remove unused code (#1741)

* remove unused code

* Update merged schema files with markdown descriptions

---------

Co-authored-by: github-actions <github-actions@cdisc.org>

Author: gerrycampion

cdisc_rules_engine/check_operators/helpers.py

@@ -430,4 +430,3 @@ def flatten_list(data, items):
 vectorized_get_dict_key = np.vectorize(get_dict_key_val)
 vectorized_is_in = np.vectorize(is_in)
 vectorized_case_insensitive_is_in = np.vectorize(case_insensitive_is_in)
-vectorized_len = np.vectorize(len)

cdisc_rules_engine/constants/__init__.py

@@ -2,17 +2,6 @@
 
 # a message like: [INFO 2021-12-29 17:10:26,575 - module.py:44] - Log Message
 LOG_FORMAT: str = "[%(levelname)s %(asctime)s - %(filename)s:%(lineno)s] - %(message)s"
-XPT_LABEL_PATTERN: str = (
-    "HEADER RECORD\\*{7}MEMBER {2}HEADER RECORD!{7}0{17}160{8}140 "
-    "{2}HEADER RECORD\\*{7}DSCRPTR HEADER RECORD!{7}0{30}"
-    "  SAS\\s{5}.{8}SASDATA .{16}\\s{24}.{16}.{16}\\s{16}(?P<label>.{40})"
-)
-
-XPT_MODIFIED_DATE_PATTERN: str = (
-    "HEADER RECORD\\*{7}MEMBER {2}HEADER RECORD!{7}0{17}160{8}140 "
-    "{2}HEADER RECORD\\*{7}DSCRPTR HEADER RECORD!{7}0{30}"
-    "  SAS\\s{5}.{8}SASDATA .{16}\\s{24}.{16}(?P<modified_date>.{16})\\s{16}.{40}"
-)
 
 NULL_FLAVORS = ["", None, {}, {None}, [], [None], np.nan]
 

cdisc_rules_engine/constants/domains.py

@@ -1,5 +1,4 @@
 SUPPLEMENTARY_DOMAINS = ("SUPP", "SQ")
-AP_DOMAIN_LENGTH: int = 4
 AP_DOMAIN: str = "AP"
 APFA_DOMAIN: str = "APFA"
 APRELSUB_DOMAIN: str = "APRELSUB"

cdisc_rules_engine/constants/patterns.py

@@ -15,7 +15,6 @@ class DefaultFilePaths(BaseEnum):
     STANDARD_MODELS_CACHE_FILE = "standards_models.pkl"
     VARIABLE_METADATA_CACHE_FILE = "variables_metadata.pkl"
     VARIABLE_CODELIST_CACHE_FILE = "variable_codelist_maps.pkl"
-    CODELIST_TERM_MAP_CACHE_FILE = "codelist_term_maps.pkl"
     CUSTOM_RULES_CACHE_FILE = "custom_rules.pkl"
     CUSTOM_RULES_DICTIONARY = "custom_rules_dictionary.pkl"
     LOCAL_XSD_FILE_DIR = join("resources", "schema", "xml")

cdisc_rules_engine/enums/default_file_paths.py

@@ -11,7 +11,6 @@
     DomainNotFoundInDefineXMLError,
     InvalidDatasetFormat,
     InvalidJSONFormat,
-    NumberOfAttemptsExceeded,
     InvalidDictionaryVariable,
     UnsupportedDictionaryType,
     FailedSchemaValidation,
@@ -37,7 +36,6 @@
     "DomainNotFoundInDefineXMLError",
     "InvalidDatasetFormat",
     "InvalidJSONFormat",
-    "NumberOfAttemptsExceeded",
     "InvalidDictionaryVariable",
     "UnsupportedDictionaryType",
     "FailedSchemaValidation",

cdisc_rules_engine/exceptions/__init__.py

@@ -87,10 +87,6 @@ class InvalidCSVFile(EngineError):
     description = "CSV data is malformed."
 
 
-class NumberOfAttemptsExceeded(EngineError):
-    pass
-
-
 class InvalidDictionaryVariable(EngineError):
     description = (
         "Provided dictionary variable does not correspond to a dictionary term type"

cdisc_rules_engine/exceptions/custom_exceptions.py

@@ -57,15 +57,6 @@ def get_variables_metadata(self, dataset_name: str) -> DatasetInterface:
         Gets variables metadata of a dataset.
         """
 
-    @abstractmethod
-    def get_dataset_by_type(
-        self, dataset_name: str, dataset_type: str, **params
-    ) -> DatasetInterface:
-        """
-        Generic function to return dataset based on the type.
-        dataset_type param can be: contents, metadata, variables_metadata.
-        """
-
     @abstractmethod
     def concat_split_datasets(
         self,

cdisc_rules_engine/interfaces/data_service_interface.py

@@ -405,10 +405,6 @@ def partition_isin(partition):
         result = self._data.map_partitions(partition_isin)
         return result
 
-    def filter_by_value(self, column, values):
-        mask = self._data[column].isin(values)
-        return self.__class__(self._data[mask])
-
     def max(self, *args, **kwargs):
         result = self._data.max(*args, **kwargs)
         return self.__class__(result)

cdisc_rules_engine/models/dataset/dask_dataset.py

@@ -3,6 +3,5 @@
 
 class DatasetTypes(BaseEnum):
     CONTENTS = "contents"
-    METADATA = "metadata"
-    RAW_METADATA = "raw_metadata"
+    DATASET_METADATA = "dataset_metadata"
     VARIABLES_METADATA = "variables_metadata"