Merge branch 'master' into master

Author: JulianWgs

.github/CODE_OF_CONDUCT.md

@@ -60,4 +60,3 @@ and the [Swift Code of Conduct][swift].
 [homepage]: https://www.contributor-covenant.org
 [version]: https://www.contributor-covenant.org/version/1/3/0/
 [swift]: https://swift.org/community/#code-of-conduct
-

.github/workflows/ci.yml

@@ -125,7 +125,7 @@ jobs:
     # This can be removed when the ipython directive fails when there are errors,
     # including the `tee sphinx.log` in te previous step (https://github.com/ipython/ipython/issues/11547)
     - name: Check ipython directive errors
-      run: "! grep -B1 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
+      run: "! grep -B10 \"^<<<-------------------------------------------------------------------------$\" sphinx.log"
 
     - name: Install ssh key
       run: |

.github/workflows/pre-commit.yml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [master]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+    - uses: pre-commit/[email protected]

.github/workflows/stale-pr.yml

@@ -0,0 +1,21 @@
+name: "Stale PRs"
+on:
+  schedule:
+  # * is a special character in YAML so you have to quote this string
+  - cron: "0 0 * * *"
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/stale@v3
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-pr-message: "This pull request is stale because it has been open for thirty days with no activity. Please update or respond to this comment if you're still interested in working on this."
+        skip-stale-pr-message: false
+        stale-pr-label: "Stale"
+        exempt-pr-labels: "Needs Review,Blocked,Needs Discussion"
+        days-before-stale: 30
+        days-before-close: -1
+        remove-stale-when-updated: false
+        debug-only: false

.pre-commit-config.yaml

@@ -1,44 +1,65 @@
 repos:
 -   repo: https://github.com/python/black
-    rev: 19.10b0
+    rev: 20.8b1
     hooks:
     -   id: black
-        language_version: python3
 -   repo: https://gitlab.com/pycqa/flake8
-    rev: 3.7.7
+    rev: 3.8.4
     hooks:
     -   id: flake8
-        language: python_venv
         additional_dependencies: [flake8-comprehensions>=3.1.0]
     -   id: flake8
         name: flake8-pyx
-        language: python_venv
         files: \.(pyx|pxd)$
         types:
           - file
         args: [--append-config=flake8/cython.cfg]
     -   id: flake8
         name: flake8-pxd
-        language: python_venv
         files: \.pxi\.in$
         types:
           - file
         args: [--append-config=flake8/cython-template.cfg]
--   repo: https://github.com/pre-commit/mirrors-isort
-    rev: v4.3.21
+-   repo: https://github.com/PyCQA/isort
+    rev: 5.6.0
     hooks:
     -   id: isort
-        language: python_venv
         exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$
--   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.730
-    hooks:
-     -  id: mypy
-        args:
-          # As long as a some files are excluded from check-untyped-defs
-          # we have to exclude it from the pre-commit hook as the configuration
-          # is based on modules but the hook runs on files.
-          - --no-check-untyped-defs
-          - --follow-imports
-          - skip
-        files: pandas/
+        files: '.pxd$|.py$'
+        types: [file]
+-   repo: https://github.com/asottile/pyupgrade
+    rev: v2.7.2
+    hooks:
+    -   id: pyupgrade
+        args: [--py37-plus]
+-   repo: https://github.com/pre-commit/pygrep-hooks
+    rev: v1.6.0
+    hooks:
+      - id: rst-backticks
+-   repo: local
+    hooks:
+    -   id: pip_to_conda
+        name: Generate pip dependency from conda
+        description: This hook checks if the conda environment.yml and requirements-dev.txt are equal
+        language: python
+        entry: python -m scripts.generate_pip_deps_from_conda
+        files: ^(environment.yml|requirements-dev.txt)$
+        pass_filenames: false
+        additional_dependencies: [pyyaml]
+    -   id: flake8-rst
+        name: flake8-rst
+        description: Run flake8 on code snippets in docstrings or RST files
+        language: python
+        entry: flake8-rst
+        types: [rst]
+        args: [--filename=*.rst]
+        additional_dependencies: [flake8-rst==0.7.0, flake8==3.7.9]
+-   repo: https://github.com/asottile/yesqa
+    rev: v1.2.2
+    hooks:
+    -   id: yesqa
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: end-of-file-fixer
+        exclude: '.html$|^LICENSES/|.csv$|.txt$|.svg$|.py$'

.travis.yml

@@ -1,6 +1,15 @@
 language: python
 python: 3.7
 
+addons:
+  apt:
+    update: true
+    packages:
+      - xvfb
+
+services:
+  - xvfb
+
 # To turn off cached cython files and compiler cache
 # set NOCACHE-true
 # To delete caches go to https://travis-ci.org/OWNER/REPOSITORY/caches or run
@@ -10,46 +19,43 @@ cache:
   ccache: true
   directories:
     - $HOME/.cache # cython cache
-    - $HOME/.ccache # compiler cache
 
 env:
   global:
-    # Variable for test workers
     - PYTEST_WORKERS="auto"
     # create a github personal access token
     # cd pandas-dev/pandas
     # travis encrypt 'PANDAS_GH_TOKEN=personal_access_token' -r pandas-dev/pandas
     - secure: "EkWLZhbrp/mXJOx38CHjs7BnjXafsqHtwxPQrqWy457VDFWhIY1DMnIR/lOWG+a20Qv52sCsFtiZEmMfUjf0pLGXOqurdxbYBGJ7/ikFLk9yV2rDwiArUlVM9bWFnFxHvdz9zewBH55WurrY4ShZWyV+x2dWjjceWG5VpWeI6sA="
 
 git:
-  # for cloning
   depth: false
 
 matrix:
   fast_finish: true
 
   include:
-    # In allowed failures
     - dist: bionic
       python: 3.9-dev
       env:
         - JOB="3.9-dev" PATTERN="(not slow and not network and not clipboard)"
-    - env:
-        - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network and not clipboard)"
 
     - env:
-        - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network and not clipboard)"
-
-    - arch: arm64
-      env:
-        - JOB="3.7, arm64" PYTEST_WORKERS=8 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard)"
+      - JOB="3.8, slow" ENV_FILE="ci/deps/travis-38-slow.yaml" PATTERN="slow" SQL="1"
+      services:
+        - mysql
+        - postgresql
 
     - env:
         - JOB="3.7, locale" ENV_FILE="ci/deps/travis-37-locale.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
       services:
         - mysql
         - postgresql
 
+    - arch: arm64
+      env:
+        - JOB="3.7, arm64" PYTEST_WORKERS=1 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard and not arm_slow)"
+
     - env:
         # Enabling Deprecations when running tests
         # PANDAS_TESTING_MODE="deprecate" causes DeprecationWarning messages to be displayed in the logs
@@ -58,13 +64,12 @@ matrix:
       services:
         - mysql
         - postgresql
+
   allow_failures:
+    # Moved to allowed_failures 2020-09-29 due to timeouts https://github.com/pandas-dev/pandas/issues/36719
     - arch: arm64
       env:
-        - JOB="3.7, arm64" PYTEST_WORKERS=8 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard)"
-    - dist: bionic
-      env:
-        - JOB="3.9-dev" PATTERN="(not slow and not network and not clipboard)"
+        - JOB="3.7, arm64" PYTEST_WORKERS=1 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard and not arm_slow)"
 
 
 before_install:
@@ -78,12 +83,6 @@ before_install:
   - uname -a
   - git --version
   - ./ci/check_git_tags.sh
-  # Because travis runs on Google Cloud and has a /etc/boto.cfg,
-  # it breaks moto import, see:
-  # https://github.com/spulec/moto/issues/1771
-  # https://github.com/boto/boto/issues/3741
-  # This overrides travis and tells it to look nowhere.
-  - export BOTO_CONFIG=/dev/null
 
 install:
   - echo "install start"

AUTHORS.md

@@ -54,4 +54,3 @@ pandas is distributed under a 3-clause ("Simplified" or "New") BSD
 license. Parts of NumPy, SciPy, numpydoc, bottleneck, which all have
 BSD-compatible licenses, are included. Their licenses follow the pandas
 license.
-

Makefile

@@ -25,3 +25,16 @@ doc:
 	cd doc; \
 	python make.py clean; \
 	python make.py html
+
+check:
+	python3 scripts/validate_unwanted_patterns.py \
+		--validation-type="private_function_across_module" \
+		--included-file-extensions="py" \
+		--excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored \
+		pandas/
+
+	python3 scripts/validate_unwanted_patterns.py \
+		--validation-type="private_import_across_module" \
+		--included-file-extensions="py" \
+		--excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored,doc/
+		pandas/

README.md

@@ -32,7 +32,7 @@ its way towards this goal.
 Here are just a few of the things that pandas does well:
 
   - Easy handling of [**missing data**][missing-data] (represented as
-    `NaN`) in floating point as well as non-floating point data
+    `NaN`, `NA`, or `NaT`) in floating point as well as non-floating point data
   - Size mutability: columns can be [**inserted and
     deleted**][insertion-deletion] from DataFrame and higher dimensional
     objects

asv_bench/asv.conf.json

@@ -26,7 +26,7 @@
     // The Pythons you'd like to test against.  If not provided, defaults
     // to the current version of Python used to run `asv`.
     // "pythons": ["2.7", "3.4"],
-    "pythons": ["3.6"],
+    "pythons": ["3.8"],
 
     // The matrix of dependencies to test.  Each key is the name of a
     // package (in PyPI) and the values are version numbers.  An empty
@@ -39,7 +39,7 @@
     // followed by the pip installed packages).
     "matrix": {
         "numpy": [],
-        "Cython": ["0.29.16"],
+        "Cython": ["0.29.21"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

asv_bench/benchmarks/arithmetic.py

@@ -125,7 +125,7 @@ def setup(self, op):
         arr1 = np.random.randn(n_rows, int(n_cols / 2)).astype("f8")
         arr2 = np.random.randn(n_rows, int(n_cols / 2)).astype("f4")
         df = pd.concat(
-            [pd.DataFrame(arr1), pd.DataFrame(arr2)], axis=1, ignore_index=True,
+            [pd.DataFrame(arr1), pd.DataFrame(arr2)], axis=1, ignore_index=True
         )
         # should already be the case, but just to be sure
         df._consolidate_inplace()

asv_bench/benchmarks/dtypes.py

@@ -1,5 +1,9 @@
+import string
+
 import numpy as np
 
+from pandas import DataFrame
+import pandas._testing as tm
 from pandas.api.types import pandas_dtype
 
 from .pandas_vb_common import (
@@ -62,4 +66,57 @@ def time_infer(self, dtype):
         lib.infer_dtype(self.data_dict[dtype], skipna=False)
 
 
+class SelectDtypes:
+
+    params = [
+        tm.ALL_INT_DTYPES
+        + tm.ALL_EA_INT_DTYPES
+        + tm.FLOAT_DTYPES
+        + tm.COMPLEX_DTYPES
+        + tm.DATETIME64_DTYPES
+        + tm.TIMEDELTA64_DTYPES
+        + tm.BOOL_DTYPES
+    ]
+    param_names = ["dtype"]
+
+    def setup(self, dtype):
+        N, K = 5000, 50
+        self.index = tm.makeStringIndex(N)
+        self.columns = tm.makeStringIndex(K)
+
+        def create_df(data):
+            return DataFrame(data, index=self.index, columns=self.columns)
+
+        self.df_int = create_df(np.random.randint(low=100, size=(N, K)))
+        self.df_float = create_df(np.random.randn(N, K))
+        self.df_bool = create_df(np.random.choice([True, False], size=(N, K)))
+        self.df_string = create_df(
+            np.random.choice(list(string.ascii_letters), size=(N, K))
+        )
+
+    def time_select_dtype_int_include(self, dtype):
+        self.df_int.select_dtypes(include=dtype)
+
+    def time_select_dtype_int_exclude(self, dtype):
+        self.df_int.select_dtypes(exclude=dtype)
+
+    def time_select_dtype_float_include(self, dtype):
+        self.df_float.select_dtypes(include=dtype)
+
+    def time_select_dtype_float_exclude(self, dtype):
+        self.df_float.select_dtypes(exclude=dtype)
+
+    def time_select_dtype_bool_include(self, dtype):
+        self.df_bool.select_dtypes(include=dtype)
+
+    def time_select_dtype_bool_exclude(self, dtype):
+        self.df_bool.select_dtypes(exclude=dtype)
+
+    def time_select_dtype_string_include(self, dtype):
+        self.df_string.select_dtypes(include=dtype)
+
+    def time_select_dtype_string_exclude(self, dtype):
+        self.df_string.select_dtypes(exclude=dtype)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip