Skip to content

TST/CLN: Remove makeMixedDataFrame and getMixedTypeDict #56202

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 27, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 0 additions & 19 deletions pandas/_testing/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -482,23 +482,6 @@ def makeDataFrame() -> DataFrame:
return DataFrame(data)


def getMixedTypeDict():
index = Index(["a", "b", "c", "d", "e"])

data = {
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": bdate_range("1/1/2009", periods=5),
}

return index, data


def makeMixedDataFrame() -> DataFrame:
return DataFrame(getMixedTypeDict()[1])


def makeCustomIndex(
nentries,
nlevels,
Expand Down Expand Up @@ -1026,7 +1009,6 @@ def shares_memory(left, right) -> bool:
"get_dtype",
"getitem",
"get_locales",
"getMixedTypeDict",
"get_finest_unit",
"get_obj",
"get_op_from_name",
Expand All @@ -1042,7 +1024,6 @@ def shares_memory(left, right) -> bool:
"makeDateIndex",
"makeFloatIndex",
"makeIntIndex",
"makeMixedDataFrame",
"makeNumericIndex",
"makeObjectSeries",
"makePeriodIndex",
Expand Down
14 changes: 12 additions & 2 deletions pandas/tests/frame/methods/test_transpose.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,11 @@
from pandas import (
DataFrame,
DatetimeIndex,
Index,
IntervalIndex,
Series,
Timestamp,
bdate_range,
date_range,
timedelta_range,
)
Expand Down Expand Up @@ -108,9 +110,17 @@ def test_transpose_float(self, float_frame):
else:
assert value == frame[col][idx]

def test_transpose_mixed(self):
# mixed type
index, data = tm.getMixedTypeDict()
mixed = DataFrame(data, index=index)
mixed = DataFrame(
{
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": bdate_range("1/1/2009", periods=5),
},
index=Index(["a", "b", "c", "d", "e"], dtype=object),
)

mixed_T = mixed.T
for col, s in mixed_T.items():
Expand Down
9 changes: 8 additions & 1 deletion pandas/tests/io/pytables/test_append.py
Original file line number Diff line number Diff line change
Expand Up @@ -397,7 +397,14 @@ def check_col(key, name, size):
store.append("df_new", df_new)

# min_itemsize on Series index (GH 11412)
df = tm.makeMixedDataFrame().set_index("C")
df = DataFrame(
{
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": pd.Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
"D": date_range("20130101", periods=5),
}
).set_index("C")
store.append("ss", df["B"], min_itemsize={"index": 4})
tm.assert_series_equal(store.select("ss"), df["B"])

Expand Down
9 changes: 8 additions & 1 deletion pandas/tests/io/pytables/test_store.py
Original file line number Diff line number Diff line change
Expand Up @@ -323,7 +323,14 @@ def test_to_hdf_with_min_itemsize(tmp_path, setup_path):
path = tmp_path / setup_path

# min_itemsize in index with to_hdf (GH 10381)
df = tm.makeMixedDataFrame().set_index("C")
df = DataFrame(
{
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
"D": date_range("20130101", periods=5),
}
).set_index("C")
df.to_hdf(path, key="ss3", format="table", min_itemsize={"index": 6})
# just make sure there is a longer string:
df2 = df.copy().reset_index().assign(C="longer").set_index("C")
Expand Down
10 changes: 8 additions & 2 deletions pandas/tests/reshape/merge/test_join.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
MultiIndex,
Series,
Timestamp,
bdate_range,
concat,
merge,
)
Expand Down Expand Up @@ -57,8 +58,13 @@ def df2(self):

@pytest.fixture
def target_source(self):
index, data = tm.getMixedTypeDict()
target = DataFrame(data, index=index)
data = {
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": bdate_range("1/1/2009", periods=5),
}
target = DataFrame(data, index=Index(["a", "b", "c", "d", "e"], dtype=object))

# Join on string value

Expand Down
18 changes: 16 additions & 2 deletions pandas/tests/series/methods/test_map.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@
Index,
MultiIndex,
Series,
bdate_range,
isna,
timedelta_range,
)
Expand Down Expand Up @@ -154,8 +155,13 @@ def test_list_raises(string_series):
string_series.map([lambda x: x])


def test_map(datetime_series):
index, data = tm.getMixedTypeDict()
def test_map():
data = {
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": bdate_range("1/1/2009", periods=5),
}

source = Series(data["B"], index=data["C"])
target = Series(data["C"][:4], index=data["D"][:4])
Expand All @@ -171,10 +177,14 @@ def test_map(datetime_series):
for k, v in merged.items():
assert v == source[target[k]]


def test_map_datetime(datetime_series):
# function
result = datetime_series.map(lambda x: x * 2)
tm.assert_series_equal(result, datetime_series * 2)


def test_map_category():
# GH 10324
a = Series([1, 2, 3, 4])
b = Series(["even", "odd", "even", "odd"], dtype="category")
Expand All @@ -185,6 +195,8 @@ def test_map(datetime_series):
exp = Series(["odd", "even", "odd", np.nan])
tm.assert_series_equal(a.map(c), exp)


def test_map_category_numeric():
a = Series(["a", "b", "c", "d"])
b = Series([1, 2, 3, 4], index=pd.CategoricalIndex(["b", "c", "d", "e"]))
c = Series([1, 2, 3, 4], index=Index(["b", "c", "d", "e"]))
Expand All @@ -194,6 +206,8 @@ def test_map(datetime_series):
exp = Series([np.nan, 1, 2, 3])
tm.assert_series_equal(a.map(c), exp)


def test_map_category_string():
a = Series(["a", "b", "c", "d"])
b = Series(
["B", "C", "D", "E"],
Expand Down
18 changes: 16 additions & 2 deletions pandas/tests/util/test_hashing.py
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,14 @@ def test_multiindex_objects():
DataFrame({"x": ["a", "b", "c"], "y": [1, 2, 3]}),
DataFrame(),
DataFrame(np.full((10, 4), np.nan)),
tm.makeMixedDataFrame(),
DataFrame(
{
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
"D": pd.date_range("20130101", periods=5),
}
),
tm.makeTimeDataFrame(),
tm.makeTimeSeries(),
Series(tm.makePeriodIndex()),
Expand All @@ -162,7 +169,14 @@ def test_hash_pandas_object(obj, index):
Series([True, False, True]),
DataFrame({"x": ["a", "b", "c"], "y": [1, 2, 3]}),
DataFrame(np.full((10, 4), np.nan)),
tm.makeMixedDataFrame(),
DataFrame(
{
"A": [0.0, 1.0, 2.0, 3.0, 4.0],
"B": [0.0, 1.0, 0.0, 1.0, 0.0],
"C": Index(["foo1", "foo2", "foo3", "foo4", "foo5"], dtype=object),
"D": pd.date_range("20130101", periods=5),
}
),
tm.makeTimeDataFrame(),
tm.makeTimeSeries(),
Series(tm.makePeriodIndex()),
Expand Down