Merge branch 'master' into issue_backupbackup

Author: charlesdong1991

asv_bench/benchmarks/groupby.py

@@ -14,7 +14,7 @@
 method_blacklist = {
     'object': {'median', 'prod', 'sem', 'cumsum', 'sum', 'cummin', 'mean',
                'max', 'skew', 'cumprod', 'cummax', 'rank', 'pct_change', 'min',
-               'var', 'mad', 'describe', 'std'},
+               'var', 'mad', 'describe', 'std', 'quantile'},
     'datetime': {'median', 'prod', 'sem', 'cumsum', 'sum', 'mean', 'skew',
                  'cumprod', 'cummax', 'pct_change', 'var', 'mad', 'describe',
                  'std'}
@@ -316,8 +316,9 @@ class GroupByMethods(object):
               ['all', 'any', 'bfill', 'count', 'cumcount', 'cummax', 'cummin',
                'cumprod', 'cumsum', 'describe', 'ffill', 'first', 'head',
                'last', 'mad', 'max', 'min', 'median', 'mean', 'nunique',
-               'pct_change', 'prod', 'rank', 'sem', 'shift', 'size', 'skew',
-               'std', 'sum', 'tail', 'unique', 'value_counts', 'var'],
+               'pct_change', 'prod', 'quantile', 'rank', 'sem', 'shift',
+               'size', 'skew', 'std', 'sum', 'tail', 'unique', 'value_counts',
+               'var'],
               ['direct', 'transformation']]
 
     def setup(self, dtype, method, application):

asv_bench/benchmarks/series_methods.py

@@ -124,6 +124,25 @@ def time_dropna(self, dtype):
         self.s.dropna()
 
 
+class SearchSorted(object):
+
+    goal_time = 0.2
+    params = ['int8', 'int16', 'int32', 'int64',
+              'uint8', 'uint16', 'uint32', 'uint64',
+              'float16', 'float32', 'float64',
+              'str']
+    param_names = ['dtype']
+
+    def setup(self, dtype):
+        N = 10**5
+        data = np.array([1] * N + [2] * N + [3] * N).astype(dtype)
+        self.s = Series(data)
+
+    def time_searchsorted(self, dtype):
+        key = '2' if dtype == 'str' else 2
+        self.s.searchsorted(key)
+
+
 class Map(object):
 
     params = ['dict', 'Series']

ci/deps/azure-27-compat.yaml

@@ -18,9 +18,10 @@ dependencies:
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
+  - isort
   - pip:
     - html5lib==1.0b2
     - beautifulsoup4==4.2.1

ci/deps/azure-27-locale.yaml

@@ -20,10 +20,11 @@ dependencies:
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - hypothesis>=3.58.0
+  - isort
   - pip:
     - html5lib==1.0b2
     - beautifulsoup4==4.2.1

ci/deps/azure-36-locale_slow.yaml

@@ -26,9 +26,10 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - moto
+  - isort
   - pip:
     - hypothesis>=3.58.0

ci/deps/azure-37-locale.yaml

@@ -25,9 +25,10 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
+  - isort
   - pip:
     - hypothesis>=3.58.0
     - moto  # latest moto in conda-forge fails with 3.7, move to conda dependencies when this is fixed

ci/deps/azure-37-numpydev.yaml

@@ -6,10 +6,11 @@ dependencies:
   - pytz
   - Cython>=0.28.2
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - hypothesis>=3.58.0
+  - isort
   - pip:
     - "git+git://github.com/dateutil/dateutil.git"
     - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"

ci/deps/azure-macos-35.yaml

@@ -21,10 +21,11 @@ dependencies:
   - xlrd
   - xlsxwriter
   - xlwt
-  # universal
-  - pytest
-  - pytest-xdist
-  - pytest-mock
+  - isort
   - pip:
     - python-dateutil==2.5.3
+    # universal
+    - pytest>=4.0.2
+    - pytest-xdist
+    - pytest-mock
     - hypothesis>=3.58.0

ci/deps/azure-windows-27.yaml

@@ -25,8 +25,9 @@ dependencies:
   - xlwt
   # universal
   - cython>=0.28.2
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - moto
   - hypothesis>=3.58.0
+  - isort

ci/deps/azure-windows-36.yaml

@@ -23,7 +23,8 @@ dependencies:
   - xlwt
   # universal
   - cython>=0.28.2
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - hypothesis>=3.58.0
+  - isort

ci/deps/travis-27.yaml

@@ -39,11 +39,12 @@ dependencies:
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - moto==1.3.4
   - hypothesis>=3.58.0
+  - isort
   - pip:
     - backports.lzma
     - pandas-gbq

ci/deps/travis-36-doc.yaml

@@ -41,5 +41,6 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
+  - isort

ci/deps/travis-36-locale.yaml

@@ -28,9 +28,10 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - moto
+  - isort
   - pip:
     - hypothesis>=3.58.0

ci/deps/travis-36-slow.yaml

@@ -25,8 +25,9 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - moto
   - hypothesis>=3.58.0
+  - isort

ci/deps/travis-36.yaml

@@ -33,11 +33,12 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-cov
   - pytest-mock
   - hypothesis>=3.58.0
+  - isort
   - pip:
     - brotlipy
     - coverage

ci/deps/travis-37.yaml

@@ -12,10 +12,11 @@ dependencies:
   - nomkl
   - pyarrow
   - pytz
-  - pytest
+  - pytest>=4.0.2
   - pytest-xdist
   - pytest-mock
   - hypothesis>=3.58.0
   - s3fs
+  - isort
   - pip:
     - moto

doc/source/development/contributing.rst

@@ -435,7 +435,7 @@ reducing the turn-around time for checking your changes.
 
     # compile the reference docs for a single function
     python make.py clean
-    python make.py --single DataFrame.join
+    python make.py --single pandas.DataFrame.join
 
 For comparison, a full documentation build may take 15 minutes, but a single
 section may take 15 seconds. Subsequent builds, which only process portions
@@ -731,7 +731,7 @@ extensions in `numpy.testing
 
 .. note::
 
-   The earliest supported pytest version is 3.6.0.
+   The earliest supported pytest version is 4.0.2.
 
 Writing tests
 ~~~~~~~~~~~~~

doc/source/development/extending.rst

@@ -33,8 +33,9 @@ decorate a class, providing the name of attribute to add. The class's
 
        @staticmethod
        def _validate(obj):
-           if 'lat' not in obj.columns or 'lon' not in obj.columns:
-               raise AttributeError("Must have 'lat' and 'lon'.")
+           # verify there is a column latitude and a column longitude
+           if 'latitude' not in obj.columns or 'longitude' not in obj.columns:
+               raise AttributeError("Must have 'latitude' and 'longitude'.")
 
        @property
        def center(self):

doc/source/install.rst

@@ -202,7 +202,7 @@ pandas is equipped with an exhaustive set of unit tests, covering about 97% of
 the code base as of this writing. To run it on your machine to verify that
 everything is working (and that you have all of the dependencies, soft and hard,
 installed), make sure you have `pytest
-<http://docs.pytest.org/en/latest/>`__ >= 3.6 and `Hypothesis
+<http://docs.pytest.org/en/latest/>`__ >= 4.0.2 and `Hypothesis
 <https://hypothesis.readthedocs.io/>`__ >= 3.58, then run:
 
 ::

doc/source/reference/groupby.rst

@@ -99,6 +99,7 @@ application to columns of a specific data type.
    DataFrameGroupBy.idxmax
    DataFrameGroupBy.idxmin
    DataFrameGroupBy.mad
+   DataFrameGroupBy.nunique
    DataFrameGroupBy.pct_change
    DataFrameGroupBy.plot
    DataFrameGroupBy.quantile

doc/source/styled.xlsx

@@ -335,7 +335,7 @@ examined :ref:`in the API <api.dataframe.missing>`.
 Interpolation
 ~~~~~~~~~~~~~
 
-.. versionadded:: 0.21.0
+.. versionadded:: 0.23.0
 
   The ``limit_area`` keyword argument was added.
 

doc/source/user_guide/missing_data.rst

@@ -633,6 +633,16 @@ We are stopping on the included end-point as it is part of the index:
    dft2 = dft2.swaplevel(0, 1).sort_index()
    dft2.loc[idx[:, '2013-01-05'], :]
 
+.. versionadded:: 0.25.0
+
+Slicing with string indexing also honors UTC offset.
+
+.. ipython:: python
+
+    df = pd.DataFrame([0], index=pd.DatetimeIndex(['2019-01-01'], tz='US/Pacific'))
+    df
+    df['2019-01-01 12:00:00+04:00':'2019-01-01 13:00:00+04:00']
+
 .. _timeseries.slice_vs_exact_match:
 
 Slice vs. Exact Match

doc/source/user_guide/timeseries.rst

@@ -23,9 +23,13 @@ Fixed Regressions
 - Fixed regression in :meth:`DataFrame.all` and :meth:`DataFrame.any` where ``bool_only=True`` was ignored (:issue:`25101`)
 - Fixed issue in ``DataFrame`` construction with passing a mixed list of mixed types could segfault. (:issue:`25075`)
 - Fixed regression in :meth:`DataFrame.apply` causing ``RecursionError`` when ``dict``-like classes were passed as argument. (:issue:`25196`)
+- Fixed regression in :meth:`DataFrame.replace` where ``regex=True`` was only replacing patterns matching the start of the string (:issue:`25259`)
 
 - Fixed regression in :meth:`DataFrame.duplicated()`, where empty dataframe was not returning a boolean dtyped Series. (:issue:`25184`)
 - Fixed regression in :meth:`Series.min` and :meth:`Series.max` where ``numeric_only=True`` was ignored when the ``Series`` contained ```Categorical`` data (:issue:`25299`)
+- Fixed regression in subtraction between :class:`Series` objects with ``datetime64[ns]`` dtype incorrectly raising ``OverflowError`` when the `Series` on the right contains null values (:issue:`25317`)
+- Fixed regression in :class:`TimedeltaIndex` where `np.sum(index)` incorrectly returned a zero-dimensional object instead of a scalar (:issue:`25282`)
+- Fixed regression in ``IntervalDtype`` construction where passing an incorrect string with 'Interval' as a prefix could result in a ``RecursionError``. (:issue:`25338`)
 
 .. _whatsnew_0242.enhancements:
 
@@ -93,7 +97,7 @@ Bug Fixes
 **Other**
 
 - Bug in :meth:`Series.is_unique` where single occurrences of ``NaN`` were not considered unique (:issue:`25180`)
--
+- Bug in :func:`merge` when merging an empty ``DataFrame`` with an ``Int64`` column or a non-empty ``DataFrame`` with an ``Int64`` column that is all ``NaN`` (:issue:`25183`)
 -
 
 .. _whatsnew_0.242.contributors: