def subsetFileMapping(self, file_type=None, sample_id=None):
"""
subset by one or more values of different columns from sample file mapping
file_type: file type/types, corresponding to 'FILE_TYPE' column
sample_id: sample ID/IDs
"""
subset = self.sampleFileMapping
subset = utils.subsetBy(subset, "FILE_TYPE", file_type)
subset = utils.subsetBy(subset, "ID", sample_id)
return subset
def subsetSampleAnnotation(self,
column,
values,
subset=None,
exact_match=True):
"""
subset by one or more values of different columns from sample file mapping
:param column: valid column in sample annotation
:param values: values of column to subset
:param subset: subset sample annotation
:param exact_match: whether to match substrings in the sample annotation, false allows substring matching
"""
sa_cols = set(self.SAMPLE_ANNOTATION_COLUMNS)
if subset is None:
subset = self.annotationTable
else:
# check type for subset
if not isinstance(subset, pd.DataFrame):
raise TypeError(f"Is not pandas DataFrame\n {subset}")
if not sa_cols <= set(
subset.columns): # check if mandatory cols not contained
raise ValueError(
f"Subset columns not the same as {sa_cols}\ngot: {subset.columns}"
)
# check if column is valid
if column not in sa_cols:
raise KeyError(
f"Column '{column}' not present in sample annotation.")
return utils.subsetBy(subset, column, values, exact_match=exact_match)
def subsetSampleAnnotation(self, column, values, subset=None):
"""
subset by one or more values of different columns from sample file mapping
:param column: valid column in sample annotation
:param values: values of column to subset
:param subset: subset sample annotation
"""
sa_cols = set(self.SAMPLE_ANNOTATION_COLUMNS)
if subset is None:
subset = self.sa
else:
# check type for subset
if not isinstance(subset, pd.DataFrame):
raise TypeError(f"Is not pandas DataFrame\n {subset}")
if not sa_cols <= set(subset.columns): # check if mandatory cols not contained
raise ValueError(f"Subset columns not the same as {sa_cols}\ngot: {subset.columns}")
# check if column is valid
if not column in sa_cols:
raise KeyError(f"Column '{column}' invalid for sample annotation")
return utils.subsetBy(subset, column, values)