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

Author: jbrockmendel

.devcontainer.json

@@ -17,7 +17,9 @@
 		"python.linting.pylintEnabled": false,
 		"python.linting.mypyEnabled": true,
 		"python.testing.pytestEnabled": true,
-		"python.testing.cwd": "pandas/tests"
+		"python.testing.pytestArgs": [
+			"pandas"
+		]
 	},
 
 	// Add the IDs of extensions you want installed when the container is created in the array below.

.github/workflows/ci.yml

@@ -4,7 +4,9 @@ on:
   push:
     branches: master
   pull_request:
-    branches: master
+    branches:
+      - master
+      - 1.1.x
 
 env:
   ENV_FILE: environment.yml

.pre-commit-config.yaml

@@ -3,7 +3,7 @@ repos:
     rev: 19.10b0
     hooks:
     -   id: black
-        language_version: python3.7
+        language_version: python3
 -   repo: https://gitlab.com/pycqa/flake8
     rev: 3.7.7
     hooks:

.travis.yml

@@ -58,20 +58,14 @@ matrix:
       services:
         - mysql
         - postgresql
-
-    - env:
-        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow" SQL="1"
-      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)"
+        - JOB="3.9-dev" PATTERN="(not slow and not network and not clipboard)"
+
 
 before_install:
   - echo "before_install"

LICENSES/XARRAY_LICENSE

@@ -1,3 +1,7 @@
+Copyright 2014-2019, xarray Developers
+
+--------------------------------------------------------------------------------
+
 Apache License
 Version 2.0, January 2004
 http://www.apache.org/licenses/

README.md

@@ -20,7 +20,7 @@
 
 ## What is it?
 
-**pandas** is a Python package providing fast, flexible, and expressive data
+**pandas** is a Python package that provides fast, flexible, and expressive data
 structures designed to make working with "relational" or "labeled" data both
 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
@@ -154,11 +154,11 @@ For usage questions, the best place to go to is [StackOverflow](https://stackove
 Further, general questions and discussions can also take place on the [pydata mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata).
 
 ## Discussion and Development
-Most development discussion is taking place on github in this repo. Further, the [pandas-dev mailing list](https://mail.python.org/mailman/listinfo/pandas-dev) can also be used for specialized discussions or design issues, and a [Gitter channel](https://gitter.im/pydata/pandas) is available for quick development related questions.
+Most development discussions take place on github in this repo. Further, the [pandas-dev mailing list](https://mail.python.org/mailman/listinfo/pandas-dev) can also be used for specialized discussions or design issues, and a [Gitter channel](https://gitter.im/pydata/pandas) is available for quick development related questions.
 
 ## Contributing to pandas [![Open Source Helpers](https://www.codetriage.com/pandas-dev/pandas/badges/users.svg)](https://www.codetriage.com/pandas-dev/pandas)
 
-All contributions, bug reports, bug fixes, documentation improvements, enhancements and ideas are welcome.
+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://pandas.pydata.org/docs/dev/development/contributing.html)**. There is also an [overview](.github/CONTRIBUTING.md) on GitHub.
 

asv_bench/asv.conf.json

@@ -53,6 +53,7 @@
         "xlwt": [],
         "odfpy": [],
         "pytest": [],
+        "jinja2": [],
         // If using Windows with python 2.7 and want to build using the
         // mingw toolchain (rather than MSVC), uncomment the following line.
         // "libpython": [],

asv_bench/benchmarks/categoricals.py

@@ -34,6 +34,7 @@ def setup(self):
         self.values_all_int8 = np.ones(N, "int8")
         self.categorical = pd.Categorical(self.values, self.categories)
         self.series = pd.Series(self.categorical)
+        self.intervals = pd.interval_range(0, 1, periods=N // 10)
 
     def time_regular(self):
         pd.Categorical(self.values, self.categories)
@@ -44,6 +45,9 @@ def time_fastpath(self):
     def time_datetimes(self):
         pd.Categorical(self.datetimes)
 
+    def time_interval(self):
+        pd.Categorical(self.datetimes, categories=self.datetimes)
+
     def time_datetimes_with_nat(self):
         pd.Categorical(self.datetimes_with_nat)
 

asv_bench/benchmarks/frame_ctor.py

@@ -6,7 +6,7 @@
 from .pandas_vb_common import tm
 
 try:
-    from pandas.tseries.offsets import Nano, Hour
+    from pandas.tseries.offsets import Hour, Nano
 except ImportError:
     # For compatibility with older versions
     from pandas.core.datetools import *  # noqa

asv_bench/benchmarks/gil.py

@@ -7,14 +7,14 @@
 
 try:
     from pandas import (
-        rolling_median,
+        rolling_kurt,
+        rolling_max,
         rolling_mean,
+        rolling_median,
         rolling_min,
-        rolling_max,
-        rolling_var,
         rolling_skew,
-        rolling_kurt,
         rolling_std,
+        rolling_var,
     )
 
     have_rolling_methods = True

asv_bench/benchmarks/groupby.py

@@ -16,7 +16,7 @@
 
 from .pandas_vb_common import tm
 
-method_blacklist = {
+method_blocklist = {
     "object": {
         "median",
         "prod",
@@ -403,7 +403,7 @@ class GroupByMethods:
     ]
 
     def setup(self, dtype, method, application):
-        if method in method_blacklist.get(dtype, {}):
+        if method in method_blocklist.get(dtype, {}):
             raise NotImplementedError  # skip benchmark
         ngroups = 1000
         size = ngroups * 2

asv_bench/benchmarks/io/json.py

@@ -1,3 +1,5 @@
+import sys
+
 import numpy as np
 
 from pandas import DataFrame, concat, date_range, read_json, timedelta_range
@@ -82,6 +84,7 @@ def setup(self, orient, frame):
         timedeltas = timedelta_range(start=1, periods=N, freq="s")
         datetimes = date_range(start=1, periods=N, freq="s")
         ints = np.random.randint(100000000, size=N)
+        longints = sys.maxsize * np.random.randint(100000000, size=N)
         floats = np.random.randn(N)
         strings = tm.makeStringIndex(N)
         self.df = DataFrame(np.random.randn(N, ncols), index=np.arange(N))
@@ -120,6 +123,18 @@ def setup(self, orient, frame):
             index=index,
         )
 
+        self.df_longint_float_str = DataFrame(
+            {
+                "longint_1": longints,
+                "longint_2": longints,
+                "float_1": floats,
+                "float_2": floats,
+                "str_1": strings,
+                "str_2": strings,
+            },
+            index=index,
+        )
+
     def time_to_json(self, orient, frame):
         getattr(self, frame).to_json(self.fname, orient=orient)
 
@@ -172,6 +187,7 @@ def setup(self):
         timedeltas = timedelta_range(start=1, periods=N, freq="s")
         datetimes = date_range(start=1, periods=N, freq="s")
         ints = np.random.randint(100000000, size=N)
+        longints = sys.maxsize * np.random.randint(100000000, size=N)
         floats = np.random.randn(N)
         strings = tm.makeStringIndex(N)
         self.df = DataFrame(np.random.randn(N, ncols), index=np.arange(N))
@@ -209,6 +225,17 @@ def setup(self):
             },
             index=index,
         )
+        self.df_longint_float_str = DataFrame(
+            {
+                "longint_1": longints,
+                "longint_2": longints,
+                "float_1": floats,
+                "float_2": floats,
+                "str_1": strings,
+                "str_2": strings,
+            },
+            index=index,
+        )
 
     def time_floats_with_int_idex_lines(self):
         self.df.to_json(self.fname, orient="records", lines=True)
@@ -225,6 +252,9 @@ def time_float_int_lines(self):
     def time_float_int_str_lines(self):
         self.df_int_float_str.to_json(self.fname, orient="records", lines=True)
 
+    def time_float_longint_str_lines(self):
+        self.df_longint_float_str.to_json(self.fname, orient="records", lines=True)
+
 
 class ToJSONMem:
     def setup_cache(self):

asv_bench/benchmarks/io/parsers.py

@@ -2,8 +2,8 @@
 
 try:
     from pandas._libs.tslibs.parsing import (
-        concat_date_cols,
         _does_string_look_like_datetime,
+        concat_date_cols,
     )
 except ImportError:
     # Avoid whole benchmark suite import failure on asv (currently 0.4)

asv_bench/benchmarks/io/style.py

@@ -0,0 +1,34 @@
+import numpy as np
+
+from pandas import DataFrame
+
+
+class RenderApply:
+
+    params = [[12, 24, 36], [12, 120]]
+    param_names = ["cols", "rows"]
+
+    def setup(self, cols, rows):
+        self.df = DataFrame(
+            np.random.randn(rows, cols),
+            columns=[f"float_{i+1}" for i in range(cols)],
+            index=[f"row_{i+1}" for i in range(rows)],
+        )
+        self._style_apply()
+
+    def time_render(self, cols, rows):
+        self.st.render()
+
+    def peakmem_apply(self, cols, rows):
+        self._style_apply()
+
+    def peakmem_render(self, cols, rows):
+        self.st.render()
+
+    def _style_apply(self):
+        def _apply_func(s):
+            return [
+                "background-color: lightcyan" if s.name == "row_1" else "" for v in s
+            ]
+
+        self.st = self.df.style.apply(_apply_func, axis=1)

asv_bench/benchmarks/pandas_vb_common.py

@@ -33,7 +33,7 @@
     np.uint8,
 ]
 datetime_dtypes = [np.datetime64, np.timedelta64]
-string_dtypes = [np.object]
+string_dtypes = [object]
 try:
     extension_dtypes = [
         pd.Int8Dtype,

asv_bench/benchmarks/rolling.py

@@ -91,11 +91,18 @@ class EWMMethods:
     def setup(self, constructor, window, dtype, method):
         N = 10 ** 5
         arr = (100 * np.random.random(N)).astype(dtype)
+        times = pd.date_range("1900", periods=N, freq="23s")
         self.ewm = getattr(pd, constructor)(arr).ewm(halflife=window)
+        self.ewm_times = getattr(pd, constructor)(arr).ewm(
+            halflife="1 Day", times=times
+        )
 
     def time_ewm(self, constructor, window, dtype, method):
         getattr(self.ewm, method)()
 
+    def time_ewm_times(self, constructor, window, dtype, method):
+        self.ewm.mean()
+
 
 class VariableWindowMethods(Methods):
     params = (

asv_bench/benchmarks/series_methods.py

@@ -58,17 +58,15 @@ def time_isin_nan_values(self):
 
 class IsInForObjects:
     def setup(self):
-        self.s_nans = Series(np.full(10 ** 4, np.nan)).astype(np.object)
-        self.vals_nans = np.full(10 ** 4, np.nan).astype(np.object)
-        self.s_short = Series(np.arange(2)).astype(np.object)
-        self.s_long = Series(np.arange(10 ** 5)).astype(np.object)
-        self.vals_short = np.arange(2).astype(np.object)
-        self.vals_long = np.arange(10 ** 5).astype(np.object)
+        self.s_nans = Series(np.full(10 ** 4, np.nan)).astype(object)
+        self.vals_nans = np.full(10 ** 4, np.nan).astype(object)
+        self.s_short = Series(np.arange(2)).astype(object)
+        self.s_long = Series(np.arange(10 ** 5)).astype(object)
+        self.vals_short = np.arange(2).astype(object)
+        self.vals_long = np.arange(10 ** 5).astype(object)
         # because of nans floats are special:
-        self.s_long_floats = Series(np.arange(10 ** 5, dtype=np.float)).astype(
-            np.object
-        )
-        self.vals_long_floats = np.arange(10 ** 5, dtype=np.float).astype(np.object)
+        self.s_long_floats = Series(np.arange(10 ** 5, dtype=np.float)).astype(object)
+        self.vals_long_floats = np.arange(10 ** 5, dtype=np.float).astype(object)
 
     def time_isin_nans(self):
         # if nan-objects are different objects,

asv_bench/benchmarks/sparse.py

@@ -32,7 +32,7 @@ def time_series_to_frame(self):
 
 class SparseArrayConstructor:
 
-    params = ([0.1, 0.01], [0, np.nan], [np.int64, np.float64, np.object])
+    params = ([0.1, 0.01], [0, np.nan], [np.int64, np.float64, object])
     param_names = ["dense_proportion", "fill_value", "dtype"]
 
     def setup(self, dense_proportion, fill_value, dtype):