def fromgff3(filename):
"""
Extract feature rows from a GFF3 file.
.. versionadded:: 0.2
"""
# parse file as tab-delimited
t0 = fromtsv(filename)
# push header
t1 = pushheader(t0, ('seqid', 'source', 'type', 'start', 'end', 'score', 'strand', 'phase', 'attributes'))
# skip comments
t2 = skipcomments(t1, '#')
# ignore any row not 9 values long (e.g., trailing fasta)
t3 = rowlenselect(t2, 9)
# parse attributes into a dict
t4 = convert(t3, 'attributes', gff3_parse_attributes)
# parse coordinates
t5 = convert(t4, ('start', 'end'), int)
return HybridRowView(t5)
def convertgff3(tbl):
# push header
t1 = pushheader(tbl, ('seqid', 'source', 'type', 'start', 'end', 'score', 'strand', 'phase', 'attributes'))
# skip comments
t2 = skipcomments(t1, '#')
# ignore any row not 9 values long (e.g., trailing fasta)
t3 = rowlenselect(t2, 9)
# parse attributes into a dict
t4 = convert(t3, 'attributes', gff3_parse_attributes)
# parse coordinates
t5 = convert(t4, ('start', 'end'), int)
return HybridRowView(t5)
def lenstats(table, field):
"""
Convenience function to report statistics on value lengths under the given
field. E.g.::
>>> from petl import lenstats
>>> table1 = [['foo', 'bar'],
... [1, 'a'],
... [2, 'aaa'],
... [3, 'aa'],
... [4, 'aaa'],
... [5, 'aaaaaaaaaaa']]
>>> lenstats(table1, 'bar')
{'count': 5, 'errors': 0, 'min': 1.0, 'max': 11.0, 'sum': 20.0, 'mean': 4.0}
"""
return stats(convert(table, field, lambda v: len(v)), field)
def lenstats(table, field):
"""
Convenience function to report statistics on value lengths under the given
field. E.g.::
>>> from petl import lenstats
>>> table1 = [['foo', 'bar'],
... [1, 'a'],
... [2, 'aaa'],
... [3, 'aa'],
... [4, 'aaa'],
... [5, 'aaaaaaaaaaa']]
>>> lenstats(table1, 'bar')
{'count': 5, 'errors': 0, 'min': 1.0, 'max': 11.0, 'sum': 20.0, 'mean': 4.0}
"""
return stats(convert(table, field, lambda v: len(v)), field)
