Merge branch 'main' into dep_excel

Author: phofl

doc/source/reference/arrays.rst

@@ -630,7 +630,6 @@ Data type introspection
     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

doc/source/user_guide/io.rst

@@ -2111,8 +2111,6 @@ is ``None``. To explicitly force ``Series`` parsing, pass ``typ=series``
 * ``convert_axes`` : boolean, try to convert the axes to the proper dtypes, default is ``True``
 * ``convert_dates`` : a list of columns to parse for dates; If ``True``, then try to parse date-like columns, default is ``True``.
 * ``keep_default_dates`` : boolean, default ``True``. If parsing dates, then parse the default date-like columns.
-* ``numpy`` : direct decoding to NumPy arrays. default is ``False``;
-  Supports numeric data only, although labels may be non-numeric. Also note that the JSON ordering **MUST** be the same for each term if ``numpy=True``.
 * ``precise_float`` : boolean, default ``False``. Set to enable usage of higher precision (strtod) function when decoding string to double values. Default (``False``) is to use fast but less precise builtin functionality.
 * ``date_unit`` : string, the timestamp unit to detect if converting dates. Default
   None. By default the timestamp precision will be detected, if this is not desired
@@ -2216,74 +2214,6 @@ Dates written in nanoseconds need to be read back in nanoseconds:
    dfju = pd.read_json(json, date_unit="ns")
    dfju
 
-The Numpy parameter
-+++++++++++++++++++
-
-.. note::
-  This param has been deprecated as of version 1.0.0 and will raise a ``FutureWarning``.
-
-  This supports numeric data only. Index and columns labels may be non-numeric, e.g. strings, dates etc.
-
-If ``numpy=True`` is passed to ``read_json`` an attempt will be made to sniff
-an appropriate dtype during deserialization and to subsequently decode directly
-to NumPy arrays, bypassing the need for intermediate Python objects.
-
-This can provide speedups if you are deserialising a large amount of numeric
-data:
-
-.. ipython:: python
-
-   randfloats = np.random.uniform(-100, 1000, 10000)
-   randfloats.shape = (1000, 10)
-   dffloats = pd.DataFrame(randfloats, columns=list("ABCDEFGHIJ"))
-
-   jsonfloats = dffloats.to_json()
-
-.. ipython:: python
-
-   %timeit pd.read_json(jsonfloats)
-
-.. ipython:: python
-   :okwarning:
-
-   %timeit pd.read_json(jsonfloats, numpy=True)
-
-The speedup is less noticeable for smaller datasets:
-
-.. ipython:: python
-
-   jsonfloats = dffloats.head(100).to_json()
-
-.. ipython:: python
-
-   %timeit pd.read_json(jsonfloats)
-
-.. ipython:: python
-   :okwarning:
-
-   %timeit pd.read_json(jsonfloats, numpy=True)
-
-.. warning::
-
-   Direct NumPy decoding makes a number of assumptions and may fail or produce
-   unexpected output if these assumptions are not satisfied:
-
-    - data is numeric.
-
-    - data is uniform. The dtype is sniffed from the first value decoded.
-      A ``ValueError`` may be raised, or incorrect output may be produced
-      if this condition is not satisfied.
-
-    - labels are ordered. Labels are only read from the first container, it is assumed
-      that each subsequent row / column has been encoded in the same order. This should be satisfied if the
-      data was encoded using ``to_json`` but may not be the case if the JSON
-      is from another source.
-
-.. ipython:: python
-   :suppress:
-
-   os.remove("test.json")
-
 .. _io.json_normalize:
 
 Normalization

doc/source/whatsnew/v2.0.0.rst

@@ -144,10 +144,19 @@ Deprecations
 
 Removal of prior version deprecations/changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+- Remove argument ``squeeze`` from :meth:`DataFrame.groupby` and :meth:`Series.groupby` (:issue:`32380`)
+- Removed ``keep_tz`` argument in :meth:`DatetimeIndex.to_series` (:issue:`29731`)
+- Remove arguments ``names`` and ``dtype`` from :meth:`Index.copy` and ``levels`` and ``codes`` from :meth:`MultiIndex.copy` (:issue:`35853`, :issue:`36685`)
+- Removed argument ``try_cast`` from :meth:`DataFrame.mask`, :meth:`DataFrame.where`, :meth:`Series.mask` and :meth:`Series.where` (:issue:`38836`)
 - Disallow passing non-round floats to :class:`Timestamp` with ``unit="M"`` or ``unit="Y"`` (:issue:`47266`)
 - Remove keywords ``convert_float`` and ``mangle_dupe_cols`` from :func:`read_excel` (:issue:`41176`)
 - Disallow passing non-keyword arguments to :func:`read_excel` except ``io`` and ``sheet_name`` (:issue:`34418`)
+- Removed the ``numeric_only`` keyword from :meth:`Categorical.min` and :meth:`Categorical.max` in favor of ``skipna`` (:issue:`48821`)
+- Removed :func:`is_extension_type` in favor of :func:`is_extension_array_dtype` (:issue:`29457`)
 - Remove :meth:`DataFrameGroupBy.pad` and :meth:`DataFrameGroupBy.backfill` (:issue:`45076`)
+- Remove ``numpy`` argument from :func:`read_json` (:issue:`30636`)
+- Removed the ``center`` keyword in :meth:`DataFrame.expanding` (:issue:`20647`)
+- Enforced :meth:`Rolling.count` with ``min_periods=None`` to default to the size of the window (:issue:`31302`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_200.performance:

pandas/_libs/src/ujson/python/JSONtoObj.c

@@ -83,12 +83,6 @@ JSOBJ Object_npyNewArrayList(void *prv, void *decoder);
 JSOBJ Object_npyEndArrayList(void *prv, JSOBJ obj);
 int Object_npyArrayListAddItem(void *prv, JSOBJ obj, JSOBJ value);
 
-// labelled support, encode keys and values of JS object into separate numpy
-// arrays
-JSOBJ Object_npyNewObject(void *prv, void *decoder);
-JSOBJ Object_npyEndObject(void *prv, JSOBJ obj);
-int Object_npyObjectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value);
-
 // free the numpy context buffer
 void Npy_releaseContext(NpyArrContext *npyarr) {
     PRINTMARK();
@@ -374,68 +368,6 @@ int Object_npyArrayListAddItem(void *prv, JSOBJ obj, JSOBJ value) {
     return 1;
 }
 
-JSOBJ Object_npyNewObject(void *prv, void *_decoder) {
-    PyObjectDecoder *decoder = (PyObjectDecoder *)_decoder;
-    PRINTMARK();
-    if (decoder->curdim > 1) {
-        PyErr_SetString(PyExc_ValueError,
-                        "labels only supported up to 2 dimensions");
-        return NULL;
-    }
-
-    return ((JSONObjectDecoder *)decoder)->newArray(prv, decoder);
-}
-
-JSOBJ Object_npyEndObject(void *prv, JSOBJ obj) {
-    PyObject *list;
-    npy_intp labelidx;
-    NpyArrContext *npyarr = (NpyArrContext *)obj;
-    PRINTMARK();
-    if (!npyarr) {
-        return NULL;
-    }
-
-    labelidx = npyarr->dec->curdim - 1;
-
-    list = npyarr->labels[labelidx];
-    if (list) {
-        npyarr->labels[labelidx] = PyArray_FROM_O(list);
-        Py_DECREF(list);
-    }
-
-    return (PyObject *)((JSONObjectDecoder *)npyarr->dec)->endArray(prv, obj);
-}
-
-int Object_npyObjectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value) {
-    PyObject *label, *labels;
-    npy_intp labelidx;
-    // add key to label array, value to values array
-    NpyArrContext *npyarr = (NpyArrContext *)obj;
-    PRINTMARK();
-    if (!npyarr) {
-        return 0;
-    }
-
-    label = (PyObject *)name;
-    labelidx = npyarr->dec->curdim - 1;
-
-    if (!npyarr->labels[labelidx]) {
-        npyarr->labels[labelidx] = PyList_New(0);
-    }
-    labels = npyarr->labels[labelidx];
-    // only fill label array once, assumes all column labels are the same
-    // for 2-dimensional arrays.
-    if (PyList_Check(labels) && PyList_GET_SIZE(labels) <= npyarr->elcount) {
-        PyList_Append(labels, label);
-    }
-
-    if (((JSONObjectDecoder *)npyarr->dec)->arrayAddItem(prv, obj, value)) {
-        Py_DECREF(label);
-        return 1;
-    }
-    return 0;
-}
-
 int Object_objectAddKey(void *prv, JSOBJ obj, JSOBJ name, JSOBJ value) {
     int ret = PyDict_SetItem(obj, name, value);
     Py_DECREF((PyObject *)name);
@@ -494,7 +426,7 @@ static void Object_releaseObject(void *prv, JSOBJ obj, void *_decoder) {
     }
 }
 
-static char *g_kwlist[] = {"obj",      "precise_float", "numpy",
+static char *g_kwlist[] = {"obj",      "precise_float",
                            "labelled", "dtype",         NULL};
 
 PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
@@ -505,7 +437,7 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     JSONObjectDecoder *decoder;
     PyObjectDecoder pyDecoder;
     PyArray_Descr *dtype = NULL;
-    int numpy = 0, labelled = 0;
+    int labelled = 0;
 
     JSONObjectDecoder dec = {
         Object_newString, Object_objectAddKey,  Object_arrayAddItem,
@@ -528,7 +460,7 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     decoder = (JSONObjectDecoder *)&pyDecoder;
 
     if (!PyArg_ParseTupleAndKeywords(args, kwargs, "O|OiiO&", g_kwlist, &arg,
-                                     &opreciseFloat, &numpy, &labelled,
+                                     &opreciseFloat, &labelled,
                                      PyArray_DescrConverter2, &dtype)) {
         Npy_releaseContext(pyDecoder.npyarr);
         return NULL;
@@ -554,19 +486,6 @@ PyObject *JSONToObj(PyObject *self, PyObject *args, PyObject *kwargs) {
     decoder->errorStr = NULL;
     decoder->errorOffset = NULL;
 
-    if (numpy) {
-        pyDecoder.dtype = dtype;
-        decoder->newArray = Object_npyNewArray;
-        decoder->endArray = Object_npyEndArray;
-        decoder->arrayAddItem = Object_npyArrayAddItem;
-
-        if (labelled) {
-            decoder->newObject = Object_npyNewObject;
-            decoder->endObject = Object_npyEndObject;
-            decoder->objectAddKey = Object_npyObjectAddKey;
-        }
-    }
-
     ret = JSON_DecodeObject(decoder, PyBytes_AS_STRING(sarg),
                             PyBytes_GET_SIZE(sarg));
 

pandas/conftest.py

@@ -155,7 +155,6 @@ def pytest_collection_modifyitems(items, config) -> None:
         ("Series.append", "The series.append method is deprecated"),
         ("dtypes.common.is_categorical", "is_categorical is deprecated"),
         ("Categorical.replace", "Categorical.replace is deprecated"),
-        ("dtypes.common.is_extension_type", "'is_extension_type' is deprecated"),
         ("Index.is_mixed", "Index.is_mixed is deprecated"),
         ("MultiIndex._is_lexsorted", "MultiIndex.is_lexsorted is deprecated"),
         # Docstring divides by zero to show behavior difference

pandas/core/algorithms.py

@@ -462,13 +462,13 @@ def isin(comps: AnyArrayLike, values: AnyArrayLike) -> npt.NDArray[np.bool_]:
         )
 
     if not isinstance(values, (ABCIndex, ABCSeries, ABCExtensionArray, np.ndarray)):
-        orig_values = values
-        values = _ensure_arraylike(list(values))
+        orig_values = list(values)
+        values = _ensure_arraylike(orig_values)
 
         if is_numeric_dtype(values) and not is_signed_integer_dtype(comps):
             # GH#46485 Use object to avoid upcast to float64 later
             # TODO: Share with _find_common_type_compat
-            values = construct_1d_object_array_from_listlike(list(orig_values))
+            values = construct_1d_object_array_from_listlike(orig_values)
 
     elif isinstance(values, ABCMultiIndex):
         # Avoid raising in extract_array

pandas/core/arrays/categorical.py

@@ -48,10 +48,7 @@
     type_t,
 )
 from pandas.compat.numpy import function as nv
-from pandas.util._decorators import (
-    deprecate_kwarg,
-    deprecate_nonkeyword_arguments,
-)
+from pandas.util._decorators import deprecate_nonkeyword_arguments
 from pandas.util._exceptions import find_stack_level
 from pandas.util._validators import validate_bool_kwarg
 
@@ -2313,7 +2310,6 @@ def _reverse_indexer(self) -> dict[Hashable, npt.NDArray[np.intp]]:
     # ------------------------------------------------------------------
     # Reductions
 
-    @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
     def min(self, *, skipna: bool = True, **kwargs):
         """
         The minimum value of the object.
@@ -2350,7 +2346,6 @@ def min(self, *, skipna: bool = True, **kwargs):
             pointer = self._codes.min()
         return self._wrap_reduction_result(None, pointer)
 
-    @deprecate_kwarg(old_arg_name="numeric_only", new_arg_name="skipna")
     def max(self, *, skipna: bool = True, **kwargs):
         """
         The maximum value of the object.

pandas/core/arrays/sparse/array.py

@@ -1383,7 +1383,7 @@ def map(self: SparseArrayT, mapper) -> SparseArrayT:
         Indices: array([1, 2], dtype=int32)
         """
         # this is used in apply.
-        # We get hit since we're an "is_extension_type" but regular extension
+        # We get hit since we're an "is_extension_array_dtype" but regular extension
         # types are not hit. This may be worth adding to the interface.
         if isinstance(mapper, ABCSeries):
             mapper = mapper.to_dict()

pandas/core/dtypes/api.py

@@ -13,7 +13,6 @@
     is_dict_like,
     is_dtype_equal,
     is_extension_array_dtype,
-    is_extension_type,
     is_file_like,
     is_float,
     is_float_dtype,
@@ -57,7 +56,6 @@
     "is_dict_like",
     "is_dtype_equal",
     "is_extension_array_dtype",
-    "is_extension_type",
     "is_file_like",
     "is_float",
     "is_float_dtype",

pandas/core/dtypes/common.py

@@ -1336,71 +1336,6 @@ def is_bool_dtype(arr_or_dtype) -> bool:
     return issubclass(dtype.type, np.bool_)
 
 
-def is_extension_type(arr) -> bool:
-    """
-    Check whether an array-like is of a pandas extension class instance.
-
-    .. deprecated:: 1.0.0
-        Use ``is_extension_array_dtype`` instead.
-
-    Extension classes include categoricals, pandas sparse objects (i.e.
-    classes represented within the pandas library and not ones external
-    to it like scipy sparse matrices), and datetime-like arrays.
-
-    Parameters
-    ----------
-    arr : array-like, scalar
-        The array-like to check.
-
-    Returns
-    -------
-    boolean
-        Whether or not the array-like is of a pandas extension class instance.
-
-    Examples
-    --------
-    >>> is_extension_type([1, 2, 3])
-    False
-    >>> is_extension_type(np.array([1, 2, 3]))
-    False
-    >>>
-    >>> cat = pd.Categorical([1, 2, 3])
-    >>>
-    >>> is_extension_type(cat)
-    True
-    >>> is_extension_type(pd.Series(cat))
-    True
-    >>> is_extension_type(pd.arrays.SparseArray([1, 2, 3]))
-    True
-    >>> from scipy.sparse import bsr_matrix
-    >>> is_extension_type(bsr_matrix([1, 2, 3]))
-    False
-    >>> is_extension_type(pd.DatetimeIndex([1, 2, 3]))
-    False
-    >>> is_extension_type(pd.DatetimeIndex([1, 2, 3], tz="US/Eastern"))
-    True
-    >>>
-    >>> dtype = DatetimeTZDtype("ns", tz="US/Eastern")
-    >>> s = pd.Series([], dtype=dtype)
-    >>> is_extension_type(s)
-    True
-    """
-    warnings.warn(
-        "'is_extension_type' is deprecated and will be removed in a future "
-        "version.  Use 'is_extension_array_dtype' instead.",
-        FutureWarning,
-        stacklevel=find_stack_level(),
-    )
-
-    if is_categorical_dtype(arr):
-        return True
-    elif is_sparse(arr):
-        return True
-    elif is_datetime64tz_dtype(arr):
-        return True
-    return False
-
-
 def is_1d_only_ea_obj(obj: Any) -> bool:
     """
     ExtensionArray that does not support 2D, or more specifically that does
@@ -1853,7 +1788,6 @@ def is_all_strings(value: ArrayLike) -> bool:
     "is_dtype_equal",
     "is_ea_or_datetimelike_dtype",
     "is_extension_array_dtype",
-    "is_extension_type",
     "is_file_like",
     "is_float_dtype",
     "is_int64_dtype",