class TestFactor(unittest.TestCase):
def setUp(self):
self.factor = Factor(["a", "b", "b", "a", "a", "c", "c", "c"])
def test_getitem(self):
self.assertEqual(self.factor[0], "a")
self.assertEqual(self.factor[-1], "c")
subf = self.factor[[0, 1, 2]]
tm.assert_almost_equal(subf.labels, [0, 1, 1])
subf = self.factor[self.factor.asarray() == "c"]
tm.assert_almost_equal(subf.labels, [2, 2, 2])
def test_constructor_unsortable(self):
arr = np.array([1, 2, 3, datetime.now()], dtype="O")
# it works!
factor = Factor(arr)
def test_factor_agg(self):
import pandas.core.frame as frame
arr = np.arange(len(self.factor))
f = np.sum
agged = frame.factor_agg(self.factor, arr, f)
labels = self.factor.labels
for i, idx in enumerate(self.factor.levels):
self.assertEqual(f(arr[labels == i]), agged[i])
class TestFactor(unittest.TestCase):
def setUp(self):
self.factor = Factor(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
def test_getitem(self):
self.assertEqual(self.factor[0], 'a')
self.assertEqual(self.factor[-1], 'c')
subf = self.factor[[0, 1, 2]]
tm.assert_almost_equal(subf.labels, [0, 1, 1])
subf = self.factor[self.factor.asarray() == 'c']
tm.assert_almost_equal(subf.labels, [2, 2, 2])
def test_factor_agg(self):
import pandas.core.frame as frame
arr = np.arange(len(self.factor))
f = np.sum
agged = frame.factor_agg(self.factor, arr, f)
labels = self.factor.labels
for i, idx in enumerate(self.factor.levels):
self.assertEqual(f(arr[labels == i]), agged[i])
class TestFactor(unittest.TestCase):
def setUp(self):
self.factor = Factor(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
def test_getitem(self):
self.assertEqual(self.factor[0], 'a')
self.assertEqual(self.factor[-1], 'c')
subf = self.factor[[0, 1, 2]]
tm.assert_almost_equal(subf.labels, [0, 1, 1])
subf = self.factor[self.factor.asarray() == 'c']
tm.assert_almost_equal(subf.labels, [2, 2, 2])
def test_constructor_unsortable(self):
arr = np.array([1, 2, 3, datetime.now()], dtype='O')
# it works!
factor = Factor(arr)
def test_factor_agg(self):
import pandas.core.frame as frame
arr = np.arange(len(self.factor))
f = np.sum
agged = frame.factor_agg(self.factor, arr, f)
labels = self.factor.labels
for i, idx in enumerate(self.factor.levels):
self.assertEqual(f(arr[labels == i]), agged[i])
def panel_index(time, panels, names=['time', 'panel']):
"""
Returns a multi-index suitable for a panel-like DataFrame
Parameters
----------
time : array-like
Time index, does not have to repeat
panels : array-like
Panel index, does not have to repeat
names : list, optional
List containing the names of the indices
Returns
-------
multi_index : MultiIndex
Time index is the first level, the panels are the second level.
Examples
--------
>>> years = range(1960,1963)
>>> panels = ['A', 'B', 'C']
>>> panel_idx = panel_index(years, panels)
>>> panel_idx
MultiIndex([(1960, 'A'), (1961, 'A'), (1962, 'A'), (1960, 'B'),
(1961, 'B'), (1962, 'B'), (1960, 'C'), (1961, 'C'),
(1962, 'C')], dtype=object)
or
>>> import numpy as np
>>> years = np.repeat(range(1960,1963), 3)
>>> panels = np.tile(['A', 'B', 'C'], 3)
>>> panel_idx = panel_index(years, panels)
>>> panel_idx
MultiIndex([(1960, 'A'), (1960, 'B'), (1960, 'C'), (1961, 'A'),
(1961, 'B'), (1961, 'C'), (1962, 'A'), (1962, 'B'),
(1962, 'C')], dtype=object)
"""
time, panels = _ensure_like_indices(time, panels)
time_factor = Factor(time)
panel_factor = Factor(panels)
labels = [time_factor.labels, panel_factor.labels]
levels = [time_factor.levels, panel_factor.levels]
return MultiIndex(levels, labels, sortorder=None, names=names)
def fromRecords(cls, data, major_field, minor_field,
exclude=None):
"""
Create LongPanel from DataFrame or record / structured ndarray
object
Parameters
----------
data : DataFrame, structured or record array, or dict
major_field : string
minor_field : string
Name of field
exclude : list-like, default None
Returns
-------
LongPanel
"""
if isinstance(data, np.ndarray):
# Dtype when you have data
if not issubclass(data.dtype.type, np.void):
raise ValueError('Input was not a structured array!')
columns = data.dtype.names
data = dict((k, data[k]) for k in columns)
elif isinstance(data, DataFrame):
data = data._series.copy()
elif isinstance(data, dict):
# otherwise will pop columns out of original
data = data.copy()
if exclude is None:
exclude = set()
else:
exclude = set(exclude)
for col in exclude:
del data[col]
major = Factor.fromarray(data.pop(major_field))
minor = Factor.fromarray(data.pop(minor_field))
index = MultiIndex(levels=[major.levels, minor.levels],
labels=[major.labels, minor.labels])
return LongPanel(data, index=index)
def setUp(self):
self.factor = Factor(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
def setUp(self):
self.factor = Factor(['a', 'b', 'b', 'a', 'a', 'c', 'c', 'c'])
def _make_concat_multiindex(indexes, keys, levels=None, names=None):
if ((levels is None and isinstance(keys[0], tuple))
or (levels is not None and len(levels) > 1)):
zipped = zip(*keys)
if names is None:
names = [None] * len(zipped)
if levels is None:
levels = [Factor(zp).levels for zp in zipped]
else:
levels = [_ensure_index(x) for x in levels]
else:
zipped = [keys]
if names is None:
names = [None]
if levels is None:
levels = [_ensure_index(keys)]
else:
levels = [_ensure_index(x) for x in levels]
if not _all_indexes_same(indexes):
label_list = []
# things are potentially different sizes, so compute the exact labels
# for each level and pass those to MultiIndex.from_arrays
for hlevel, level in zip(zipped, levels):
to_concat = []
for key, index in zip(hlevel, indexes):
i = level.get_loc(key)
to_concat.append(np.repeat(i, len(index)))
label_list.append(np.concatenate(to_concat))
concat_index = _concat_indexes(indexes)
# these go at the end
if isinstance(concat_index, MultiIndex):
levels.extend(concat_index.levels)
label_list.extend(concat_index.labels)
else:
factor = Factor(concat_index)
levels.append(factor.levels)
label_list.append(factor.labels)
# also copies
names = names + _get_consensus_names(indexes)
return MultiIndex(levels=levels, labels=label_list, names=names)
new_index = indexes[0]
n = len(new_index)
kpieces = len(indexes)
# also copies
new_names = list(names)
new_levels = list(levels)
# construct labels
new_labels = []
# do something a bit more speedy
for hlevel, level in zip(zipped, levels):
mapped = level.get_indexer(hlevel)
new_labels.append(np.repeat(mapped, n))
if isinstance(new_index, MultiIndex):
new_levels.extend(new_index.levels)
new_labels.extend([np.tile(lab, kpieces) for lab in new_index.labels])
new_names.extend(new_index.names)
else:
new_levels.append(new_index)
new_names.append(new_index.name)
new_labels.append(np.tile(np.arange(n), kpieces))
return MultiIndex(levels=new_levels, labels=new_labels, names=new_names)
def setUp(self):
self.factor = Factor(["a", "b", "b", "a", "a", "c", "c", "c"])
def setUp(self):
self.factor = Factor.fromarray(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'])
def _read_panel_table(self, group, where=None):
from pandas.core.index import unique_int64, Factor
from pandas.core.common import _asarray_tuplesafe
from pandas.core.internals import BlockManager
from pandas.core.reshape import block2d_to_block3d
table = getattr(group, 'table')
# create the selection
sel = Selection(table, where)
sel.select()
fields = table._v_attrs.fields
columns = _maybe_convert(sel.values['column'],
table._v_attrs.columns_kind)
index = _maybe_convert(sel.values['index'], table._v_attrs.index_kind)
values = sel.values['values']
major = Factor(index)
minor = Factor(columns)
J, K = len(major.levels), len(minor.levels)
key = major.labels * K + minor.labels
if len(unique_int64(key)) == len(key):
sorter, _ = lib.groupsort_indexer(key, J * K)
# the data need to be sorted
sorted_values = values.take(sorter, axis=0)
major_labels = major.labels.take(sorter)
minor_labels = minor.labels.take(sorter)
block = block2d_to_block3d(sorted_values, fields, (J, K),
major_labels, minor_labels)
mgr = BlockManager([block],
[block.items, major.levels, minor.levels])
wp = Panel(mgr)
else:
if not self._quiet: # pragma: no cover
print(
'Duplicate entries in table, taking most recently '
'appended')
# reconstruct
long_index = MultiIndex.from_arrays([index, columns])
lp = DataFrame(values, index=long_index, columns=fields)
# need a better algorithm
tuple_index = long_index.get_tuple_index()
index_map = lib.map_indices_object(tuple_index)
unique_tuples = lib.fast_unique(tuple_index)
unique_tuples = _asarray_tuplesafe(unique_tuples)
indexer = lib.merge_indexer_object(unique_tuples, index_map)
new_index = long_index.take(indexer)
new_values = lp.values.take(indexer, axis=0)
lp = DataFrame(new_values, index=new_index, columns=lp.columns)
wp = lp.to_panel()
if sel.column_filter:
new_minor = sorted(set(wp.minor_axis) & sel.column_filter)
wp = wp.reindex(minor=new_minor)
return wp
def test_constructor_unsortable(self):
arr = np.array([1, 2, 3, datetime.now()], dtype='O')
# it works!
factor = Factor(arr)
