You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
28 lines
841 B
28 lines
841 B
1 year ago
|
import numpy as np
|
||
|
|
|
||
|
|
import pandas as pd
|
||
|
|
import pandas._testing as tm
|
||
|
|
|
||
|
|
|
||
|
|
def test_groupby_skew_equivalence():
|
||
|
|
# Test that that groupby skew method (which uses libgroupby.group_skew)
|
||
|
|
# matches the results of operating group-by-group (which uses nanops.nanskew)
|
||
|
|
nrows = 1000
|
||
|
|
ngroups = 3
|
||
|
|
ncols = 2
|
||
|
|
nan_frac = 0.05
|
||
|
|
|
||
|
|
arr = np.random.default_rng(2).standard_normal((nrows, ncols))
|
||
|
|
arr[np.random.default_rng(2).random(nrows) < nan_frac] = np.nan
|
||
|
|
|
||
|
|
df = pd.DataFrame(arr)
|
||
|
|
grps = np.random.default_rng(2).integers(0, ngroups, size=nrows)
|
||
|
|
gb = df.groupby(grps)
|
||
|
|
|
||
|
|
result = gb.skew()
|
||
|
|
|
||
|
|
grpwise = [grp.skew().to_frame(i).T for i, grp in gb]
|
||
|
|
expected = pd.concat(grpwise, axis=0)
|
||
|
|
expected.index = expected.index.astype(result.index.dtype) # 32bit builds
|
||
|
|
tm.assert_frame_equal(result, expected)
|