def test_winsorize():
outlier_test = pd.DataFrame([
92, 19, 101, 58, 1053, 91, 26, 78, 10, 13, -40, 101, 86, 85, 15, 89,
89, 28, -5, 41
])
out = winsorize(outlier_test,
cutoff={
'quantile': [0.05, .95]
},
replace_with_cutoff=False).values.squeeze()
correct_result = np.array([
92, 19, 101, 58, 101, 91, 26, 78, 10, 13, -5, 101, 86, 85, 15, 89, 89,
28, -5, 41
])
assert (np.sum(out == correct_result) == 20)
out = winsorize(outlier_test,
cutoff={
'std': [2, 2]
},
replace_with_cutoff=False).values.squeeze()
correct_result = np.array([
92, 19, 101, 58, 101, 91, 26, 78, 10, 13, -40, 101, 86, 85, 15, 89, 89,
28, -5, 41
])
assert (np.sum(out == correct_result) == 20)
out = winsorize(outlier_test,
cutoff={
'std': [2, 2]
},
replace_with_cutoff=True).values.squeeze()
correct_result = np.array([
92., 19., 101., 58., 556.97961997, 91., 26., 78., 10., 13., -40., 101.,
86., 85., 15., 89., 89., 28., -5., 41.
])
assert (np.round(np.mean(out)) == np.round(np.mean(correct_result)))
def test_winsorize():
outlier_test = pd.DataFrame([
92,
19,
101,
58,
1053,
91,
26,
78,
10,
13,
-40,
101,
86,
85,
15,
89,
89,
28,
-5,
41,
])
out = winsorize(outlier_test,
cutoff={
"quantile": [0.05, 0.95]
},
replace_with_cutoff=False).values.squeeze()
correct_result = np.array([
92,
19,
101,
58,
101,
91,
26,
78,
10,
13,
-5,
101,
86,
85,
15,
89,
89,
28,
-5,
41,
])
assert np.sum(out == correct_result) == 20
out = winsorize(outlier_test,
cutoff={
"std": [2, 2]
},
replace_with_cutoff=False).values.squeeze()
correct_result = np.array([
92,
19,
101,
58,
101,
91,
26,
78,
10,
13,
-40,
101,
86,
85,
15,
89,
89,
28,
-5,
41,
])
assert np.sum(out == correct_result) == 20
out = winsorize(outlier_test,
cutoff={
"std": [2, 2]
},
replace_with_cutoff=True).values.squeeze()
correct_result = np.array([
92.0,
19.0,
101.0,
58.0,
556.97961997,
91.0,
26.0,
78.0,
10.0,
13.0,
-40.0,
101.0,
86.0,
85.0,
15.0,
89.0,
89.0,
28.0,
-5.0,
41.0,
])
assert np.round(np.mean(out)) == np.round(np.mean(correct_result))