Skip to content

Commit

Permalink
Release version 0.13.3 - pin pypi and docs (#4334)
Browse files Browse the repository at this point in the history 
* Release version 0.13.3
* FIX-#4113, FIX-#4116, FIX-#4115: Apply new `black` formatting, fix pydocstyle check and readthedocs build (#4114)

Co-authored-by: Alexey Prutskov <[email protected]>
Signed-off-by: Vasilij Litvinov <[email protected]>
  • Loading branch information
@vnlitvinov @prutskov
vnlitvinov and prutskov authored Mar 17, 2022
1 parent 9670c1c commit bac4031
Show file tree
Hide file tree
Showing 14 changed files with 46 additions and 43 deletions.
4 changes: 2 additions & 2 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,8 @@
<a href='https://join.slack.com/t/modin-project/shared_invite/zt-yvk5hr3b-f08p_ulbuRWsAfg9rMY3uA'><img src='https://img.shields.io/static/v1?label=chat&logo=slack&message=Slack&color=brightgreen' alt='Slack' align="center"/></a>
<a href="https://codecov.io/gh/modin-project/modin"><img src="https://codecov.io/gh/modin-project/modin/branch/master/graph/badge.svg" align="center"/></a>
<a href="https://github.com/modin-project/modin/actions"><img src="https://github.com/modin-project/modin/workflows/master/badge.svg" align="center"></a>
<a href="https://modin.readthedocs.io/en/0.13.2/?badge=0.13.2"><img alt="" src="https://readthedocs.org/projects/modin/badge/?version=0.13.2" align="center"></a>
<a href="https://pypi.org/project/modin/0.13.2/"><img alt="" src="https://img.shields.io/badge/pypi-0.13.2-blue.svg" align="center"></a>
<a href="https://modin.readthedocs.io/en/0.13.3/?badge=0.13.3"><img alt="" src="https://readthedocs.org/projects/modin/badge/?version=0.13.3" align="center"></a>
<a href="https://pypi.org/project/modin/0.13.3/"><img alt="" src="https://img.shields.io/badge/pypi-0.13.3-blue.svg" align="center"></a>
<a href="https://modin.org/modin-bench/#/"><img src="https://img.shields.io/badge/benchmarked%20by-asv-blue.svg" align="center"></a>
</p>

Expand Down
1 change: 1 addition & 0 deletions docs/requirements-doc.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,3 +13,4 @@ git+https://github.com/modin-project/modin.git@master#egg=modin[all]
sphinxcontrib_plantuml
sphinx-issues
xgboost
pip
4 changes: 2 additions & 2 deletions modin/core/storage_formats/pandas/parsers.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -519,14 +519,14 @@ def update_row_nums(match):
"""
b = match.group(0)
return re.sub(
br"\d+",
rb"\d+",
lambda c: str(int(c.group(0).decode("utf-8")) - _skiprows).encode(
"utf-8"
),
b,
)

bytes_data = re.sub(br'r="[A-Z]*\d+"', update_row_nums, bytes_data)
bytes_data = re.sub(rb'r="[A-Z]*\d+"', update_row_nums, bytes_data)
bytesio = BytesIO(excel_header + bytes_data + footer)
# Use openpyxl to read/parse sheet data
reader = WorksheetReader(ws, bytesio, ex.shared_strings, False)
Expand Down
4 changes: 2 additions & 2 deletions modin/experimental/core/execution/native/implementations/omnisci_on_native/omnisci_worker.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -203,8 +203,8 @@ def put_arrow_to_omnisci(cls, table, name=None):
cpu_count = os.cpu_count()
if cpu_count is not None:
fragment_size = table.num_rows // cpu_count
fragment_size = min(fragment_size, 2 ** 25)
fragment_size = max(fragment_size, 2 ** 18)
fragment_size = min(fragment_size, 2**25)
fragment_size = max(fragment_size, 2**18)
else:
fragment_size = 0
else:
Expand Down
2 changes: 1 addition & 1 deletion modin/pandas/test/dataframe/test_binary.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -72,7 +72,7 @@ def test_math_functions(other, axis, op):

@pytest.mark.parametrize(
"other",
[lambda df: df[: -(2 ** 4)], lambda df: df[df.columns[0]].reset_index(drop=True)],
[lambda df: df[: -(2**4)], lambda df: df[df.columns[0]].reset_index(drop=True)],
ids=["check_missing_value", "check_different_index"],
)
@pytest.mark.parametrize("fill_value", [None, 3.0])
Expand Down
32 changes: 16 additions & 16 deletions modin/pandas/test/dataframe/test_join_sort.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -64,20 +64,20 @@ def test_combine(data):
"test_data, test_data2",
[
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 7, 2 ** 6)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
np.random.uniform(0, 100, size=(2**7, 2**6)),
),
(
np.random.uniform(0, 100, size=(2 ** 7, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2**7, 2**6)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
),
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 7)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
np.random.uniform(0, 100, size=(2**6, 2**7)),
),
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 7)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2**6, 2**7)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
),
],
)
Expand Down Expand Up @@ -162,20 +162,20 @@ def test_join(test_data, test_data2):
"test_data, test_data2",
[
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 7, 2 ** 6)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
np.random.uniform(0, 100, size=(2**7, 2**6)),
),
(
np.random.uniform(0, 100, size=(2 ** 7, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2**7, 2**6)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
),
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 7)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
np.random.uniform(0, 100, size=(2**6, 2**7)),
),
(
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 7)),
np.random.uniform(0, 100, size=(2 ** 6, 2 ** 6)),
np.random.uniform(0, 100, size=(2**6, 2**7)),
np.random.uniform(0, 100, size=(2**6, 2**6)),
),
],
)
Expand Down
6 changes: 3 additions & 3 deletions modin/pandas/test/dataframe/test_reduce.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -165,12 +165,12 @@ def test_describe(data, percentiles):
@pytest.mark.parametrize("datetime_is_numeric", [True, False, None])
def test_2195(datetime_is_numeric, has_numeric_column):
data = {
"categorical": pd.Categorical(["d"] * 10 ** 2),
"date": [np.datetime64("2000-01-01")] * 10 ** 2,
"categorical": pd.Categorical(["d"] * 10**2),
"date": [np.datetime64("2000-01-01")] * 10**2,
}

if has_numeric_column:
data.update({"numeric": [5] * 10 ** 2})
data.update({"numeric": [5] * 10**2})

modin_df, pandas_df = pd.DataFrame(data), pandas.DataFrame(data)

Expand Down
2 changes: 1 addition & 1 deletion modin/pandas/test/test_concat.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@ def test_ignore_index_concat():


def test_concat_non_subscriptable_keys():
frame_data = np.random.randint(0, 100, size=(2 ** 10, 2 ** 6))
frame_data = np.random.randint(0, 100, size=(2**10, 2**6))
df = pd.DataFrame(frame_data).add_prefix("col")
pdf = pandas.DataFrame(frame_data).add_prefix("col")

Expand Down
10 changes: 5 additions & 5 deletions modin/pandas/test/test_groupby.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@ def wrapper(obj1, obj2, *args, **kwargs):

@pytest.mark.parametrize("as_index", [True, False])
def test_mixed_dtypes_groupby(as_index):
frame_data = np.random.randint(97, 198, size=(2 ** 6, 2 ** 4))
frame_data = np.random.randint(97, 198, size=(2**6, 2**4))
pandas_df = pandas.DataFrame(frame_data).add_prefix("col")
# Convert every other column to string
for col in pandas_df.iloc[
Expand Down Expand Up @@ -885,13 +885,13 @@ def test_simple_col_groupby():


@pytest.mark.parametrize(
"by", [np.random.randint(0, 100, size=2 ** 8), lambda x: x % 3, None]
"by", [np.random.randint(0, 100, size=2**8), lambda x: x % 3, None]
)
@pytest.mark.parametrize("as_index_series_or_dataframe", [0, 1, 2])
def test_series_groupby(by, as_index_series_or_dataframe):
if as_index_series_or_dataframe <= 1:
as_index = as_index_series_or_dataframe == 1
series_data = np.random.randint(97, 198, size=2 ** 8)
series_data = np.random.randint(97, 198, size=2**8)
modin_series = pd.Series(series_data)
pandas_series = pandas.Series(series_data)
else:
Expand Down Expand Up @@ -1292,7 +1292,7 @@ def eval_shift(modin_groupby, pandas_groupby):


def test_groupby_on_index_values_with_loop():
length = 2 ** 6
length = 2**6
data = {
"a": np.random.randint(0, 100, size=length),
"b": np.random.randint(0, 100, size=length),
Expand Down Expand Up @@ -1332,7 +1332,7 @@ def test_groupby_on_index_values_with_loop():
],
)
def test_groupby_multiindex(groupby_kwargs):
frame_data = np.random.randint(0, 100, size=(2 ** 6, 2 ** 4))
frame_data = np.random.randint(0, 100, size=(2**6, 2**4))
modin_df = pd.DataFrame(frame_data)
pandas_df = pandas.DataFrame(frame_data)

Expand Down
2 changes: 1 addition & 1 deletion modin/pandas/test/test_series.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3474,7 +3474,7 @@ def sort_sensitive_comparator(df1, df2):
)

# from issue #2365
arr = np.random.rand(2 ** 6)
arr = np.random.rand(2**6)
arr[::10] = np.nan
eval_general(
*create_test_series(arr),
Expand Down
6 changes: 3 additions & 3 deletions modin/pandas/test/utils.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -42,9 +42,9 @@
random_state = np.random.RandomState(seed=42)

DATASET_SIZE_DICT = {
"Small": (2 ** 2, 2 ** 3),
"Normal": (2 ** 6, 2 ** 8),
"Big": (2 ** 7, 2 ** 12),
"Small": (2**2, 2**3),
"Normal": (2**6, 2**8),
"Big": (2**7, 2**12),
}

# Size of test dataframes
Expand Down
4 changes: 2 additions & 2 deletions modin/test/test_envvar_npartitions.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@
@pytest.mark.parametrize("num_partitions", [2, 4, 6, 8, 10])
def test_set_npartitions(num_partitions):
NPartitions.put(num_partitions)
data = np.random.randint(0, 100, size=(2 ** 16, 2 ** 8))
data = np.random.randint(0, 100, size=(2**16, 2**8))
df = pd.DataFrame(data)
part_shape = df._query_compiler._modin_frame._partitions.shape
assert part_shape[0] == num_partitions and part_shape[1] == min(num_partitions, 8)
Expand All @@ -31,7 +31,7 @@ def test_set_npartitions(num_partitions):
@pytest.mark.parametrize("right_num_partitions", [2, 4, 6, 8, 10])
def test_runtime_change_npartitions(left_num_partitions, right_num_partitions):
NPartitions.put(left_num_partitions)
data = np.random.randint(0, 100, size=(2 ** 16, 2 ** 8))
data = np.random.randint(0, 100, size=(2**16, 2**8))
left_df = pd.DataFrame(data)
part_shape = left_df._query_compiler._modin_frame._partitions.shape
assert part_shape[0] == left_num_partitions and part_shape[1] == min(
Expand Down
10 changes: 5 additions & 5 deletions modin/test/test_partition_api.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,7 @@

@pytest.mark.parametrize("axis", [None, 0, 1])
def test_unwrap_partitions(axis):
data = np.random.randint(0, 100, size=(2 ** 16, 2 ** 8))
data = np.random.randint(0, 100, size=(2**16, 2**8))
df = pd.DataFrame(data)

if axis is None:
Expand Down Expand Up @@ -108,8 +108,8 @@ def test_unwrap_partitions(axis):
@pytest.mark.parametrize("index", [None, "index"])
@pytest.mark.parametrize("axis", [None, 0, 1])
def test_from_partitions(axis, index, columns, row_lengths, column_widths):
num_rows = 2 ** 16
num_cols = 2 ** 8
num_rows = 2**16
num_cols = 2**8
data = np.random.randint(0, 100, size=(num_rows, num_cols))
df1, df2 = pandas.DataFrame(data), pandas.DataFrame(data)
expected_df = pandas.concat([df1, df2], axis=1 if axis is None else axis)
Expand Down Expand Up @@ -157,8 +157,8 @@ def test_from_partitions(axis, index, columns, row_lengths, column_widths):
@pytest.mark.parametrize("index", ["original_idx", "new_idx"])
@pytest.mark.parametrize("axis", [None, 0, 1])
def test_from_partitions_mismatched_labels(axis, index, columns):
num_rows = 2 ** 16
num_cols = 2 ** 8
num_rows = 2**16
num_cols = 2**8
expected_df = pd.DataFrame(np.random.randint(0, 100, size=(num_rows, num_cols)))
partitions = unwrap_partitions(expected_df, axis=axis)

Expand Down
2 changes: 2 additions & 0 deletions scripts/doc_checker.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,8 @@
)
if not hasattr(sys.modules["cudf"], "DataFrame"):
sys.modules["cudf"].DataFrame = type("DataFrame", (object,), {})
if not hasattr(sys.modules["cupy"], "ndarray"):
sys.modules["cupy"].ndarray = type("ndarray", (object,), {})

logging.basicConfig(
stream=sys.stdout, format="%(levelname)s:%(message)s", level=logging.INFO
Expand Down

0 comments on commit bac4031

Please sign in to comment.