done
This commit is contained in:
File diff suppressed because it is too large
Load Diff
@ -0,0 +1,437 @@
|
||||
"""
|
||||
test cython .agg behavior
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from pandas.core.dtypes.common import (
|
||||
is_float_dtype,
|
||||
is_integer_dtype,
|
||||
)
|
||||
|
||||
import pandas as pd
|
||||
from pandas import (
|
||||
DataFrame,
|
||||
Index,
|
||||
NaT,
|
||||
Series,
|
||||
Timedelta,
|
||||
Timestamp,
|
||||
bdate_range,
|
||||
)
|
||||
import pandas._testing as tm
|
||||
import pandas.core.common as com
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"op_name",
|
||||
[
|
||||
"count",
|
||||
"sum",
|
||||
"std",
|
||||
"var",
|
||||
"sem",
|
||||
"mean",
|
||||
pytest.param(
|
||||
"median",
|
||||
# ignore mean of empty slice
|
||||
# and all-NaN
|
||||
marks=[pytest.mark.filterwarnings("ignore::RuntimeWarning")],
|
||||
),
|
||||
"prod",
|
||||
"min",
|
||||
"max",
|
||||
],
|
||||
)
|
||||
def test_cythonized_aggers(op_name):
|
||||
data = {
|
||||
"A": [0, 0, 0, 0, 1, 1, 1, 1, 1, 1.0, np.nan, np.nan],
|
||||
"B": ["A", "B"] * 6,
|
||||
"C": np.random.default_rng(2).standard_normal(12),
|
||||
}
|
||||
df = DataFrame(data)
|
||||
df.loc[2:10:2, "C"] = np.nan
|
||||
|
||||
op = lambda x: getattr(x, op_name)()
|
||||
|
||||
# single column
|
||||
grouped = df.drop(["B"], axis=1).groupby("A")
|
||||
exp = {cat: op(group["C"]) for cat, group in grouped}
|
||||
exp = DataFrame({"C": exp})
|
||||
exp.index.name = "A"
|
||||
result = op(grouped)
|
||||
tm.assert_frame_equal(result, exp)
|
||||
|
||||
# multiple columns
|
||||
grouped = df.groupby(["A", "B"])
|
||||
expd = {}
|
||||
for (cat1, cat2), group in grouped:
|
||||
expd.setdefault(cat1, {})[cat2] = op(group["C"])
|
||||
exp = DataFrame(expd).T.stack(future_stack=True)
|
||||
exp.index.names = ["A", "B"]
|
||||
exp.name = "C"
|
||||
|
||||
result = op(grouped)["C"]
|
||||
if op_name in ["sum", "prod"]:
|
||||
tm.assert_series_equal(result, exp)
|
||||
|
||||
|
||||
def test_cython_agg_boolean():
|
||||
frame = DataFrame(
|
||||
{
|
||||
"a": np.random.default_rng(2).integers(0, 5, 50),
|
||||
"b": np.random.default_rng(2).integers(0, 2, 50).astype("bool"),
|
||||
}
|
||||
)
|
||||
result = frame.groupby("a")["b"].mean()
|
||||
msg = "using SeriesGroupBy.mean"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
# GH#53425
|
||||
expected = frame.groupby("a")["b"].agg(np.mean)
|
||||
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_cython_agg_nothing_to_agg():
|
||||
frame = DataFrame(
|
||||
{"a": np.random.default_rng(2).integers(0, 5, 50), "b": ["foo", "bar"] * 25}
|
||||
)
|
||||
|
||||
msg = "Cannot use numeric_only=True with SeriesGroupBy.mean and non-numeric dtypes"
|
||||
with pytest.raises(TypeError, match=msg):
|
||||
frame.groupby("a")["b"].mean(numeric_only=True)
|
||||
|
||||
frame = DataFrame(
|
||||
{"a": np.random.default_rng(2).integers(0, 5, 50), "b": ["foo", "bar"] * 25}
|
||||
)
|
||||
|
||||
result = frame[["b"]].groupby(frame["a"]).mean(numeric_only=True)
|
||||
expected = DataFrame(
|
||||
[],
|
||||
index=frame["a"].sort_values().drop_duplicates(),
|
||||
columns=Index([], dtype="str"),
|
||||
)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_cython_agg_nothing_to_agg_with_dates():
|
||||
frame = DataFrame(
|
||||
{
|
||||
"a": np.random.default_rng(2).integers(0, 5, 50),
|
||||
"b": ["foo", "bar"] * 25,
|
||||
"dates": pd.date_range("now", periods=50, freq="min"),
|
||||
}
|
||||
)
|
||||
msg = "Cannot use numeric_only=True with SeriesGroupBy.mean and non-numeric dtypes"
|
||||
with pytest.raises(TypeError, match=msg):
|
||||
frame.groupby("b").dates.mean(numeric_only=True)
|
||||
|
||||
|
||||
def test_cython_agg_frame_columns():
|
||||
# #2113
|
||||
df = DataFrame({"x": [1, 2, 3], "y": [3, 4, 5]})
|
||||
|
||||
msg = "DataFrame.groupby with axis=1 is deprecated"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
df.groupby(level=0, axis="columns").mean()
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
df.groupby(level=0, axis="columns").mean()
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
df.groupby(level=0, axis="columns").mean()
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
df.groupby(level=0, axis="columns").mean()
|
||||
|
||||
|
||||
def test_cython_agg_return_dict():
|
||||
# GH 16741
|
||||
df = 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),
|
||||
}
|
||||
)
|
||||
|
||||
ts = df.groupby("A")["B"].agg(lambda x: x.value_counts().to_dict())
|
||||
expected = Series(
|
||||
[{"two": 1, "one": 1, "three": 1}, {"two": 2, "one": 2, "three": 1}],
|
||||
index=Index(["bar", "foo"], name="A"),
|
||||
name="B",
|
||||
)
|
||||
tm.assert_series_equal(ts, expected)
|
||||
|
||||
|
||||
def test_cython_fail_agg():
|
||||
dr = bdate_range("1/1/2000", periods=50)
|
||||
ts = Series(["A", "B", "C", "D", "E"] * 10, dtype=object, index=dr)
|
||||
|
||||
grouped = ts.groupby(lambda x: x.month)
|
||||
summed = grouped.sum()
|
||||
msg = "using SeriesGroupBy.sum"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
# GH#53425
|
||||
expected = grouped.agg(np.sum).astype(object)
|
||||
tm.assert_series_equal(summed, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"op, targop",
|
||||
[
|
||||
("mean", np.mean),
|
||||
("median", np.median),
|
||||
("var", np.var),
|
||||
("sum", np.sum),
|
||||
("prod", np.prod),
|
||||
("min", np.min),
|
||||
("max", np.max),
|
||||
("first", lambda x: x.iloc[0]),
|
||||
("last", lambda x: x.iloc[-1]),
|
||||
],
|
||||
)
|
||||
def test__cython_agg_general(op, targop):
|
||||
df = DataFrame(np.random.default_rng(2).standard_normal(1000))
|
||||
labels = np.random.default_rng(2).integers(0, 50, size=1000).astype(float)
|
||||
|
||||
result = df.groupby(labels)._cython_agg_general(op, alt=None, numeric_only=True)
|
||||
warn = FutureWarning if targop in com._cython_table else None
|
||||
msg = f"using DataFrameGroupBy.{op}"
|
||||
with tm.assert_produces_warning(warn, match=msg):
|
||||
# GH#53425
|
||||
expected = df.groupby(labels).agg(targop)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"op, targop",
|
||||
[
|
||||
("mean", np.mean),
|
||||
("median", lambda x: np.median(x) if len(x) > 0 else np.nan),
|
||||
("var", lambda x: np.var(x, ddof=1)),
|
||||
("min", np.min),
|
||||
("max", np.max),
|
||||
],
|
||||
)
|
||||
def test_cython_agg_empty_buckets(op, targop, observed):
|
||||
df = DataFrame([11, 12, 13])
|
||||
grps = range(0, 55, 5)
|
||||
|
||||
# calling _cython_agg_general directly, instead of via the user API
|
||||
# which sets different values for min_count, so do that here.
|
||||
g = df.groupby(pd.cut(df[0], grps), observed=observed)
|
||||
result = g._cython_agg_general(op, alt=None, numeric_only=True)
|
||||
|
||||
g = df.groupby(pd.cut(df[0], grps), observed=observed)
|
||||
expected = g.agg(lambda x: targop(x))
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_cython_agg_empty_buckets_nanops(observed):
|
||||
# GH-18869 can't call nanops on empty groups, so hardcode expected
|
||||
# for these
|
||||
df = DataFrame([11, 12, 13], columns=["a"])
|
||||
grps = np.arange(0, 25, 5, dtype=int)
|
||||
# add / sum
|
||||
result = df.groupby(pd.cut(df["a"], grps), observed=observed)._cython_agg_general(
|
||||
"sum", alt=None, numeric_only=True
|
||||
)
|
||||
intervals = pd.interval_range(0, 20, freq=5)
|
||||
expected = DataFrame(
|
||||
{"a": [0, 0, 36, 0]},
|
||||
index=pd.CategoricalIndex(intervals, name="a", ordered=True),
|
||||
)
|
||||
if observed:
|
||||
expected = expected[expected.a != 0]
|
||||
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
# prod
|
||||
result = df.groupby(pd.cut(df["a"], grps), observed=observed)._cython_agg_general(
|
||||
"prod", alt=None, numeric_only=True
|
||||
)
|
||||
expected = DataFrame(
|
||||
{"a": [1, 1, 1716, 1]},
|
||||
index=pd.CategoricalIndex(intervals, name="a", ordered=True),
|
||||
)
|
||||
if observed:
|
||||
expected = expected[expected.a != 1]
|
||||
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("op", ["first", "last", "max", "min"])
|
||||
@pytest.mark.parametrize(
|
||||
"data", [Timestamp("2016-10-14 21:00:44.557"), Timedelta("17088 days 21:00:44.557")]
|
||||
)
|
||||
def test_cython_with_timestamp_and_nat(op, data):
|
||||
# https://github.com/pandas-dev/pandas/issues/19526
|
||||
df = DataFrame({"a": [0, 1], "b": [data, NaT]})
|
||||
index = Index([0, 1], name="a")
|
||||
|
||||
# We will group by a and test the cython aggregations
|
||||
expected = DataFrame({"b": [data, NaT]}, index=index)
|
||||
|
||||
result = df.groupby("a").aggregate(op)
|
||||
tm.assert_frame_equal(expected, result)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"agg",
|
||||
[
|
||||
"min",
|
||||
"max",
|
||||
"count",
|
||||
"sum",
|
||||
"prod",
|
||||
"var",
|
||||
"mean",
|
||||
"median",
|
||||
"ohlc",
|
||||
"cumprod",
|
||||
"cumsum",
|
||||
"shift",
|
||||
"any",
|
||||
"all",
|
||||
"quantile",
|
||||
"first",
|
||||
"last",
|
||||
"rank",
|
||||
"cummin",
|
||||
"cummax",
|
||||
],
|
||||
)
|
||||
def test_read_only_buffer_source_agg(agg):
|
||||
# https://github.com/pandas-dev/pandas/issues/36014
|
||||
df = DataFrame(
|
||||
{
|
||||
"sepal_length": [5.1, 4.9, 4.7, 4.6, 5.0],
|
||||
"species": ["setosa", "setosa", "setosa", "setosa", "setosa"],
|
||||
}
|
||||
)
|
||||
df._mgr.arrays[0].flags.writeable = False
|
||||
|
||||
result = df.groupby(["species"]).agg({"sepal_length": agg})
|
||||
expected = df.copy().groupby(["species"]).agg({"sepal_length": agg})
|
||||
|
||||
tm.assert_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"op_name",
|
||||
[
|
||||
"count",
|
||||
"sum",
|
||||
"std",
|
||||
"var",
|
||||
"sem",
|
||||
"mean",
|
||||
"median",
|
||||
"prod",
|
||||
"min",
|
||||
"max",
|
||||
],
|
||||
)
|
||||
def test_cython_agg_nullable_int(op_name):
|
||||
# ensure that the cython-based aggregations don't fail for nullable dtype
|
||||
# (eg https://github.com/pandas-dev/pandas/issues/37415)
|
||||
df = DataFrame(
|
||||
{
|
||||
"A": ["A", "B"] * 5,
|
||||
"B": pd.array([1, 2, 3, 4, 5, 6, 7, 8, 9, pd.NA], dtype="Int64"),
|
||||
}
|
||||
)
|
||||
result = getattr(df.groupby("A")["B"], op_name)()
|
||||
df2 = df.assign(B=df["B"].astype("float64"))
|
||||
expected = getattr(df2.groupby("A")["B"], op_name)()
|
||||
if op_name in ("mean", "median"):
|
||||
convert_integer = False
|
||||
else:
|
||||
convert_integer = True
|
||||
expected = expected.convert_dtypes(convert_integer=convert_integer)
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("dtype", ["Int64", "Float64", "boolean"])
|
||||
def test_count_masked_returns_masked_dtype(dtype):
|
||||
df = DataFrame(
|
||||
{
|
||||
"A": [1, 1],
|
||||
"B": pd.array([1, pd.NA], dtype=dtype),
|
||||
"C": pd.array([1, 1], dtype=dtype),
|
||||
}
|
||||
)
|
||||
result = df.groupby("A").count()
|
||||
expected = DataFrame(
|
||||
[[1, 2]], index=Index([1], name="A"), columns=["B", "C"], dtype="Int64"
|
||||
)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("with_na", [True, False])
|
||||
@pytest.mark.parametrize(
|
||||
"op_name, action",
|
||||
[
|
||||
# ("count", "always_int"),
|
||||
("sum", "large_int"),
|
||||
# ("std", "always_float"),
|
||||
("var", "always_float"),
|
||||
# ("sem", "always_float"),
|
||||
("mean", "always_float"),
|
||||
("median", "always_float"),
|
||||
("prod", "large_int"),
|
||||
("min", "preserve"),
|
||||
("max", "preserve"),
|
||||
("first", "preserve"),
|
||||
("last", "preserve"),
|
||||
],
|
||||
)
|
||||
@pytest.mark.parametrize(
|
||||
"data",
|
||||
[
|
||||
pd.array([1, 2, 3, 4], dtype="Int64"),
|
||||
pd.array([1, 2, 3, 4], dtype="Int8"),
|
||||
pd.array([0.1, 0.2, 0.3, 0.4], dtype="Float32"),
|
||||
pd.array([0.1, 0.2, 0.3, 0.4], dtype="Float64"),
|
||||
pd.array([True, True, False, False], dtype="boolean"),
|
||||
],
|
||||
)
|
||||
def test_cython_agg_EA_known_dtypes(data, op_name, action, with_na):
|
||||
if with_na:
|
||||
data[3] = pd.NA
|
||||
|
||||
df = DataFrame({"key": ["a", "a", "b", "b"], "col": data})
|
||||
grouped = df.groupby("key")
|
||||
|
||||
if action == "always_int":
|
||||
# always Int64
|
||||
expected_dtype = pd.Int64Dtype()
|
||||
elif action == "large_int":
|
||||
# for any int/bool use Int64, for float preserve dtype
|
||||
if is_float_dtype(data.dtype):
|
||||
expected_dtype = data.dtype
|
||||
elif is_integer_dtype(data.dtype):
|
||||
# match the numpy dtype we'd get with the non-nullable analogue
|
||||
expected_dtype = data.dtype
|
||||
else:
|
||||
expected_dtype = pd.Int64Dtype()
|
||||
elif action == "always_float":
|
||||
# for any int/bool use Float64, for float preserve dtype
|
||||
if is_float_dtype(data.dtype):
|
||||
expected_dtype = data.dtype
|
||||
else:
|
||||
expected_dtype = pd.Float64Dtype()
|
||||
elif action == "preserve":
|
||||
expected_dtype = data.dtype
|
||||
|
||||
result = getattr(grouped, op_name)()
|
||||
assert result["col"].dtype == expected_dtype
|
||||
|
||||
result = grouped.aggregate(op_name)
|
||||
assert result["col"].dtype == expected_dtype
|
||||
|
||||
result = getattr(grouped["col"], op_name)()
|
||||
assert result.dtype == expected_dtype
|
||||
|
||||
result = grouped["col"].aggregate(op_name)
|
||||
assert result.dtype == expected_dtype
|
||||
@ -0,0 +1,402 @@
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from pandas.compat import is_platform_arm
|
||||
from pandas.errors import NumbaUtilError
|
||||
|
||||
from pandas import (
|
||||
DataFrame,
|
||||
Index,
|
||||
NamedAgg,
|
||||
Series,
|
||||
option_context,
|
||||
)
|
||||
import pandas._testing as tm
|
||||
from pandas.util.version import Version
|
||||
|
||||
pytestmark = [pytest.mark.single_cpu]
|
||||
|
||||
numba = pytest.importorskip("numba")
|
||||
pytestmark.append(
|
||||
pytest.mark.skipif(
|
||||
Version(numba.__version__) == Version("0.61") and is_platform_arm(),
|
||||
reason=f"Segfaults on ARM platforms with numba {numba.__version__}",
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
def test_correct_function_signature():
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def incorrect_function(x):
|
||||
return sum(x) * 2.7
|
||||
|
||||
data = DataFrame(
|
||||
{"key": ["a", "a", "b", "b", "a"], "data": [1.0, 2.0, 3.0, 4.0, 5.0]},
|
||||
columns=["key", "data"],
|
||||
)
|
||||
with pytest.raises(NumbaUtilError, match="The first 2"):
|
||||
data.groupby("key").agg(incorrect_function, engine="numba")
|
||||
|
||||
with pytest.raises(NumbaUtilError, match="The first 2"):
|
||||
data.groupby("key")["data"].agg(incorrect_function, engine="numba")
|
||||
|
||||
|
||||
def test_check_nopython_kwargs():
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def incorrect_function(values, index):
|
||||
return sum(values) * 2.7
|
||||
|
||||
data = DataFrame(
|
||||
{"key": ["a", "a", "b", "b", "a"], "data": [1.0, 2.0, 3.0, 4.0, 5.0]},
|
||||
columns=["key", "data"],
|
||||
)
|
||||
with pytest.raises(NumbaUtilError, match="numba does not support"):
|
||||
data.groupby("key").agg(incorrect_function, engine="numba", a=1)
|
||||
|
||||
with pytest.raises(NumbaUtilError, match="numba does not support"):
|
||||
data.groupby("key")["data"].agg(incorrect_function, engine="numba", a=1)
|
||||
|
||||
|
||||
@pytest.mark.filterwarnings("ignore")
|
||||
# Filter warnings when parallel=True and the function can't be parallelized by Numba
|
||||
@pytest.mark.parametrize("jit", [True, False])
|
||||
@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
|
||||
@pytest.mark.parametrize("as_index", [True, False])
|
||||
def test_numba_vs_cython(jit, pandas_obj, nogil, parallel, nopython, as_index):
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def func_numba(values, index):
|
||||
return np.mean(values) * 2.7
|
||||
|
||||
if jit:
|
||||
# Test accepted jitted functions
|
||||
import numba
|
||||
|
||||
func_numba = numba.jit(func_numba)
|
||||
|
||||
data = DataFrame(
|
||||
{0: ["a", "a", "b", "b", "a"], 1: [1.0, 2.0, 3.0, 4.0, 5.0]}, columns=[0, 1]
|
||||
)
|
||||
engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
|
||||
grouped = data.groupby(0, as_index=as_index)
|
||||
if pandas_obj == "Series":
|
||||
grouped = grouped[1]
|
||||
|
||||
result = grouped.agg(func_numba, engine="numba", engine_kwargs=engine_kwargs)
|
||||
expected = grouped.agg(lambda x: np.mean(x) * 2.7, engine="cython")
|
||||
|
||||
tm.assert_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.filterwarnings("ignore")
|
||||
# Filter warnings when parallel=True and the function can't be parallelized by Numba
|
||||
@pytest.mark.parametrize("jit", [True, False])
|
||||
@pytest.mark.parametrize("pandas_obj", ["Series", "DataFrame"])
|
||||
def test_cache(jit, pandas_obj, nogil, parallel, nopython):
|
||||
# Test that the functions are cached correctly if we switch functions
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def func_1(values, index):
|
||||
return np.mean(values) - 3.4
|
||||
|
||||
def func_2(values, index):
|
||||
return np.mean(values) * 2.7
|
||||
|
||||
if jit:
|
||||
import numba
|
||||
|
||||
func_1 = numba.jit(func_1)
|
||||
func_2 = numba.jit(func_2)
|
||||
|
||||
data = DataFrame(
|
||||
{0: ["a", "a", "b", "b", "a"], 1: [1.0, 2.0, 3.0, 4.0, 5.0]}, columns=[0, 1]
|
||||
)
|
||||
engine_kwargs = {"nogil": nogil, "parallel": parallel, "nopython": nopython}
|
||||
grouped = data.groupby(0)
|
||||
if pandas_obj == "Series":
|
||||
grouped = grouped[1]
|
||||
|
||||
result = grouped.agg(func_1, engine="numba", engine_kwargs=engine_kwargs)
|
||||
expected = grouped.agg(lambda x: np.mean(x) - 3.4, engine="cython")
|
||||
tm.assert_equal(result, expected)
|
||||
|
||||
# Add func_2 to the cache
|
||||
result = grouped.agg(func_2, engine="numba", engine_kwargs=engine_kwargs)
|
||||
expected = grouped.agg(lambda x: np.mean(x) * 2.7, engine="cython")
|
||||
tm.assert_equal(result, expected)
|
||||
|
||||
# Retest func_1 which should use the cache
|
||||
result = grouped.agg(func_1, engine="numba", engine_kwargs=engine_kwargs)
|
||||
expected = grouped.agg(lambda x: np.mean(x) - 3.4, engine="cython")
|
||||
tm.assert_equal(result, expected)
|
||||
|
||||
|
||||
def test_use_global_config():
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def func_1(values, index):
|
||||
return np.mean(values) - 3.4
|
||||
|
||||
data = DataFrame(
|
||||
{0: ["a", "a", "b", "b", "a"], 1: [1.0, 2.0, 3.0, 4.0, 5.0]}, columns=[0, 1]
|
||||
)
|
||||
grouped = data.groupby(0)
|
||||
expected = grouped.agg(func_1, engine="numba")
|
||||
with option_context("compute.use_numba", True):
|
||||
result = grouped.agg(func_1, engine=None)
|
||||
tm.assert_frame_equal(expected, result)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"agg_kwargs",
|
||||
[
|
||||
{"func": ["min", "max"]},
|
||||
{"func": "min"},
|
||||
{"func": {1: ["min", "max"], 2: "sum"}},
|
||||
{"bmin": NamedAgg(column=1, aggfunc="min")},
|
||||
],
|
||||
)
|
||||
def test_multifunc_numba_vs_cython_frame(agg_kwargs):
|
||||
pytest.importorskip("numba")
|
||||
data = DataFrame(
|
||||
{
|
||||
0: ["a", "a", "b", "b", "a"],
|
||||
1: [1.0, 2.0, 3.0, 4.0, 5.0],
|
||||
2: [1, 2, 3, 4, 5],
|
||||
},
|
||||
columns=[0, 1, 2],
|
||||
)
|
||||
grouped = data.groupby(0)
|
||||
result = grouped.agg(**agg_kwargs, engine="numba")
|
||||
expected = grouped.agg(**agg_kwargs, engine="cython")
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"agg_kwargs,expected_func",
|
||||
[
|
||||
({"func": lambda values, index: values.sum()}, "sum"),
|
||||
# FIXME
|
||||
pytest.param(
|
||||
{
|
||||
"func": [
|
||||
lambda values, index: values.sum(),
|
||||
lambda values, index: values.min(),
|
||||
]
|
||||
},
|
||||
["sum", "min"],
|
||||
marks=pytest.mark.xfail(
|
||||
reason="This doesn't work yet! Fails in nopython pipeline!"
|
||||
),
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_multifunc_numba_udf_frame(agg_kwargs, expected_func):
|
||||
pytest.importorskip("numba")
|
||||
data = DataFrame(
|
||||
{
|
||||
0: ["a", "a", "b", "b", "a"],
|
||||
1: [1.0, 2.0, 3.0, 4.0, 5.0],
|
||||
2: [1, 2, 3, 4, 5],
|
||||
},
|
||||
columns=[0, 1, 2],
|
||||
)
|
||||
grouped = data.groupby(0)
|
||||
result = grouped.agg(**agg_kwargs, engine="numba")
|
||||
expected = grouped.agg(expected_func, engine="cython")
|
||||
# check_dtype can be removed if GH 44952 is addressed
|
||||
# Currently, UDFs still always return float64 while reductions can preserve dtype
|
||||
tm.assert_frame_equal(result, expected, check_dtype=False)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"agg_kwargs",
|
||||
[{"func": ["min", "max"]}, {"func": "min"}, {"min_val": "min", "max_val": "max"}],
|
||||
)
|
||||
def test_multifunc_numba_vs_cython_series(agg_kwargs):
|
||||
pytest.importorskip("numba")
|
||||
labels = ["a", "a", "b", "b", "a"]
|
||||
data = Series([1.0, 2.0, 3.0, 4.0, 5.0])
|
||||
grouped = data.groupby(labels)
|
||||
agg_kwargs["engine"] = "numba"
|
||||
result = grouped.agg(**agg_kwargs)
|
||||
agg_kwargs["engine"] = "cython"
|
||||
expected = grouped.agg(**agg_kwargs)
|
||||
if isinstance(expected, DataFrame):
|
||||
tm.assert_frame_equal(result, expected)
|
||||
else:
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.single_cpu
|
||||
@pytest.mark.parametrize(
|
||||
"data,agg_kwargs",
|
||||
[
|
||||
(Series([1.0, 2.0, 3.0, 4.0, 5.0]), {"func": ["min", "max"]}),
|
||||
(Series([1.0, 2.0, 3.0, 4.0, 5.0]), {"func": "min"}),
|
||||
(
|
||||
DataFrame(
|
||||
{1: [1.0, 2.0, 3.0, 4.0, 5.0], 2: [1, 2, 3, 4, 5]}, columns=[1, 2]
|
||||
),
|
||||
{"func": ["min", "max"]},
|
||||
),
|
||||
(
|
||||
DataFrame(
|
||||
{1: [1.0, 2.0, 3.0, 4.0, 5.0], 2: [1, 2, 3, 4, 5]}, columns=[1, 2]
|
||||
),
|
||||
{"func": "min"},
|
||||
),
|
||||
(
|
||||
DataFrame(
|
||||
{1: [1.0, 2.0, 3.0, 4.0, 5.0], 2: [1, 2, 3, 4, 5]}, columns=[1, 2]
|
||||
),
|
||||
{"func": {1: ["min", "max"], 2: "sum"}},
|
||||
),
|
||||
(
|
||||
DataFrame(
|
||||
{1: [1.0, 2.0, 3.0, 4.0, 5.0], 2: [1, 2, 3, 4, 5]}, columns=[1, 2]
|
||||
),
|
||||
{"min_col": NamedAgg(column=1, aggfunc="min")},
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_multifunc_numba_kwarg_propagation(data, agg_kwargs):
|
||||
pytest.importorskip("numba")
|
||||
labels = ["a", "a", "b", "b", "a"]
|
||||
grouped = data.groupby(labels)
|
||||
result = grouped.agg(**agg_kwargs, engine="numba", engine_kwargs={"parallel": True})
|
||||
expected = grouped.agg(**agg_kwargs, engine="numba")
|
||||
if isinstance(expected, DataFrame):
|
||||
tm.assert_frame_equal(result, expected)
|
||||
else:
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_args_not_cached():
|
||||
# GH 41647
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def sum_last(values, index, n):
|
||||
return values[-n:].sum()
|
||||
|
||||
df = DataFrame({"id": [0, 0, 1, 1], "x": [1, 1, 1, 1]})
|
||||
grouped_x = df.groupby("id")["x"]
|
||||
result = grouped_x.agg(sum_last, 1, engine="numba")
|
||||
expected = Series([1.0] * 2, name="x", index=Index([0, 1], name="id"))
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
result = grouped_x.agg(sum_last, 2, engine="numba")
|
||||
expected = Series([2.0] * 2, name="x", index=Index([0, 1], name="id"))
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_index_data_correctly_passed():
|
||||
# GH 43133
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def f(values, index):
|
||||
return np.mean(index)
|
||||
|
||||
df = DataFrame({"group": ["A", "A", "B"], "v": [4, 5, 6]}, index=[-1, -2, -3])
|
||||
result = df.groupby("group").aggregate(f, engine="numba")
|
||||
expected = DataFrame(
|
||||
[-1.5, -3.0], columns=["v"], index=Index(["A", "B"], name="group")
|
||||
)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_engine_kwargs_not_cached():
|
||||
# If the user passes a different set of engine_kwargs don't return the same
|
||||
# jitted function
|
||||
pytest.importorskip("numba")
|
||||
nogil = True
|
||||
parallel = False
|
||||
nopython = True
|
||||
|
||||
def func_kwargs(values, index):
|
||||
return nogil + parallel + nopython
|
||||
|
||||
engine_kwargs = {"nopython": nopython, "nogil": nogil, "parallel": parallel}
|
||||
df = DataFrame({"value": [0, 0, 0]})
|
||||
result = df.groupby(level=0).aggregate(
|
||||
func_kwargs, engine="numba", engine_kwargs=engine_kwargs
|
||||
)
|
||||
expected = DataFrame({"value": [2.0, 2.0, 2.0]})
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
nogil = False
|
||||
engine_kwargs = {"nopython": nopython, "nogil": nogil, "parallel": parallel}
|
||||
result = df.groupby(level=0).aggregate(
|
||||
func_kwargs, engine="numba", engine_kwargs=engine_kwargs
|
||||
)
|
||||
expected = DataFrame({"value": [1.0, 1.0, 1.0]})
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.filterwarnings("ignore")
|
||||
def test_multiindex_one_key(nogil, parallel, nopython):
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def numba_func(values, index):
|
||||
return 1
|
||||
|
||||
df = DataFrame([{"A": 1, "B": 2, "C": 3}]).set_index(["A", "B"])
|
||||
engine_kwargs = {"nopython": nopython, "nogil": nogil, "parallel": parallel}
|
||||
result = df.groupby("A").agg(
|
||||
numba_func, engine="numba", engine_kwargs=engine_kwargs
|
||||
)
|
||||
expected = DataFrame([1.0], index=Index([1], name="A"), columns=["C"])
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_multiindex_multi_key_not_supported(nogil, parallel, nopython):
|
||||
pytest.importorskip("numba")
|
||||
|
||||
def numba_func(values, index):
|
||||
return 1
|
||||
|
||||
df = DataFrame([{"A": 1, "B": 2, "C": 3}]).set_index(["A", "B"])
|
||||
engine_kwargs = {"nopython": nopython, "nogil": nogil, "parallel": parallel}
|
||||
with pytest.raises(NotImplementedError, match="more than 1 grouping labels"):
|
||||
df.groupby(["A", "B"]).agg(
|
||||
numba_func, engine="numba", engine_kwargs=engine_kwargs
|
||||
)
|
||||
|
||||
|
||||
def test_multilabel_numba_vs_cython(numba_supported_reductions):
|
||||
pytest.importorskip("numba")
|
||||
reduction, kwargs = numba_supported_reductions
|
||||
df = 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),
|
||||
}
|
||||
)
|
||||
gb = df.groupby(["A", "B"])
|
||||
res_agg = gb.agg(reduction, engine="numba", **kwargs)
|
||||
expected_agg = gb.agg(reduction, engine="cython", **kwargs)
|
||||
tm.assert_frame_equal(res_agg, expected_agg)
|
||||
# Test that calling the aggregation directly also works
|
||||
direct_res = getattr(gb, reduction)(engine="numba", **kwargs)
|
||||
direct_expected = getattr(gb, reduction)(engine="cython", **kwargs)
|
||||
tm.assert_frame_equal(direct_res, direct_expected)
|
||||
|
||||
|
||||
def test_multilabel_udf_numba_vs_cython():
|
||||
pytest.importorskip("numba")
|
||||
df = 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),
|
||||
}
|
||||
)
|
||||
gb = df.groupby(["A", "B"])
|
||||
result = gb.agg(lambda values, index: values.min(), engine="numba")
|
||||
expected = gb.agg(lambda x: x.min(), engine="cython")
|
||||
tm.assert_frame_equal(result, expected)
|
||||
@ -0,0 +1,676 @@
|
||||
"""
|
||||
test all other .agg behavior
|
||||
"""
|
||||
|
||||
import datetime as dt
|
||||
from functools import partial
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from pandas.errors import SpecificationError
|
||||
|
||||
import pandas as pd
|
||||
from pandas import (
|
||||
DataFrame,
|
||||
Index,
|
||||
MultiIndex,
|
||||
PeriodIndex,
|
||||
Series,
|
||||
date_range,
|
||||
period_range,
|
||||
)
|
||||
import pandas._testing as tm
|
||||
|
||||
from pandas.io.formats.printing import pprint_thing
|
||||
|
||||
|
||||
def test_agg_partial_failure_raises():
|
||||
# GH#43741
|
||||
|
||||
df = DataFrame(
|
||||
{
|
||||
"data1": np.random.default_rng(2).standard_normal(5),
|
||||
"data2": np.random.default_rng(2).standard_normal(5),
|
||||
"key1": ["a", "a", "b", "b", "a"],
|
||||
"key2": ["one", "two", "one", "two", "one"],
|
||||
}
|
||||
)
|
||||
grouped = df.groupby("key1")
|
||||
|
||||
def peak_to_peak(arr):
|
||||
return arr.max() - arr.min()
|
||||
|
||||
with pytest.raises(TypeError, match="unsupported operand type"):
|
||||
grouped.agg([peak_to_peak])
|
||||
|
||||
with pytest.raises(TypeError, match="unsupported operand type"):
|
||||
grouped.agg(peak_to_peak)
|
||||
|
||||
|
||||
def test_agg_datetimes_mixed():
|
||||
data = [[1, "2012-01-01", 1.0], [2, "2012-01-02", 2.0], [3, None, 3.0]]
|
||||
|
||||
df1 = DataFrame(
|
||||
{
|
||||
"key": [x[0] for x in data],
|
||||
"date": [x[1] for x in data],
|
||||
"value": [x[2] for x in data],
|
||||
}
|
||||
)
|
||||
|
||||
data = [
|
||||
[
|
||||
row[0],
|
||||
(dt.datetime.strptime(row[1], "%Y-%m-%d").date() if row[1] else None),
|
||||
row[2],
|
||||
]
|
||||
for row in data
|
||||
]
|
||||
|
||||
df2 = DataFrame(
|
||||
{
|
||||
"key": [x[0] for x in data],
|
||||
"date": [x[1] for x in data],
|
||||
"value": [x[2] for x in data],
|
||||
}
|
||||
)
|
||||
|
||||
df1["weights"] = df1["value"] / df1["value"].sum()
|
||||
gb1 = df1.groupby("date").aggregate("sum")
|
||||
|
||||
df2["weights"] = df1["value"] / df1["value"].sum()
|
||||
gb2 = df2.groupby("date").aggregate("sum")
|
||||
|
||||
assert len(gb1) == len(gb2)
|
||||
|
||||
|
||||
def test_agg_period_index():
|
||||
prng = period_range("2012-1-1", freq="M", periods=3)
|
||||
df = DataFrame(np.random.default_rng(2).standard_normal((3, 2)), index=prng)
|
||||
rs = df.groupby(level=0).sum()
|
||||
assert isinstance(rs.index, PeriodIndex)
|
||||
|
||||
# GH 3579
|
||||
index = period_range(start="1999-01", periods=5, freq="M")
|
||||
s1 = Series(np.random.default_rng(2).random(len(index)), index=index)
|
||||
s2 = Series(np.random.default_rng(2).random(len(index)), index=index)
|
||||
df = DataFrame.from_dict({"s1": s1, "s2": s2})
|
||||
grouped = df.groupby(df.index.month)
|
||||
list(grouped)
|
||||
|
||||
|
||||
def test_agg_dict_parameter_cast_result_dtypes():
|
||||
# GH 12821
|
||||
|
||||
df = DataFrame(
|
||||
{
|
||||
"class": ["A", "A", "B", "B", "C", "C", "D", "D"],
|
||||
"time": date_range("1/1/2011", periods=8, freq="h"),
|
||||
}
|
||||
)
|
||||
df.loc[[0, 1, 2, 5], "time"] = None
|
||||
|
||||
# test for `first` function
|
||||
exp = df.loc[[0, 3, 4, 6]].set_index("class")
|
||||
grouped = df.groupby("class")
|
||||
tm.assert_frame_equal(grouped.first(), exp)
|
||||
tm.assert_frame_equal(grouped.agg("first"), exp)
|
||||
tm.assert_frame_equal(grouped.agg({"time": "first"}), exp)
|
||||
tm.assert_series_equal(grouped.time.first(), exp["time"])
|
||||
tm.assert_series_equal(grouped.time.agg("first"), exp["time"])
|
||||
|
||||
# test for `last` function
|
||||
exp = df.loc[[0, 3, 4, 7]].set_index("class")
|
||||
grouped = df.groupby("class")
|
||||
tm.assert_frame_equal(grouped.last(), exp)
|
||||
tm.assert_frame_equal(grouped.agg("last"), exp)
|
||||
tm.assert_frame_equal(grouped.agg({"time": "last"}), exp)
|
||||
tm.assert_series_equal(grouped.time.last(), exp["time"])
|
||||
tm.assert_series_equal(grouped.time.agg("last"), exp["time"])
|
||||
|
||||
# count
|
||||
exp = Series([2, 2, 2, 2], index=Index(list("ABCD"), name="class"), name="time")
|
||||
tm.assert_series_equal(grouped.time.agg(len), exp)
|
||||
tm.assert_series_equal(grouped.time.size(), exp)
|
||||
|
||||
exp = Series([0, 1, 1, 2], index=Index(list("ABCD"), name="class"), name="time")
|
||||
tm.assert_series_equal(grouped.time.count(), exp)
|
||||
|
||||
|
||||
def test_agg_cast_results_dtypes():
|
||||
# similar to GH12821
|
||||
# xref #11444
|
||||
u = [dt.datetime(2015, x + 1, 1) for x in range(12)]
|
||||
v = list("aaabbbbbbccd")
|
||||
df = DataFrame({"X": v, "Y": u})
|
||||
|
||||
result = df.groupby("X")["Y"].agg(len)
|
||||
expected = df.groupby("X")["Y"].count()
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_aggregate_float64_no_int64():
|
||||
# see gh-11199
|
||||
df = DataFrame({"a": [1, 2, 3, 4, 5], "b": [1, 2, 2, 4, 5], "c": [1, 2, 3, 4, 5]})
|
||||
|
||||
expected = DataFrame({"a": [1, 2.5, 4, 5]}, index=[1, 2, 4, 5])
|
||||
expected.index.name = "b"
|
||||
|
||||
result = df.groupby("b")[["a"]].mean()
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
expected = DataFrame({"a": [1, 2.5, 4, 5], "c": [1, 2.5, 4, 5]}, index=[1, 2, 4, 5])
|
||||
expected.index.name = "b"
|
||||
|
||||
result = df.groupby("b")[["a", "c"]].mean()
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_aggregate_api_consistency():
|
||||
# GH 9052
|
||||
# make sure that the aggregates via dict
|
||||
# are consistent
|
||||
df = DataFrame(
|
||||
{
|
||||
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
|
||||
"B": ["one", "one", "two", "two", "two", "two", "one", "two"],
|
||||
"C": np.random.default_rng(2).standard_normal(8) + 1.0,
|
||||
"D": np.arange(8),
|
||||
}
|
||||
)
|
||||
|
||||
grouped = df.groupby(["A", "B"])
|
||||
c_mean = grouped["C"].mean()
|
||||
c_sum = grouped["C"].sum()
|
||||
d_mean = grouped["D"].mean()
|
||||
d_sum = grouped["D"].sum()
|
||||
|
||||
result = grouped["D"].agg(["sum", "mean"])
|
||||
expected = pd.concat([d_sum, d_mean], axis=1)
|
||||
expected.columns = ["sum", "mean"]
|
||||
tm.assert_frame_equal(result, expected, check_like=True)
|
||||
|
||||
result = grouped.agg(["sum", "mean"])
|
||||
expected = pd.concat([c_sum, c_mean, d_sum, d_mean], axis=1)
|
||||
expected.columns = MultiIndex.from_product([["C", "D"], ["sum", "mean"]])
|
||||
tm.assert_frame_equal(result, expected, check_like=True)
|
||||
|
||||
result = grouped[["D", "C"]].agg(["sum", "mean"])
|
||||
expected = pd.concat([d_sum, d_mean, c_sum, c_mean], axis=1)
|
||||
expected.columns = MultiIndex.from_product([["D", "C"], ["sum", "mean"]])
|
||||
tm.assert_frame_equal(result, expected, check_like=True)
|
||||
|
||||
result = grouped.agg({"C": "mean", "D": "sum"})
|
||||
expected = pd.concat([d_sum, c_mean], axis=1)
|
||||
tm.assert_frame_equal(result, expected, check_like=True)
|
||||
|
||||
result = grouped.agg({"C": ["mean", "sum"], "D": ["mean", "sum"]})
|
||||
expected = pd.concat([c_mean, c_sum, d_mean, d_sum], axis=1)
|
||||
expected.columns = MultiIndex.from_product([["C", "D"], ["mean", "sum"]])
|
||||
|
||||
msg = r"Column\(s\) \['r', 'r2'\] do not exist"
|
||||
with pytest.raises(KeyError, match=msg):
|
||||
grouped[["D", "C"]].agg({"r": "sum", "r2": "mean"})
|
||||
|
||||
|
||||
def test_agg_dict_renaming_deprecation():
|
||||
# 15931
|
||||
df = DataFrame({"A": [1, 1, 1, 2, 2], "B": range(5), "C": range(5)})
|
||||
|
||||
msg = r"nested renamer is not supported"
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
df.groupby("A").agg(
|
||||
{"B": {"foo": ["sum", "max"]}, "C": {"bar": ["count", "min"]}}
|
||||
)
|
||||
|
||||
msg = r"Column\(s\) \['ma'\] do not exist"
|
||||
with pytest.raises(KeyError, match=msg):
|
||||
df.groupby("A")[["B", "C"]].agg({"ma": "max"})
|
||||
|
||||
msg = r"nested renamer is not supported"
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
df.groupby("A").B.agg({"foo": "count"})
|
||||
|
||||
|
||||
def test_agg_compat():
|
||||
# GH 12334
|
||||
df = DataFrame(
|
||||
{
|
||||
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
|
||||
"B": ["one", "one", "two", "two", "two", "two", "one", "two"],
|
||||
"C": np.random.default_rng(2).standard_normal(8) + 1.0,
|
||||
"D": np.arange(8),
|
||||
}
|
||||
)
|
||||
|
||||
g = df.groupby(["A", "B"])
|
||||
|
||||
msg = r"nested renamer is not supported"
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g["D"].agg({"C": ["sum", "std"]})
|
||||
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g["D"].agg({"C": "sum", "D": "std"})
|
||||
|
||||
|
||||
def test_agg_nested_dicts():
|
||||
# API change for disallowing these types of nested dicts
|
||||
df = DataFrame(
|
||||
{
|
||||
"A": ["foo", "bar", "foo", "bar", "foo", "bar", "foo", "foo"],
|
||||
"B": ["one", "one", "two", "two", "two", "two", "one", "two"],
|
||||
"C": np.random.default_rng(2).standard_normal(8) + 1.0,
|
||||
"D": np.arange(8),
|
||||
}
|
||||
)
|
||||
|
||||
g = df.groupby(["A", "B"])
|
||||
|
||||
msg = r"nested renamer is not supported"
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g.aggregate({"r1": {"C": ["mean", "sum"]}, "r2": {"D": ["mean", "sum"]}})
|
||||
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g.agg({"C": {"ra": ["mean", "std"]}, "D": {"rb": ["mean", "std"]}})
|
||||
|
||||
# same name as the original column
|
||||
# GH9052
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g["D"].agg({"result1": np.sum, "result2": np.mean})
|
||||
|
||||
with pytest.raises(SpecificationError, match=msg):
|
||||
g["D"].agg({"D": np.sum, "result2": np.mean})
|
||||
|
||||
|
||||
def test_agg_item_by_item_raise_typeerror():
|
||||
df = DataFrame(np.random.default_rng(2).integers(10, size=(20, 10)))
|
||||
|
||||
def raiseException(df):
|
||||
pprint_thing("----------------------------------------")
|
||||
pprint_thing(df.to_string())
|
||||
raise TypeError("test")
|
||||
|
||||
with pytest.raises(TypeError, match="test"):
|
||||
df.groupby(0).agg(raiseException)
|
||||
|
||||
|
||||
def test_series_agg_multikey():
|
||||
ts = Series(
|
||||
np.arange(10, dtype=np.float64), index=date_range("2020-01-01", periods=10)
|
||||
)
|
||||
grouped = ts.groupby([lambda x: x.year, lambda x: x.month])
|
||||
|
||||
result = grouped.agg("sum")
|
||||
expected = grouped.sum()
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_series_agg_multi_pure_python():
|
||||
data = 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),
|
||||
}
|
||||
)
|
||||
|
||||
def bad(x):
|
||||
if isinstance(x.values, np.ndarray):
|
||||
assert len(x.values.base) > 0
|
||||
return "foo"
|
||||
|
||||
result = data.groupby(["A", "B"]).agg(bad)
|
||||
expected = data.groupby(["A", "B"]).agg(lambda x: "foo")
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_consistency():
|
||||
# agg with ([]) and () not consistent
|
||||
# GH 6715
|
||||
def P1(a):
|
||||
return np.percentile(a.dropna(), q=1)
|
||||
|
||||
df = DataFrame(
|
||||
{
|
||||
"col1": [1, 2, 3, 4],
|
||||
"col2": [10, 25, 26, 31],
|
||||
"date": [
|
||||
dt.date(2013, 2, 10),
|
||||
dt.date(2013, 2, 10),
|
||||
dt.date(2013, 2, 11),
|
||||
dt.date(2013, 2, 11),
|
||||
],
|
||||
}
|
||||
)
|
||||
|
||||
g = df.groupby("date")
|
||||
|
||||
expected = g.agg([P1])
|
||||
expected.columns = expected.columns.levels[0]
|
||||
|
||||
result = g.agg(P1)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_callables():
|
||||
# GH 7929
|
||||
df = DataFrame({"foo": [1, 2], "bar": [3, 4]}).astype(np.int64)
|
||||
|
||||
class fn_class:
|
||||
def __call__(self, x):
|
||||
return sum(x)
|
||||
|
||||
equiv_callables = [
|
||||
sum,
|
||||
np.sum,
|
||||
lambda x: sum(x),
|
||||
lambda x: x.sum(),
|
||||
partial(sum),
|
||||
fn_class(),
|
||||
]
|
||||
|
||||
expected = df.groupby("foo").agg("sum")
|
||||
for ecall in equiv_callables:
|
||||
warn = FutureWarning if ecall is sum or ecall is np.sum else None
|
||||
msg = "using DataFrameGroupBy.sum"
|
||||
with tm.assert_produces_warning(warn, match=msg):
|
||||
result = df.groupby("foo").agg(ecall)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_over_numpy_arrays():
|
||||
# GH 3788
|
||||
df = DataFrame(
|
||||
[
|
||||
[1, np.array([10, 20, 30])],
|
||||
[1, np.array([40, 50, 60])],
|
||||
[2, np.array([20, 30, 40])],
|
||||
],
|
||||
columns=["category", "arraydata"],
|
||||
)
|
||||
gb = df.groupby("category")
|
||||
|
||||
expected_data = [[np.array([50, 70, 90])], [np.array([20, 30, 40])]]
|
||||
expected_index = Index([1, 2], name="category")
|
||||
expected_column = ["arraydata"]
|
||||
expected = DataFrame(expected_data, index=expected_index, columns=expected_column)
|
||||
|
||||
alt = gb.sum(numeric_only=False)
|
||||
tm.assert_frame_equal(alt, expected)
|
||||
|
||||
result = gb.agg("sum", numeric_only=False)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
# FIXME: the original version of this test called `gb.agg(sum)`
|
||||
# and that raises TypeError if `numeric_only=False` is passed
|
||||
|
||||
|
||||
@pytest.mark.parametrize("as_period", [True, False])
|
||||
def test_agg_tzaware_non_datetime_result(as_period):
|
||||
# discussed in GH#29589, fixed in GH#29641, operating on tzaware values
|
||||
# with function that is not dtype-preserving
|
||||
dti = date_range("2012-01-01", periods=4, tz="UTC")
|
||||
if as_period:
|
||||
dti = dti.tz_localize(None).to_period("D")
|
||||
|
||||
df = DataFrame({"a": [0, 0, 1, 1], "b": dti})
|
||||
gb = df.groupby("a")
|
||||
|
||||
# Case that _does_ preserve the dtype
|
||||
result = gb["b"].agg(lambda x: x.iloc[0])
|
||||
expected = Series(dti[::2], name="b")
|
||||
expected.index.name = "a"
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
# Cases that do _not_ preserve the dtype
|
||||
result = gb["b"].agg(lambda x: x.iloc[0].year)
|
||||
expected = Series([2012, 2012], name="b")
|
||||
expected.index.name = "a"
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
result = gb["b"].agg(lambda x: x.iloc[-1] - x.iloc[0])
|
||||
expected = Series([pd.Timedelta(days=1), pd.Timedelta(days=1)], name="b")
|
||||
expected.index.name = "a"
|
||||
if as_period:
|
||||
expected = Series([pd.offsets.Day(1), pd.offsets.Day(1)], name="b")
|
||||
expected.index.name = "a"
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_timezone_round_trip():
|
||||
# GH 15426
|
||||
ts = pd.Timestamp("2016-01-01 12:00:00", tz="US/Pacific")
|
||||
df = DataFrame({"a": 1, "b": [ts + dt.timedelta(minutes=nn) for nn in range(10)]})
|
||||
|
||||
result1 = df.groupby("a")["b"].agg("min").iloc[0]
|
||||
result2 = df.groupby("a")["b"].agg(lambda x: np.min(x)).iloc[0]
|
||||
result3 = df.groupby("a")["b"].min().iloc[0]
|
||||
|
||||
assert result1 == ts
|
||||
assert result2 == ts
|
||||
assert result3 == ts
|
||||
|
||||
dates = [
|
||||
pd.Timestamp(f"2016-01-0{i:d} 12:00:00", tz="US/Pacific") for i in range(1, 5)
|
||||
]
|
||||
df = DataFrame({"A": ["a", "b"] * 2, "B": dates})
|
||||
grouped = df.groupby("A")
|
||||
|
||||
ts = df["B"].iloc[0]
|
||||
assert ts == grouped.nth(0)["B"].iloc[0]
|
||||
assert ts == grouped.head(1)["B"].iloc[0]
|
||||
assert ts == grouped.first()["B"].iloc[0]
|
||||
|
||||
# GH#27110 applying iloc should return a DataFrame
|
||||
msg = "DataFrameGroupBy.apply operated on the grouping columns"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
assert ts == grouped.apply(lambda x: x.iloc[0]).iloc[0, 1]
|
||||
|
||||
ts = df["B"].iloc[2]
|
||||
assert ts == grouped.last()["B"].iloc[0]
|
||||
|
||||
# GH#27110 applying iloc should return a DataFrame
|
||||
msg = "DataFrameGroupBy.apply operated on the grouping columns"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
assert ts == grouped.apply(lambda x: x.iloc[-1]).iloc[0, 1]
|
||||
|
||||
|
||||
def test_sum_uint64_overflow():
|
||||
# see gh-14758
|
||||
# Convert to uint64 and don't overflow
|
||||
df = DataFrame([[1, 2], [3, 4], [5, 6]], dtype=object)
|
||||
df = df + 9223372036854775807
|
||||
|
||||
index = Index(
|
||||
[9223372036854775808, 9223372036854775810, 9223372036854775812], dtype=np.uint64
|
||||
)
|
||||
expected = DataFrame(
|
||||
{1: [9223372036854775809, 9223372036854775811, 9223372036854775813]},
|
||||
index=index,
|
||||
dtype=object,
|
||||
)
|
||||
|
||||
expected.index.name = 0
|
||||
result = df.groupby(0).sum(numeric_only=False)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
# out column is non-numeric, so with numeric_only=True it is dropped
|
||||
result2 = df.groupby(0).sum(numeric_only=True)
|
||||
expected2 = expected[[]]
|
||||
tm.assert_frame_equal(result2, expected2)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"structure, expected",
|
||||
[
|
||||
(tuple, DataFrame({"C": {(1, 1): (1, 1, 1), (3, 4): (3, 4, 4)}})),
|
||||
(list, DataFrame({"C": {(1, 1): [1, 1, 1], (3, 4): [3, 4, 4]}})),
|
||||
(
|
||||
lambda x: tuple(x),
|
||||
DataFrame({"C": {(1, 1): (1, 1, 1), (3, 4): (3, 4, 4)}}),
|
||||
),
|
||||
(
|
||||
lambda x: list(x),
|
||||
DataFrame({"C": {(1, 1): [1, 1, 1], (3, 4): [3, 4, 4]}}),
|
||||
),
|
||||
],
|
||||
)
|
||||
def test_agg_structs_dataframe(structure, expected):
|
||||
df = DataFrame(
|
||||
{"A": [1, 1, 1, 3, 3, 3], "B": [1, 1, 1, 4, 4, 4], "C": [1, 1, 1, 3, 4, 4]}
|
||||
)
|
||||
|
||||
result = df.groupby(["A", "B"]).aggregate(structure)
|
||||
expected.index.names = ["A", "B"]
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"structure, expected",
|
||||
[
|
||||
(tuple, Series([(1, 1, 1), (3, 4, 4)], index=[1, 3], name="C")),
|
||||
(list, Series([[1, 1, 1], [3, 4, 4]], index=[1, 3], name="C")),
|
||||
(lambda x: tuple(x), Series([(1, 1, 1), (3, 4, 4)], index=[1, 3], name="C")),
|
||||
(lambda x: list(x), Series([[1, 1, 1], [3, 4, 4]], index=[1, 3], name="C")),
|
||||
],
|
||||
)
|
||||
def test_agg_structs_series(structure, expected):
|
||||
# Issue #18079
|
||||
df = DataFrame(
|
||||
{"A": [1, 1, 1, 3, 3, 3], "B": [1, 1, 1, 4, 4, 4], "C": [1, 1, 1, 3, 4, 4]}
|
||||
)
|
||||
|
||||
result = df.groupby("A")["C"].aggregate(structure)
|
||||
expected.index.name = "A"
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_category_nansum(observed):
|
||||
categories = ["a", "b", "c"]
|
||||
df = DataFrame(
|
||||
{"A": pd.Categorical(["a", "a", "b"], categories=categories), "B": [1, 2, 3]}
|
||||
)
|
||||
msg = "using SeriesGroupBy.sum"
|
||||
with tm.assert_produces_warning(FutureWarning, match=msg):
|
||||
result = df.groupby("A", observed=observed).B.agg(np.nansum)
|
||||
expected = Series(
|
||||
[3, 3, 0],
|
||||
index=pd.CategoricalIndex(["a", "b", "c"], categories=categories, name="A"),
|
||||
name="B",
|
||||
)
|
||||
if observed:
|
||||
expected = expected[expected != 0]
|
||||
tm.assert_series_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_list_like_func():
|
||||
# GH 18473
|
||||
df = DataFrame({"A": [str(x) for x in range(3)], "B": [str(x) for x in range(3)]})
|
||||
grouped = df.groupby("A", as_index=False, sort=False)
|
||||
result = grouped.agg({"B": lambda x: list(x)})
|
||||
expected = DataFrame(
|
||||
{"A": [str(x) for x in range(3)], "B": [[str(x)] for x in range(3)]}
|
||||
)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
def test_agg_lambda_with_timezone():
|
||||
# GH 23683
|
||||
df = DataFrame(
|
||||
{
|
||||
"tag": [1, 1],
|
||||
"date": [
|
||||
pd.Timestamp("2018-01-01", tz="UTC"),
|
||||
pd.Timestamp("2018-01-02", tz="UTC"),
|
||||
],
|
||||
}
|
||||
)
|
||||
result = df.groupby("tag").agg({"date": lambda e: e.head(1)})
|
||||
expected = DataFrame(
|
||||
[pd.Timestamp("2018-01-01", tz="UTC")],
|
||||
index=Index([1], name="tag"),
|
||||
columns=["date"],
|
||||
)
|
||||
tm.assert_frame_equal(result, expected)
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"err_cls",
|
||||
[
|
||||
NotImplementedError,
|
||||
RuntimeError,
|
||||
KeyError,
|
||||
IndexError,
|
||||
OSError,
|
||||
ValueError,
|
||||
ArithmeticError,
|
||||
AttributeError,
|
||||
],
|
||||
)
|
||||
def test_groupby_agg_err_catching(err_cls):
|
||||
# make sure we suppress anything other than TypeError or AssertionError
|
||||
# in _python_agg_general
|
||||
|
||||
# Use a non-standard EA to make sure we don't go down ndarray paths
|
||||
from pandas.tests.extension.decimal.array import (
|
||||
DecimalArray,
|
||||
make_data,
|
||||
to_decimal,
|
||||
)
|
||||
|
||||
data = make_data()[:5]
|
||||
df = DataFrame(
|
||||
{"id1": [0, 0, 0, 1, 1], "id2": [0, 1, 0, 1, 1], "decimals": DecimalArray(data)}
|
||||
)
|
||||
|
||||
expected = Series(to_decimal([data[0], data[3]]))
|
||||
|
||||
def weird_func(x):
|
||||
# weird function that raise something other than TypeError or IndexError
|
||||
# in _python_agg_general
|
||||
if len(x) == 0:
|
||||
raise err_cls
|
||||
return x.iloc[0]
|
||||
|
||||
result = df["decimals"].groupby(df["id1"]).agg(weird_func)
|
||||
tm.assert_series_equal(result, expected, check_names=False)
|
||||
Reference in New Issue
Block a user