS': 'Nevi and melanomas',
-        'Malignant peripheral nerve sheath tumor with rhabdomyoblastic differentiation': 'Nerve sheath tumors',
-        'Malignant peripheral nerve sheath tumor, NOS': 'Nerve sheath tumors',
-        'Malignant tumor, small cell type': 'Neoplasms',
-        'Malignant tumor, spindle cell type': 'Neoplasms',
-        'Mantle cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Marginal zone B-cell lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Mast cell leukemia': 'Mast Cell Tumors',
-        'Mastocytoma, NOS': 'Mast Cell Tumors',
-        'Mature B-cell lymphomas': 'Hodgkin and non-Hodgkin lymphomas',
-        'Mature T- and NK-cell lymphomas': 'Hodgkin and non-Hodgkin lymphomas',
-        'Mature T-cell lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Mediastinal large B-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Medullary carcinoma, NOS': 'Ductal and lobular neoplasms',
-        'Medulloblastoma, NOS': 'Gliomas',
-        'Medulloblastoma, non-WNT/non-SHH': 'Gliomas',
-        'Medulloepithelioma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Melanoma in situ': 'Nevi and melanomas',
-        'Melanotic neuroectodermal tumor': 'Miscellaneous tumors',
-        'Melanotic schwannoma': 'Nerve sheath tumors',
-        'Meningeal melanocytoma': 'Nevi and melanomas',
-        'Meningeal melanocytosis': 'Nevi and melanomas',
-        'Meningeal melanomatosis': 'Nevi and melanomas',
-        'Meningioma, NOS': 'Meningiomas',
-        'Meningioma, malignant': 'Meningiomas',
-        'Meningiomatosis, NOS': 'Meningiomas',
-        'Meningothelial meningioma': 'Meningiomas',
-        'Merkel cell carcinoma': 'Adenomas and adenocarcinomas',
-        'Mesenchymal chondrosarcoma': 'Osseous and chondromatous neoplasms',
-        'Mesenchymoma, NOS': 'Complex mixed and stromal neoplasms',
-        'Mesenchymoma, malignant': 'Complex mixed and stromal neoplasms',
-        'Mesoblastic nephroma': 'Complex mixed and stromal neoplasms',
-        'Mesodermal mixed tumor': 'Complex mixed and stromal neoplasms',
-        'Mesonephroma, malignant': 'Mesonephromas',
-        'Mesothelioma, biphasic, malignant': 'Mesothelial neoplasms',
-        'Mesothelioma, malignant': 'Mesothelial neoplasms',
-        'Metaplastic carcinoma, NOS': 'Complex epithelial neoplasms',
-        'Metastatic  Atypical carcinoid tumor': 'Adenomas and adenocarcinomas',
-        'Metastatic Alveolar rhabdomyosarcoma': 'Myomatous neoplasms',
-        'Metastatic Epithelioid sarcoma': 'Soft tissue tumors and sarcomas',
-        'Metastatic Infiltrating duct carcinoma': 'Ductal and lobular neoplasms',
-        'Metastatic Malignant melanoma': 'Nevi and melanomas',
-        'Metastatic Mullerian mixed tumor': 'Complex mixed and stromal neoplasms',
-        'Metastatic Neuroendocrine carcinoma': 'Adenomas and adenocarcinomas',
-        'Metastatic Serous cystadenocarcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Metastatic Serous surface papilloma': 'Cystic, mucinous and serous neoplasms',
-        'Metastatic Spindle cell sarcoma': 'Soft tissue tumors and sarcomas',
-        'Metastatic Tubular adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Metastatic carcinoma': 'Epithelial neoplasms',
-        'Metastatic signet ring cell carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Metastatic small cell carcinoma': 'Epithelial neoplasms',
-        'Micronodular thymoma with lymphoid stroma': 'Thymic epithelial neoplasms',
-        'Micropapillary carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Mixed germ cell tumor': 'Germ cell neoplasms',
-        'Mixed phenotype acute leukemia with t(9;22)(q34;q11.2); BCR-ABL1': 'Leukemias',
-        'Mixed phenotype acute leukemia with t(v;11q23); MLL rearranged': 'Leukemias',
-        'Mixed phenotype acute leukemia, B/myeloid, NOS': 'Leukemias',
-        'Mixed phenotype acute leukemia, T/myeloid, NOS': 'Leukemias',
-        'Mixed type rhabdomyosarcoma': 'Myomatous neoplasms',
-        'Mucin-producing adenocarcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Mucinous adenocarcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Mucinous carcinoma, gastric type': 'Cystic, mucinous and serous neoplasms',
-        'Mucinous cystadenoma, NOS': 'Cystic, mucinous and serous neoplasms',
-        'Mucinous cystic neoplasm with high grade dysplasia': 'Cystic, mucinous and serous neoplasms',
-        'Mucinous cystic tumor of borderline malignancy': 'Cystic, mucinous and serous neoplasms',
-        'Mucoepidermoid carcinoma': 'Mucoepidermoid neoplasms',
-        'Mucosal lentiginous melanoma': 'Nevi and melanomas',
-        'Mullerian mixed tumor': 'Complex mixed and stromal neoplasms',
-        'Mycosis fungoides': 'Hodgkin and non-Hodgkin lymphomas',
-        'Myelodysplastic syndrome with excess blasts': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome with isolated del (5q)': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome with multilineage dysplasia': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome with ring sideroblasts and multilineage dysplasia': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome with ring sideroblasts and single lineage dysplasia': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome with single lineage dysplasia': 'Myelodysplastic syndromes',
-        'Myelodysplastic syndrome, NOS': 'Myelodysplastic syndromes',
-        'Myeloid leukemia associated with Down syndrome': 'Leukemias',
-        'Myeloid leukemia, NOS': 'Leukemias',
-        'Myeloid or lymphoid neoplasm with PDGFRA rearrangement': 'Chronic myeloproliferative disorders',
-        'Myeloid sarcoma': 'Leukemias',
-        'Myeloproliferative neoplasm, NOS': 'Chronic myeloproliferative disorders',
-        'Myeloproliferative neoplasm, unclassifiable': 'Other hematologic disorders',
-        'Myoepithelial carcinoma': 'Complex mixed and stromal neoplasms',
-        'Myofibroblastic tumor, NOS': 'Fibromatous neoplasms',
-        'Myofibroblastic tumor, peribronchial': 'Fibromatous neoplasms',
-        'Myofibroma': 'Fibromatous neoplasms',
-        'Myofibromatosis': 'Fibromatous neoplasms',
-        'Myxofibrosarcoma': 'Fibromatous neoplasms',
-        'Myxoid chondrosarcoma': 'Osseous and chondromatous neoplasms',
-        'Myxoid leiomyosarcoma': 'Myomatous neoplasms',
-        'Myxoid liposarcoma': 'Lipomatous neoplasms',
-        'Myxoma, NOS': 'Myxomatous neoplasms',
-        'Myxopapillary ependymoma': 'Gliomas',
-        'Myxosarcoma': 'Myxomatous neoplasms',
-        'Neoplasm, benign': 'Neoplasms',
-        'Neoplasm, malignant': 'Neoplasms',
-        'Neoplasm, metastatic': 'Neoplasms',
-        'Neoplasm, uncertain whether benign or malignant': 'Neoplasms',
-        'Nephroblastoma, NOS': 'Complex mixed and stromal neoplasms',
-        'Nerve sheath tumors': 'Nerve sheath tumors',
-        'Neuroblastoma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Neuroendocrine carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Neuroendocrine tumor, NOS': 'Adenomas and adenocarcinomas',
-        'Neuroendocrine tumor, grade 2': 'Adenomas and adenocarcinomas',
-        'Neuroepithelioma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Neurofibroma, NOS': 'Nerve sheath tumors',
-        'Neuroma, NOS': 'Nerve sheath tumors',
-        'Nevi and melanomas': 'Nevi and melanomas',
-        'Nodular melanoma': 'Nevi and melanomas',
-        'Non-small cell carcinoma': 'Epithelial neoplasms',
-        'Nonencapsulated sclerosing carcinoma': 'Adenomas and adenocarcinomas',
-        'Noninfiltrating intraductal papillary adenocarcinoma': 'Ductal and lobular neoplasms',
-        'Nuclear protein in testis (NUT) associated carcinoma': 'Epithelial neoplasms',
-        'Oat cell carcinoma': 'Epithelial neoplasms',
-        'Odontogenic carcinosarcoma': 'Odontogenic tumors',
-        'Odontogenic tumor, malignant': 'Odontogenic tumors',
-        'Olfactory neuroblastoma': 'Neuroepitheliomatous neoplasms',
-        'Olfactory neurocytoma': 'Neuroepitheliomatous neoplasms',
-        'Oligoastrocytoma, NOS': 'Gliomas',
-        'Oligodendroglioma, NOS': 'Gliomas',
-        'Oligodendroglioma, anaplastic, NOS': 'Gliomas',
-        'Osseous and chondromatous neoplasms': 'Osseous and chondromatous neoplasms',
-        'Ossifying fibroma': 'Miscellaneous bone tumors',
-        'Ossifying fibromyxoid tumor, NOS': 'Myxomatous neoplasms',
-        'Osteoblastoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Osteoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Osteosarcoma in Paget disease of bone': 'Osseous and chondromatous neoplasms',
-        'Osteosarcoma, NOS': 'Osseous and chondromatous neoplasms',
-        'Oxyphilic adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Oxyphilic adenoma': 'Adenomas and adenocarcinomas',
-        'Paget disease and infiltrating duct carcinoma of breast': 'Ductal and lobular neoplasms',
-        'Paget disease, extramammary': 'Ductal and lobular neoplasms',
-        'Paget disease, mammary': 'Ductal and lobular neoplasms',
-        'Pancreatic endocrine tumor, NOS': 'Adenomas and adenocarcinomas',
-        'Pancreatic neuroendocrine tumor, nonfunctioning': 'Adenomas and adenocarcinomas',
-        'Pancreatobiliary type carcinoma': 'Adenomas and adenocarcinomas',
-        'Pancreatoblastoma': 'Complex mixed and stromal neoplasms',
-        'Papillary adenocarcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Papillary carcinoma, NOS': 'Squamous cell neoplasms',
-        'Papillary carcinoma, columnar cell': 'Adenomas and adenocarcinomas',
-        'Papillary carcinoma, follicular variant': 'Adenomas and adenocarcinomas',
-        'Papillary carcinoma, oncocytic variant': 'Adenomas and adenocarcinomas',
-        'Papillary glioneuronal tumor': 'Neuroepitheliomatous neoplasms',
-        'Papillary intralymphatic angioendothelioma': 'Blood vessel tumors',
-        'Papillary meningioma': 'Meningiomas',
-        'Papillary microcarcinoma': 'Adenomas and adenocarcinomas',
-        'Papillary squamous cell carcinoma': 'Squamous cell neoplasms',
-        'Papillary transitional cell carcinoma': 'Transitional cell papillomas and carcinomas',
-        'Papillary tumor of the pineal region': 'Gliomas',
-        'Papillary urothelial carcinoma, non-invasive': 'Transitional cell papillomas and carcinomas',
-        'Papilloma, NOS': 'Squamous cell neoplasms',
-        'Paraganglioma, NOS': 'Paragangliomas and glomus tumors',
-        'Paragangliomas and glomus tumors': 'Paragangliomas and glomus tumors',
-        'Parosteal osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Perineurioma, NOS': 'Nerve sheath tumors',
-        'Periosteal osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Perivascular epithelioid tumor, malignant': 'Paragangliomas and glomus tumors',
-        'Pheochromocytoma, NOS': 'Paragangliomas and glomus tumors',
-        'Phyllodes tumor, borderline': 'Fibroepithelial neoplasms',
-        'Phyllodes tumor, malignant': 'Fibroepithelial neoplasms',
-        'Pigmented dermatofibrosarcoma protuberans': 'Fibromatous neoplasms',
-        'Pigmented nevus, NOS': 'Nevi and melanomas',
-        'Pilocytic astrocytoma': 'Gliomas',
-        'Pilomyxoid astrocytoma': 'Gliomas',
-        'Pinealoma': 'Miscellaneous tumors',
-        'Pineoblastoma': 'Miscellaneous tumors',
-        'Pituicytoma': 'Gliomas',
-        'Pituitary adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Pituitary carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Plasma cell myeloma': 'Plasma Cell Tumors',
-        'Plasmacytoma, NOS': 'Plasma Cell Tumors',
-        'Plasmacytoma, extramedullary': 'Plasma Cell Tumors',
-        'Pleomorphic adenoma': 'Complex mixed and stromal neoplasms',
-        'Pleomorphic carcinoma': 'Epithelial neoplasms',
-        'Pleomorphic liposarcoma': 'Lipomatous neoplasms',
-        'Pleomorphic rhabdomyosarcoma, adult type': 'Myomatous neoplasms',
-        'Pleomorphic xanthoastrocytoma': 'Gliomas',
-        'Pleuropulmonary blastoma': 'Complex mixed and stromal neoplasms',
-        'Plexiform fibrohistiocytic tumor': 'Fibromatous neoplasms',
-        'Plexiform neurofibroma': 'Nerve sheath tumors',
-        'Polycythemia vera': 'Chronic myeloproliferative disorders',
-        'Poorly differentiated thyroid carcinoma': 'Adenomas and adenocarcinomas',
-        'Porocarcinoma, NOS': 'Adnexal and skin appendage neoplasms',
-        'Precursor T-cell lymphoblastic leukemia': 'Leukemias',
-        'Precursor cell lymphoblastic leukemia, NOS': 'Leukemias',
-        'Precursor cell lymphoblastic lymphoma, NOS': 'Hodgkin and non-Hodgkin lymphomas',
-        'Primary cutaneous anaplastic large cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Primary cutaneous follicle centre lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Primary effusion lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Primary myelofibrosis': 'Chronic myeloproliferative disorders',
-        'Proliferative dermal lesion in congenital nevus': 'Nevi and melanomas',
-        'Prolymphocytic leukemia, T-cell type': 'Leukemias',
-        'Psammomatous meningioma': 'Meningiomas',
-        'Pseudomyogenic (epithelioid sarcoma-like) hemangioendothelioma': 'Blood vessel tumors',
-        'Pseudomyxoma peritonei': 'Cystic, mucinous and serous neoplasms',
-        'Pseudosarcomatous carcinoma': 'Epithelial neoplasms',
-        'Racemose hemangioma': 'Blood vessel tumors',
-        'Renal cell carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Renal cell carcinoma, chromophobe type': 'Adenomas and adenocarcinomas',
-        'Renal cell carcinoma, sarcomatoid': 'Adenomas and adenocarcinomas',
-        'Retinoblastoma, NOS': 'Neuroepitheliomatous neoplasms',
-        'Retinoblastoma, differentiated': 'Neuroepitheliomatous neoplasms',
-        'Retinoblastoma, undifferentiated': 'Neuroepitheliomatous neoplasms',
-        'Rhabdoid tumor, NOS': 'Complex mixed and stromal neoplasms',
-        'Rhabdomyoma, NOS': 'Myomatous neoplasms',
-        'Rhabdomyosarcoma, NOS': 'Myomatous neoplasms',
-        'Sarcoma, NOS': 'Soft tissue tumors and sarcomas',
-        'Schneiderian carcinoma': 'Transitional cell papillomas and carcinomas',
-        'Schwannoma, NOS': 'Nerve sheath tumors',
-        'Sclerosing stromal tumor': 'Specialized gonadal neoplasms',
-        'Sclerotic fibroma': 'Fibromatous neoplasms',
-        'Sebaceoma': 'Adnexal and skin appendage neoplasms',
-        'Sebaceous carcinoma': 'Adnexal and skin appendage neoplasms',
-        'Secretory carcinoma': 'Ductal and lobular neoplasms',
-        'Seminoma, NOS': 'Germ cell neoplasms',
-        'Seromucinous carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Serous borderline tumor, NOS': 'Cystic, mucinous and serous neoplasms',
-        'Serous carcinoma, NOS': 'Cystic, mucinous and serous neoplasms',
-        'Serous cystadenoma, NOS': 'Cystic, mucinous and serous neoplasms',
-        'Serrated adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Sertoli-Leydig cell tumor of intermediate differentiation': 'Specialized gonadal neoplasms',
-        'Sertoli-Leydig cell tumor, intermediate differentiation, with heterologous elements': 'Specialized gonadal neoplasms',
-        'Sertoli-Leydig cell tumor, poorly differentiated': 'Specialized gonadal neoplasms',
-        'Sertoli-Leydig cell tumor, poorly differentiated, with heterologous elements': 'Specialized gonadal neoplasms',
-        'Sex cord-gonadal stromal tumor, NOS': 'Specialized gonadal neoplasms',
-        'Sex cord-gonadal stromal tumor, incompletely differentiated': 'Specialized gonadal neoplasms',
-        'Sex cord-gonadal stromal tumor, mixed forms': 'Specialized gonadal neoplasms',
-        'Sezary syndrome': 'Hodgkin and non-Hodgkin lymphomas',
-        'Signet ring cell carcinoma': 'Cystic, mucinous and serous neoplasms',
-        'Sinonasal papilloma, inverted': 'Transitional cell papillomas and carcinomas',
-        'Small cell carcinoma, NOS': 'Epithelial neoplasms',
-        'Small cell osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Small cell sarcoma': 'Soft tissue tumors and sarcomas',
-        'Smooth muscle tumor of uncertain malignant potential': 'Myomatous neoplasms',
-        'Soft tissue tumor, benign': 'Soft tissue tumors and sarcomas',
-        'Soft tissue tumors and sarcomas, NOS': 'Soft tissue tumors and sarcomas',
-        'Solid carcinoma, NOS': 'Adenomas and adenocarcinomas',
-        'Solid pseudopapillary neoplasm of the pancreas': 'Cystic, mucinous and serous neoplasms',
-        'Solid pseudopapillary tumor of ovary': 'Cystic, mucinous and serous neoplasms',
-        'Solitary fibrous tumor, NOS': 'Fibromatous neoplasms',
-        'Solitary fibrous tumor/Hemangiopericytoma, grade 1': 'Fibromatous neoplasms',
-        'Specialized gonadal neoplasms': 'Specialized gonadal neoplasms',
-        'Spindle cell carcinoma, NOS': 'Epithelial neoplasms',
-        'Spindle cell melanoma, NOS': 'Nevi and melanomas',
-        'Spindle cell melanoma, type B': 'Nevi and melanomas',
-        'Spindle cell nevus, NOS': 'Nevi and melanomas',
-        'Spindle cell rhabdomyosarcoma': 'Myomatous neoplasms',
-        'Spindle cell sarcoma': 'Soft tissue tumors and sarcomas',
-        'Spiradenoma, NOS': 'Adnexal and skin appendage neoplasms',
-        'Squamous cell carcinoma in situ, NOS': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, NOS': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, adenoid': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, clear cell type': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, keratinizing, NOS': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, large cell, nonkeratinizing, NOS': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, metastatic, NOS': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, small cell, nonkeratinizing': 'Squamous cell neoplasms',
-        'Squamous cell carcinoma, spindle cell': 'Squamous cell neoplasms',
-        'Squamous cell neoplasms': 'Squamous cell neoplasms',
-        'Subcutaneous panniculitis-like T-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Subependymal giant cell astrocytoma': 'Gliomas',
-        'Subependymoma': 'Gliomas',
-        'Sweat gland adenocarcinoma': 'Adnexal and skin appendage neoplasms',
-        'Synovial sarcoma, NOS': 'Synovial-like neoplasms',
-        'Synovial sarcoma, biphasic': 'Synovial-like neoplasms',
-        'Synovial sarcoma, spindle cell': 'Synovial-like neoplasms',
-        'T-cell large granular lymphocytic leukemia': 'Leukemias',
-        'T-cell/histiocyte rich large B-cell lymphoma': 'Hodgkin and non-Hodgkin lymphomas',
-        'Telangiectatic osteosarcoma': 'Osseous and chondromatous neoplasms',
-        'Tenosynovial giant cell tumor, NOS': 'Giant cell tumors',
-        'Teratocarcinoma': 'Germ cell neoplasms',
-        'Teratoma with malignant transformation': 'Germ cell neoplasms',
-        'Teratoma, NOS': 'Germ cell neoplasms',
-        'Teratoma, benign': 'Germ cell neoplasms',
-        'Teratoma, malignant, NOS': 'Germ cell neoplasms',
-        'Thecoma, NOS': 'Specialized gonadal neoplasms',
-        'Therapy-related myelodysplastic syndrome, NOS': 'Myelodysplastic syndromes',
-        'Therapy-related myeloid neoplasm': 'Leukemias',
-        'Thymic carcinoma, NOS': 'Thymic epithelial neoplasms',
-        'Thymic epithelial neoplasms': 'Thymic epithelial neoplasms',
-        'Thymoma, NOS': 'Thymic epithelial neoplasms',
-        'Thymoma, type A': 'Thymic epithelial neoplasms',
-        'Thymoma, type AB': 'Thymic epithelial neoplasms',
-        'Thymoma, type B1': 'Thymic epithelial neoplasms',
-        'Thymoma, type B2': 'Thymic epithelial neoplasms',
-        'Thymoma, type B3': 'Thymic epithelial neoplasms',
-        'Trabecular adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Transient abnormal myelopoiesis': 'Leukemias',
-        'Transitional cell carcinoma, NOS': 'Transitional cell papillomas and carcinomas',
-        'Transitional cell papillomas and carcinomas': 'Transitional cell papillomas and carcinomas',
-        'Trophoblastic tumor, epithelioid': 'Trophoblastic neoplasms',
-        'Tubular adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Tubular adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Tubulovillous adenoma, NOS': 'Adenomas and adenocarcinomas',
-        'Tumor cells, benign': 'Neoplasms',
-        'Tumor cells, malignant': 'Neoplasms',
-        'Tumor cells, uncertain whether benign or malignant': 'Neoplasms',
-        'Undifferentiated sarcoma': 'Soft tissue tumors and sarcomas',
-        'Urothelial carcinoma in situ': 'Transitional cell papillomas and carcinomas',
-        'Verrucous carcinoma, NOS': 'Squamous cell neoplasms',
-        'Villous adenocarcinoma': 'Adenomas and adenocarcinomas',
-        'Waldenstrom macroglobulinemia': 'Immunoproliferative diseases',
-        'Yolk sac tumor, NOS': 'Germ cell neoplasms',
-        'metastatic neuroblastoma': 'Neuroepitheliomatous neoplasms',
-        'myomatous neoplasm': 'myomatous neoplasm',
-    }
-    if include_disease_slims and not collate_results and ( 'diagnosis' in result_dataframe or 'morphology' in result_dataframe ):
-        # Make a new column called 'disease_slims', populated with slim terms corresponding to any mapped terms from `observation.diagnosis` or `observation.morphology`.
-        result_dataframe['disease_slims'] = [ set() for _ in range( len( result_dataframe ) ) ]
-        column_data_types['disease_slims'] = 'text'
-        for row_index, result_record in result_dataframe.iterrows():
-            for disease_column in [ 'diagnosis', 'morphology' ]:
-                if disease_column in result_dataframe:
-                    for term in result_dataframe.loc[row_index, disease_column]:
-                        if term in disease_slim_map and term != '':
-                            result_dataframe.loc[row_index, 'disease_slims'].add( disease_slim_map[term] )
-    # END :: REMOVE ME AFTER SLIM DB INFRASTRUCTURE UPDATE
-
     # Ensure the contents and ordering of the set of default columns for this endpoint
     # is the same whether or not additional column data (e.g. from other tables) has
     # been requested. Also make sure non-user-facing columns (e.g. `subject_data_at_gdc`)
@@ -1717,7 +1119,7 @@ def get_data(
                         # We have a nonzero-length list of non-null data values.
                         processed_cell_value = list()
 
-                        for list_element in current_cell_value:
+                        for list_element in sorted( current_cell_value ):
                             
                             processed_list_element = list_element
 

{cdapython-2.0.13 → cdapython-2.1.0}/cdapython/summarize.py

@@ -509,7 +509,7 @@ def intersect_results(
 #############################################################################################################################
 
 def summarize_files(
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -525,6 +525,13 @@ def summarize_files(
     set of rows, profiled across (user-modifiable) columns of interest.
 
     Arguments:
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Users can add a wildcard character * to
+            either or both ends of each search term to enable partial matches
+            to longer values. Example:
+                summarize_files( 'kidney', 'adeno*', 'hispanic or latino' )
+
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
             ALL of which must be met by all result rows.
@@ -634,7 +641,7 @@ def summarize_files(
         And yes, we know how those first two paragraphs look. We apologize to the entire English language.
     """
 
-    return summarize( table='file', match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, return_data_as=return_data_as, output_file=output_file )
+    return summarize( *search_terms, match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, return_data_as=return_data_as, output_file=output_file, table='file' )
 
 #############################################################################################################################
 #
@@ -651,7 +658,7 @@ def summarize_files(
 #############################################################################################################################
 
 def summarize_subjects(
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -667,6 +674,13 @@ def summarize_subjects(
     set of rows, profiled across (user-modifiable) columns of interest.
 
     Arguments:
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Users can add a wildcard character * to
+            either or both ends of each search term to enable partial matches
+            to longer values. Example:
+                summarize_subjects( 'kidney', 'adeno*', 'hispanic or latino' )
+
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
             ALL of which must be met by all result rows.
@@ -775,7 +789,7 @@ def summarize_subjects(
         And yes, we know how those first two paragraphs look. We apologize to the entire English language.
     """
 
-    return summarize( table='subject', match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, return_data_as=return_data_as, output_file=output_file )
+    return summarize( *search_terms, match_all=match_all, match_any=match_any, match_from_file=match_from_file, data_source=data_source, add_columns=add_columns, exclude_columns=exclude_columns, return_data_as=return_data_as, output_file=output_file, table='subject' )
 
 #############################################################################################################################
 #
@@ -793,8 +807,7 @@ def summarize_subjects(
 #############################################################################################################################
 
 def summarize(
-    table='',
-    *,
+    *search_terms,
     match_all=None,
     match_any=None,
     match_from_file={ 'input_file': '', 'input_column': '', 'cda_column_to_match': '' },
@@ -802,7 +815,8 @@ def summarize(
     add_columns=None,
     exclude_columns=None,
     return_data_as='',
-    output_file=''
+    output_file='',
+    table=''
 ):
     """
     For a set of rows in a user-specified table that all match a user-specified set of
@@ -810,8 +824,11 @@ def summarize(
     set of rows, profiled across (user-modifiable) columns of interest.
 
     Arguments:
-        table ( string; required: 'file' or 'subject' ):
-            The CDA table to be queried and summarized.
+        search_terms ( zero or more strings; optional: ):
+            One or more search terms (including phrases), all of which must be
+            associated with each result row. Leading and trailing wildcards '*'
+            are supported. Example:
+                summarize( 'kidney', 'adeno*', 'hispanic or latino', table='subject' )
 
         match_all ( string or list of strings; optional ):
             One or more conditions, expressed as filter strings (see below),
@@ -854,6 +871,9 @@ def summarize(
             resolvable path to a file into which summarize() will write
             JSON-formatted results.
 
+        table ( string; required: 'file' or 'subject' ):
+            The CDA table to be queried and summarized.
+
     Filter strings:
         Filter strings are expressions of the form "COLUMN_NAME OP VALUE"
         (note in particular that the whitespace surrounding OP is required),
@@ -882,13 +902,13 @@ def summarize(
         String VALUEs need not be quoted inside of filter strings. For example, to include
         the filters specified just above in the `match_all` argument, we can write:
 
-            summarize( table='subject', match_all=[ 'diagnosis = *duct*', 'sex = F*' ] )
+            summarize( match_all=[ 'diagnosis = *duct*', 'sex = F*' ], table='subject' )
 
         NULL is a special VALUE which can be used to match missing data. For
         example, to get a count summary for rows where the `sex` field is missing data,
         we can write:
 
-            summarize( table='subject', match_all=[ 'sex = NULL' ] )
+            summarize( match_all=[ 'sex = NULL' ], table='subject' )
 
     Returns:
 
@@ -934,6 +954,13 @@ def summarize(
     # Validate parameter inputs.
     #############################################################################################################################
 
+    search_list = list()
+    if len( search_terms ) > 0:
+        for search_string in search_terms:
+            # Let's not _immediately_ break our downstream processing with funky characters or evadable anomalies. Also,
+            # strip leading and trailing whitespace.
+            search_list.append( json.dumps( search_string ).strip( '"' ).strip() )
+
     # Normalize user-supplied parameter data so we can assume from here on out that these are always lists of values:
     # convert any of the following that come in as single values (instead of lists of values) into one-element lists,
     # and leave the rest unmodified.
@@ -993,6 +1020,7 @@ def summarize(
             cached_column_metadata=cached_column_metadata,
             valid_data_sources=valid_data_sources,
             table=table,
+            search_list=search_list,
             column=None,
             match_from_file=match_from_file,
             data_source=data_source,
@@ -1191,6 +1219,7 @@ def summarize(
     # Build an object to represent our upcoming API query.
 
     query_object = SummaryRequestBody()
+    query_object.search_list = search_list
     query_object.match_all = queries_for_match_all
     query_object.match_some = queries_for_match_any
     query_object.add_columns = columns_to_add

{cdapython-2.0.13 → cdapython-2.1.0}/cdapython/validation.py

@@ -395,7 +395,7 @@ def validate_and_transform_match_from_file_values( cda_column_to_match, target_d
 
 #############################################################################################################################
 #
-# validate_parameter_values( called_function, cached_column_metadata, valid_data_sources, table, match_from_file, data_source, add_columns, exclude_columns, return_data_as, output_file, log ):
+# validate_parameter_values( called_function, cached_column_metadata, valid_data_sources, table, search_list, match_from_file, data_source, add_columns, exclude_columns, return_data_as, output_file, log ):
 # 
 # Validate user-supplied parameters as passed to `called_function`, after first
 # having passed relevant parameters (`data_source`, `add_columns`, `exclude_columns`)
@@ -405,6 +405,7 @@ def validate_and_transform_match_from_file_values( cda_column_to_match, target_d
 # 
 #     * `called_function` is not in [ 'column_values', 'get_data', 'summarize' ]
 #     * `table` is not a CDA table (unless `called_function` is 'column_values', in which case `table` must be None)
+#     * `search_list` is not a list of strings
 #     * `column` is not a CDA column (unless `called_function` is 'get_data' or 'summarize', in which case `column` must be None)
 #     * `match_from_file` isn't a dict which (if non-null) specifies an accessible input file
 #       containing a user-specified column, whose values are to be matched against a CDA column
@@ -425,6 +426,7 @@ def validate_parameter_values(
     cached_column_metadata,
     valid_data_sources,
     table,
+    search_list,
     column,
     match_from_file,
     data_source,
@@ -447,6 +449,14 @@ def validate_parameter_values(
         if table is None or not isinstance( table, str ) or table not in cached_column_metadata['table'].unique():
             raise RuntimeError( f"The required parameter 'table' must be a searchable CDA table; you supplied '{table}', which is not. Please run tables() for a list." )
 
+    # Make sure `search_list` is a list of strings.
+    if not isinstance( search_list, list ):
+        raise RuntimeError( f"The internal 'search_list' parameter must be a string; please alert the CDA devs to this event, something is misconfigured in our code." )
+    else:
+        for search_term in search_list:
+            if not isinstance( search_term, str ):
+                raise RuntimeError( f"Search terms must be strings: you supplied '{search_term}', which is not." )
+
     # Make sure `column` exists, unless we're called by get_data() or summarize().
     if called_function in [ 'get_data', 'summarize' ]:
         if column is not None:

{cdapython-2.0.13 → cdapython-2.1.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cdapython"
-version = "2.0.13"
+version = "2.1.0"
 description = "NCI CRDC CDA front-end user interface library"
 authors = []
 readme = "README.md"
@@ -10,8 +10,8 @@ packages = [
 include = ["CHANGELOG.md"]
 
 [tool.poetry.dependencies]
-cda-client = ">=2.0.0"
-pandas = ">=2.2.3"
+cda-client = ">=2.1.0"
+pandas = ">=2.2.3,<3.0.0"
 python = "^3.9"
 pyyaml = ">= 6.0.0"
 tabulate = ">=0.9.0"

cdapython-2.0.13/CHANGELOG.md

@@ -1,21 +0,0 @@
-2025-12-09: 2.0.13: add POC `include\_disease\_slims` Boolean flag to get\_data()
-
-2025-10-31: 2.0.12: standardize debug-layer SQL echo; adjust column\_values() to handle known pathologies
-
-2025-10-27: 2.0.11: _cough_ bugfix for previous
-
-2025-10-27: 2.0.10: integrate column\_values() parameter validation with shared validation library; expand support for column\_values( data\_source ) to accept list values in addition to single strings
-
-2025-10-22: 2.0.9: parametrize data\_source check in column\_values()
-
-2025-10-20: 2.0.8: rename CDS to GC throughout
-
-2025-10-08: 2.0.7: fix malformed column metadata selector inside `collate=True` provenance management in get\_data()
-
-2025-09-17: 2.0.6: update ternary numeric comparison handling for latest API ternary operator syntax support
-
-2025-08-18: 2.0.2: update PyYAML build dependency
-
-2025-08-18: 2.0.1: update default API URL
-
-2025-08-18: 2.0.0: initial public release to PyPI