Merge remote-tracking branch 'upstream/main' into arrow/docs

Author: mroeschke

.github/workflows/codeql.yml

@@ -0,0 +1,31 @@
+name: CodeQL
+on:
+  schedule:
+    # every day at midnight
+    - cron: "0 0 * * *"
+
+concurrency:
+  group: ${{ github.repository }}-${{ github.head_ref || github.sha }}-${{ github.workflow }}
+  cancel-in-progress: true
+
+jobs:
+  analyze:
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language:
+          - python
+
+    steps:
+      - uses: actions/checkout@v3
+      - uses: github/codeql-action/init@v2
+        with:
+          languages: ${{ matrix.language }}
+      - uses: github/codeql-action/autobuild@v2
+      - uses: github/codeql-action/analyze@v2

.pre-commit-config.yaml

@@ -85,32 +85,42 @@ repos:
 -   repo: local
     hooks:
     -   id: pyright
+        # note: assumes python env is setup and activated
         name: pyright
         entry: pyright
-        # note: assumes python env is setup and activated
         language: node
         pass_filenames: false
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
         - [email protected]
     -   id: pyright_reportGeneralTypeIssues
+        # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues
         entry: pyright --skipunannotated -p pyright_reportGeneralTypeIssues.json
-        # note: assumes python env is setup and activated
         language: node
         pass_filenames: false
         types: [python]
         stages: [manual]
         additional_dependencies: *pyright_dependencies
     -   id: mypy
+        # note: assumes python env is setup and activated
         name: mypy
         entry: mypy
-        # note: assumes python env is setup and activated
         language: system
         pass_filenames: false
         types: [python]
         stages: [manual]
+    -   id: stubtest
+        # note: assumes python env is setup and activated
+        # note: requires pandas dev to be installed
+        name: mypy (stubtest)
+        entry: python
+        language: system
+        pass_filenames: false
+        types: [pyi]
+        args: [scripts/run_stubtest.py]
+        stages: [manual]
     -   id: flake8-rst
         name: flake8-rst
         description: Run flake8 on code snippets in docstrings or RST files

ci/code_checks.sh

@@ -78,8 +78,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05
+    MSG='Validate docstrings (EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

doc/source/reference/general_functions.rst

@@ -85,4 +85,4 @@ Importing from other DataFrame libraries
 .. autosummary::
    :toctree: api/
 
-   api.exchange.from_dataframe
+   api.interchange.from_dataframe

pandas/_config/config.py

@@ -102,8 +102,9 @@ class RegisteredOption(NamedTuple):
 
 class OptionError(AttributeError, KeyError):
     """
-    Exception for pandas.options, backwards compatible with KeyError
-    checks.
+    Exception raised for pandas.options.
+
+    Backwards compatible with KeyError checks.
     """
 
 

pandas/_libs/groupby.pyi

@@ -50,7 +50,7 @@ def group_any_all(
     val_test: Literal["any", "all"],
     skipna: bool,
 ) -> None: ...
-def group_add(
+def group_sum(
     out: np.ndarray,  # complexfloating_t[:, ::1]
     counts: np.ndarray,  # int64_t[::1]
     values: np.ndarray,  # ndarray[complexfloating_t, ndim=2]

pandas/_libs/groupby.pyx

@@ -124,7 +124,7 @@ def group_median_float64(
         ndarray[intp_t] indexer
         float64_t* ptr
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     ngroups = len(counts)
     N, K = (<object>values).shape
@@ -502,7 +502,7 @@ def group_any_all(
 
 
 # ----------------------------------------------------------------------
-# group_add, group_prod, group_var, group_mean, group_ohlc
+# group_sum, group_prod, group_var, group_mean, group_ohlc
 # ----------------------------------------------------------------------
 
 ctypedef fused mean_t:
@@ -511,17 +511,17 @@ ctypedef fused mean_t:
     complex64_t
     complex128_t
 
-ctypedef fused add_t:
+ctypedef fused sum_t:
     mean_t
     object
 
 
 @cython.wraparound(False)
 @cython.boundscheck(False)
-def group_add(
-    add_t[:, ::1] out,
+def group_sum(
+    sum_t[:, ::1] out,
     int64_t[::1] counts,
-    ndarray[add_t, ndim=2] values,
+    ndarray[sum_t, ndim=2] values,
     const intp_t[::1] labels,
     Py_ssize_t min_count=0,
     bint is_datetimelike=False,
@@ -531,8 +531,8 @@ def group_add(
     """
     cdef:
         Py_ssize_t i, j, N, K, lab, ncounts = len(counts)
-        add_t val, t, y
-        add_t[:, ::1] sumx, compensation
+        sum_t val, t, y
+        sum_t[:, ::1] sumx, compensation
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
@@ -546,7 +546,7 @@ def group_add(
 
     N, K = (<object>values).shape
 
-    if add_t is object:
+    if sum_t is object:
         # NB: this does not use 'compensation' like the non-object track does.
         for i in range(N):
             lab = labels[i]
@@ -588,10 +588,10 @@ def group_add(
 
                     # not nan
                     # With dt64/td64 values, values have been cast to float64
-                    #  instead if int64 for group_add, but the logic
+                    #  instead if int64 for group_sum, but the logic
                     #  is otherwise the same as in _treat_as_na
                     if val == val and not (
-                        add_t is float64_t
+                        sum_t is float64_t
                         and is_datetimelike
                         and val == <float64_t>NPY_NAT
                     ):
@@ -677,7 +677,7 @@ def group_var(
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len_values != len_labels:
         raise ValueError("len(index) != len(labels)")
@@ -745,7 +745,7 @@ def group_mean(
         Array containing unique label for each group, with its
         ordering matching up to the corresponding record in `values`.
     min_count : Py_ssize_t
-        Only used in add and prod. Always -1.
+        Only used in sum and prod. Always -1.
     is_datetimelike : bool
         True if `values` contains datetime-like entries.
     mask : ndarray[bool, ndim=2], optional
@@ -766,7 +766,7 @@ def group_mean(
         int64_t[:, ::1] nobs
         Py_ssize_t len_values = len(values), len_labels = len(labels)
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len_values != len_labels:
         raise ValueError("len(index) != len(labels)")
@@ -821,7 +821,7 @@ def group_ohlc(
         Py_ssize_t i, j, N, K, lab
         floating val
 
-    assert min_count == -1, "'min_count' only used in add and prod"
+    assert min_count == -1, "'min_count' only used in sum and prod"
 
     if len(labels) == 0:
         return

pandas/_libs/hashtable.pyi

@@ -39,72 +39,72 @@ class Int64Factorizer(Factorizer):
     ) -> npt.NDArray[np.intp]: ...
 
 class Int64Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.int64]: ...
 
 class Int32Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.int32]: ...
 
 class Int16Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.int16]: ...
 
 class Int8Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.int8]: ...
 
 class UInt64Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.uint64]: ...
 
 class UInt32Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.uint32]: ...
 
 class UInt16Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.uint16]: ...
 
 class UInt8Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.uint8]: ...
 
 class Float64Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.float64]: ...
 
 class Float32Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.float32]: ...
 
 class Complex128Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.complex128]: ...
 
 class Complex64Vector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.complex64]: ...
 
 class StringVector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.object_]: ...
 
 class ObjectVector:
-    def __init__(self): ...
+    def __init__(self, *args): ...
     def __len__(self) -> int: ...
     def to_array(self) -> npt.NDArray[np.object_]: ...
 

pandas/_libs/interval.pyx

@@ -352,8 +352,9 @@ cdef class Interval(IntervalMixin):
 
     cdef readonly str inclusive
     """
-    Whether the interval is inclusive on the left-side, right-side, both or
-    neither.
+    String describing the inclusive side the intervals.
+
+    Either ``left``, ``right``, ``both`` or ``neither``.
     """
 
     def __init__(self, left, right, inclusive: str | None = None, closed: None | lib.NoDefault = lib.no_default):
@@ -384,10 +385,11 @@ cdef class Interval(IntervalMixin):
     @property
     def closed(self):
         """
-        Whether the interval is closed on the left-side, right-side, both or
-        neither.
+        String describing the inclusive side the intervals.
 
         .. deprecated:: 1.5.0
+
+        Either ``left``, ``right``, ``both`` or ``neither``.
         """
         warnings.warn(
             "Attribute `closed` is deprecated in favor of `inclusive`.",

pandas/_libs/lib.pyx

@@ -1347,8 +1347,7 @@ cdef object _try_infer_map(object dtype):
 
 def infer_dtype(value: object, skipna: bool = True) -> str:
     """
-    Efficiently infer the type of a passed val, or list-like
-    array of values. Return a string describing the type.
+    Return a string label of the type of a scalar or list-like of values.
 
     Parameters
     ----------