Handle New PyFlakes Issues

.pep8speaks.yml

@@ -16,4 +16,5 @@ pycodestyle:
         - E731,  # do not assign a lambda expression, use a def
         - C406,  # Unnecessary list literal - rewrite as a dict literal.
         - C408,  # Unnecessary dict call - rewrite as a literal.
-        - C409   # Unnecessary list passed to tuple() - rewrite as a tuple literal.
+        - C409,  # Unnecessary list passed to tuple() - rewrite as a tuple literal.
+        - F821   # undefined name (temporarily for type hints)

pandas/_libs/tslibs/nattype.pyx

@@ -353,7 +353,7 @@ class NaTType(_NaT):
 
         .. versionadded:: 0.23.0
         """)
-    day_name = _make_nan_func('day_name', # noqa:E128
+    day_name = _make_nan_func('day_name',  # noqa:E128
         """
         Return the day name of the Timestamp with specified locale.
 

pandas/core/dtypes/dtypes.py

@@ -937,7 +937,7 @@ def construct_from_string(cls, string):
 
         if (string.lower() == 'interval' or
            cls._match.search(string) is not None):
-                return cls(string)
+            return cls(string)
 
         msg = ('Incorrectly formatted string passed to constructor. '
                'Valid formats include Interval or Interval[dtype] '

pandas/io/formats/format.py

@@ -440,7 +440,6 @@ def _chk_truncate(self):
         max_rows = self.max_rows
 
         if max_cols == 0 or max_rows == 0:  # assume we are in the terminal
-                                            # (why else = 0)
             (w, h) = get_terminal_size()
             self.w = w
             self.h = h

pandas/tests/frame/test_alter_axes.py

@@ -201,7 +201,8 @@ def test_set_index_pass_arrays_duplicate(self, frame_of_index_cols, drop,
         # need to adapt first drop for case that both keys are 'A' --
         # cannot drop the same column twice;
         # use "is" because == would give ambiguous Boolean error for containers
-        first_drop = False if (keys[0] is 'A' and keys[1] is 'A') else drop
+        first_drop = False if (
+            keys[0] is 'A' and keys[1] is 'A') else drop  # noqa: F632
 
         # to test against already-tested behaviour, we add sequentially,
         # hence second append always True; must wrap keys in list, otherwise
@@ -1272,7 +1273,7 @@ def test_rename_axis_style_raises(self):
             df.rename(id, mapper=id)
 
     def test_reindex_api_equivalence(self):
-            # equivalence of the labels/axis and index/columns API's
+        # equivalence of the labels/axis and index/columns API's
         df = DataFrame([[1, 2, 3], [3, 4, 5], [5, 6, 7]],
                        index=['a', 'b', 'c'],
                        columns=['d', 'e', 'f'])

pandas/tests/groupby/test_apply.py

@@ -9,7 +9,7 @@
 
 
 def test_apply_issues():
-        # GH 5788
+    # GH 5788
 
     s = """2011.05.16,00:00,1.40893
 2011.05.16,01:00,1.40760

pandas/tests/groupby/test_grouping.py

@@ -649,17 +649,17 @@ def test_groupby_with_single_column(self):
         tm.assert_frame_equal(df.groupby('a').nth(1), exp)
 
     def test_gb_key_len_equal_axis_len(self):
-            # GH16843
-            # test ensures that index and column keys are recognized correctly
-            # when number of keys equals axis length of groupby
-            df = pd.DataFrame([['foo', 'bar', 'B', 1],
-                               ['foo', 'bar', 'B', 2],
-                               ['foo', 'baz', 'C', 3]],
-                              columns=['first', 'second', 'third', 'one'])
-            df = df.set_index(['first', 'second'])
-            df = df.groupby(['first', 'second', 'third']).size()
-            assert df.loc[('foo', 'bar', 'B')] == 2
-            assert df.loc[('foo', 'baz', 'C')] == 1
+        # GH16843
+        # test ensures that index and column keys are recognized correctly
+        # when number of keys equals axis length of groupby
+        df = pd.DataFrame([['foo', 'bar', 'B', 1],
+                           ['foo', 'bar', 'B', 2],
+                           ['foo', 'baz', 'C', 3]],
+                          columns=['first', 'second', 'third', 'one'])
+        df = df.set_index(['first', 'second'])
+        df = df.groupby(['first', 'second', 'third']).size()
+        assert df.loc[('foo', 'bar', 'B')] == 2
+        assert df.loc[('foo', 'baz', 'C')] == 1
 
 
 # groups & iteration

pandas/tests/indexes/interval/test_interval_tree.py

@@ -159,7 +159,7 @@ def test_is_overlapping_endpoints(self, closed, order):
         left, right = np.arange(3), np.arange(1, 4)
         tree = IntervalTree(left[order], right[order], closed=closed)
         result = tree.is_overlapping
-        expected = closed is 'both'
+        expected = closed == 'both'
         assert result is expected
 
     @pytest.mark.parametrize('left, right', [

pandas/tests/io/test_pytables.py

@@ -2386,8 +2386,8 @@ def test_empty_series_frame(self):
     @pytest.mark.parametrize(
         'dtype', [np.int64, np.float64, np.object, 'm8[ns]', 'M8[ns]'])
     def test_empty_series(self, dtype):
-            s = Series(dtype=dtype)
-            self._check_roundtrip(s, tm.assert_series_equal)
+        s = Series(dtype=dtype)
+        self._check_roundtrip(s, tm.assert_series_equal)
 
     def test_can_serialize_dates(self):
 

pandas/tests/series/test_rank.py

@@ -421,10 +421,10 @@ def test_rank_modify_inplace(self):
     ([1, 1, 3, 3, 5, 5], [1. / 3, 1. / 3, 2. / 3, 2. / 3, 3. / 3, 3. / 3]),
     ([-5, -4, -3, -2, -1], [1. / 5, 2. / 5, 3. / 5, 4. / 5, 5. / 5])])
 def test_rank_dense_pct(dtype, ser, exp):
-        s = Series(ser).astype(dtype)
-        result = s.rank(method='dense', pct=True)
-        expected = Series(exp).astype(result.dtype)
-        assert_series_equal(result, expected)
+    s = Series(ser).astype(dtype)
+    result = s.rank(method='dense', pct=True)
+    expected = Series(exp).astype(result.dtype)
+    assert_series_equal(result, expected)
 
 
 @pytest.mark.parametrize('dtype', ['O', 'f8', 'i8'])
@@ -439,10 +439,10 @@ def test_rank_dense_pct(dtype, ser, exp):
     ([1, 1, 3, 3, 5, 5], [1. / 6, 1. / 6, 3. / 6, 3. / 6, 5. / 6, 5. / 6]),
     ([-5, -4, -3, -2, -1], [1. / 5, 2. / 5, 3. / 5, 4. / 5, 5. / 5])])
 def test_rank_min_pct(dtype, ser, exp):
-        s = Series(ser).astype(dtype)
-        result = s.rank(method='min', pct=True)
-        expected = Series(exp).astype(result.dtype)
-        assert_series_equal(result, expected)
+    s = Series(ser).astype(dtype)
+    result = s.rank(method='min', pct=True)
+    expected = Series(exp).astype(result.dtype)
+    assert_series_equal(result, expected)
 
 
 @pytest.mark.parametrize('dtype', ['O', 'f8', 'i8'])
@@ -457,10 +457,10 @@ def test_rank_min_pct(dtype, ser, exp):
     ([1, 1, 3, 3, 5, 5], [2. / 6, 2. / 6, 4. / 6, 4. / 6, 6. / 6, 6. / 6]),
     ([-5, -4, -3, -2, -1], [1. / 5, 2. / 5, 3. / 5, 4. / 5, 5. / 5])])
 def test_rank_max_pct(dtype, ser, exp):
-        s = Series(ser).astype(dtype)
-        result = s.rank(method='max', pct=True)
-        expected = Series(exp).astype(result.dtype)
-        assert_series_equal(result, expected)
+    s = Series(ser).astype(dtype)
+    result = s.rank(method='max', pct=True)
+    expected = Series(exp).astype(result.dtype)
+    assert_series_equal(result, expected)
 
 
 @pytest.mark.parametrize('dtype', ['O', 'f8', 'i8'])
@@ -476,10 +476,10 @@ def test_rank_max_pct(dtype, ser, exp):
      [1.5 / 6, 1.5 / 6, 3.5 / 6, 3.5 / 6, 5.5 / 6, 5.5 / 6]),
     ([-5, -4, -3, -2, -1], [1. / 5, 2. / 5, 3. / 5, 4. / 5, 5. / 5])])
 def test_rank_average_pct(dtype, ser, exp):
-        s = Series(ser).astype(dtype)
-        result = s.rank(method='average', pct=True)
-        expected = Series(exp).astype(result.dtype)
-        assert_series_equal(result, expected)
+    s = Series(ser).astype(dtype)
+    result = s.rank(method='average', pct=True)
+    expected = Series(exp).astype(result.dtype)
+    assert_series_equal(result, expected)
 
 
 @pytest.mark.parametrize('dtype', ['f8', 'i8'])
@@ -494,16 +494,16 @@ def test_rank_average_pct(dtype, ser, exp):
     ([1, 1, 3, 3, 5, 5], [1. / 6, 2. / 6, 3. / 6, 4. / 6, 5. / 6, 6. / 6]),
     ([-5, -4, -3, -2, -1], [1. / 5, 2. / 5, 3. / 5, 4. / 5, 5. / 5])])
 def test_rank_first_pct(dtype, ser, exp):
-        s = Series(ser).astype(dtype)
-        result = s.rank(method='first', pct=True)
-        expected = Series(exp).astype(result.dtype)
-        assert_series_equal(result, expected)
+    s = Series(ser).astype(dtype)
+    result = s.rank(method='first', pct=True)
+    expected = Series(exp).astype(result.dtype)
+    assert_series_equal(result, expected)
 
 
 @pytest.mark.single
 @pytest.mark.high_memory
 def test_pct_max_many_rows():
-        # GH 18271
-        s = Series(np.arange(2**24 + 1))
-        result = s.rank(pct=True).max()
-        assert result == 1
+    # GH 18271
+    s = Series(np.arange(2**24 + 1))
+    result = s.rank(pct=True).max()
+    assert result == 1