Format and docstrings

tests/test_fugue/conftest.py

@@ -2,6 +2,7 @@
 import numpy as np
 import pandas as pd
 
+
 @pytest.fixture
 def ref_df():
     np.random.seed(0)

tests/test_fugue/test_duckdb.py

@@ -1,3 +1,18 @@
+#
+# Copyright 2020 Capital One Services, LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Test fugue functionality with duckdb."""
 import pytest
 from ordered_set import OrderedSet
 from pytest import raises

tests/test_fugue/test_fugue_helpers.py

@@ -0,0 +1,22 @@
+#
+# Copyright 2020 Capital One Services, LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""One test helper for fugue reports."""
+
+def _compare_report(expected, actual, truncate=False):
+    """Compare datacompy reports."""
+    if truncate:
+        expected = expected.split("Sample Rows", 1)[0]
+        actual = actual.split("Sample Rows", 1)[0]
+    assert expected == actual

tests/test_fugue/test_fugue_pandas.py

@@ -12,10 +12,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-
-"""
-Testing out the fugue is_match functionality
-"""
+"""Test the fugue functionality with pandas."""
 from io import StringIO
 import pandas as pd
 from ordered_set import OrderedSet
@@ -31,7 +28,7 @@
     unq_columns,
 )
 
-from test_fuge_helpers import _compare_report
+from test_fugue_helpers import _compare_report
 
 
 def test_is_match_native(
@@ -81,9 +78,6 @@ def test_is_match_native(
         )
 
 
-
-
-
 def test_doc_case():
     data1 = """acct_id,dollar_amt,name,float_fld,date_fld
     10000001234,123.45,George Maharis,14530.1555,2017-01-01
@@ -115,6 +109,7 @@ def test_doc_case():
         parallelism=2,
     )
 
+
 def test_report_pandas(
     simple_diff_df1,
     simple_diff_df2,
@@ -146,6 +141,7 @@ def test_report_pandas(
     a = report(large_diff_df1, large_diff_df2, "x", parallelism=2)
     _compare_report(comp.report(), a, truncate=True)
 
+
 def test_unique_columns_native(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
@@ -159,9 +155,6 @@ def test_unique_columns_native(ref_df):
     assert unq_columns(df3, df2) == OrderedSet(["c"])
 
 
-
-
-
 def test_intersect_columns_native(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
@@ -175,8 +168,6 @@ def test_intersect_columns_native(ref_df):
     assert intersect_columns(df3, df2) == OrderedSet()
 
 
-
-
 def test_all_columns_match_native(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
@@ -190,8 +181,6 @@ def test_all_columns_match_native(ref_df):
     assert all_columns_match(df3, df2) is False
 
 
-
-
 def test_all_rows_overlap_native(
     ref_df,
     shuffle_df,
@@ -203,4 +192,3 @@ def test_all_rows_overlap_native(
     # Fugue
     assert all_rows_overlap(ref_df[0], shuffle_df, join_columns="a", parallelism=2)
     assert not all_rows_overlap(ref_df[0], ref_df[4], join_columns="a", parallelism=2)
-

tests/test_fugue/test_fugue_polars.py

@@ -1,3 +1,18 @@
+#
+# Copyright 2020 Capital One Services, LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Test fugue and polars."""
 import pytest
 from ordered_set import OrderedSet
 from pytest import raises
@@ -9,8 +24,10 @@
     is_match,
     unq_columns,
 )
+
 pl = pytest.importorskip("polars")
 
+
 def test_is_match_polars(
     ref_df,
     shuffle_df,
@@ -19,7 +36,6 @@ def test_is_match_polars(
     space_df,
     upper_col_df,
 ):
-
     rdf = pl.from_pandas(ref_df[0])
 
     assert is_match(rdf, shuffle_df, join_columns="a")
@@ -39,8 +55,8 @@ def test_is_match_polars(
     with raises(AssertionError):
         is_match(rdf, upper_col_df, join_columns="a", cast_column_names_lower=False)
 
-def test_unique_columns_polars(ref_df):
 
+def test_unique_columns_polars(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
     df2 = ref_df[2]
@@ -57,8 +73,8 @@ def test_unique_columns_polars(ref_df):
     assert unq_columns(pdf1_copy, pdf1) == OrderedSet()
     assert unq_columns(pdf3, pdf2) == OrderedSet(["c"])
 
-def test_intersect_columns_polars(ref_df):
 
+def test_intersect_columns_polars(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
     df2 = ref_df[2]
@@ -75,8 +91,8 @@ def test_intersect_columns_polars(ref_df):
     assert intersect_columns(pdf1_copy, pdf1) == OrderedSet(["a", "b", "c"])
     assert intersect_columns(pdf3, pdf2) == OrderedSet()
 
-def test_all_columns_match_polars(ref_df):
 
+def test_all_columns_match_polars(ref_df):
     df1 = ref_df[0]
     df1_copy = ref_df[1]
     df2 = ref_df[2]
@@ -93,11 +109,11 @@ def test_all_columns_match_polars(ref_df):
     assert all_columns_match(df1_copy, df1) is True
     assert all_columns_match(df3, df2) is False
 
+
 def test_all_rows_overlap_polars(
     ref_df,
     shuffle_df,
 ):
-
     rdf = pl.from_pandas(ref_df[0])
     rdf_copy = pl.from_pandas(ref_df[0].copy())
     rdf4 = pl.from_pandas(ref_df[4])

tests/test_fugue/test_fugue_spark.py

@@ -1,3 +1,18 @@
+#
+# Copyright 2020 Capital One Services, LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Test fugue and spark."""
 import pytest
 from datacompy import (
     Compare,
@@ -11,10 +26,11 @@
 from ordered_set import OrderedSet
 from pytest import raises
 
-from test_fuge_helpers import _compare_report
+from test_fugue_helpers import _compare_report
 
 pyspark = pytest.importorskip("pyspark")
 
+
 def test_is_match_spark(
     spark_session,
     ref_df,