Merge remote-tracking branch 'upstream/master' into grp-desc-perf

Author: WillAyd

.circleci/config.yml

@@ -0,0 +1,32 @@
+version: 2
+jobs:
+  build:
+    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"
+      ENV_FILE: "ci/deps/circle-36-locale.yaml"
+      LOCALE_OVERRIDE: "zh_CN.UTF-8"
+      MINICONDA_DIR: /home/ubuntu/miniconda3
+    steps:
+      - checkout
+      - run:
+          name: build
+          command: |
+            ./ci/circle/install_circle.sh
+            ./ci/circle/show_circle.sh
+      - run:
+          name: test
+          command: ./ci/circle/run_circle.sh  --skip-slow --skip-network

.coveragerc

@@ -62,6 +62,8 @@ dist
 coverage.xml
 coverage_html_report
 *.pytest_cache
+# hypothesis test database
+.hypothesis/
 
 # OS generated files #
 ######################

.gitignore

@@ -3,10 +3,18 @@
 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
-        - E741,  # do not use variables named 'l', 'O', or 'I'
-        - W503   # line break before binary operator
+        - 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.

.pep8speaks.yml

@@ -30,63 +30,53 @@ matrix:
     exclude:
       # Exclude the default Python 3.5 build
       - python: 3.5
-    include:
-    - os: osx
-      language: generic
-      env:
-        - JOB="3.5, OSX" ENV_FILE="ci/travis-35-osx.yaml" TEST_ARGS="--skip-slow --skip-network"
 
+    include:
     - dist: trusty
       env:
-        - JOB="3.7" ENV_FILE="ci/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
+        - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
 
     - dist: trusty
       env:
-        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true
+        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/deps/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true
       addons:
         apt:
           packages:
           - 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/deps/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
-    # 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/deps/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true LINT=true
     - dist: trusty
       env:
-        - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+        - JOB="3.7, NumPy dev" ENV_FILE="ci/deps/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, doc" ENV_FILE="ci/travis-36-doc.yaml" DOC=true
+        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" SLOW=true
+
+    # In allow_failures
+    - dist: trusty
+      env:
+        - JOB="3.6, doc" ENV_FILE="ci/deps/travis-36-doc.yaml" DOC=true
     allow_failures:
       - dist: trusty
         env:
-          - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
-      - dist: trusty
-        env:
-          - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
-        addons:
-          apt:
-            packages:
-            - xsel
+          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" SLOW=true
       - dist: trusty
         env:
-          - JOB="3.6, doc" ENV_FILE="ci/travis-36-doc.yaml" DOC=true
+          - JOB="3.6, doc" ENV_FILE="ci/deps/travis-36-doc.yaml" DOC=true
 
 before_install:
   - echo "before_install"
@@ -118,21 +108,18 @@ script:
   - ci/run_build_docs.sh
   - ci/script_single.sh
   - ci/script_multi.sh
-  - ci/lint.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
 
 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"

.travis.yml

@@ -13,7 +13,7 @@ build: clean_pyc
 	python setup.py build_ext --inplace
 
 lint-diff:
-	git diff master --name-only -- "*.py" | grep "pandas" | xargs flake8
+	git diff master --name-only -- "*.py" | grep -E "pandas|scripts" | xargs flake8
 
 develop: build
 	-python setup.py develop

Makefile

@@ -56,8 +56,8 @@
 <tr>
   <td></td>
   <td>
-    <a href="https://ci.appveyor.com/project/pandas-dev/pandas">
-    <img src="https://ci.appveyor.com/api/projects/status/86vn83mxgnl4xf1s/branch/master?svg=true" alt="appveyor build status" />
+    <a href="https://dev.azure.com/pandas-dev/pandas/_build/latest?definitionId=1&branch=master">
+      <img src="https://dev.azure.com/pandas-dev/pandas/_apis/build/status/pandas-dev.pandas?branch=master" alt="Azure Pipelines build status" />
     </a>
   </td>
 </tr>
@@ -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:

README.md

@@ -9,16 +9,12 @@
     try:
         hashing = import_module(imp)
         break
-    except:
+    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