Skip to content

TST add test for dtype consistency with pd replace #23305 #35234

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 10 commits into from
Jul 16, 2020
80 changes: 80 additions & 0 deletions pandas/tests/frame/methods/test_replace.py
Original file line number Diff line number Diff line change
Expand Up @@ -1420,3 +1420,83 @@ def test_replace_period_ignore_float(self):
result = df.replace(1.0, 0.0)
expected = pd.DataFrame({"Per": [pd.Period("2020-01")] * 3})
tm.assert_frame_equal(expected, result)

def test_replace_value_category_type(self):
"""
Test for #23305: to ensure category dtypes are maintained
after replace with direct values
"""

# create input data
input_dict = {
"col1": [1, 2, 3, 4],
"col2": ["a", "b", "c", "d"],
"col3": [1.5, 2.5, 3.5, 4.5],
"col4": ["cat1", "cat2", "cat3", "cat4"],
"col5": ["obj1", "obj2", "obj3", "obj4"],
}
# explicitly cast columns as category and order them
input_df = pd.DataFrame(data=input_dict).astype(
{"col2": "category", "col4": "category"}
)
input_df["col2"] = input_df["col2"].cat.reorder_categories(
["a", "b", "c", "d"], ordered=True
)
input_df["col4"] = input_df["col4"].cat.reorder_categories(
["cat1", "cat2", "cat3", "cat4"], ordered=True
)

# create expected dataframe
expected_dict = {
"col1": [1, 2, 3, 4],
"col2": ["a", "b", "c", "z"],
"col3": [1.5, 2.5, 3.5, 4.5],
"col4": ["cat1", "catX", "cat3", "cat4"],
"col5": ["obj9", "obj2", "obj3", "obj4"],
}
# explicitly cast columns as category and order them
expected = pd.DataFrame(data=expected_dict).astype(
{"col2": "category", "col4": "category"}
)
expected["col2"] = expected["col2"].cat.reorder_categories(
["a", "b", "c", "z"], ordered=True
)
expected["col4"] = expected["col4"].cat.reorder_categories(
["cat1", "catX", "cat3", "cat4"], ordered=True
)

# replace values in input dataframe
input_df = input_df.replace("d", "z")
input_df = input_df.replace("obj1", "obj9")
result = input_df.replace("cat2", "catX")

tm.assert_frame_equal(result, expected)

@pytest.mark.xfail(
reason="category dtype gets changed to object type after replace, see #35268",
strict=True,
)
def test_replace_dict_category_type(self, input_category_df, expected_category_df):
"""
Test to ensure category dtypes are maintained
after replace with dict values
"""

# create input dataframe
input_dict = {"col1": ["a"], "col2": ["obj1"], "col3": ["cat1"]}
# explicitly cast columns as category
input_df = pd.DataFrame(data=input_dict).astype(
{"col1": "category", "col2": "category", "col3": "category"}
)

# create expected dataframe
expected_dict = {"col1": ["z"], "col2": ["obj9"], "col3": ["catX"]}
# explicitly cast columns as category
expected = pd.DataFrame(data=expected_dict).astype(
{"col1": "category", "col2": "category", "col3": "category"}
)

# replace values in input dataframe using a dict
result = input_df.replace({"a": "z", "obj1": "obj9", "cat1": "catX"})

tm.assert_frame_equal(result, expected)