Merge remote-tracking branch 'upstream/master' into zhezherun-master

Author: TomAugspurger

.circleci/config.yml

@@ -1,39 +1,6 @@
 version: 2
 jobs:
 
-  # --------------------------------------------------------------------------
-  # 0. py27_compat
-  # --------------------------------------------------------------------------
-  py27_compat:
-    docker:
-      - image: continuumio/miniconda:latest
-      # databases configuration
-      - image: circleci/postgres:9.6.5-alpine-ram
-        environment:
-            POSTGRES_USER: postgres
-            POSTGRES_DB: pandas_nosetest
-      - image: circleci/mysql:8-ram
-        environment:
-          MYSQL_USER: "root"
-          MYSQL_HOST: "localhost"
-          MYSQL_ALLOW_EMPTY_PASSWORD: "true"
-          MYSQL_DATABASE: "pandas_nosetest"
-    environment:
-      JOB: "2.7_COMPAT"
-      ENV_FILE: "ci/circle-27-compat.yaml"
-      LOCALE_OVERRIDE: "it_IT.UTF-8"
-      MINICONDA_DIR: /home/ubuntu/miniconda3
-    steps:
-      - checkout
-      - run:
-          name: build
-          command: |
-            ./ci/install_circle.sh
-            ./ci/show_circle.sh
-      - run:
-          name: test
-          command: ./ci/run_circle.sh  --skip-slow --skip-network
-
   # --------------------------------------------------------------------------
   # 1. py36_locale
   # --------------------------------------------------------------------------
@@ -62,86 +29,14 @@ jobs:
       - run:
           name: build
           command: |
-            ./ci/install_circle.sh
-            ./ci/show_circle.sh
+            ./ci/circle/install_circle.sh
+            ./ci/circle/show_circle.sh
       - run:
           name: test
-          command: ./ci/run_circle.sh  --skip-slow --skip-network
-
-  # --------------------------------------------------------------------------
-  # 2. py36_locale_slow
-  # --------------------------------------------------------------------------
-  py36_locale_slow:
-    docker:
-      - image: continuumio/miniconda:latest
-      # databases configuration
-      - image: circleci/postgres:9.6.5-alpine-ram
-        environment:
-            POSTGRES_USER: postgres
-            POSTGRES_DB: pandas_nosetest
-      - image: circleci/mysql:8-ram
-        environment:
-          MYSQL_USER: "root"
-          MYSQL_HOST: "localhost"
-          MYSQL_ALLOW_EMPTY_PASSWORD: "true"
-          MYSQL_DATABASE: "pandas_nosetest"
-
-    environment:
-      JOB: "3.6_LOCALE_SLOW"
-      ENV_FILE: "ci/circle-36-locale_slow.yaml"
-      LOCALE_OVERRIDE: "zh_CN.UTF-8"
-      MINICONDA_DIR: /home/ubuntu/miniconda3
-    steps:
-      - checkout
-      - run:
-          name: build
-          command: |
-            ./ci/install_circle.sh
-            ./ci/show_circle.sh
-      - run:
-          name: test
-          command: ./ci/run_circle.sh  --only-slow --skip-network
-
-  # --------------------------------------------------------------------------
-  # 3. py35_ascii
-  # --------------------------------------------------------------------------
-  py35_ascii:
-    docker:
-      - image: continuumio/miniconda:latest
-      # databases configuration
-      - image: circleci/postgres:9.6.5-alpine-ram
-        environment:
-            POSTGRES_USER: postgres
-            POSTGRES_DB: pandas_nosetest
-      - image: circleci/mysql:8-ram
-        environment:
-          MYSQL_USER: "root"
-          MYSQL_HOST: "localhost"
-          MYSQL_ALLOW_EMPTY_PASSWORD: "true"
-          MYSQL_DATABASE: "pandas_nosetest"
-
-    environment:
-      JOB: "3.5_ASCII"
-      ENV_FILE: "ci/circle-35-ascii.yaml"
-      LOCALE_OVERRIDE: "C"
-      MINICONDA_DIR: /home/ubuntu/miniconda3
-    steps:
-      - checkout
-      - run:
-          name: build
-          command: |
-            ./ci/install_circle.sh
-            ./ci/show_circle.sh
-      - run:
-          name: test
-          command: ./ci/run_circle.sh  --skip-slow --skip-network
-
+          command: ./ci/circle/run_circle.sh  --skip-slow --skip-network
 
 workflows:
   version: 2
   build_and_test:
     jobs:
-      - py27_compat
       - py36_locale
-      - py36_locale_slow
-      - py35_ascii

.pep8speaks.yml

@@ -11,10 +11,10 @@ pycodestyle:
     max-line-length: 79
     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
-        - 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

@@ -116,10 +116,10 @@ after_success:
 after_script:
   - echo "after_script start"
   - source activate pandas && pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
-  - if [ -e /tmp/single.xml ]; then
-    ci/print_skipped.py /tmp/single.xml;
+  - if [ -e test-data-single.xml ]; then
+    ci/print_skipped.py test-data-single.xml;
     fi
-  - if [ -e /tmp/multiple.xml ]; then
-    ci/print_skipped.py /tmp/multiple.xml;
+  - if [ -e test-data-multiple.xml ]; then
+    ci/print_skipped.py test-data-multiple.xml;
     fi
   - echo "after_script done"

asv_bench/benchmarks/algorithms.py

@@ -12,13 +12,9 @@
     except (ImportError, TypeError, ValueError):
         pass
 
-from .pandas_vb_common import setup # noqa
-
 
 class Factorize(object):
 
-    goal_time = 0.2
-
     params = [True, False]
     param_names = ['sort']
 
@@ -40,8 +36,6 @@ def time_factorize_string(self, sort):
 
 class Duplicated(object):
 
-    goal_time = 0.2
-
     params = ['first', 'last', False]
     param_names = ['keep']
 
@@ -63,8 +57,6 @@ def time_duplicated_string(self, keep):
 
 class DuplicatedUniqueIndex(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**5
         self.idx_int_dup = pd.Int64Index(np.arange(N * 5))
@@ -77,8 +69,6 @@ def time_duplicated_unique_int(self):
 
 class Match(object):
 
-    goal_time = 0.2
-
     def setup(self):
         self.uniques = tm.makeStringIndex(1000).values
         self.all = self.uniques.repeat(10)
@@ -90,8 +80,6 @@ def time_match_string(self):
 
 class Hashing(object):
 
-    goal_time = 0.2
-
     def setup_cache(self):
         N = 10**5
 
@@ -126,3 +114,6 @@ 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

@@ -5,13 +5,9 @@
 except ImportError:
     from pandas.util.decorators import cache_readonly
 
-from .pandas_vb_common import setup  # noqa
-
 
 class DataFrameAttributes(object):
 
-    goal_time = 0.2
-
     def setup(self):
         self.df = DataFrame(np.random.randn(10, 6))
         self.cur_index = self.df.index
@@ -25,8 +21,6 @@ def time_set_index(self):
 
 class CacheReadonly(object):
 
-    goal_time = 0.2
-
     def setup(self):
 
         class Foo:
@@ -38,3 +32,6 @@ 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

@@ -6,13 +6,9 @@
 except ImportError:
     import pandas.computation.expressions as expr
 
-from .pandas_vb_common import setup # noqa
-
 
 class Ops(object):
 
-    goal_time = 0.2
-
     params = [[True, False], ['default', 1]]
     param_names = ['use_numexpr', 'threads']
 
@@ -44,8 +40,6 @@ def teardown(self, use_numexpr, threads):
 
 class Ops2(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**3
         self.df = DataFrame(np.random.randn(N, N))
@@ -83,8 +77,6 @@ def time_frame_float_mod(self):
 
 class Timeseries(object):
 
-    goal_time = 0.2
-
     params = [None, 'US/Eastern']
     param_names = ['tz']
 
@@ -111,8 +103,6 @@ def time_timestamp_ops_diff_with_shift(self, tz):
 
 class AddOverflowScalar(object):
 
-    goal_time = 0.2
-
     params = [1, -1, 0]
     param_names = ['scalar']
 
@@ -126,8 +116,6 @@ def time_add_overflow_scalar(self, scalar):
 
 class AddOverflowArray(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**6
         self.arr = np.arange(N)
@@ -149,3 +137,6 @@ 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

@@ -11,13 +11,9 @@
     except ImportError:
         pass
 
-from .pandas_vb_common import setup # noqa
-
 
 class Concat(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**5
         self.s = pd.Series(list('aabbcd') * N).astype('category')
@@ -34,8 +30,6 @@ def time_union(self):
 
 class Constructor(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**5
         self.categories = list('abcde')
@@ -77,8 +71,6 @@ def time_from_codes_all_int8(self):
 
 class ValueCounts(object):
 
-    goal_time = 0.2
-
     params = [True, False]
     param_names = ['dropna']
 
@@ -93,8 +85,6 @@ def time_value_counts(self, dropna):
 
 class Repr(object):
 
-    goal_time = 0.2
-
     def setup(self):
         self.sel = pd.Series(['s1234']).astype('category')
 
@@ -104,8 +94,6 @@ def time_rendering(self):
 
 class SetCategories(object):
 
-    goal_time = 0.2
-
     def setup(self):
         n = 5 * 10**5
         arr = ['s%04d' % i for i in np.random.randint(0, n // 10, size=n)]
@@ -117,8 +105,6 @@ def time_set_categories(self):
 
 class Rank(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**5
         ncats = 100
@@ -156,8 +142,6 @@ def time_rank_int_cat_ordered(self):
 
 class Isin(object):
 
-    goal_time = 0.2
-
     params = ['object', 'int64']
     param_names = ['dtype']
 
@@ -197,8 +181,6 @@ def time_categorical_series_is_monotonic_decreasing(self):
 
 class Contains(object):
 
-    goal_time = 0.2
-
     def setup(self):
         N = 10**5
         self.ci = tm.makeCategoricalIndex(N)
@@ -214,7 +196,6 @@ def time_categorical_contains(self):
 
 class CategoricalSlicing(object):
 
-    goal_time = 0.2
     params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
     param_names = ['index']
 
@@ -245,3 +226,6 @@ 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