Skip to content

Commit

Permalink
CLN/TST: Clean groupby.test_allowlist (#52537)
Browse files Browse the repository at this point in the history 
* CLN/TST: Clean groupby.test_allowlist

* Add description to test_api.
  • Loading branch information
@rhshadrach
rhshadrach authored Apr 9, 2023
1 parent 328a620 commit e9e034b
Show file tree
Hide file tree
Showing 2 changed files with 129 additions and 177 deletions.
178 changes: 2 additions & 176 deletions pandas/tests/groupby/test_allowlist.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
"""
test methods relating to generic function evaluation
the so-called white/black lists
TODO: Existing tests should be moved or deduplicated
Do not add tests here!
"""

from string import ascii_lowercase
Expand All @@ -14,11 +14,6 @@
date_range,
)
import pandas._testing as tm
from pandas.core.groupby.base import (
groupby_other_methods,
reduction_kernels,
transformation_kernels,
)

AGG_FUNCTIONS = [
"sum",
Expand Down Expand Up @@ -100,131 +95,6 @@ def test_regression_allowlist_methods(raw_frame, op, axis, skipna, sort):
tm.assert_frame_equal(result, expected)


def test_groupby_blocklist(df_letters):
df = df_letters
s = df_letters.floats

blocklist = [
"eval",
"query",
"abs",
"where",
"mask",
"align",
"groupby",
"clip",
"astype",
"at",
"combine",
"consolidate",
"convert_objects",
]
to_methods = [method for method in dir(df) if method.startswith("to_")]

blocklist.extend(to_methods)

for bl in blocklist:
for obj in (df, s):
gb = obj.groupby(df.letters)

# e.g., to_csv
defined_but_not_allowed = (
f"(?:^Cannot.+{repr(bl)}.+'{type(gb).__name__}'.+try "
f"using the 'apply' method$)"
)

# e.g., query, eval
not_defined = (
f"(?:^'{type(gb).__name__}' object has no attribute {repr(bl)}$)"
)

msg = f"{defined_but_not_allowed}|{not_defined}"

with pytest.raises(AttributeError, match=msg):
getattr(gb, bl)


def test_tab_completion(mframe):
grp = mframe.groupby(level="second")
results = {v for v in dir(grp) if not v.startswith("_")}
expected = {
"A",
"B",
"C",
"agg",
"aggregate",
"apply",
"boxplot",
"filter",
"first",
"get_group",
"groups",
"hist",
"indices",
"last",
"max",
"mean",
"median",
"min",
"ngroups",
"nth",
"ohlc",
"plot",
"prod",
"size",
"std",
"sum",
"transform",
"var",
"sem",
"count",
"nunique",
"head",
"describe",
"cummax",
"quantile",
"rank",
"cumprod",
"tail",
"resample",
"cummin",
"fillna",
"cumsum",
"cumcount",
"ngroup",
"all",
"shift",
"skew",
"take",
"pct_change",
"any",
"corr",
"corrwith",
"cov",
"dtypes",
"ndim",
"diff",
"idxmax",
"idxmin",
"ffill",
"bfill",
"rolling",
"expanding",
"pipe",
"sample",
"ewm",
"value_counts",
}
assert results == expected


def test_groupby_function_rename(mframe):
grp = mframe.groupby(level="second")
for name in ["sum", "prod", "min", "max", "first", "last"]:
f = getattr(grp, name)
assert f.__name__ == name


@pytest.mark.parametrize(
"method",
[
Expand Down Expand Up @@ -285,47 +155,3 @@ def test_groupby_selection_other_methods(df):
tm.assert_frame_equal(
g.filter(lambda x: len(x) == 3), g_exp.filter(lambda x: len(x) == 3)
)


def test_all_methods_categorized(mframe):
grp = mframe.groupby(mframe.iloc[:, 0])
names = {_ for _ in dir(grp) if not _.startswith("_")} - set(mframe.columns)
new_names = set(names)
new_names -= reduction_kernels
new_names -= transformation_kernels
new_names -= groupby_other_methods

assert not reduction_kernels & transformation_kernels
assert not reduction_kernels & groupby_other_methods
assert not transformation_kernels & groupby_other_methods

# new public method?
if new_names:
msg = f"""
There are uncategorized methods defined on the Grouper class:
{new_names}.
Was a new method recently added?
Every public method On Grouper must appear in exactly one the
following three lists defined in pandas.core.groupby.base:
- `reduction_kernels`
- `transformation_kernels`
- `groupby_other_methods`
see the comments in pandas/core/groupby/base.py for guidance on
how to fix this test.
"""
raise AssertionError(msg)

# removed a public method?
all_categorized = reduction_kernels | transformation_kernels | groupby_other_methods
if names != all_categorized:
msg = f"""
Some methods which are supposed to be on the Grouper class
are missing:
{all_categorized - names}.
They're still defined in one of the lists that live in pandas/core/groupby/base.py.
If you removed a method, you should update them
"""
raise AssertionError(msg)
128 changes: 127 additions & 1 deletion pandas/tests/groupby/test_api_consistency.py → pandas/tests/groupby/test_api.py
View file
Original file line number Diff line number Diff line change
@@ -1,5 +1,8 @@
"""
Test the consistency of the groupby API, both internally and with other pandas objects.
Tests of the groupby API, including internal consistency and with other pandas objects.
Tests in this file should only check the existence, names, and arguments of groupby
methods. It should not test the results of any groupby operation.
"""

import inspect
Expand All @@ -10,12 +13,135 @@
DataFrame,
Series,
)
from pandas.core.groupby.base import (
groupby_other_methods,
reduction_kernels,
transformation_kernels,
)
from pandas.core.groupby.generic import (
DataFrameGroupBy,
SeriesGroupBy,
)


def test_tab_completion(mframe):
grp = mframe.groupby(level="second")
results = {v for v in dir(grp) if not v.startswith("_")}
expected = {
"A",
"B",
"C",
"agg",
"aggregate",
"apply",
"boxplot",
"filter",
"first",
"get_group",
"groups",
"hist",
"indices",
"last",
"max",
"mean",
"median",
"min",
"ngroups",
"nth",
"ohlc",
"plot",
"prod",
"size",
"std",
"sum",
"transform",
"var",
"sem",
"count",
"nunique",
"head",
"describe",
"cummax",
"quantile",
"rank",
"cumprod",
"tail",
"resample",
"cummin",
"fillna",
"cumsum",
"cumcount",
"ngroup",
"all",
"shift",
"skew",
"take",
"pct_change",
"any",
"corr",
"corrwith",
"cov",
"dtypes",
"ndim",
"diff",
"idxmax",
"idxmin",
"ffill",
"bfill",
"rolling",
"expanding",
"pipe",
"sample",
"ewm",
"value_counts",
}
assert results == expected


def test_all_methods_categorized(mframe):
grp = mframe.groupby(mframe.iloc[:, 0])
names = {_ for _ in dir(grp) if not _.startswith("_")} - set(mframe.columns)
new_names = set(names)
new_names -= reduction_kernels
new_names -= transformation_kernels
new_names -= groupby_other_methods

assert not reduction_kernels & transformation_kernels
assert not reduction_kernels & groupby_other_methods
assert not transformation_kernels & groupby_other_methods

# new public method?
if new_names:
msg = f"""
There are uncategorized methods defined on the Grouper class:
{new_names}.
Was a new method recently added?
Every public method On Grouper must appear in exactly one the
following three lists defined in pandas.core.groupby.base:
- `reduction_kernels`
- `transformation_kernels`
- `groupby_other_methods`
see the comments in pandas/core/groupby/base.py for guidance on
how to fix this test.
"""
raise AssertionError(msg)

# removed a public method?
all_categorized = reduction_kernels | transformation_kernels | groupby_other_methods
if names != all_categorized:
msg = f"""
Some methods which are supposed to be on the Grouper class
are missing:
{all_categorized - names}.
They're still defined in one of the lists that live in pandas/core/groupby/base.py.
If you removed a method, you should update them
"""
raise AssertionError(msg)


def test_frame_consistency(groupby_func):
# GH#48028
if groupby_func in ("first", "last"):
Expand Down

0 comments on commit e9e034b

Please sign in to comment.