STYLE: final flake8 fixes, add back check for travis-ci

closes #11928
closes #12208

Author: jreback

.travis.yml

@@ -164,11 +164,10 @@ script:
   - echo "script"
   - ci/run_build_docs.sh
   - ci/script.sh
+  - ci/lint.sh
 # nothing here, or failed tests won't fail travis
 
 after_script:
   - ci/install_test.sh
   - source activate pandas && ci/print_versions.py
   - ci/print_skipped.py /tmp/nosetests.xml
-  - ci/lint.sh
-  - ci/lint_ok_for_now.sh

ci/lint.sh

@@ -4,17 +4,14 @@ echo "inside $0"
 
 source activate pandas
 
-for path in 'core'
+RET=0
+for path in 'core' 'io' 'stats' 'compat' 'sparse' 'tools' 'tseries' 'tests' 'computation' 'util'
 do
     echo "linting -> pandas/$path"
-    flake8 pandas/$path --filename '*.py' --statistics -q
+    flake8 pandas/$path --filename '*.py'
+    if [ $? -ne "0" ]; then
+        RET=1
+    fi
 done
 
-RET="$?"
-
-# we are disabling the return code for now
-# to have Travis-CI pass. When the code
-# passes linting, re-enable
-#exit "$RET"
-
-exit 0
+exit $RET

ci/lint_ok_for_now.sh

@@ -19,7 +19,8 @@
 _np_version_under1p11 = LooseVersion(_np_version) < '1.11'
 
 if LooseVersion(_np_version) < '1.7.0':
-    raise ImportError('this version of pandas is incompatible with numpy < 1.7.0\n'
+    raise ImportError('this version of pandas is incompatible with '
+                      'numpy < 1.7.0\n'
                       'your numpy version is {0}.\n'
                       'Please upgrade numpy to >= 1.7.0 to use '
                       'this pandas version'.format(_np_version))
@@ -61,7 +62,7 @@ def np_array_datetime64_compat(arr, *args, **kwargs):
            isinstance(arr, string_and_binary_types):
             arr = [tz_replacer(s) for s in arr]
         else:
-            arr = tz_replacer(s)
+            arr = tz_replacer(arr)
 
     return np.array(arr, *args, **kwargs)
 

pandas/compat/numpy_compat.py

@@ -51,7 +51,6 @@
 from pandas.tseries.index import DatetimeIndex
 from pandas.tseries.tdi import TimedeltaIndex
 
-import pandas.core.algorithms as algos
 import pandas.core.base as base
 import pandas.core.common as com
 import pandas.core.format as fmt

pandas/core/frame.py

@@ -2310,10 +2310,9 @@ def _get_grouper(obj, key=None, axis=0, level=None, sort=True):
     except Exception:
         all_in_columns = False
 
-    if (not any_callable and not all_in_columns
-        and not any_arraylike and not any_groupers
-            and match_axis_length
-            and level is None):
+    if not any_callable and not all_in_columns and \
+       not any_arraylike and not any_groupers and \
+       match_axis_length and level is None:
         keys = [com._asarray_tuplesafe(keys)]
 
     if isinstance(level, (tuple, list)):
@@ -3695,7 +3694,7 @@ def count(self):
         return self._wrap_agged_blocks(data.items, list(blk))
 
 
-from pandas.tools.plotting import boxplot_frame_groupby
+from pandas.tools.plotting import boxplot_frame_groupby  # noqa
 DataFrameGroupBy.boxplot = boxplot_frame_groupby
 
 

pandas/core/groupby.py

@@ -3981,7 +3981,7 @@ def form_blocks(arrays, names, axes):
                                   klass=DatetimeTZBlock,
                                   fastpath=True,
                                   placement=[i], )
-                       for i, names, array in datetime_tz_items]
+                       for i, _, array in datetime_tz_items]
         blocks.extend(dttz_blocks)
 
     if len(bool_items):
@@ -3999,7 +3999,7 @@ def form_blocks(arrays, names, axes):
     if len(cat_items) > 0:
         cat_blocks = [make_block(array, klass=CategoricalBlock, fastpath=True,
                                  placement=[i])
-                      for i, names, array in cat_items]
+                      for i, _, array in cat_items]
         blocks.extend(cat_blocks)
 
     if len(extra_locs):

pandas/core/internals.py

@@ -282,7 +282,7 @@ def _unstack_multiple(data, clocs):
             for i in range(len(clocs)):
                 val = clocs[i]
                 result = result.unstack(val)
-                clocs = [val if i > val else val - 1 for val in clocs]
+                clocs = [v if i > v else v - 1 for v in clocs]
 
             return result
 

pandas/core/reshape.py

@@ -520,10 +520,10 @@ def _convert_frames(frames, index, columns, fill_value=np.nan, kind='block'):
         output[item] = df
 
     if index is None:
-        all_indexes = [df.index for df in output.values()]
+        all_indexes = [x.index for x in output.values()]
         index = _get_combined_index(all_indexes)
     if columns is None:
-        all_columns = [df.columns for df in output.values()]
+        all_columns = [x.columns for x in output.values()]
         columns = _get_combined_index(all_columns)
 
     index = _ensure_index(index)

pandas/sparse/panel.py

@@ -262,8 +262,8 @@ def transform(row):
             return row
 
         def transform2(row):
-            if (notnull(row['C']) and row['C'].startswith('shin')
-                    and row['A'] == 'foo'):
+            if (notnull(row['C']) and row['C'].startswith('shin') and
+                    row['A'] == 'foo'):
                 row['D'] = 7
             return row
 

pandas/tests/frame/test_apply.py

@@ -2178,8 +2178,8 @@ def test_where(self):
         def _safe_add(df):
             # only add to the numeric items
             def is_ok(s):
-                return (issubclass(s.dtype.type, (np.integer, np.floating))
-                        and s.dtype != 'uint8')
+                return (issubclass(s.dtype.type, (np.integer, np.floating)) and
+                        s.dtype != 'uint8')
 
             return DataFrame(dict([(c, s + 1) if is_ok(s) else (c, s)
                                    for c, s in compat.iteritems(df)]))

pandas/tests/frame/test_indexing.py

@@ -581,8 +581,7 @@ def test_chained_cmp_and_in(self):
         df = DataFrame(randn(100, len(cols)), columns=cols)
         res = df.query('a < b < c and a not in b not in c', engine=engine,
                        parser=parser)
-        ind = ((df.a < df.b) & (df.b < df.c) & ~df.b.isin(df.a) &
-               ~df.c.isin(df.b))
+        ind = (df.a < df.b) & (df.b < df.c) & ~df.b.isin(df.a) & ~df.c.isin(df.b)  # noqa
         expec = df[ind]
         assert_frame_equal(res, expec)
 

pandas/tests/frame/test_query_eval.py

@@ -328,13 +328,13 @@ def test_info_memory_usage(self):
         res = buf.getvalue().splitlines()
         self.assertTrue(re.match(r"memory usage: [^+]+$", res[-1]))
 
-        self.assertTrue(df_with_object_index.memory_usage(index=True,
-                                                          deep=True).sum()
-                        > df_with_object_index.memory_usage(index=True).sum())
+        self.assertGreater(df_with_object_index.memory_usage(index=True,
+                                                             deep=True).sum(),
+                           df_with_object_index.memory_usage(index=True).sum())
 
         df_object = pd.DataFrame({'a': ['a']})
-        self.assertTrue(df_object.memory_usage(deep=True).sum()
-                        > df_object.memory_usage().sum())
+        self.assertGreater(df_object.memory_usage(deep=True).sum(),
+                           df_object.memory_usage().sum())
 
         # Test a DataFrame with duplicate columns
         dtypes = ['int64', 'int64', 'int64', 'float64']

pandas/tests/frame/test_repr_info.py

@@ -10,7 +10,8 @@
 import numpy as np
 
 from pandas.compat import u
-from pandas import DataFrame, Index, Series, MultiIndex, date_range, Timedelta, Period
+from pandas import (DataFrame, Index, Series, MultiIndex, date_range,
+                    Timedelta, Period)
 import pandas as pd
 
 from pandas.util.testing import (assert_series_equal,

pandas/tests/frame/test_reshape.py

@@ -332,7 +332,7 @@ def test_none_comparison(self):
                 self.assertTrue(result.iat[0])
                 self.assertTrue(result.iat[1])
 
-                result = None == o
+                result = None == o  # noqa
                 self.assertFalse(result.iat[0])
                 self.assertFalse(result.iat[1])
 

pandas/tests/test_base.py

@@ -3858,8 +3858,8 @@ def test_groupby_categorical(self):
             np.arange(4).repeat(8), levels, ordered=True)
         exp = CategoricalIndex(expc)
         self.assert_index_equal(desc_result.index.get_level_values(0), exp)
-        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max']
-                    * 4)
+        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%',
+                     '75%', 'max'] * 4)
         self.assert_index_equal(desc_result.index.get_level_values(1), exp)
 
     def test_groupby_datetime_categorical(self):
@@ -3899,8 +3899,8 @@ def test_groupby_datetime_categorical(self):
             np.arange(4).repeat(8), levels, ordered=True)
         exp = CategoricalIndex(expc)
         self.assert_index_equal(desc_result.index.get_level_values(0), exp)
-        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%', '75%', 'max']
-                    * 4)
+        exp = Index(['count', 'mean', 'std', 'min', '25%', '50%',
+                     '75%', 'max'] * 4)
         self.assert_index_equal(desc_result.index.get_level_values(1), exp)
 
     def test_groupby_categorical_index(self):

pandas/tests/test_groupby.py

@@ -105,8 +105,8 @@ def test_append_index(self):
         expected = Index._simple_new(
             np.array([(1.1, datetime.datetime(2011, 1, 1, tzinfo=tz), 'A'),
                       (1.2, datetime.datetime(2011, 1, 2, tzinfo=tz), 'B'),
-                      (1.3, datetime.datetime(2011, 1, 3, tzinfo=tz), 'C')]
-                     + expected_tuples), None)
+                      (1.3, datetime.datetime(2011, 1, 3, tzinfo=tz), 'C')] +
+                     expected_tuples), None)
         self.assertTrue(result.equals(expected))
 
     def test_dataframe_constructor(self):

pandas/tests/test_multilevel.py

@@ -1,6 +1,13 @@
 import os
 from nose import SkipTest
 
+import copy
+import numpy as np
+import pandas as pd
+from pandas import DataFrame
+from pandas.util.testing import TestCase
+import pandas.util.testing as tm
+
 # this is a mess. Getting failures on a python 2.7 build with
 # whenever we try to import jinja, whether it's installed or not.
 # so we're explicitly skipping that one *before* we try to import
@@ -14,14 +21,6 @@
 except ImportError:
     raise SkipTest("No Jinja2")
 
-import copy
-
-import numpy as np
-import pandas as pd
-from pandas import DataFrame
-from pandas.util.testing import TestCase
-import pandas.util.testing as tm
-
 
 class TestStyler(TestCase):
 
@@ -196,8 +195,8 @@ def test_apply_subset(self):
                 expected = dict(((r, c), ['color: baz'])
                                 for r, row in enumerate(self.df.index)
                                 for c, col in enumerate(self.df.columns)
-                                if row in self.df.loc[slice_].index
-                                and col in self.df.loc[slice_].columns)
+                                if row in self.df.loc[slice_].index and
+                                col in self.df.loc[slice_].columns)
                 self.assertEqual(result, expected)
 
     def test_applymap_subset(self):
@@ -213,8 +212,8 @@ def f(x):
             expected = dict(((r, c), ['foo: bar'])
                             for r, row in enumerate(self.df.index)
                             for c, col in enumerate(self.df.columns)
-                            if row in self.df.loc[slice_].index
-                            and col in self.df.loc[slice_].columns)
+                            if row in self.df.loc[slice_].index and
+                            col in self.df.loc[slice_].columns)
             self.assertEqual(result, expected)
 
     def test_empty(self):

pandas/tests/test_style.py

@@ -1002,32 +1002,31 @@ def simple_wma(s, w):
             return (s.multiply(w).cumsum() / w.cumsum()).fillna(method='ffill')
 
         for (s, adjust, ignore_na, w) in [
-                (s0, True, False, [np.nan, (1. - alpha), 1.]),
-                (s0, True, True, [np.nan, (1. - alpha), 1.]),
-                (s0, False, False, [np.nan, (1. - alpha), alpha]),
-                (s0, False, True, [np.nan, (1. - alpha), alpha]),
-                (s1, True, False, [(1. - alpha) ** 2, np.nan, 1.]),
-                (s1, True, True, [(1. - alpha), np.nan, 1.]),
-                (s1, False, False, [(1. - alpha) ** 2, np.nan, alpha]),
-                (s1, False, True, [(1. - alpha), np.nan, alpha]),
-                (s2, True, False, [np.nan, (1. - alpha)
-                                   ** 3, np.nan, np.nan, 1., np.nan]),
-                (s2, True, True, [np.nan, (1. - alpha),
-                                  np.nan, np.nan, 1., np.nan]),
-                (s2, False, False, [np.nan, (1. - alpha)
-                                    ** 3, np.nan, np.nan, alpha, np.nan]),
-                (s2, False, True, [np.nan, (1. - alpha),
-                                   np.nan, np.nan, alpha, np.nan]),
-                (s3, True, False, [(1. - alpha)
-                                   ** 3, np.nan, (1. - alpha), 1.]),
-                (s3, True, True, [(1. - alpha) **
-                                  2, np.nan, (1. - alpha), 1.]),
-                (s3, False, False, [(1. - alpha) ** 3, np.nan,
-                                    (1. - alpha) * alpha,
-                                    alpha * ((1. - alpha) ** 2 + alpha)]),
-                (s3, False, True, [(1. - alpha) ** 2,
-                                   np.nan, (1. - alpha) * alpha, alpha]),
-        ]:
+            (s0, True, False, [np.nan, (1. - alpha), 1.]),
+            (s0, True, True, [np.nan, (1. - alpha), 1.]),
+            (s0, False, False, [np.nan, (1. - alpha), alpha]),
+            (s0, False, True, [np.nan, (1. - alpha), alpha]),
+            (s1, True, False, [(1. - alpha) ** 2, np.nan, 1.]),
+            (s1, True, True, [(1. - alpha), np.nan, 1.]),
+            (s1, False, False, [(1. - alpha) ** 2, np.nan, alpha]),
+            (s1, False, True, [(1. - alpha), np.nan, alpha]),
+            (s2, True, False, [np.nan, (1. - alpha) **
+                               3, np.nan, np.nan, 1., np.nan]),
+            (s2, True, True, [np.nan, (1. - alpha),
+                              np.nan, np.nan, 1., np.nan]),
+            (s2, False, False, [np.nan, (1. - alpha) **
+                                3, np.nan, np.nan, alpha, np.nan]),
+            (s2, False, True, [np.nan, (1. - alpha),
+                               np.nan, np.nan, alpha, np.nan]),
+            (s3, True, False, [(1. - alpha) **
+                               3, np.nan, (1. - alpha), 1.]),
+            (s3, True, True, [(1. - alpha) **
+                              2, np.nan, (1. - alpha), 1.]),
+            (s3, False, False, [(1. - alpha) ** 3, np.nan,
+                                (1. - alpha) * alpha,
+                                alpha * ((1. - alpha) ** 2 + alpha)]),
+            (s3, False, True, [(1. - alpha) ** 2,
+                               np.nan, (1. - alpha) * alpha, alpha])]:
             expected = simple_wma(s, Series(w))
             result = s.ewm(com=com, adjust=adjust, ignore_na=ignore_na).mean()
 

pandas/tests/test_window.py

@@ -470,8 +470,7 @@ def _get_merge_keys(self):
 
     def _validate_specification(self):
         # Hm, any way to make this logic less complicated??
-        if (self.on is None and self.left_on is None
-                and self.right_on is None):
+        if self.on is None and self.left_on is None and self.right_on is None:
 
             if self.left_index and self.right_index:
                 self.left_on, self.right_on = (), ()
@@ -1185,7 +1184,7 @@ def _make_concat_multiindex(indexes, keys, levels=None, names=None):
             names = list(names)
         else:
             # make sure that all of the passed indices have the same nlevels
-            if not len(set([i.nlevels for i in indexes])) == 1:
+            if not len(set([idx.nlevels for idx in indexes])) == 1:
                 raise AssertionError("Cannot concat indices that do"
                                      " not have the same number of levels")
 

pandas/tools/merge.py

@@ -357,8 +357,8 @@ def _convert_by(by):
     if by is None:
         by = []
     elif (np.isscalar(by) or isinstance(by, (np.ndarray, Index,
-                                             Series, Grouper))
-          or hasattr(by, '__call__')):
+                                             Series, Grouper)) or
+          hasattr(by, '__call__')):
         by = [by]
     else:
         by = list(by)