Resolve doctest conflict and get latest upstream changes

.pep8speaks.yml

@@ -3,9 +3,19 @@
 scanner:
  diff_only: True # If True, errors caused by only the patch are shown
 
+# Opened issue in pep8speaks, so we can directly use the config in setup.cfg
+# (and avoid having to duplicate it here):
+# https://github.com/OrkoHunter/pep8speaks/issues/95
+
 pycodestyle:
  max-line-length: 79
- ignore: # Errors and warnings to ignore
+ ignore:
+ - W503, # line break before binary operator
+ - W504, # line break after binary operator
  - E402, # module level import not at top of file
+ - E722, # do not use bare except
  - E731, # do not assign a lambda expression, use a def
- - W503 # line break before binary operator
+ - E741, # ambiguous variable name 'l'
+ - 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.

.travis.yml

@@ -45,26 +45,27 @@ matrix:
  - language-pack-zh-hans
  - dist: trusty
  env:
- - JOB="2.7, lint" ENV_FILE="ci/travis-27.yaml" TEST_ARGS="--skip-slow" LINT=true
+ - JOB="2.7" ENV_FILE="ci/travis-27.yaml" TEST_ARGS="--skip-slow"
  addons:
  apt:
  packages:
  - python-gtk2
  - dist: trusty
  env:
- - JOB="3.6, coverage" ENV_FILE="ci/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true DOCTEST=true
- # In allow_failures
- - dist: trusty
- env:
- - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
- # In allow_failures
+ - JOB="3.6, lint, coverage" ENV_FILE="ci/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true LINT=true
  - dist: trusty
  env:
  - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
  addons:
  apt:
  packages:
  - xsel
+
+ # In allow_failures
+ - dist: trusty
+ env:
+ - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
+
  # In allow_failures
  - dist: trusty
  env:
@@ -73,13 +74,6 @@ matrix:
  - dist: trusty
  env:
  - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
- - dist: trusty
- env:
- - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
- addons:
- apt:
- packages:
- - xsel
  - dist: trusty
  env:
  - JOB="3.6, doc" ENV_FILE="ci/travis-36-doc.yaml" DOC=true
@@ -114,11 +108,7 @@ script:
  - ci/run_build_docs.sh
  - ci/script_single.sh
  - ci/script_multi.sh
- - ci/lint.sh
- - ci/doctests.sh
- - echo "checking imports"
- - source activate pandas && python ci/check_imports.py
- - echo "script done"
+ - ci/code_checks.sh
 
 after_success:
  - ci/upload_coverage.sh

README.md

@@ -97,7 +97,7 @@ easy and intuitive. It aims to be the fundamental high-level building block for
 doing practical, **real world** data analysis in Python. Additionally, it has
 the broader goal of becoming **the most powerful and flexible open source data
 analysis / manipulation tool available in any language**. It is already well on
-its way toward this goal.
+its way towards this goal.
 
 ## Main Features
 Here are just a few of the things that pandas does well:

asv_bench/benchmarks/algorithms.py

@@ -9,11 +9,9 @@
  try:
  hashing = import_module(imp)
  break
- except:
+ except (ImportError, TypeError, ValueError):
  pass
 
-from .pandas_vb_common import setup # noqa
-
 
 class Factorize(object):
 
@@ -126,3 +124,6 @@ def time_series_timedeltas(self, df):
 
  def time_series_dates(self, df):
  hashing.hash_pandas_object(df['dates'])
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/attrs_caching.py

@@ -5,8 +5,6 @@
 except ImportError:
  from pandas.util.decorators import cache_readonly
 
-from .pandas_vb_common import setup # noqa
-
 
 class DataFrameAttributes(object):
 
@@ -38,3 +36,6 @@ def prop(self):
 
  def time_cache_readonly(self):
  self.obj.prop
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/binary_ops.py

@@ -6,8 +6,6 @@
 except ImportError:
  import pandas.computation.expressions as expr
 
-from .pandas_vb_common import setup # noqa
-
 
 class Ops(object):
 
@@ -149,3 +147,6 @@ def time_add_overflow_b_mask_nan(self):
  def time_add_overflow_both_arg_nan(self):
  checked_add_with_arr(self.arr, self.arr_mixed, arr_mask=self.arr_nan_1,
  b_mask=self.arr_nan_2)
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/categoricals.py

@@ -11,8 +11,6 @@
  except ImportError:
  pass
 
-from .pandas_vb_common import setup # noqa
-
 
 class Concat(object):
 
@@ -245,3 +243,6 @@ def time_getitem_list(self, index):
 
  def time_getitem_bool_array(self, index):
  self.data[self.data == self.cat_scalar]
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/ctors.py

@@ -2,8 +2,6 @@
 import pandas.util.testing as tm
 from pandas import Series, Index, DatetimeIndex, Timestamp, MultiIndex
 
-from .pandas_vb_common import setup # noqa
-
 
 class SeriesConstructors(object):
 
@@ -64,3 +62,6 @@ def setup(self):
 
  def time_multiindex_from_iterables(self):
  MultiIndex.from_product(self.iterables)
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/eval.py

@@ -5,8 +5,6 @@
 except ImportError:
  import pandas.computation.expressions as expr
 
-from .pandas_vb_common import setup # noqa
-
 
 class Eval(object):
 
@@ -65,3 +63,6 @@ def time_query_datetime_column(self):
 
  def time_query_with_boolean_selection(self):
  self.df.query('(a >= @self.min_val) & (a <= @self.max_val)')
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/frame_ctor.py

@@ -7,8 +7,6 @@
  # For compatibility with older versions
  from pandas.core.datetools import * # noqa
 
-from .pandas_vb_common import setup # noqa
-
 
 class FromDicts(object):
 
@@ -99,3 +97,6 @@ def setup(self):
 
  def time_frame_from_ndarray(self):
  self.df = DataFrame(self.data)
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/frame_methods.py

@@ -6,8 +6,6 @@
 from pandas import (DataFrame, Series, MultiIndex, date_range, period_range,
  isnull, NaT)
 
-from .pandas_vb_common import setup # noqa
-
 
 class GetNumericData(object):
 
@@ -537,3 +535,6 @@ def time_series_describe(self):
 
  def time_dataframe_describe(self):
  self.df.describe()
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/gil.py

@@ -23,7 +23,7 @@ def wrapper(fname):
  return fname
  return wrapper
 
-from .pandas_vb_common import BaseIO, setup # noqa
+from .pandas_vb_common import BaseIO
 
 
 class ParallelGroupbyMethods(object):
@@ -273,3 +273,6 @@ def time_parallel(self, threads):
  def time_loop(self, threads):
  for i in range(threads):
  self.loop()
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/groupby.py

@@ -8,8 +8,6 @@
  TimeGrouper, Categorical, Timestamp)
 import pandas.util.testing as tm
 
-from .pandas_vb_common import setup # noqa
-
 
 method_blacklist = {
  'object': {'median', 'prod', 'sem', 'cumsum', 'sum', 'cummin', 'mean',
@@ -579,3 +577,6 @@ def setup(self):
 
  def time_first(self):
  self.df_nans.groupby('key').transform('first')
+
+
+from .pandas_vb_common import setup # noqa: F401

asv_bench/benchmarks/index_object.py

@@ -3,8 +3,6 @@
 from pandas import (Series, date_range, DatetimeIndex, Index, RangeIndex,
  Float64Index)
 
-from .pandas_vb_common import setup # noqa
-
 
 class SetOperations(object):
 
@@ -192,3 +190,6 @@ def setup(self):
 
  def time_get_loc(self):
  self.ind.get_loc(0)
+
+
+from .pandas_vb_common import setup # noqa: F401