merge in main that now has offsets

Author: Dr-Irv

.github/workflows/posix.yml

@@ -28,7 +28,7 @@ jobs:
         pattern: ["not single_cpu", "single_cpu"]
         # Don't test pyarrow v2/3: Causes timeouts in read_csv engine
         # even if tests are skipped/xfailed
-        pyarrow_version: ["5", "6", "7"]
+        pyarrow_version: ["5", "7"]
         include:
           - env_file: actions-38-downstream_compat.yaml
             pattern: "not slow and not network and not single_cpu"

.pre-commit-config.yaml

@@ -178,7 +178,7 @@ repos:
         language: python
         files: ^pandas/core/generic\.py$
     -   id: pandas-errors-documented
-        name: Ensure pandas errors are documented in doc/source/reference/general_utility_functions.rst
+        name: Ensure pandas errors are documented in doc/source/reference/testing.rst
         entry: python scripts/pandas_errors_documented.py
         language: python
         files: ^pandas/errors/__init__.py$

asv_bench/benchmarks/groupby.py

@@ -18,6 +18,7 @@
 
 method_blocklist = {
     "object": {
+        "diff",
         "median",
         "prod",
         "sem",
@@ -405,7 +406,7 @@ class GroupByMethods:
 
     param_names = ["dtype", "method", "application", "ncols"]
     params = [
-        ["int", "float", "object", "datetime", "uint"],
+        ["int", "int16", "float", "object", "datetime", "uint"],
         [
             "all",
             "any",
@@ -417,6 +418,7 @@ class GroupByMethods:
             "cumprod",
             "cumsum",
             "describe",
+            "diff",
             "ffill",
             "first",
             "head",
@@ -478,7 +480,7 @@ def setup(self, dtype, method, application, ncols):
         values = rng.take(taker, axis=0)
         if dtype == "int":
             key = np.random.randint(0, size, size=size)
-        elif dtype == "uint":
+        elif dtype in ("int16", "uint"):
             key = np.random.randint(0, size, size=size, dtype=dtype)
         elif dtype == "float":
             key = np.concatenate(

asv_bench/benchmarks/indexing.py

@@ -290,12 +290,24 @@ def setup(self):
         self.dti = dti
         self.dti2 = dti2
 
+        index = np.random.choice(dti, 10000, replace=True)
+        df = DataFrame(index=index, data={"a": 1})
+        df_sort = df.sort_index()
+        self.df = df
+        self.df_sort = df_sort
+
     def time_get_indexer_mismatched_tz(self):
         # reached via e.g.
         #  ser = Series(range(len(dti)), index=dti)
         #  ser[dti2]
         self.dti.get_indexer(self.dti2)
 
+    def time_loc_unsorted(self):
+        self.df.loc["2016-6-11"]
+
+    def time_loc_sorted(self):
+        self.df_sort.loc["2016-6-11"]
+
 
 class CategoricalIndexIndexing:
 

ci/run_tests.sh

@@ -30,10 +30,6 @@ if [[ "$PATTERN" ]]; then
   PYTEST_CMD="$PYTEST_CMD -m \"$PATTERN\""
 fi
 
-if [[ $(uname) != "Linux"  && $(uname) != "Darwin" ]]; then
-    PYTEST_CMD="$PYTEST_CMD --ignore=pandas/tests/plotting/"
-fi
-
 echo $PYTEST_CMD
 sh -c "$PYTEST_CMD"
 

doc/source/_static/style/footer_extended.png

@@ -26,14 +26,28 @@ with a full pandas development environment.
 
 **Docker Commands**
 
-Pass your GitHub username in the ``DockerFile`` to use your own fork::
+Build the Docker image::
 
     # Build the image pandas-yourname-env
     docker build --tag pandas-yourname-env .
-    # Run a container and bind your local forked repo, pandas-yourname, to the container
-    docker run -it --rm -v path-to-pandas-yourname:/home/pandas-yourname pandas-yourname-env
+    # Or build the image by passing your GitHub username to use your own fork
+    docker build --build-arg gh_username=yourname --tag pandas-yourname-env .
 
-Even easier, you can integrate Docker with the following IDEs:
+Run Container::
+
+    # Run a container and bind your local repo to the container
+    docker run -it -w /home/pandas --rm -v path-to-local-pandas-repo:/home/pandas pandas-yourname-env
+
+.. note::
+    If you bind your local repo for the first time, you have to build the C extensions afterwards.
+    Run the following command inside the container::
+
+        python setup.py build_ext -j 4
+
+    You need to rebuild the C extensions anytime the Cython code in ``pandas/_libs`` changes.
+    This most frequently occurs when changing or merging branches.
+
+*Even easier, you can integrate Docker with the following IDEs:*
 
 **Visual Studio Code**
 
@@ -47,11 +61,6 @@ Enable Docker support and use the Services tool window to build and manage image
 run and interact with containers.
 See https://www.jetbrains.com/help/pycharm/docker.html for details.
 
-Note that you might need to rebuild the C extensions if/when you merge with upstream/main using::
-
-    python setup.py build_ext -j 4
-
-
 Creating an environment without Docker
 ---------------------------------------
 

doc/source/_static/style/footer_simple.png

@@ -6,6 +6,10 @@
 pandas arrays, scalars, and data types
 ======================================
 
+*******
+Objects
+*******
+
 .. currentmodule:: pandas
 
 For most data types, pandas uses NumPy arrays as the concrete
@@ -40,8 +44,8 @@ stored in a :class:`Series`, :class:`Index`, or as a column in a :class:`DataFra
 
 .. _api.arrays.datetime:
 
-Datetime data
--------------
+Datetimes
+---------
 
 NumPy cannot natively represent timezone-aware datetimes. pandas supports this
 with the :class:`arrays.DatetimeArray` extension array, which can hold timezone-naive
@@ -161,8 +165,8 @@ If the data are timezone-aware, then every value in the array must have the same
 
 .. _api.arrays.timedelta:
 
-Timedelta data
---------------
+Timedeltas
+----------
 
 NumPy can natively represent timedeltas. pandas provides :class:`Timedelta`
 for symmetry with :class:`Timestamp`.
@@ -216,8 +220,8 @@ A collection of :class:`Timedelta` may be stored in a :class:`TimedeltaArray`.
 
 .. _api.arrays.period:
 
-Timespan data
--------------
+Periods
+-------
 
 pandas represents spans of times as :class:`Period` objects.
 
@@ -284,8 +288,8 @@ Every period in a :class:`arrays.PeriodArray` must have the same ``freq``.
 
 .. _api.arrays.interval:
 
-Interval data
--------------
+Intervals
+---------
 
 Arbitrary intervals can be represented as :class:`Interval` objects.
 
@@ -379,8 +383,8 @@ pandas provides this through :class:`arrays.IntegerArray`.
 
 .. _api.arrays.categorical:
 
-Categorical data
-----------------
+Categoricals
+------------
 
 pandas defines a custom data type for representing data that can take only a
 limited, fixed set of values. The dtype of a :class:`Categorical` can be described by
@@ -444,8 +448,8 @@ data. See :ref:`api.series.cat` for more.
 
 .. _api.arrays.sparse:
 
-Sparse data
------------
+Sparse
+------
 
 Data where a single value is repeated many times (e.g. ``0`` or ``NaN``) may
 be stored efficiently as a :class:`arrays.SparseArray`.
@@ -469,8 +473,8 @@ and methods if the :class:`Series` contains sparse values. See
 
 .. _api.arrays.string:
 
-Text data
----------
+Strings
+-------
 
 When working with text data, where each valid element is a string or missing,
 we recommend using :class:`StringDtype` (with the alias ``"string"``).
@@ -494,8 +498,8 @@ See :ref:`api.series.str` for more.
 
 .. _api.arrays.bool:
 
-Boolean data with missing values
---------------------------------
+Nullable Boolean
+----------------
 
 The boolean dtype (with the alias ``"boolean"``) provides support for storing
 boolean data (``True``, ``False``) with missing values, which is not possible
@@ -525,3 +529,72 @@ with a bool :class:`numpy.ndarray`.
       DatetimeTZDtype.tz
       PeriodDtype.freq
       IntervalDtype.subtype
+
+*********
+Utilities
+*********
+
+Constructors
+------------
+.. autosummary::
+   :toctree: api/
+
+   api.types.union_categoricals
+   api.types.infer_dtype
+   api.types.pandas_dtype
+
+Data type introspection
+~~~~~~~~~~~~~~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    api.types.is_bool_dtype
+    api.types.is_categorical_dtype
+    api.types.is_complex_dtype
+    api.types.is_datetime64_any_dtype
+    api.types.is_datetime64_dtype
+    api.types.is_datetime64_ns_dtype
+    api.types.is_datetime64tz_dtype
+    api.types.is_extension_type
+    api.types.is_extension_array_dtype
+    api.types.is_float_dtype
+    api.types.is_int64_dtype
+    api.types.is_integer_dtype
+    api.types.is_interval_dtype
+    api.types.is_numeric_dtype
+    api.types.is_object_dtype
+    api.types.is_period_dtype
+    api.types.is_signed_integer_dtype
+    api.types.is_string_dtype
+    api.types.is_timedelta64_dtype
+    api.types.is_timedelta64_ns_dtype
+    api.types.is_unsigned_integer_dtype
+    api.types.is_sparse
+
+Iterable introspection
+~~~~~~~~~~~~~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    api.types.is_dict_like
+    api.types.is_file_like
+    api.types.is_list_like
+    api.types.is_named_tuple
+    api.types.is_iterator
+
+Scalar introspection
+~~~~~~~~~~~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    api.types.is_bool
+    api.types.is_categorical
+    api.types.is_complex
+    api.types.is_float
+    api.types.is_hashable
+    api.types.is_integer
+    api.types.is_interval
+    api.types.is_number
+    api.types.is_re
+    api.types.is_re_compilable
+    api.types.is_scalar

doc/source/development/contributing_environment.rst

@@ -78,10 +78,3 @@ Hashing
 
    util.hash_array
    util.hash_pandas_object
-
-Testing
-~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   test