def set_meta( self, dataset, overwrite = True, **kwd ):
"""Sets the metadata information for datasets previously determined to be in bed format."""
i = 0
if dataset.has_data():
for i, line in enumerate( file(dataset.file_name) ):
metadata_set = False
line = line.rstrip('\r\n')
if line and not line.startswith('#'):
elems = line.split('\t')
if len(elems) > 2:
for startswith in data.col1_startswith:
if line.lower().startswith( startswith ):
if len( elems ) > 3:
if overwrite or not dataset.metadata.element_is_set( 'nameCol' ):
dataset.metadata.nameCol = 4
if len(elems) < 6:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 0
else:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 6
metadata_set = True
break
if metadata_set: break
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i )
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
line = line.rstrip('\r\n')
if line and not line.startswith( '#' ):
elems = line.split( '\t' )
valid_start = False
valid_end = False
if len( elems ) == 9:
try:
start = int( elems[3] )
valid_start = True
except:
if elems[3] == '.':
valid_start = True
try:
end = int( elems[4] )
valid_end = True
except:
if elems[4] == '.':
valid_end = True
strand = elems[6]
phase = elems[7]
if valid_start and valid_end and start < end and strand in self.valid_gff3_strand and phase in self.valid_gff3_phase:
break
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i )
def set_meta(self, dataset, **kwd):
Tabular.set_meta( self, dataset, **kwd)
dataset.metadata.markerCol = 1
header = file(dataset.file_name, 'r').readlines()[0].strip().split('\t')
dataset.metadata.columns = len(header)
t = ['numeric' for x in header]
t[0] = 'string'
dataset.metadata.column_types = t
return True
def set_meta(self, dataset, **kwd):
Tabular.set_meta(self, dataset, **kwd)
dataset.metadata.markerCol = 1
header = open(dataset.file_name, 'r').readlines()[0].strip().split('\t')
dataset.metadata.columns = len(header)
t = ['numeric' for x in header]
t[0] = 'string'
dataset.metadata.column_types = t
return True
def set_meta(self, dataset, overwrite=True, **kwd):
Tabular.set_meta(self,
dataset,
overwrite=overwrite,
max_data_lines=None,
max_guess_type_data_lines=1000,
**kwd)
if dataset.metadata.comment_metadata is None:
dataset_comment_metadata = DatasetCommentMetadata(dataset)
dataset.metadata.comment_metadata = dataset_comment_metadata.comment_metadata.copy(
)
self.set_dataset_metadata_from_comments(dataset)
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
line = line.rstrip('\r\n')
if line and not line.startswith( '#' ):
elems = line.split( '\t' )
if len(elems) == 9:
try:
int( elems[3] )
int( elems[4] )
break
except:
pass
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i )
def set_meta(self, dataset, overwrite=True, skip=None, max_data_lines=None, **kwd):
Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines)
tis_args = set()
try:
fh = open(dataset.file_name)
for line in fh:
fields = line.strip().split("\t")
try:
tis_args.add(fields[0])
except IndexError:
pass
dataset.metadata.args = []
dataset.metadata.args += tis_args
finally:
fh.close()
def set_meta( self, dataset, overwrite = True, **kwd ):
i = 0
for i, line in enumerate( file ( dataset.file_name ) ):
line = line.rstrip('\r\n')
if line and not line.startswith( '#' ):
elems = line.split( '\t' )
try:
float( elems[0] ) #"Wiggle track data values can be integer or real, positive or negative values"
break
except:
do_break = False
for str in data.col1_startswith:
if elems[0].lower().startswith(str):
do_break = True
break
if do_break:
break
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i )
def set_meta(self,
dataset,
overwrite=True,
skip=None,
max_data_lines=None,
**kwd):
Tabular.set_meta(self, dataset, overwrite, skip, max_data_lines)
tis_args = set()
try:
fh = open(dataset.file_name)
for line in fh:
fields = line.strip().split('\t')
try:
tis_args.add(fields[0])
except IndexError:
pass
dataset.metadata.args = []
dataset.metadata.args += tis_args
finally:
fh.close()
def set_meta(self, dataset, **kwd):
Tabular.set_meta(self, dataset, skip=None, **kwd)
def set_meta( self, dataset, overwrite = True, **kwd ):
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 1 )
def set_meta( self, dataset, overwrite = True, first_line_is_header = False, **kwd ):
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 0 )
"""Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
if dataset.has_data():
for i, line in enumerate( file( dataset.file_name ) ):
line = line.rstrip( '\r\n' )
if line:
if ( first_line_is_header or line[0] == '#' ):
self.init_meta( dataset )
line = line.strip( '#' )
elems = line.split( '\t' )
valid = dict( alias_helper ) # shrinks
for index, col_name in enumerate( elems ):
if col_name in valid:
meta_name = valid[col_name]
if overwrite or not dataset.metadata.element_is_set( meta_name ):
setattr( dataset.metadata, meta_name, index+1 )
values = alias_spec[ meta_name ]
start = values.index( col_name )
for lower in values[ start: ]:
del valid[ lower ] # removes lower priority keys
break # Our metadata is set, so break out of the outer loop
else:
# Header lines in Interval files are optional. For example, BED is Interval but has no header.
# We'll make a best guess at the location of the metadata columns.
metadata_is_set = False
elems = line.split( '\t' )
if len( elems ) > 2:
for str in data.col1_startswith:
if line.lower().startswith( str ):
if overwrite or not dataset.metadata.element_is_set( 'chromCol' ):
dataset.metadata.chromCol = 1
try:
int( elems[1] )
if overwrite or not dataset.metadata.element_is_set( 'startCol' ):
dataset.metadata.startCol = 2
except:
pass # Metadata default will be used
try:
int( elems[2] )
if overwrite or not dataset.metadata.element_is_set( 'endCol' ):
dataset.metadata.endCol = 3
except:
pass # Metadata default will be used
if len( elems ) > 3:
try:
int( elems[3] )
except:
if overwrite or not dataset.metadata.element_is_set( 'nameCol' ):
dataset.metadata.nameCol = 4
if len( elems ) < 6 or elems[5] not in data.valid_strand:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 0
else:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 6
metadata_is_set = True
break
if metadata_is_set:
break # Our metadata is set, so break out of the outer loop
def set_meta( self, dataset, overwrite = True, **kwd ):
Tabular.set_meta( self, dataset, overwrite=overwrite, max_data_lines=None, max_guess_type_data_lines=1000, **kwd )
if dataset.metadata.comment_metadata is None:
dataset_comment_metadata = DatasetCommentMetadata( dataset )
dataset.metadata.comment_metadata = dataset_comment_metadata.comment_metadata.copy()
self.set_dataset_metadata_from_comments( dataset )
def set_meta(self, dataset, **kwd):
Tabular.set_meta(self, dataset, **kwd)
if dataset.has_data():
with open(dataset.file_name, errors='ignore') as fh:
dataset.metadata.dimension = self._get_dimension(fh)
def set_meta(self, dataset, **kwd):
Tabular.set_meta(self, dataset, **kwd)
def set_meta( self, dataset, **kwd ):
Tabular.set_meta( self, dataset, **kwd )
def set_meta( self, dataset, overwrite = True, first_line_is_header = False, **kwd ):
Tabular.set_meta( self, dataset, overwrite = overwrite, skip = 0 )
"""Tries to guess from the line the location number of the column for the chromosome, region start-end and strand"""
if dataset.has_data():
empty_line_count = 0
num_check_lines = 100 # only check up to this many non empty lines
for i, line in enumerate( file( dataset.file_name ) ):
line = line.rstrip( '\r\n' )
if line:
if ( first_line_is_header or line[0] == '#' ):
self.init_meta( dataset )
line = line.strip( '#' )
elems = line.split( '\t' )
valid = dict( alias_helper ) # shrinks
for index, col_name in enumerate( elems ):
if col_name in valid:
meta_name = valid[col_name]
if overwrite or not dataset.metadata.element_is_set( meta_name ):
setattr( dataset.metadata, meta_name, index+1 )
values = alias_spec[ meta_name ]
start = values.index( col_name )
for lower in values[ start: ]:
del valid[ lower ] # removes lower priority keys
break # Our metadata is set, so break out of the outer loop
else:
# Header lines in Interval files are optional. For example, BED is Interval but has no header.
# We'll make a best guess at the location of the metadata columns.
metadata_is_set = False
elems = line.split( '\t' )
if len( elems ) > 2:
for str in data.col1_startswith:
if line.lower().startswith( str ):
if overwrite or not dataset.metadata.element_is_set( 'chromCol' ):
dataset.metadata.chromCol = 1
try:
int( elems[1] )
if overwrite or not dataset.metadata.element_is_set( 'startCol' ):
dataset.metadata.startCol = 2
except:
pass # Metadata default will be used
try:
int( elems[2] )
if overwrite or not dataset.metadata.element_is_set( 'endCol' ):
dataset.metadata.endCol = 3
except:
pass # Metadata default will be used
#we no longer want to guess that this column is the 'name', name must now be set manually for interval files
#we will still guess at the strand, as we can make a more educated guess
#if len( elems ) > 3:
# try:
# int( elems[3] )
# except:
# if overwrite or not dataset.metadata.element_is_set( 'nameCol' ):
# dataset.metadata.nameCol = 4
if len( elems ) < 6 or elems[5] not in data.valid_strand:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 0
else:
if overwrite or not dataset.metadata.element_is_set( 'strandCol' ):
dataset.metadata.strandCol = 6
metadata_is_set = True
break
if metadata_is_set or ( i - empty_line_count ) > num_check_lines:
break # Our metadata is set or we examined 100 non-empty lines, so break out of the outer loop
else:
empty_line_count += 1
