Merge branch 'master' into 3698-dask-optimize

Author: max-sixty

ci/requirements/doc.yml

@@ -18,9 +18,7 @@ dependencies:
   - netcdf4>=1.5
   - numba
   - numpy>=1.17
-  # FIXME https://github.com/pydata/xarray/issues/4287
-  # - pandas>=1.0
-  - pandas=1.0
+  - pandas>=1.0
   - rasterio>=1.1
   - seaborn
   - setuptools

conftest.py

@@ -24,7 +24,7 @@ def pytest_runtest_setup(item):
 
 
 @pytest.fixture(autouse=True)
-def add_standard_imports(doctest_namespace):
+def add_standard_imports(doctest_namespace, tmpdir):
     import numpy as np
     import pandas as pd
 
@@ -33,3 +33,9 @@ def add_standard_imports(doctest_namespace):
     doctest_namespace["np"] = np
     doctest_namespace["pd"] = pd
     doctest_namespace["xr"] = xr
+
+    # always seed numpy.random to make the examples deterministic
+    np.random.seed(0)
+
+    # always switch to the temporary directory, so files get written there
+    tmpdir.chdir()

doc/related-projects.rst

@@ -58,6 +58,7 @@ Other domains
 ~~~~~~~~~~~~~
 - `ptsa <https://pennmem.github.io/ptsa_new/html/index.html>`_: EEG Time Series Analysis
 - `pycalphad <https://pycalphad.org/docs/latest/>`_: Computational Thermodynamics in Python
+- `pyomeca <https://pyomeca.github.io/>`_: Python framework for biomechanical analysis
 
 Extend xarray capabilities
 ~~~~~~~~~~~~~~~~~~~~~~~~~~

doc/whats-new.rst

@@ -85,6 +85,12 @@ Bug fixes
   that contains NaNs (:pull:`4233`).
   By `Jens Svensmark <https://github.com/jenssss>`_
 - Fix ``dask.optimize`` on ``DataArray`` producing an invalid Dask task graph (:issue:`3698`)
+- Fix incorrect legend labels for :py:meth:`Dataset.plot.scatter` (:issue:`4126`).
+  By `Peter Hausamann <https://github.com/phausamann>`_.
+- Fix indexing with datetime64 scalars with pandas 1.1 (:issue:`4283`).
+  By `Stephan Hoyer <https://github.com/shoyer>`_ and
+  `Justus Magin <https://github.com/keewis>`_.
+  
 
 Documentation
 ~~~~~~~~~~~~~

xarray/backends/api.py

@@ -1189,6 +1189,17 @@ def save_mfdataset(
 
     Save a dataset into one netCDF per year of data:
 
+    >>> ds = xr.Dataset(
+    ...     {"a": ("time", np.linspace(0, 1, 48))},
+    ...     coords={"time": pd.date_range("2010-01-01", freq="M", periods=48)},
+    ... )
+    >>> ds
+    <xarray.Dataset>
+    Dimensions:  (time: 48)
+    Coordinates:
+      * time     (time) datetime64[ns] 2010-01-31 2010-02-28 ... 2013-12-31
+    Data variables:
+        a        (time) float64 0.0 0.02128 0.04255 0.06383 ... 0.9574 0.9787 1.0
     >>> years, datasets = zip(*ds.groupby("time.year"))
     >>> paths = ["%s.nc" % y for y in years]
     >>> xr.save_mfdataset(datasets, paths)

xarray/coding/cftime_offsets.py

@@ -939,7 +939,7 @@ def cftime_range(
     >>> xr.cftime_range(start="2000", periods=6, freq="2MS", calendar="noleap")
     CFTimeIndex([2000-01-01 00:00:00, 2000-03-01 00:00:00, 2000-05-01 00:00:00,
                  2000-07-01 00:00:00, 2000-09-01 00:00:00, 2000-11-01 00:00:00],
-                dtype='object')
+                dtype='object', length=6, calendar='noleap')
 
     As in the standard pandas function, three of the ``start``, ``end``,
     ``periods``, or ``freq`` arguments must be specified at a given time, with

xarray/coding/cftimeindex.py

@@ -523,9 +523,11 @@ def shift(self, n, freq):
         --------
         >>> index = xr.cftime_range("2000", periods=1, freq="M")
         >>> index
-        CFTimeIndex([2000-01-31 00:00:00], dtype='object')
+        CFTimeIndex([2000-01-31 00:00:00],
+                    dtype='object', length=1, calendar='gregorian')
         >>> index.shift(1, "M")
-        CFTimeIndex([2000-02-29 00:00:00], dtype='object')
+        CFTimeIndex([2000-02-29 00:00:00],
+                    dtype='object', length=1, calendar='gregorian')
         """
         from .cftime_offsets import to_offset
 
@@ -611,7 +613,8 @@ def to_datetimeindex(self, unsafe=False):
         >>> import xarray as xr
         >>> times = xr.cftime_range("2000", periods=2, calendar="gregorian")
         >>> times
-        CFTimeIndex([2000-01-01 00:00:00, 2000-01-02 00:00:00], dtype='object')
+        CFTimeIndex([2000-01-01 00:00:00, 2000-01-02 00:00:00],
+                    dtype='object', length=2, calendar='gregorian')
         >>> times.to_datetimeindex()
         DatetimeIndex(['2000-01-01', '2000-01-02'], dtype='datetime64[ns]', freq=None)
         """

xarray/coding/strings.py

@@ -199,9 +199,9 @@ class StackedBytesArray(indexing.ExplicitlyIndexedNDArrayMixin):
     """Wrapper around array-like objects to create a new indexable object where
     values, when accessed, are automatically stacked along the last dimension.
 
-    >>> StackedBytesArray(np.array(["a", "b", "c"]))[:]
-    array('abc',
-          dtype='|S3')
+    >>> indexer = indexing.BasicIndexer((slice(None),))
+    >>> StackedBytesArray(np.array(["a", "b", "c"], dtype="S1"))[indexer]
+    array(b'abc', dtype='|S3')
     """
 
     def __init__(self, array):

xarray/conventions.py

@@ -24,10 +24,11 @@ class NativeEndiannessArray(indexing.ExplicitlyIndexedNDArrayMixin):
     >>> x.dtype
     dtype('>i2')
 
-    >>> NativeEndianArray(x).dtype
+    >>> NativeEndiannessArray(x).dtype
     dtype('int16')
 
-    >>> NativeEndianArray(x)[:].dtype
+    >>> indexer = indexing.BasicIndexer((slice(None),))
+    >>> NativeEndiannessArray(x)[indexer].dtype
     dtype('int16')
     """
 
@@ -53,12 +54,13 @@ class BoolTypeArray(indexing.ExplicitlyIndexedNDArrayMixin):
     >>> x = np.array([1, 0, 1, 1, 0], dtype="i1")
 
     >>> x.dtype
-    dtype('>i2')
+    dtype('int8')
 
     >>> BoolTypeArray(x).dtype
     dtype('bool')
 
-    >>> BoolTypeArray(x)[:].dtype
+    >>> indexer = indexing.BasicIndexer((slice(None),))
+    >>> BoolTypeArray(x)[indexer].dtype
     dtype('bool')
     """
 

xarray/core/accessor_dt.py

@@ -249,30 +249,30 @@ class DatetimeAccessor(Properties):
     >>> ts
     <xarray.DataArray (time: 10)>
     array(['2000-01-01T00:00:00.000000000', '2000-01-02T00:00:00.000000000',
-        '2000-01-03T00:00:00.000000000', '2000-01-04T00:00:00.000000000',
-        '2000-01-05T00:00:00.000000000', '2000-01-06T00:00:00.000000000',
-        '2000-01-07T00:00:00.000000000', '2000-01-08T00:00:00.000000000',
-        '2000-01-09T00:00:00.000000000', '2000-01-10T00:00:00.000000000'],
-        dtype='datetime64[ns]')
+           '2000-01-03T00:00:00.000000000', '2000-01-04T00:00:00.000000000',
+           '2000-01-05T00:00:00.000000000', '2000-01-06T00:00:00.000000000',
+           '2000-01-07T00:00:00.000000000', '2000-01-08T00:00:00.000000000',
+           '2000-01-09T00:00:00.000000000', '2000-01-10T00:00:00.000000000'],
+          dtype='datetime64[ns]')
     Coordinates:
-    * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
-    >>> ts.dt
-    <xarray.core.accessor_dt.DatetimeAccessor object at 0x118b54d68>
+      * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
+    >>> ts.dt  # doctest: +ELLIPSIS
+    <xarray.core.accessor_dt.DatetimeAccessor object at 0x...>
     >>> ts.dt.dayofyear
     <xarray.DataArray 'dayofyear' (time: 10)>
     array([ 1,  2,  3,  4,  5,  6,  7,  8,  9, 10])
     Coordinates:
-    * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
+      * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
     >>> ts.dt.quarter
     <xarray.DataArray 'quarter' (time: 10)>
     array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
     Coordinates:
-    * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
+      * time     (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2000-01-10
 
     """
 
     def strftime(self, date_format):
-        '''
+        """
         Return an array of formatted strings specified by date_format, which
         supports the same string format as the python standard library. Details
         of the string format can be found in `python string format doc
@@ -290,13 +290,12 @@ def strftime(self, date_format):
 
         Examples
         --------
+        >>> import datetime
         >>> rng = xr.Dataset({"time": datetime.datetime(2000, 1, 1)})
         >>> rng["time"].dt.strftime("%B %d, %Y, %r")
         <xarray.DataArray 'strftime' ()>
         array('January 01, 2000, 12:00:00 AM', dtype=object)
         """
-
-        '''
         obj_type = type(self._obj)
 
         result = _strftime(self._obj.data, date_format)
@@ -398,32 +397,32 @@ class TimedeltaAccessor(Properties):
     >>> ts
     <xarray.DataArray (time: 20)>
     array([ 86400000000000, 108000000000000, 129600000000000, 151200000000000,
-        172800000000000, 194400000000000, 216000000000000, 237600000000000,
-        259200000000000, 280800000000000, 302400000000000, 324000000000000,
-        345600000000000, 367200000000000, 388800000000000, 410400000000000,
-        432000000000000, 453600000000000, 475200000000000, 496800000000000],
-        dtype='timedelta64[ns]')
+           172800000000000, 194400000000000, 216000000000000, 237600000000000,
+           259200000000000, 280800000000000, 302400000000000, 324000000000000,
+           345600000000000, 367200000000000, 388800000000000, 410400000000000,
+           432000000000000, 453600000000000, 475200000000000, 496800000000000],
+          dtype='timedelta64[ns]')
     Coordinates:
-    * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
-    >>> ts.dt
-    <xarray.core.accessor_dt.TimedeltaAccessor object at 0x109a27d68>
+      * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
+    >>> ts.dt  # doctest: +ELLIPSIS
+    <xarray.core.accessor_dt.TimedeltaAccessor object at 0x...>
     >>> ts.dt.days
     <xarray.DataArray 'days' (time: 20)>
     array([1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 5, 5, 5, 5])
     Coordinates:
-    * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
+      * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
     >>> ts.dt.microseconds
     <xarray.DataArray 'microseconds' (time: 20)>
     array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0])
     Coordinates:
-    * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
+      * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
     >>> ts.dt.seconds
     <xarray.DataArray 'seconds' (time: 20)>
     array([    0, 21600, 43200, 64800,     0, 21600, 43200, 64800,     0,
-        21600, 43200, 64800,     0, 21600, 43200, 64800,     0, 21600,
-        43200, 64800])
+           21600, 43200, 64800,     0, 21600, 43200, 64800,     0, 21600,
+           43200, 64800])
     Coordinates:
-    * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
+      * time     (time) timedelta64[ns] 1 days 00:00:00 ... 5 days 18:00:00
     """
 
     days = Properties._tslib_field_accessor(