def groups(self):
if self._groups is None:
axis = self._group_axis
self._groups = tseries.groupby(axis, self.grouper,
output=GroupDict())
return self._groups
def bench_groupby():
N = 200
arr = np.arange(10000).astype(object)
values = np.random.randn(10000)
keys = arr // 10
d = dict(zip(arr, keys))
f = lambda: groupby_nocython(arr, d.get)
print 'no cython: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
f = lambda: tseries.arrmap(arr, d.get)
timing = _timeit(f, n=N) * 1000
print 'arrmap: %.2f ms per iteration' % timing
f = lambda: isnull(tseries.arrmap(arr, d.get))
print 'isnull: %.2f ms per iteration' % (_timeit(f, n=N) * 1000 - timing)
f = lambda: tseries.groupby(arr, d.get)
print 'groupby: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
f = lambda: tseries.groupby_indices(arr, d.get)
print 'groupby_inds: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
def _test():
groups = tseries.groupby_indices(arr, d.get)
result = {}
for k, v in groups.iteritems():
result[k] = np.mean(values.take(v))
return result
print 'test: %.2f ms per iteration' % (_timeit(_test, n=N) * 1000)
def bench_groupby():
N = 200
arr = np.arange(10000).astype(object)
values = np.random.randn(10000)
keys = arr // 10
d = dict(zip(arr, keys))
f = lambda: groupby_nocython(arr, d.get)
print 'no cython: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
f = lambda: tseries.arrmap(arr, d.get)
timing = _timeit(f, n=N) * 1000
print 'arrmap: %.2f ms per iteration' % timing
f = lambda: isnull(tseries.arrmap(arr, d.get))
print 'isnull: %.2f ms per iteration' % (_timeit(f, n=N) * 1000 - timing)
f = lambda: tseries.groupby(arr, d.get)
print 'groupby: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
f = lambda: tseries.groupby_indices(arr, d.get)
print 'groupby_inds: %.2f ms per iteration' % (_timeit(f, n=N) * 1000)
def _test():
groups = tseries.groupby_indices(arr, d.get)
result = {}
for k, v in groups.iteritems():
result[k] = np.mean(values.take(v))
return result
print 'test: %.2f ms per iteration' % (_timeit(_test, n=N) * 1000)
def test_groupby():
mapping = Series({
1 : 2.,
2 : 2.,
3 : np.NaN,
4 : np.NaN,
5 : 3.,
6 : 3.,
7 : np.NaN
})
index = Index([1, 2, 3, 4, 5, 6, 7])
expected = {
2 : [1, 2],
3 : [5, 6],
np.NaN : [3, 4, 7]
}
def compare_with_null(d1, d2):
d1_nulls = None
d2_nulls = None
for k, v in d1.iteritems():
if _isnan(k):
d1_nulls = v
else:
assert(k in d2)
assert(np.array_equal(v, d2[k]))
for k, v in d2.iteritems():
if _isnan(k):
d2_nulls = v
else:
assert(k in d1)
if d1_nulls is not None or d2_nulls is not None:
assert(np.array_equal(d1_nulls, d2_nulls))
grouped = tseries.groupby(index, mapping.get)
compare_with_null(grouped, expected)
def test_groupby():
mapping = Series({
1: 2.,
2: 2.,
3: np.NaN,
4: np.NaN,
5: 3.,
6: 3.,
7: np.NaN
})
index = Index([1, 2, 3, 4, 5, 6, 7])
expected = {2: [1, 2], 3: [5, 6], np.NaN: [3, 4, 7]}
def compare_with_null(d1, d2):
d1_nulls = None
d2_nulls = None
for k, v in d1.iteritems():
if _isnan(k):
d1_nulls = v
else:
assert (k in d2)
assert (np.array_equal(v, d2[k]))
for k, v in d2.iteritems():
if _isnan(k):
d2_nulls = v
else:
assert (k in d1)
if d1_nulls is not None or d2_nulls is not None:
assert (np.array_equal(d1_nulls, d2_nulls))
grouped = tseries.groupby(index, mapping.get)
compare_with_null(grouped, expected)
