File size: 4,785 Bytes
7885a28 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 |
import numpy as np
import pytest
from pandas import (
DataFrame,
Index,
Series,
date_range,
)
from pandas.core.groupby.base import (
reduction_kernels,
transformation_kernels,
)
@pytest.fixture(params=[True, False])
def sort(request):
return request.param
@pytest.fixture(params=[True, False])
def as_index(request):
return request.param
@pytest.fixture(params=[True, False])
def dropna(request):
return request.param
@pytest.fixture(params=[True, False])
def observed(request):
return request.param
@pytest.fixture
def df():
return DataFrame(
{
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
"B": ["one", "one", "two", "three", "two", "two", "one", "three"],
"C": np.random.default_rng(2).standard_normal(8),
"D": np.random.default_rng(2).standard_normal(8),
}
)
@pytest.fixture
def ts():
return Series(
np.random.default_rng(2).standard_normal(30),
index=date_range("2000-01-01", periods=30, freq="B"),
)
@pytest.fixture
def tsframe():
return DataFrame(
np.random.default_rng(2).standard_normal((30, 4)),
columns=Index(list("ABCD"), dtype=object),
index=date_range("2000-01-01", periods=30, freq="B"),
)
@pytest.fixture
def three_group():
return DataFrame(
{
"A": [
"foo",
"foo",
"foo",
"foo",
"bar",
"bar",
"bar",
"bar",
"foo",
"foo",
"foo",
],
"B": [
"one",
"one",
"one",
"two",
"one",
"one",
"one",
"two",
"two",
"two",
"one",
],
"C": [
"dull",
"dull",
"shiny",
"dull",
"dull",
"shiny",
"shiny",
"dull",
"shiny",
"shiny",
"shiny",
],
"D": np.random.default_rng(2).standard_normal(11),
"E": np.random.default_rng(2).standard_normal(11),
"F": np.random.default_rng(2).standard_normal(11),
}
)
@pytest.fixture()
def slice_test_df():
data = [
[0, "a", "a0_at_0"],
[1, "b", "b0_at_1"],
[2, "a", "a1_at_2"],
[3, "b", "b1_at_3"],
[4, "c", "c0_at_4"],
[5, "a", "a2_at_5"],
[6, "a", "a3_at_6"],
[7, "a", "a4_at_7"],
]
df = DataFrame(data, columns=["Index", "Group", "Value"])
return df.set_index("Index")
@pytest.fixture()
def slice_test_grouped(slice_test_df):
return slice_test_df.groupby("Group", as_index=False)
@pytest.fixture(params=sorted(reduction_kernels))
def reduction_func(request):
"""
yields the string names of all groupby reduction functions, one at a time.
"""
return request.param
@pytest.fixture(params=sorted(transformation_kernels))
def transformation_func(request):
"""yields the string names of all groupby transformation functions."""
return request.param
@pytest.fixture(params=sorted(reduction_kernels) + sorted(transformation_kernels))
def groupby_func(request):
"""yields both aggregation and transformation functions."""
return request.param
@pytest.fixture(params=[True, False])
def parallel(request):
"""parallel keyword argument for numba.jit"""
return request.param
# Can parameterize nogil & nopython over True | False, but limiting per
# https://github.com/pandas-dev/pandas/pull/41971#issuecomment-860607472
@pytest.fixture(params=[False])
def nogil(request):
"""nogil keyword argument for numba.jit"""
return request.param
@pytest.fixture(params=[True])
def nopython(request):
"""nopython keyword argument for numba.jit"""
return request.param
@pytest.fixture(
params=[
("mean", {}),
("var", {"ddof": 1}),
("var", {"ddof": 0}),
("std", {"ddof": 1}),
("std", {"ddof": 0}),
("sum", {}),
("min", {}),
("max", {}),
("sum", {"min_count": 2}),
("min", {"min_count": 2}),
("max", {"min_count": 2}),
],
ids=[
"mean",
"var_1",
"var_0",
"std_1",
"std_0",
"sum",
"min",
"max",
"sum-min_count",
"min-min_count",
"max-min_count",
],
)
def numba_supported_reductions(request):
"""reductions supported with engine='numba'"""
return request.param
|