from petl import skipcomments, look
look(table1)
table2 = skipcomments(table1, '##')
look(table2)
# unpack
table1 = [['foo', 'bar'],
[1, ['a', 'b']],
[2, ['c', 'd']],
[3, ['e', 'f']]]
from petl import unpack, look
look(table1)
table2 = unpack(table1, 'bar', ['baz', 'quux'])
look(table2)
# join
table1 = [['id', 'colour'],
[1, 'blue'],
[2, 'red'],
[3, 'purple']]
table2 = [['id', 'shape'],
[1, 'circle'],
[3, 'square'],
[4, 'ellipse']]
table5 = [['id', 'colour'],
[1, 'blue'],
from petl import skipcomments, look
look(table1)
table2 = skipcomments(table1, '##')
look(table2)
# unpack
table1 = [['foo', 'bar'],
[1, ['a', 'b']],
[2, ['c', 'd']],
[3, ['e', 'f']]]
from petl import unpack, look
look(table1)
table2 = unpack(table1, 'bar', ['baz', 'quux'])
look(table2)
# join
table1 = [['id', 'colour'],
[1, 'blue'],
[2, 'red'],
[3, 'purple']]
table2 = [['id', 'shape'],
[1, 'circle'],
[3, 'square'],
[4, 'ellipse']]
table5 = [['id', 'colour'],
[1, 'blue'],
def unpack_list(self,
column,
include_original=False,
missing=None,
replace=False,
max_columns=None):
"""
Unpack list values from one column into separate columns. Numbers the
columns.
.. code-block:: python
# Begin with a list in column
json = [{'id': '5421',
'name': 'Jane Green',
'phones': ['512-699-3334', '512-222-5478']
}
]
tbl = Table(json)
print (tbl)
>>> {'id': '5421', 'name': 'Jane Green', 'phones': ['512-699-3334', '512-222-5478']}
tbl.unpack_list('phones', replace=True)
print (tbl)
>>> {'id': '5421', 'name': 'Jane Green', 'phones_0': '512-699-3334', 'phones_1': '512-222-5478'} # noqa: E501
`Args:`
column: str
The column name to unpack
include_original: boolean
Retain original column after unpacking
sample_size: int
Number of rows to sample before determining columns
missing: str
If a value is missing, the value to fill it with
replace: boolean
Return new table or replace existing
max_columns: int
The maximum number of columns to unpack
`Returns:`
None
"""
# Convert all column values to list to avoid unpack errors
self.table = petl.convert(
self.table, column, lambda v: [v]
if not isinstance(v, list) else v)
# Find the max number of values in list for all rows
col_count = 0
for row in self.cut(column):
if len(row[column]) > col_count:
col_count = len(row[column])
# If max columns provided, set max columns
if col_count > 0 and max_columns:
col_count = max_columns
# Create new column names "COL_01, COL_02"
new_cols = []
for i in range(col_count):
new_cols.append(column + '_' + str(i))
tbl = petl.unpack(self.table,
column,
new_cols,
include_original=include_original,
missing=missing)
if replace:
self.table = tbl
else:
return tbl
