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

Author: jiangyue12392

.github/FUNDING.yml

@@ -1 +1,2 @@
 custom: https://pandas.pydata.org/donate.html
+tidelift: pypi/pandas

.github/SECURITY.md

@@ -0,0 +1 @@
+To report a security vulnerability to pandas, please go to https://tidelift.com/security and see the instructions there.

.gitignore

@@ -57,6 +57,7 @@ dist
 # wheel files
 *.whl
 **/wheelhouse/*
+pip-wheel-metadata
 # coverage
 .coverage
 coverage.xml
@@ -66,6 +67,9 @@ coverage_html_report
 # hypothesis test database
 .hypothesis/
 __pycache__
+# pytest-monkeytype
+monkeytype.sqlite3
+
 
 # OS generated files #
 ######################

.pre-commit-config.yaml

@@ -1,16 +1,18 @@
 repos:
-    - repo: https://github.com/python/black
-      rev: stable
-      hooks:
-          - id: black
-            language_version: python3.7
-    - repo: https://gitlab.com/pycqa/flake8
-      rev: 3.7.7
-      hooks:
-          - id: flake8
-            language: python_venv
-    - repo: https://github.com/pre-commit/mirrors-isort
-      rev: v4.3.20
-      hooks:
-          - id: isort
-            language: python_venv
+-   repo: https://github.com/python/black
+    rev: stable
+    hooks:
+    -   id: black
+        language_version: python3.7
+-   repo: https://gitlab.com/pycqa/flake8
+    rev: 3.7.7
+    hooks:
+    -   id: flake8
+        language: python_venv
+        additional_dependencies: [flake8-comprehensions]
+-   repo: https://github.com/pre-commit/mirrors-isort
+    rev: v4.3.20
+    hooks:
+    -   id: isort
+        language: python_venv
+        exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$

.travis.yml

@@ -1,4 +1,3 @@
-sudo: false
 language: python
 python: 3.5
 
@@ -22,7 +21,7 @@ env:
 
 git:
     # for cloning
-    depth: 2000
+    depth: false
 
 matrix:
     fast_finish: true
@@ -64,7 +63,7 @@ before_install:
   - pwd
   - uname -a
   - git --version
-  - git tag
+  - ./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

MANIFEST.in

@@ -3,6 +3,7 @@ include LICENSE
 include RELEASE.md
 include README.md
 include setup.py
+include pyproject.toml
 
 graft doc
 prune doc/build
@@ -14,6 +15,7 @@ graft pandas
 global-exclude *.bz2
 global-exclude *.csv
 global-exclude *.dta
+global-exclude *.feather
 global-exclude *.gz
 global-exclude *.h5
 global-exclude *.html
@@ -23,7 +25,10 @@ global-exclude *.pickle
 global-exclude *.png
 global-exclude *.pyc
 global-exclude *.pyd
+global-exclude *.ods
+global-exclude *.odt
 global-exclude *.sas7bdat
+global-exclude *.sav
 global-exclude *.so
 global-exclude *.xls
 global-exclude *.xlsm

Makefile

@@ -1,5 +1,7 @@
 .PHONY : develop build clean clean_pyc doc lint-diff black
 
+all: develop
+
 clean:
 	-python setup.py clean
 
@@ -13,10 +15,10 @@ lint-diff:
 	git diff upstream/master --name-only -- "*.py" | xargs flake8
 
 black:
-	black . --exclude '(asv_bench/env|\.egg|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|_build|buck-out|build|dist)'
+	black . --exclude '(asv_bench/env|\.egg|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|_build|buck-out|build|dist|setup.py)'
 
 develop: build
-	python setup.py develop
+	python -m pip install --no-build-isolation -e .
 
 doc:
 	-rm -rf doc/build doc/source/generated

README.md

@@ -188,16 +188,17 @@ python setup.py install
 
 or for installing in [development mode](https://pip.pypa.io/en/latest/reference/pip_install.html#editable-installs):
 
+
 ```sh
-python setup.py develop
+python -m pip install --no-build-isolation -e .
 ```
 
-Alternatively, you can use `pip` if you want all the dependencies pulled
-in automatically (the `-e` option is for installing it in [development
-mode](https://pip.pypa.io/en/latest/reference/pip_install.html#editable-installs)):
+If you have `make`, you can also use `make develop` to run the same command.
+
+or alternatively
 
 ```sh
-pip install -e .
+python setup.py develop
 ```
 
 See the full instructions for [installing from source](https://pandas.pydata.org/pandas-docs/stable/install.html#installing-from-source).
@@ -224,7 +225,7 @@ Most development discussion is taking place on github in this repo. Further, the
 
 All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome.
 
-A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
+A detailed overview on how to contribute can be found in the **[contributing guide](https://dev.pandas.io/docs/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
 
 If you are simply looking to start working with the pandas codebase, navigate to the [GitHub "issues" tab](https://github.com/pandas-dev/pandas/issues) and start looking through interesting issues. There are a number of issues listed under [Docs](https://github.com/pandas-dev/pandas/issues?labels=Docs&sort=updated&state=open) and [good first issue](https://github.com/pandas-dev/pandas/issues?labels=good+first+issue&sort=updated&state=open) where you could start out.
 
@@ -233,3 +234,5 @@ You can also triage issues which may include reproducing bug reports, or asking
 Or maybe through using pandas you have an idea of your own or are looking for something in the documentation and thinking ‘this can be improved’...you can do something about it!
 
 Feel free to ask questions on the [mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata) or on [Gitter](https://gitter.im/pydata/pandas).
+
+As contributors and maintainers to this project, you are expected to abide by pandas' code of conduct. More information can be found at: [Contributor Code of Conduct](https://github.com/pandas-dev/pandas/blob/master/.github/CODE_OF_CONDUCT.md)

asv_bench/asv.conf.json

@@ -50,12 +50,13 @@
         "xlsxwriter": [],
         "xlrd": [],
         "xlwt": [],
+        "odfpy": [],
         "pytest": [],
         // If using Windows with python 2.7 and want to build using the
         // mingw toolchain (rather than MSVC), uncomment the following line.
         // "libpython": [],
     },
-
+    "conda_channels": ["defaults", "conda-forge"],
     // Combinations of libraries/python versions can be excluded/included
     // from the set to test. Each entry is a dictionary containing additional
     // key-value pairs to include/exclude.

asv_bench/benchmarks/attrs_caching.py

@@ -1,4 +1,5 @@
 import numpy as np
+
 from pandas import DataFrame
 
 try:
@@ -32,4 +33,4 @@ def time_cache_readonly(self):
         self.obj.prop
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/binary_ops.py

@@ -1,4 +1,5 @@
 import numpy as np
+
 from pandas import DataFrame, Series, date_range
 from pandas.core.algorithms import checked_add_with_arr
 
@@ -155,4 +156,4 @@ def time_add_overflow_both_arg_nan(self):
         )
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/categoricals.py

@@ -1,7 +1,9 @@
+import warnings
+
 import numpy as np
+
 import pandas as pd
 import pandas.util.testing as tm
-import warnings
 
 try:
     from pandas.api.types import union_categoricals
@@ -280,4 +282,18 @@ def time_sort_values(self):
         self.index.sort_values(ascending=False)
 
 
-from .pandas_vb_common import setup  # noqa: F401
+class SearchSorted:
+    def setup(self):
+        N = 10 ** 5
+        self.ci = tm.makeCategoricalIndex(N).sort_values()
+        self.c = self.ci.values
+        self.key = self.ci.categories[1]
+
+    def time_categorical_index_contains(self):
+        self.ci.searchsorted(self.key)
+
+    def time_categorical_contains(self):
+        self.c.searchsorted(self.key)
+
+
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/ctors.py

@@ -1,6 +1,7 @@
 import numpy as np
+
+from pandas import DatetimeIndex, Index, MultiIndex, Series, Timestamp
 import pandas.util.testing as tm
-from pandas import Series, Index, DatetimeIndex, Timestamp, MultiIndex
 
 
 def no_change(arr):
@@ -113,4 +114,4 @@ def time_multiindex_from_iterables(self):
         MultiIndex.from_product(self.iterables)
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/dtypes.py

@@ -1,14 +1,14 @@
+import numpy as np
+
 from pandas.api.types import pandas_dtype
 
-import numpy as np
 from .pandas_vb_common import (
-    numeric_dtypes,
     datetime_dtypes,
-    string_dtypes,
     extension_dtypes,
+    numeric_dtypes,
+    string_dtypes,
 )
 
-
 _numpy_dtypes = [
     np.dtype(dtype) for dtype in (numeric_dtypes + datetime_dtypes + string_dtypes)
 ]
@@ -40,4 +40,4 @@ def time_pandas_dtype_invalid(self, dtype):
             pass
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/eval.py

@@ -1,4 +1,5 @@
 import numpy as np
+
 import pandas as pd
 
 try:
@@ -62,4 +63,4 @@ 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
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/frame_ctor.py

@@ -1,6 +1,7 @@
 import numpy as np
+
+from pandas import DataFrame, MultiIndex, Series, Timestamp, date_range
 import pandas.util.testing as tm
-from pandas import DataFrame, Series, MultiIndex, Timestamp, date_range
 
 try:
     from pandas.tseries.offsets import Nano, Hour
@@ -104,4 +105,4 @@ def time_frame_from_lists(self):
         self.df = DataFrame(self.data)
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/frame_methods.py

@@ -1,5 +1,5 @@
-import warnings
 import string
+import warnings
 
 import numpy as np
 
@@ -115,15 +115,15 @@ def setup(self):
         )
         self.df4 = DataFrame(np.random.randn(N * 1000, 10))
 
-    def time_iteritems(self):
+    def time_items(self):
         # (monitor no-copying behaviour)
         if hasattr(self.df, "_item_cache"):
             self.df._item_cache.clear()
-        for name, col in self.df.iteritems():
+        for name, col in self.df.items():
             pass
 
-    def time_iteritems_cached(self):
-        for name, col in self.df.iteritems():
+    def time_items_cached(self):
+        for name, col in self.df.items():
             pass
 
     def time_iteritems_indexing(self):
@@ -609,4 +609,15 @@ def time_dataframe_describe(self):
         self.df.describe()
 
 
-from .pandas_vb_common import setup  # noqa: F401
+class SelectDtypes:
+    params = [100, 1000]
+    param_names = ["n"]
+
+    def setup(self, n):
+        self.df = DataFrame(np.random.randn(10, n))
+
+    def time_select_dtypes(self, n):
+        self.df.select_dtypes(include="int")
+
+
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/gil.py

@@ -1,7 +1,8 @@
 import numpy as np
-import pandas.util.testing as tm
-from pandas import DataFrame, Series, read_csv, factorize, date_range
+
+from pandas import DataFrame, Series, date_range, factorize, read_csv
 from pandas.core.algorithms import take_1d
+import pandas.util.testing as tm
 
 try:
     from pandas import (
@@ -36,7 +37,7 @@ def wrapper(fname):
         return wrapper
 
 
-from .pandas_vb_common import BaseIO
+from .pandas_vb_common import BaseIO  # noqa: E402 isort:skip
 
 
 class ParallelGroupbyMethods:
@@ -301,4 +302,4 @@ def time_loop(self, threads):
             self.loop()
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/groupby.py

@@ -15,7 +15,6 @@
 )
 import pandas.util.testing as tm
 
-
 method_blacklist = {
     "object": {
         "median",
@@ -626,4 +625,4 @@ def time_first(self):
         self.df_nans.groupby("key").transform("first")
 
 
-from .pandas_vb_common import setup  # noqa: F401
+from .pandas_vb_common import setup  # noqa: F401 isort:skip