Merge branch 'master' of https://github.com/pandas-dev/pandas into boilerplate-4

Author: jbrockmendel

.travis.yml

@@ -14,6 +14,8 @@ 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
@@ -27,12 +29,21 @@ 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)"
+
     - env:
         - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
       services:
@@ -53,11 +64,18 @@ matrix:
       services:
         - mysql
         - postgresql
+  allow_failures:
+    - 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
+      python: 3.9-dev
+      env:
+        - JOB="3.9-dev" PATTERN="(not slow and not network)"
 
 before_install:
   - echo "before_install"
-  # set non-blocking IO on travis
-  # https://github.com/travis-ci/travis-ci/issues/8920#issuecomment-352661024
+  # Use blocking IO on travis.  Ref:  https://github.com/travis-ci/travis-ci/issues/8920#issuecomment-352661024
   - python -c 'import os,sys,fcntl; flags = fcntl.fcntl(sys.stdout, fcntl.F_GETFL); fcntl.fcntl(sys.stdout, fcntl.F_SETFL, flags&~os.O_NONBLOCK);'
   - source ci/travis_process_gbq_encryption.sh
   - export PATH="$HOME/miniconda3/bin:$PATH"
@@ -83,7 +101,7 @@ install:
 script:
   - echo "script start"
   - echo "$JOB"
-  - source activate pandas-dev
+  - if [ "$JOB" != "3.9-dev" ]; then source activate pandas-dev; fi
   - ci/run_tests.sh
 
 after_script:

README.md

@@ -16,6 +16,7 @@
 [![Downloads](https://anaconda.org/conda-forge/pandas/badges/downloads.svg)](https://pandas.pydata.org)
 [![Gitter](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/pydata/pandas)
 [![Powered by NumFOCUS](https://img.shields.io/badge/powered%20by-NumFOCUS-orange.svg?style=flat&colorA=E1523D&colorB=007D8A)](https://numfocus.org)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
 
 ## What is it?
 

asv_bench/benchmarks/algorithms.py

@@ -34,7 +34,16 @@ class Factorize:
     params = [
         [True, False],
         [True, False],
-        ["int", "uint", "float", "string", "datetime64[ns]", "datetime64[ns, tz]"],
+        [
+            "int",
+            "uint",
+            "float",
+            "string",
+            "datetime64[ns]",
+            "datetime64[ns, tz]",
+            "Int64",
+            "boolean",
+        ],
     ]
     param_names = ["unique", "sort", "dtype"]
 
@@ -49,13 +58,15 @@ def setup(self, unique, sort, dtype):
             "datetime64[ns, tz]": pd.date_range(
                 "2011-01-01", freq="H", periods=N, tz="Asia/Tokyo"
             ),
+            "Int64": pd.array(np.arange(N), dtype="Int64"),
+            "boolean": pd.array(np.random.randint(0, 2, N), dtype="boolean"),
         }[dtype]
         if not unique:
             data = data.repeat(5)
-        self.idx = data
+        self.data = data
 
     def time_factorize(self, unique, sort, dtype):
-        self.idx.factorize(sort=sort)
+        pd.factorize(self.data, sort=sort)
 
 
 class Duplicated:

asv_bench/benchmarks/arithmetic.py

@@ -101,6 +101,59 @@ def time_frame_op_with_series_axis1(self, opname):
         getattr(operator, opname)(self.df, self.ser)
 
 
+class FrameWithFrameWide:
+    # Many-columns, mixed dtypes
+
+    params = [
+        [
+            # GH#32779 has discussion of which operators are included here
+            operator.add,
+            operator.floordiv,
+            operator.gt,
+        ]
+    ]
+    param_names = ["op"]
+
+    def setup(self, op):
+        # we choose dtypes so as to make the blocks
+        #  a) not perfectly match between right and left
+        #  b) appreciably bigger than single columns
+        n_cols = 2000
+        n_rows = 500
+
+        # construct dataframe with 2 blocks
+        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,
+        )
+        # should already be the case, but just to be sure
+        df._consolidate_inplace()
+
+        # TODO: GH#33198 the setting here shoudlnt need two steps
+        arr1 = np.random.randn(n_rows, int(n_cols / 4)).astype("f8")
+        arr2 = np.random.randn(n_rows, int(n_cols / 2)).astype("i8")
+        arr3 = np.random.randn(n_rows, int(n_cols / 4)).astype("f8")
+        df2 = pd.concat(
+            [pd.DataFrame(arr1), pd.DataFrame(arr2), pd.DataFrame(arr3)],
+            axis=1,
+            ignore_index=True,
+        )
+        # should already be the case, but just to be sure
+        df2._consolidate_inplace()
+
+        self.left = df
+        self.right = df2
+
+    def time_op_different_blocks(self, op):
+        # blocks (and dtypes) are not aligned
+        op(self.left, self.right)
+
+    def time_op_same_blocks(self, op):
+        # blocks (and dtypes) are aligned
+        op(self.left, self.left)
+
+
 class Ops:
 
     params = [[True, False], ["default", 1]]
@@ -416,4 +469,29 @@ def time_apply_index(self, offset):
         offset.apply_index(self.rng)
 
 
+class BinaryOpsMultiIndex:
+    params = ["sub", "add", "mul", "div"]
+    param_names = ["func"]
+
+    def setup(self, func):
+        date_range = pd.date_range("20200101 00:00", "20200102 0:00", freq="S")
+        level_0_names = [str(i) for i in range(30)]
+
+        index = pd.MultiIndex.from_product([level_0_names, date_range])
+        column_names = ["col_1", "col_2"]
+
+        self.df = pd.DataFrame(
+            np.random.rand(len(index), 2), index=index, columns=column_names
+        )
+
+        self.arg_df = pd.DataFrame(
+            np.random.randint(1, 10, (len(level_0_names), 2)),
+            index=level_0_names,
+            columns=column_names,
+        )
+
+    def time_binary_op_multiindex(self, func):
+        getattr(self.df, func)(self.arg_df, level=0)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/indexing.py

@@ -158,9 +158,9 @@ def time_boolean_rows_boolean(self):
 class DataFrameNumericIndexing:
     def setup(self):
         self.idx_dupe = np.array(range(30)) * 99
-        self.df = DataFrame(np.random.randn(10000, 5))
+        self.df = DataFrame(np.random.randn(100000, 5))
         self.df_dup = concat([self.df, 2 * self.df, 3 * self.df])
-        self.bool_indexer = [True] * 5000 + [False] * 5000
+        self.bool_indexer = [True] * 50000 + [False] * 50000
 
     def time_iloc_dups(self):
         self.df_dup.iloc[self.idx_dupe]

asv_bench/benchmarks/rolling.py

@@ -186,4 +186,27 @@ def peakmem_rolling(self, constructor, window_size, dtype, method):
         getattr(self.roll, method)()
 
 
+class Groupby:
+
+    params = ["sum", "median", "mean", "max", "min", "kurt", "sum"]
+
+    def setup(self, method):
+        N = 1000
+        df = pd.DataFrame(
+            {
+                "A": [str(i) for i in range(N)] * 10,
+                "B": list(range(N)) * 10,
+                "C": pd.date_range(start="1900-01-01", freq="1min", periods=N * 10),
+            }
+        )
+        self.groupby_roll_int = df.groupby("A").rolling(window=2)
+        self.groupby_roll_offset = df.groupby("A").rolling(window="30s", on="C")
+
+    def time_rolling_int(self, method):
+        getattr(self.groupby_roll_int, method)()
+
+    def time_rolling_offset(self, method):
+        getattr(self.groupby_roll_offset, method)()
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

azure-pipelines.yml

@@ -5,6 +5,9 @@ trigger:
 pr:
 - master
 
+variables:
+  PYTEST_WORKERS: auto
+
 jobs:
 # Mac and Linux use the same template
 - template: ci/azure/posix.yml

ci/build39.sh

@@ -0,0 +1,21 @@
+#!/bin/bash -e
+# Special build for python3.9 until numpy puts its own wheels up
+
+sudo apt-get install build-essential gcc xvfb
+pip install --no-deps -U pip wheel setuptools
+pip install python-dateutil pytz pytest pytest-xdist hypothesis
+pip install cython --pre # https://github.com/cython/cython/issues/3395
+
+git clone https://github.com/numpy/numpy
+cd numpy
+python setup.py build_ext --inplace
+python setup.py install
+cd ..
+rm -rf numpy
+
+python setup.py build_ext -inplace
+python -m pip install --no-build-isolation -e .
+
+python -c "import sys; print(sys.version_info)"
+python -c "import pandas as pd"
+python -c "import hypothesis"

ci/code_checks.sh

@@ -353,8 +353,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03,SA05
+    MSG='Validate docstrings (GL03, GL04, GL05, GL06, GL07, GL09, GL10, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT01, RT04, RT05, SA02, SA03)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=GL03,GL04,GL05,GL06,GL07,GL09,GL10,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT01,RT04,RT05,SA02,SA03
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Validate correct capitalization among titles in documentation' ; echo $MSG

ci/deps/azure-37-numpydev.yaml

@@ -14,9 +14,9 @@ dependencies:
   - pytz
   - pip
   - pip:
-    - cython>=0.29.16
+    - cython==0.29.16 # GH#34014
     - "git+git://github.com/dateutil/dateutil.git"
-    - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"
+    - "--extra-index-url https://pypi.anaconda.org/scipy-wheels-nightly/simple"
     - "--pre"
     - "numpy"
     - "scipy"

ci/deps/travis-37-arm64.yaml

@@ -0,0 +1,21 @@
+name: pandas-dev
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - python=3.7.*
+
+  # tools
+  - cython>=0.29.13
+  - pytest>=5.0.1
+  - pytest-xdist>=1.21
+  - hypothesis>=3.58.0
+
+  # pandas dependencies
+  - botocore>=1.11
+  - numpy
+  - python-dateutil
+  - pytz
+  - pip
+  - pip:
+    - moto

ci/run_tests.sh

@@ -20,7 +20,7 @@ if [[ $(uname) == "Linux" && -z $DISPLAY ]]; then
     XVFB="xvfb-run "
 fi
 
-PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n auto --dist=loadfile -s --strict --durations=10 --junitxml=test-data.xml $TEST_ARGS $COVERAGE pandas"
+PYTEST_CMD="${XVFB}pytest -m \"$PATTERN\" -n $PYTEST_WORKERS --dist=loadfile -s --strict --durations=30 --junitxml=test-data.xml $TEST_ARGS $COVERAGE pandas"
 
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"

ci/setup_env.sh

@@ -1,5 +1,10 @@
 #!/bin/bash -e
 
+if [ "$JOB" == "3.9-dev" ]; then
+    /bin/bash ci/build39.sh
+    exit 0
+fi
+
 # edit the locale file if needed
 if [[ "$(uname)" == "Linux" && -n "$LC_ALL" ]]; then
     echo "Adding locale to the first line of pandas/__init__.py"
@@ -36,9 +41,17 @@ else
   exit 1
 fi
 
-wget -q "https://repo.continuum.io/miniconda/Miniconda3-latest-$CONDA_OS.sh" -O miniconda.sh
+if [ "${TRAVIS_CPU_ARCH}" == "arm64" ]; then
+  sudo apt-get -y install xvfb
+  CONDA_URL="https://github.com/conda-forge/miniforge/releases/download/4.8.2-1/Miniforge3-4.8.2-1-Linux-aarch64.sh"
+else
+  CONDA_URL="https://repo.continuum.io/miniconda/Miniconda3-latest-$CONDA_OS.sh"
+fi
+wget -q $CONDA_URL -O miniconda.sh
 chmod +x miniconda.sh
-./miniconda.sh -b
+
+# Installation path is required for ARM64 platform as miniforge script installs in path $HOME/miniforge3.
+./miniconda.sh -b -p $MINICONDA_DIR
 
 export PATH=$MINICONDA_DIR/bin:$PATH
 

doc/source/development/contributing.rst

@@ -110,7 +110,7 @@ version control to allow many people to work together on the project.
 Some great resources for learning Git:
 
 * the `GitHub help pages <https://help.github.com/>`_.
-* the `NumPy's documentation <https://docs.scipy.org/doc/numpy/dev/index.html>`_.
+* the `NumPy's documentation <https://numpy.org/doc/stable/dev/index.html>`_.
 * Matthew Brett's `Pydagogue <https://matthew-brett.github.com/pydagogue/>`_.
 
 Getting started with Git
@@ -974,7 +974,7 @@ it is worth getting in the habit of writing tests ahead of time so this is never
 Like many packages, pandas uses `pytest
 <https://docs.pytest.org/en/latest/>`_ and the convenient
 extensions in `numpy.testing
-<https://docs.scipy.org/doc/numpy/reference/routines.testing.html>`_.
+<https://numpy.org/doc/stable/reference/routines.testing.html>`_.
 
 .. note::
 
@@ -1275,8 +1275,8 @@ Performance matters and it is worth considering whether your code has introduced
 performance regressions. pandas is in the process of migrating to
 `asv benchmarks <https://github.com/spacetelescope/asv>`__
 to enable easy monitoring of the performance of critical pandas operations.
-These benchmarks are all found in the ``pandas/asv_bench`` directory.  asv
-supports both python2 and python3.
+These benchmarks are all found in the ``pandas/asv_bench`` directory, and the
+test results can be found `here <https://pandas.pydata.org/speed/pandas/#/>`__.
 
 To use all features of asv, you will need either ``conda`` or
 ``virtualenv``. For more details please check the `asv installation

doc/source/development/extending.rst

@@ -219,7 +219,7 @@ and re-boxes it if necessary.
 
 If applicable, we highly recommend that you implement ``__array_ufunc__`` in your
 extension array to avoid coercion to an ndarray. See
-`the numpy documentation <https://docs.scipy.org/doc/numpy/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html>`__
+`the numpy documentation <https://numpy.org/doc/stable/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html>`__
 for an example.
 
 As part of your implementation, we require that you defer to pandas when a pandas