Skip to content

TST/CLN: Split out some to_string tests #37234

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.

Sign up for GitHub

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 2 commits into from
Oct 20, 2020
Merged

TST/CLN: Split out some to_string tests #37234

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2ef1095
TST/CLN: Split out some to_string tests
dsaxton Oct 19, 2020
e30ef0b
Merge remote-tracking branch 'upstream/master' into split-formatting-…
dsaxton Oct 20, 2020
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
208 changes: 0 additions & 208 deletions pandas/tests/io/formats/test_format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -158,16 +158,6 @@ def has_expanded_repr(df):

@pytest.mark.filterwarnings("ignore::FutureWarning:.*format")
class TestDataFrameFormatting:
def test_repr_embedded_ndarray(self):
arr = np.empty(10, dtype=[("err", object)])
for i in range(len(arr)):
arr["err"][i] = np.random.randn(i)

df = DataFrame(arr)
repr(df["err"])
repr(df)
df.to_string()

def test_eng_float_formatter(self, float_frame):
df = float_frame
df.loc[5] = 0
Expand Down Expand Up @@ -204,13 +194,6 @@ def check(null_counts, result):
check(True, False)
check(False, False)

def test_repr_tuples(self):
buf = StringIO()

df = DataFrame({"tups": list(zip(range(10), range(10)))})
repr(df)
df.to_string(col_space=10, buf=buf)

def test_repr_truncation(self):
max_len = 20
with option_context("display.max_colwidth", max_len):
Expand Down Expand Up @@ -534,45 +517,6 @@ def test_str_max_colwidth(self):
"1 foo bar stuff 1"
)

def test_to_string_truncate(self):
# GH 9784 - dont truncate when calling DataFrame.to_string
df = pd.DataFrame(
[
{
"a": "foo",
"b": "bar",
"c": "let's make this a very VERY long line that is longer "
"than the default 50 character limit",
"d": 1,
},
{"a": "foo", "b": "bar", "c": "stuff", "d": 1},
]
)
df.set_index(["a", "b", "c"])
assert df.to_string() == (
" a b "
" c d\n"
"0 foo bar let's make this a very VERY long line t"
"hat is longer than the default 50 character limit 1\n"
"1 foo bar "
" stuff 1"
)
with option_context("max_colwidth", 20):
# the display option has no effect on the to_string method
assert df.to_string() == (
" a b "
" c d\n"
"0 foo bar let's make this a very VERY long line t"
"hat is longer than the default 50 character limit 1\n"
"1 foo bar "
" stuff 1"
)
assert df.to_string(max_colwidth=20) == (
" a b c d\n"
"0 foo bar let's make this ... 1\n"
"1 foo bar stuff 1"
)

def test_auto_detect(self):
term_width, term_height = get_terminal_size()
fac = 1.05 # Arbitrary large factor to exceed term width
Expand Down Expand Up @@ -633,95 +577,6 @@ def test_to_string_repr_unicode(self):
finally:
sys.stdin = _stdin

def test_to_string_unicode_columns(self, float_frame):
df = DataFrame({"\u03c3": np.arange(10.0)})

buf = StringIO()
df.to_string(buf=buf)
buf.getvalue()

buf = StringIO()
df.info(buf=buf)
buf.getvalue()

result = float_frame.to_string()
assert isinstance(result, str)

def test_to_string_utf8_columns(self):
n = "\u05d0".encode()

with option_context("display.max_rows", 1):
df = DataFrame([1, 2], columns=[n])
repr(df)

def test_to_string_unicode_two(self):
dm = DataFrame({"c/\u03c3": []})
buf = StringIO()
dm.to_string(buf)

def test_to_string_unicode_three(self):
dm = DataFrame(["\xc2"])
buf = StringIO()
dm.to_string(buf)

def test_to_string_with_formatters(self):
df = DataFrame(
{
"int": [1, 2, 3],
"float": [1.0, 2.0, 3.0],
"object": [(1, 2), True, False],
},
columns=["int", "float", "object"],
)

formatters = [
("int", lambda x: f"0x{x:x}"),
("float", lambda x: f"[{x: 4.1f}]"),
("object", lambda x: f"-{x!s}-"),
]
result = df.to_string(formatters=dict(formatters))
result2 = df.to_string(formatters=list(zip(*formatters))[1])
assert result == (
" int float object\n"
"0 0x1 [ 1.0] -(1, 2)-\n"
"1 0x2 [ 2.0] -True-\n"
"2 0x3 [ 3.0] -False-"
)
assert result == result2

def test_to_string_with_datetime64_monthformatter(self):
months = [datetime(2016, 1, 1), datetime(2016, 2, 2)]
x = DataFrame({"months": months})

def format_func(x):
return x.strftime("%Y-%m")

result = x.to_string(formatters={"months": format_func})
expected = "months\n0 2016-01\n1 2016-02"
assert result.strip() == expected

def test_to_string_with_datetime64_hourformatter(self):

x = DataFrame(
{
"hod": pd.to_datetime(
["10:10:10.100", "12:12:12.120"], format="%H:%M:%S.%f"
)
}
)

def format_func(x):
return x.strftime("%H:%M")

result = x.to_string(formatters={"hod": format_func})
expected = "hod\n0 10:10\n1 12:12"
assert result.strip() == expected

def test_to_string_with_formatters_unicode(self):
df = DataFrame({"c/\u03c3": [1, 2, 3]})
result = df.to_string(formatters={"c/\u03c3": str})
assert result == " c/\u03c3\n" + "0 1\n1 2\n2 3"

def test_east_asian_unicode_false(self):
# not aligned properly because of east asian width

Expand Down Expand Up @@ -3398,66 +3253,3 @@ def test_filepath_or_buffer_bad_arg_raises(float_frame, method):
msg = "buf is not a file name and it has no write method"
with pytest.raises(TypeError, match=msg):
getattr(float_frame, method)(buf=object())


@pytest.mark.parametrize(
"input_array, expected",
[
("a", "a"),
(["a", "b"], "a\nb"),
([1, "a"], "1\na"),
(1, "1"),
([0, -1], " 0\n-1"),
(1.0, "1.0"),
([" a", " b"], " a\n b"),
([".1", "1"], ".1\n 1"),
(["10", "-10"], " 10\n-10"),
],
)
def test_format_remove_leading_space_series(input_array, expected):
# GH: 24980
s = pd.Series(input_array).to_string(index=False)
assert s == expected


@pytest.mark.parametrize(
"input_array, expected",
[
({"A": ["a"]}, "A\na"),
({"A": ["a", "b"], "B": ["c", "dd"]}, "A B\na c\nb dd"),
({"A": ["a", 1], "B": ["aa", 1]}, "A B\na aa\n1 1"),
],
)
def test_format_remove_leading_space_dataframe(input_array, expected):
# GH: 24980
df = pd.DataFrame(input_array).to_string(index=False)
assert df == expected


def test_to_string_complex_number_trims_zeros():
s = pd.Series([1.000000 + 1.000000j, 1.0 + 1.0j, 1.05 + 1.0j])
result = s.to_string()
expected = "0 1.00+1.00j\n1 1.00+1.00j\n2 1.05+1.00j"
assert result == expected


def test_nullable_float_to_string(float_ea_dtype):
# https://github.com/pandas-dev/pandas/issues/36775
dtype = float_ea_dtype
s = pd.Series([0.0, 1.0, None], dtype=dtype)
result = s.to_string()
expected = """0 0.0
1 1.0
2 <NA>"""
assert result == expected


def test_nullable_int_to_string(any_nullable_int_dtype):
# https://github.com/pandas-dev/pandas/issues/36775
dtype = any_nullable_int_dtype
s = pd.Series([0, 1, None], dtype=dtype)
result = s.to_string()
expected = """0 0
1 1
2 <NA>"""
assert result == expected
Loading