def group_by(self, key, key_name=None, key_type=None):
"""
Create a new :class:`Table` for unique value and return them as a
:class:`.TableSet`. The :code:`key` can be either a column name
or a function that returns a value to group by.
Note that when group names will always be coerced to a string,
regardless of the format of the input column.
:param key: Either the name of a column from the this table
to group by, or a :class:`function` that takes a row and returns
a value to group by.
:param key_name: A name that describes the grouped properties.
Defaults to the column name that was grouped on or "group" if
grouping with a key function. See :class:`.TableSet` for more.
:param key_type: An instance some subclass of :class:`.DataType`. If
not provided it will default to a :class`.Text`.
:returns: A :class:`.TableSet` mapping where the keys are unique
values from the :code:`key` and the values are new :class:`Table`
instances containing the grouped rows.
"""
from agate.tableset import TableSet
key_is_row_function = hasattr(key, '__call__')
if key_is_row_function:
key_name = key_name or 'group'
key_type = key_type or Text()
else:
column = self._columns[key]
key_name = key_name or column.name
key_type = key_type or column.data_type
groups = OrderedDict()
for row in self._rows:
if key_is_row_function:
group_name = key(row)
else:
group_name = row[column.name]
group_name = key_type.cast(group_name)
if group_name not in groups:
groups[group_name] = []
groups[group_name].append(row)
output = OrderedDict()
for group, rows in groups.items():
output[group] = self._fork(rows)
return TableSet(output.values(),
output.keys(),
key_name=key_name,
key_type=key_type)
def group_by(self, key, key_name=None, key_type=None):
"""
Create a new :class:`Table` for unique value and return them as a
:class:`.TableSet`. The :code:`key` can be either a column name
or a function that returns a value to group by.
Note that when group names will always be coerced to a string,
regardless of the format of the input column.
:param key: Either the name of a column from the this table
to group by, or a :class:`function` that takes a row and returns
a value to group by.
:param key_name: A name that describes the grouped properties.
Defaults to the column name that was grouped on or "group" if
grouping with a key function. See :class:`.TableSet` for more.
:param key_type: An instance some subclass of :class:`.ColumnType`. If
not provided it will default to a :class`.TextType`.
:returns: A :class:`.TableSet` mapping where the keys are unique
values from the :code:`key` and the values are new :class:`Table`
instances containing the grouped rows.
:raises: :exc:`.ColumnDoesNotExistError`
"""
key_is_row_function = hasattr(key, '__call__')
if key_is_row_function:
key_name = key_name or 'group'
else:
key_name = key_name or key
try:
i = self._column_names.index(key)
except ValueError:
raise ColumnDoesNotExistError(key)
groups = OrderedDict()
for row in self.rows:
if key_is_row_function:
group_name = six.text_type(key(row))
else:
group_name = six.text_type(row[i])
# print group_name
if group_name not in groups:
groups[group_name] = []
groups[group_name].append(row)
output = OrderedDict()
for group, rows in groups.items():
output[group] = self._fork(rows)
return TableSet(output, key_name=key_name, key_type=key_type)
def test_tableset_from_csv(self):
tableset = TableSet.from_csv('examples/tableset', self.tester)
self.assertSequenceEqual(tableset.column_names, ['letter', 'number'])
self.assertSequenceEqual(tuple(map(type, tableset.column_types)), [Text, Number])
self.assertEqual(len(tableset['table1'].columns), 2)
self.assertSequenceEqual(tableset['table1'].rows[0], ['a', 1])
self.assertSequenceEqual(tableset['table1'].rows[1], ['a', 3])
self.assertSequenceEqual(tableset['table1'].rows[2], ['b', 2])
def test_tableset_from_csv(self):
tableset = TableSet.from_csv('examples/tableset', column_types=self.tester)
self.assertSequenceEqual(tableset.column_names, ['letter', 'number'])
self.assertSequenceEqual(tuple(map(type, tableset.column_types)), [Text, Number])
self.assertEqual(len(tableset['table1'].columns), 2)
self.assertSequenceEqual(tableset['table1'].rows[0], ['a', 1])
self.assertSequenceEqual(tableset['table1'].rows[1], ['a', 3])
self.assertSequenceEqual(tableset['table1'].rows[2], ['b', 2])
def from_json(cls, path, column_names=None, column_types=None, keys=None, **kwargs):
"""
Create a new :class:`TableSet` from a directory of JSON files or a
single JSON object with key value (Table key and list of row objects)
pairs for each :class:`Table`.
See :meth:`.Table.from_json` for additional details.
:param path:
Path to a directory containing JSON files or filepath/file-like
object of nested JSON file.
:param keys:
A list of keys of the top-level dictionaries for each file. If
specified, length must be equal to number of JSON files in path.
:param column_types:
See :meth:`Table.__init__`.
"""
from agate.tableset import TableSet
if isinstance(path, six.string_types) and not os.path.isdir(path) and not os.path.isfile(path):
raise IOError('Specified path doesn\'t exist.')
tables = OrderedDict()
if isinstance(path, six.string_types) and os.path.isdir(path):
filepaths = glob(os.path.join(path, '*.json'))
if keys is not None and len(keys) != len(filepaths):
raise ValueError('If specified, keys must have length equal to number of JSON files')
for i, filepath in enumerate(filepaths):
name = os.path.split(filepath)[1].strip('.json')
if keys is not None:
tables[name] = Table.from_json(filepath, keys[i], column_types=column_types, **kwargs)
else:
tables[name] = Table.from_json(filepath, column_types=column_types, **kwargs)
else:
if hasattr(path, 'read'):
js = json.load(path, object_pairs_hook=OrderedDict, parse_float=Decimal, **kwargs)
else:
with open(path, 'r') as f:
js = json.load(f, object_pairs_hook=OrderedDict, parse_float=Decimal, **kwargs)
for key, value in js.items():
tables[key] = Table.from_object(value, column_types=column_types, **kwargs)
return TableSet(tables.values(), tables.keys())
def group_by(self, key):
"""
Create a new :class:`Table` for unique value and return them as a
:class:`.TableSet`. The :code:`key` can be either a column name
or a function that returns a value to group by.
Note that when group names will always be coerced to a string,
regardless of the format of the input column.
:param key: Either the name of a column from the this table
to group by, or a :class:`function` that takes a row and returns
a value to group by.
:returns: A :class:`.TableSet` mapping where the keys are unique
values from the :code:`key` and the values are new :class:`Table`
instances containing the grouped rows.
:raises: :exc:`.ColumnDoesNotExistError`
"""
key_is_row_function = hasattr(key, '__call__')
if not key_is_row_function:
try:
i = self._column_names.index(key)
except ValueError:
raise ColumnDoesNotExistError(key)
groups = OrderedDict()
for row in self.rows:
if key_is_row_function:
group_name = six.text_type(key(row))
else:
group_name = six.text_type(row[i])
if group_name not in groups:
groups[group_name] = []
groups[group_name].append(row)
output = {}
for group, rows in groups.items():
output[group] = self._fork(rows)
return TableSet(output)
def from_csv(cls,
dir_path,
column_names=None,
column_types=None,
row_names=None,
header=True,
**kwargs):
"""
Create a new :class:`TableSet` from a directory of CSVs.
See :meth:`.Table.from_csv` for additional details.
:param dir_path:
Path to a directory full of CSV files. All CSV files in this
directory will be loaded.
:param column_names:
See :meth:`Table.__init__`.
:param column_types:
See :meth:`Table.__init__`.
:param row_names:
See :meth:`Table.__init__`.
:param header:
See :meth:`Table.from_csv`.
"""
from agate.tableset import TableSet
if not os.path.isdir(dir_path):
raise IOError('Specified path doesn\'t exist or isn\'t a directory.')
tables = OrderedDict()
for path in glob(os.path.join(dir_path, '*.csv')):
name = os.path.split(path)[1].strip('.csv')
tables[name] = Table.from_csv(path,
column_names,
column_types,
row_names=row_names,
header=header,
**kwargs)
return TableSet(tables.values(), tables.keys())
def test_tableset_from_csv_invalid_dir(self):
with self.assertRaises(IOError):
TableSet.from_csv('quack', self.tester)
def test_tableset_from_csv_no_headers(self):
with self.assertRaises(ValueError):
TableSet.from_csv('examples/tableset', self.tester, header=False)
def test_tableset_from_csv_invalid_dir(self):
with self.assertRaises(IOError):
TableSet.from_csv('quack', self.tester)
def test_tableset_from_csv_no_headers(self):
with self.assertRaises(ValueError):
TableSet.from_csv('examples/tableset', self.tester, header=False)
