Merge remote-tracking branch 'upstream/master' into pd-todatetime-unit_s-float-vs-int

Author: arw2019

Makefile

@@ -32,3 +32,9 @@ check:
 		--included-file-extensions="py" \
 		--excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored \
 		pandas/
+
+	python3 scripts/validate_unwanted_patterns.py \
+		--validation-type="private_import_across_module" \
+		--included-file-extensions="py" \
+		--excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored,doc/
+		pandas/

asv_bench/benchmarks/groupby.py

@@ -627,49 +627,63 @@ def time_first(self):
 
 
 class TransformEngine:
-    def setup(self):
+
+    param_names = ["parallel"]
+    params = [[True, False]]
+
+    def setup(self, parallel):
         N = 10 ** 3
         data = DataFrame(
             {0: [str(i) for i in range(100)] * N, 1: list(range(100)) * N},
             columns=[0, 1],
         )
+        self.parallel = parallel
         self.grouper = data.groupby(0)
 
-    def time_series_numba(self):
+    def time_series_numba(self, parallel):
         def function(values, index):
             return values * 5
 
-        self.grouper[1].transform(function, engine="numba")
+        self.grouper[1].transform(
+            function, engine="numba", engine_kwargs={"parallel": self.parallel}
+        )
 
-    def time_series_cython(self):
+    def time_series_cython(self, parallel):
         def function(values):
             return values * 5
 
         self.grouper[1].transform(function, engine="cython")
 
-    def time_dataframe_numba(self):
+    def time_dataframe_numba(self, parallel):
         def function(values, index):
             return values * 5
 
-        self.grouper.transform(function, engine="numba")
+        self.grouper.transform(
+            function, engine="numba", engine_kwargs={"parallel": self.parallel}
+        )
 
-    def time_dataframe_cython(self):
+    def time_dataframe_cython(self, parallel):
         def function(values):
             return values * 5
 
         self.grouper.transform(function, engine="cython")
 
 
 class AggEngine:
-    def setup(self):
+
+    param_names = ["parallel"]
+    params = [[True, False]]
+
+    def setup(self, parallel):
         N = 10 ** 3
         data = DataFrame(
             {0: [str(i) for i in range(100)] * N, 1: list(range(100)) * N},
             columns=[0, 1],
         )
+        self.parallel = parallel
         self.grouper = data.groupby(0)
 
-    def time_series_numba(self):
+    def time_series_numba(self, parallel):
         def function(values, index):
             total = 0
             for i, value in enumerate(values):
@@ -679,9 +693,11 @@ def function(values, index):
                     total += value * 2
             return total
 
-        self.grouper[1].agg(function, engine="numba")
+        self.grouper[1].agg(
+            function, engine="numba", engine_kwargs={"parallel": self.parallel}
+        )
 
-    def time_series_cython(self):
+    def time_series_cython(self, parallel):
         def function(values):
             total = 0
             for i, value in enumerate(values):
@@ -693,7 +709,7 @@ def function(values):
 
         self.grouper[1].agg(function, engine="cython")
 
-    def time_dataframe_numba(self):
+    def time_dataframe_numba(self, parallel):
         def function(values, index):
             total = 0
             for i, value in enumerate(values):
@@ -703,9 +719,11 @@ def function(values, index):
                     total += value * 2
             return total
 
-        self.grouper.agg(function, engine="numba")
+        self.grouper.agg(
+            function, engine="numba", engine_kwargs={"parallel": self.parallel}
+        )
 
-    def time_dataframe_cython(self):
+    def time_dataframe_cython(self, parallel):
         def function(values):
             total = 0
             for i, value in enumerate(values):

ci/build39.sh

@@ -3,16 +3,9 @@
 
 sudo apt-get install build-essential gcc xvfb
 pip install --no-deps -U pip wheel setuptools
-pip install python-dateutil pytz pytest pytest-xdist hypothesis
+pip install numpy python-dateutil pytz pytest pytest-xdist hypothesis
 pip install cython --pre # https://github.com/cython/cython/issues/3395
 
-git clone https://github.com/numpy/numpy
-cd numpy
-python setup.py build_ext --inplace
-python setup.py install
-cd ..
-rm -rf numpy
-
 python setup.py build_ext -inplace
 python -m pip install --no-build-isolation -e .
 

ci/code_checks.sh

@@ -116,11 +116,19 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     fi
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Check for use of private module attribute access' ; echo $MSG
+    MSG='Check for import of private attributes across modules' ; echo $MSG
     if [[ "$GITHUB_ACTIONS" == "true" ]]; then
-        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored --format="##[error]{source_path}:{line_number}:{msg}" pandas/
+        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored --format="##[error]{source_path}:{line_number}:{msg}" pandas/
     else
-        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored pandas/
+        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_import_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored pandas/
+    fi
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
+    MSG='Check for use of private functions across modules' ; echo $MSG
+    if [[ "$GITHUB_ACTIONS" == "true" ]]; then
+        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored,doc/ --format="##[error]{source_path}:{line_number}:{msg}" pandas/
+    else
+        $BASE_DIR/scripts/validate_unwanted_patterns.py --validation-type="private_function_across_module" --included-file-extensions="py" --excluded-file-paths=pandas/tests,asv_bench/,pandas/_vendored,doc/ pandas/
     fi
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 

doc/source/development/extending.rst

@@ -73,8 +73,6 @@ applies only to certain dtypes.
 Extension types
 ---------------
 
-.. versionadded:: 0.23.0
-
 .. warning::
 
    The :class:`pandas.api.extensions.ExtensionDtype` and :class:`pandas.api.extensions.ExtensionArray` APIs are new and

doc/source/getting_started/install.rst

@@ -301,8 +301,6 @@ Optional dependencies for parsing HTML
 One of the following combinations of libraries is needed to use the
 top-level :func:`~pandas.read_html` function:
 
-.. versionchanged:: 0.23.0
-
 * `BeautifulSoup4`_ and `html5lib`_
 * `BeautifulSoup4`_ and `lxml`_
 * `BeautifulSoup4`_ and `html5lib`_ and `lxml`_

doc/source/user_guide/advanced.rst

@@ -1065,8 +1065,6 @@ are closed on.  Intervals are closed on the right side by default.
 
    pd.interval_range(start=0, end=4, closed='neither')
 
-.. versionadded:: 0.23.0
-
 Specifying ``start``, ``end``, and ``periods`` will generate a range of evenly spaced
 intervals from ``start`` to ``end`` inclusively, with ``periods`` number of elements
 in the resulting ``IntervalIndex``:

doc/source/user_guide/basics.rst

@@ -1877,8 +1877,6 @@ different columns.
 By indexes and values
 ~~~~~~~~~~~~~~~~~~~~~
 
-.. versionadded:: 0.23.0
-
 Strings passed as the ``by`` parameter to :meth:`DataFrame.sort_values` may
 refer to either columns or index level names.
 

doc/source/user_guide/categorical.rst

@@ -112,8 +112,6 @@ only labels present in a given column are categories:
     df['B']
 
 
-.. versionadded:: 0.23.0
-
 Analogously, all columns in an existing ``DataFrame`` can be batch converted using :meth:`DataFrame.astype`:
 
 .. ipython:: python

doc/source/user_guide/dsintro.rst

@@ -597,8 +597,6 @@ to be inserted (for example, a ``Series`` or NumPy array), or a function
 of one argument to be called on the ``DataFrame``. A *copy* of the original
 DataFrame is returned, with the new values inserted.
 
-.. versionchanged:: 0.23.0
-
 Starting with Python 3.6 the order of ``**kwargs`` is preserved. This allows
 for *dependent* assignment, where an expression later in ``**kwargs`` can refer
 to a column created earlier in the same :meth:`~DataFrame.assign`.