o 5c@sUdZddlmZddlZddlZddlmZmZmZm Z m Z m Z m Z m Z mZmZddlZddlZddlmZddlmZmZmZmZmZmZmZmZmZmZddl m!Z!ddl"m#Z$dd l%m&Z&dd l'm(Z(m)Z)m*Z*m+Z+dd l,m-Z-dd l.m/Z/m0Z0m1Z1dd l2m3Z3ddl4m5Z5m6Z6m7Z7m8Z8ddl9m:Z:ddl;mZ>ddl?m@Z@ddlAmBZBmCZCmDZDddlEmFZFmGZGmHZHmIZImJZJmKZKddlLmMZMddlNmOZOmPZPerGddddZQddlmRZRmSZSiZTdeUd<e dddZVGdddZWGdd d ZXGd!d"d"eXZYdS)#z An interface for extending pandas with custom arrays. .. warning:: This is an experimental API and subject to breaking changes without warning. ) annotationsN) TYPE_CHECKINGAnyCallableClassVarIteratorLiteralSequenceTypeVarcastoverload)lib) ArrayLike AstypeArgDtype FillnaOptionsPositionalIndexer ScalarIndexerSequenceIndexerShape TakeIndexernpt)set_function_name)functionAbstractMethodError)Appender Substitutioncache_readonlydeprecate_nonkeyword_arguments)find_stack_level)validate_bool_kwargvalidate_fillna_kwargsvalidate_insert_loc)maybe_cast_to_extension_array)is_dtype_equal is_list_like is_scalar pandas_dtype)ExtensionDtype) ABCDataFrameABCIndex ABCSeriesisna) arraylikemissing roperator)factorize_arrayisinmoderankresolve_na_sentinelunique)quantile_with_mask) nargminmaxnargsortc@s,eZdZddd ddZddd dd Zd S) ExtensionArraySupportsAnyAllTskipnar=boolreturncCdSNselfr=rBrBM/var/www/html/gps/gps/lib/python3.10/site-packages/pandas/core/arrays/base.pyany_z ExtensionArraySupportsAnyAll.anycCr@rArBrCrBrBrEallbrGz ExtensionArraySupportsAnyAll.allN)r=r>r?r>)__name__ __module__ __qualname__rFrHrBrBrBrEr;^sr;ExtensionArray) NumpySorterNumpyValueArrayLikezdict[str, str]_extension_array_shared_docsExtensionArrayT)boundc@seZdZUdZdZedddddd Zeddddd d Zed d Ze dddZ e dddZ dddZ ddd Z dd"d#Z dd%d&Z dd)d*Zdd-d.Zdd/d0Zdd1d2Zddejfdd8d9Zedd;d<Zedd>d?Zedd@dAZeddBdCZeddDdEZe dddHdIZe dddJdIZe dddLdIZdddNdIZddPdQZeddRdSZddTdUZeddgdV M W Xddd]d^Z ddd`daZ!dddbdcZ"   dddidjZ#ddkdlZ$dddpdqZ%ddrdsZ& t ddd{d|Z'dd}d~Z(dddZ)dddZ*ejejfdddZ+de,d<e-dde.e,d ddddZ/dddd ddZ0dddZ1dd ddZ2d ddZ3d ddZ4d d ddZ5dddZ6edddZ7ddddZ8edddZ9e:dddZ;dMddddZdddÄZ?dddńZ@dddȄZAdddʄZBddd̄ZCddddMddМdddԄZDedddׄZEddd܄ZFdddd߄ZGdddZHdS(rLa% Abstract base class for custom 1-D array types. pandas will recognize instances of this class as proper arrays with a custom type and will not attempt to coerce them to objects. They may be stored directly inside a :class:`DataFrame` or :class:`Series`. Attributes ---------- dtype nbytes ndim shape Methods ------- argsort astype copy dropna factorize fillna equals insert isin isna ravel repeat searchsorted shift take tolist unique view _concat_same_type _formatter _from_factorized _from_sequence _from_sequence_of_strings _reduce _values_for_argsort _values_for_factorize Notes ----- The interface includes the following abstract methods that must be implemented by subclasses: * _from_sequence * _from_factorized * __getitem__ * __len__ * __eq__ * dtype * nbytes * isna * take * copy * _concat_same_type A default repr displaying the type, (truncated) data, length, and dtype is provided. It can be customized or replaced by by overriding: * __repr__ : A default repr for the ExtensionArray. * _formatter : Print scalars inside a Series or DataFrame. Some methods require casting the ExtensionArray to an ndarray of Python objects with ``self.astype(object)``, which may be expensive. When performance is a concern, we highly recommend overriding the following methods: * fillna * dropna * unique * factorize / _values_for_factorize * argsort, argmax, argmin / _values_for_argsort * searchsorted The remaining methods implemented on this class should be performant, as they only compose abstract methods. Still, a more efficient implementation may be available, and these methods can be overridden. One can implement methods to handle array reductions. * _reduce One can implement methods to handle parsing from strings that will be used in methods such as ``pandas.io.parsers.read_csv``. * _from_sequence_of_strings This class does not inherit from 'abc.ABCMeta' for performance reasons. Methods and properties required by the interface raise ``pandas.errors.AbstractMethodError`` and no ``register`` method is provided for registering virtual subclasses. ExtensionArrays are limited to 1 dimension. They may be backed by none, one, or many NumPy arrays. For example, ``pandas.Categorical`` is an extension array backed by two arrays, one for codes and one for categories. An array of IPv6 address may be backed by a NumPy structured array with two fields, one for the lower 64 bits and one for the upper 64 bits. Or they may be backed by some other storage type, like Python lists. Pandas makes no assumptions on how the data are stored, just that it can be converted to a NumPy array. The ExtensionArray interface does not impose any rules on how this data is stored. However, currently, the backing data cannot be stored in attributes called ``.values`` or ``._values`` to ensure full compatibility with pandas internals. But other names as ``.data``, ``._data``, ``._items``, ... can be freely used. If implementing NumPy's ``__array_ufunc__`` interface, pandas expects that 1. You defer by returning ``NotImplemented`` when any Series are present in `inputs`. Pandas will extract the arrays and call the ufunc again. 2. You define a ``_HANDLED_TYPES`` tuple as an attribute on the class. Pandas inspect this to determine whether the ufunc is valid for the types present. See :ref:`extending.extension.ufunc` for more. By default, ExtensionArrays are not hashable. Immutable subclasses may override this behavior. extensionNFdtypecopyrT Dtype | NonecCt|)aN Construct a new ExtensionArray from a sequence of scalars. Parameters ---------- scalars : Sequence Each element will be an instance of the scalar type for this array, ``cls.dtype.type`` or be converted into this type in this method. dtype : dtype, optional Construct for this particular dtype. This should be a Dtype compatible with the ExtensionArray. copy : bool, default False If True, copy the underlying data. Returns ------- ExtensionArray r)clsscalarsrTrUrBrBrE_from_sequencezExtensionArray._from_sequencecCrW)a  Construct a new ExtensionArray from a sequence of strings. Parameters ---------- strings : Sequence Each element will be an instance of the scalar type for this array, ``cls.dtype.type``. dtype : dtype, optional Construct for this particular dtype. This should be a Dtype compatible with the ExtensionArray. copy : bool, default False If True, copy the underlying data. Returns ------- ExtensionArray r)rXstringsrTrUrBrBrE_from_sequence_of_stringssz(ExtensionArray._from_sequence_of_stringscCrW)a Reconstruct an ExtensionArray after factorization. Parameters ---------- values : ndarray An integer ndarray with the factorized values. original : ExtensionArray The original ExtensionArray that factorize was called on. See Also -------- factorize : Top-level factorize method that dispatches here. ExtensionArray.factorize : Encode the extension array as an enumerated type. r)rXvaluesoriginalrBrBrE_from_factorized'szExtensionArray._from_factorizeditemrr?rcCr@rArBrDrarBrBrE __getitem__=zExtensionArray.__getitem__rDrPrcCr@rArBrbrBrBrErcArdrExtensionArrayT | AnycCrW)an Select a subset of self. Parameters ---------- item : int, slice, or ndarray * int: The position in 'self' to get. * slice: A slice object, where 'start', 'stop', and 'step' are integers or None * ndarray: A 1-d boolean NumPy ndarray the same length as 'self' * list[int]: A list of int Returns ------- item : scalar or ExtensionArray Notes ----- For scalar ``item``, return a scalar value suitable for the array's type. This should be an instance of ``self.dtype.type``. For slice ``key``, return an instance of ``ExtensionArray``, even if the slice is length 0 or 1. For a boolean mask, return an instance of ``ExtensionArray``, filtered to the values where ``item`` is True. rrbrBrBrErcEs!keyint | slice | np.ndarrayvalueNonecCstt|d)a^ Set one or more values inplace. This method is not required to satisfy the pandas extension array interface. Parameters ---------- key : int, ndarray, or slice When called from, e.g. ``Series.__setitem__``, ``key`` will be one of * scalar int * ndarray of integers. * boolean ndarray * slice object value : ExtensionDtype.type, Sequence[ExtensionDtype.type], or object value or values to be set of ``key``. Returns ------- None z does not implement __setitem__.)NotImplementedErrortype)rDrfrhrBrBrE __setitem__hs+zExtensionArray.__setitem__intcCrW)z\ Length of this array Returns ------- length : int rrDrBrBrE__len__zExtensionArray.__len__ Iterator[Any]ccs"tt|D]}||VqdS)z5 Iterate over elements of the array. N)rangelen)rDirBrBrE__iter__s zExtensionArray.__iter__objectbool | np.bool_cCsJt|rt|r|js dS||jjust||jjr|jSdS||kS)z, Return for `item in self`. F) r'r. _can_hold_narTna_value isinstancerk_hasnarFrbrBrBrE __contains__s zExtensionArray.__contains__otherrcCrW)zE Return for `self == other` (element-wise equality). rrDr}rBrBrE__eq__s zExtensionArray.__eq__cCs ||kS)zH Return for `self != other` (element-wise in-equality). rBr~rBrBrE__ne__s zExtensionArray.__ne__cKsVt|d}dt|jvr'|jdvr)|j}tjd|d|dttddSdSdS)N factorizeuse_na_sentinel) TimelikeOps DatetimeArrayTimedeltaArrayzThe `na_sentinel` argument of `zy.factorize` is deprecated. In the future, pandas will use the `use_na_sentinel` argument instead. Add this argument to `zU.factorize` to be compatible with future versions of pandas and silence this warning.) stacklevel) getattrinspect signature parametersrIwarningswarnDeprecationWarningr )rXkwargsrnamerBrBrE__init_subclass__s  z ExtensionArray.__init_subclass__npt.DTypeLike | NonerUr>ry np.ndarraycCs>tj||d}|s|tjur|}|tjur|||<|S)aj Convert to a NumPy ndarray. .. versionadded:: 1.0.0 This is similar to :meth:`numpy.asarray`, but may provide additional control over how the conversion is done. Parameters ---------- dtype : str or numpy.dtype, optional The dtype to pass to :meth:`numpy.asarray`. copy : bool, default False Whether to ensure that the returned value is a not a view on another array. Note that ``copy=False`` does not *ensure* that ``to_numpy()`` is no-copy. Rather, ``copy=True`` ensure that a copy is made, even if not strictly necessary. na_value : Any, optional The value to use for missing values. The default value depends on `dtype` and the type of the array. Returns ------- numpy.ndarray rT)npasarrayr no_defaultrUr.)rDrTrUryresultrBrBrEto_numpys   zExtensionArray.to_numpyr)cCrW)z2 An instance of 'ExtensionDtype'. rrnrBrBrErT szExtensionArray.dtypercCs t|fS)z9 Return a tuple of the array dimensions. )rsrnrBrBrEshapes zExtensionArray.shapecCs t|jS)z6 The number of elements in the array. )rprodrrnrBrBrEsize zExtensionArray.sizecCsdS)zH Extension Arrays are only allowed to be 1-dimensional. rBrnrBrBrEndim#szExtensionArray.ndimcCrW)zL The number of bytes needed to store this object in memory. rrnrBrBrEnbytes*szExtensionArray.nbytes. npt.DTypeLikecCr@rArBrDrTrUrBrBrEastype7rdzExtensionArray.astypecCr@rArBrrBrBrEr;rdrcCr@rArBrrBrBrEr?rdTcCsVt|}t||jr|s|S|St|tr#|}|j|||dStj |||dS)aW Cast to a NumPy array or ExtensionArray with 'dtype'. Parameters ---------- dtype : str or dtype Typecode or data-type to which the array is cast. copy : bool, default True Whether to copy the data, even if not necessary. If False, a copy is made only if the old dtype does not match the new dtype. Returns ------- array : np.ndarray or ExtensionArray An ExtensionArray if dtype is ExtensionDtype, Otherwise a NumPy ndarray with 'dtype' for its dtype. rS) r(r%rTrUrzr)construct_array_typerZrarray)rDrTrUrXrBrBrErCs  )np.ndarray | ExtensionArraySupportsAnyAllcCrW)a A 1-D array indicating if each value is missing. Returns ------- na_values : Union[np.ndarray, ExtensionArray] In most cases, this should return a NumPy ndarray. For exceptional cases like ``SparseArray``, where returning an ndarray would be expensive, an ExtensionArray may be returned. Notes ----- If returning an ExtensionArray, then * ``na_values._is_boolean`` should be True * `na_values` should implement :func:`ExtensionArray._reduce` * ``na_values.any`` and ``na_values.all`` should be implemented rrnrBrBrEr.dr[zExtensionArray.isnacCst|S)z Equivalent to `self.isna().any()`. Some ExtensionArray subclasses may be able to optimize this check. )r>r.rFrnrBrBrEr{zszExtensionArray._hasnacCs t|S)a  Return values for sorting. Returns ------- ndarray The transformed values should maintain the ordering between values within the array. See Also -------- ExtensionArray.argsort : Return the indices that would sort this array. Notes ----- The caller is responsible for *not* modifying these values in-place, so it is safe for implementors to give views on `self`. Functions that use this (e.g. ExtensionArray.argsort) should ignore entries with missing values in the original array (according to `self.isna()`). This means that the corresponding entries in the returned array don't need to be modified to sort correctly. )rrrnrBrBrE_values_for_argsorts z"ExtensionArray._values_for_argsort)version allowed_args quicksortlast ascendingkindstr na_positionc Os2t|||}|}t||||t|dS)a Return the indices that would sort this array. Parameters ---------- ascending : bool, default True Whether the indices should result in an ascending or descending sort. kind : {'quicksort', 'mergesort', 'heapsort', 'stable'}, optional Sorting algorithm. *args, **kwargs: Passed through to :func:`numpy.argsort`. Returns ------- np.ndarray[np.intp] Array of indices that sort ``self``. If NaN values are contained, NaN values are placed at the end. See Also -------- numpy.argsort : Sorting implementation used internally. )rrrmask)nvvalidate_argsort_with_ascendingrr:rrr.)rDrrrargsrr^rBrBrEargsorts% zExtensionArray.argsortr=cC"t|d|s |jr tt|dS)aq Return the index of minimum value. In case of multiple occurrences of the minimum value, the index corresponding to the first occurrence is returned. Parameters ---------- skipna : bool, default True Returns ------- int See Also -------- ExtensionArray.argmax r=argminr!r{rjr9rCrBrBrEr   zExtensionArray.argmincCr)aq Return the index of maximum value. In case of multiple occurrences of the maximum value, the index corresponding to the first occurrence is returned. Parameters ---------- skipna : bool, default True Returns ------- int See Also -------- ExtensionArray.argmin r=argmaxrrCrBrBrErrzExtensionArray.argmaxobject | ArrayLike | NonemethodFillnaOptions | Nonelimit int | NonecCst||\}}|}t||t|}|rA|dur7t|}|t}||||d|j ||j d}|S| }|||<|S| }|S)a Fill NA/NaN values using the specified method. Parameters ---------- value : scalar, array-like If a scalar value is passed it is used to fill all missing values. Alternatively, an array-like 'value' can be given. It's expected that the array-like have the same length as 'self'. method : {'backfill', 'bfill', 'pad', 'ffill', None}, default None Method to use for filling holes in reindexed Series pad / ffill: propagate last valid observation forward to next valid backfill / bfill: use NEXT valid observation to fill gap. limit : int, default None If method is specified, this is the maximum number of consecutive NaN values to forward/backward fill. In other words, if there is a gap with more than this number of consecutive NaNs, it will only be partially filled. If method is not specified, this is the maximum number of entries along the entire axis where NaNs will be filled. Returns ------- ExtensionArray With NA/NaN filled. Nrrr) r"r.r0check_value_sizersrF get_fill_funcrrvrZrTrU)rDrhrrrfuncnpvalues new_valuesrBrBrEfillnas"    zExtensionArray.fillnacCs||S)zz Return ExtensionArray without NA values. Returns ------- valid : ExtensionArray r-rnrBrBrEdropna>s zExtensionArray.dropnarperiods fill_valuecCst|r|dkr |St|r|jj}|j|gtt|t||jd}|dkr4|}|d| }n |t|d}|}|||gS)a> Shift values by desired number. Newly introduced missing values are filled with ``self.dtype.na_value``. Parameters ---------- periods : int, default 1 The number of periods to shift. Negative values are allowed for shifting backwards. fill_value : object, optional The scalar value to use for newly introduced missing values. The default is ``self.dtype.na_value``. Returns ------- ExtensionArray Shifted. Notes ----- If ``self`` is empty or ``periods`` is 0, a copy of ``self`` is returned. If ``periods > len(self)``, then an array of size len(self) is returned, with all values filled with ``self.dtype.na_value``. rrN) rsrUr.rTryrZminabs_concat_same_type)rDrremptyabrBrBrEshiftIs!zExtensionArray.shiftcCst|t}|j||jdS)z Compute the ExtensionArray of unique values. Returns ------- uniques : ExtensionArray r)r7rrvrZrT)rDuniquesrBrBrEr7{szExtensionArray.uniqueleft$NumpyValueArrayLike | ExtensionArraysideLiteral['left', 'right']sorterrMnpt.NDArray[np.intp] | np.intpcCs.|t}t|tr|t}|j|||dS)a Find indices where elements should be inserted to maintain order. Find the indices into a sorted array `self` (a) such that, if the corresponding elements in `value` were inserted before the indices, the order of `self` would be preserved. Assuming that `self` is sorted: ====== ================================ `side` returned index `i` satisfies ====== ================================ left ``self[i-1] < value <= self[i]`` right ``self[i-1] <= value < self[i]`` ====== ================================ Parameters ---------- value : array-like, list or scalar Value(s) to insert into `self`. side : {'left', 'right'}, optional If 'left', the index of the first suitable location found is given. If 'right', return the last such index. If there is no suitable index, return either 0 or N (where N is the length of `self`). sorter : 1-D array-like, optional Optional array of integer indices that sort array a into ascending order. They are typically the result of argsort. Returns ------- array of ints or int If value is array-like, array of insertion points. If value is scalar, a single integer. See Also -------- numpy.searchsorted : Similar method from NumPy. )rr)rrvrzrL searchsorted)rDrhrrarrrBrBrErs 1  zExtensionArray.searchsortedcCst|t|kr dStt|}t|j|jsdSt|t|kr"dS||k}t|tr0|d}||@}t ||B S)a Return if another array is equivalent to this array. Equivalent means that both arrays have the same shape and dtype, and all values compare equal. Missing values in the same location are considered equal (in contrast with normal equality). Parameters ---------- other : ExtensionArray Array to compare to this Array. Returns ------- boolean Whether the arrays are equivalent. F) rkr rLr%rTrsrzrr.r>rH)rDr} equal_valuesequal_narBrBrEequalss   zExtensionArray.equalsnpt.NDArray[np.bool_]cCstt||S)a Pointwise comparison for set containment in the given values. Roughly equivalent to `np.array([x in values for x in self])` Parameters ---------- values : Sequence Returns ------- np.ndarray[bool] )r3rr)rDr^rBrBrEr3szExtensionArray.isintuple[np.ndarray, Any]cCs|ttjfS)a Return an array and missing value suitable for factorization. Returns ------- values : ndarray An array suitable for factorization. This should maintain order and be a supported dtype (Float64, Int64, UInt64, String, Object). By default, the extension array is cast to object dtype. na_value : object The value in `values` to consider missing. This will be treated as NA in the factorization routines, so it will be coded as `na_sentinel` and not included in `uniques`. By default, ``np.nan`` is used. Notes ----- The values returned by this method are also used in :func:`pandas.util.hash_pandas_object`. )rrvrnanrnrBrBrE_values_for_factorizesz$ExtensionArray._values_for_factorize na_sentinelint | lib.NoDefaultrbool | lib.NoDefault!tuple[np.ndarray, ExtensionArray]c Cs<t||}|\}}t|||d\}}|||}||fS)aj Encode the extension array as an enumerated type. Parameters ---------- na_sentinel : int, default -1 Value to use in the `codes` array to indicate missing values. .. deprecated:: 1.5.0 The na_sentinel argument is deprecated and will be removed in a future version of pandas. Specify use_na_sentinel as either True or False. use_na_sentinel : bool, default True If True, the sentinel -1 will be used for NaN values. If False, NaN values will be encoded as non-negative integers and will not drop the NaN from the uniques of the values. .. versionadded:: 1.5.0 Returns ------- codes : ndarray An integer NumPy array that's an indexer into the original ExtensionArray. uniques : ExtensionArray An ExtensionArray containing the unique values of `self`. .. note:: uniques will *not* contain an entry for the NA value of the ExtensionArray if there are any missing values present in `self`. See Also -------- factorize : Top-level factorize method that dispatches here. Notes ----- :meth:`pandas.factorize` offers a `sort` keyword as well. )rry)r6rr2r`) rDrrresolved_na_sentinelrrycodesr uniques_earBrBrErs 7  zExtensionArray.factorizeaL Repeat elements of a %(klass)s. Returns a new %(klass)s where each element of the current %(klass)s is repeated consecutively a given number of times. Parameters ---------- repeats : int or array of ints The number of repetitions for each element. This should be a non-negative integer. Repeating 0 times will return an empty %(klass)s. axis : None Must be ``None``. Has no effect but is accepted for compatibility with numpy. Returns ------- repeated_array : %(klass)s Newly created %(klass)s with repeated elements. See Also -------- Series.repeat : Equivalent function for Series. Index.repeat : Equivalent function for Index. numpy.repeat : Similar method for :class:`numpy.ndarray`. ExtensionArray.take : Take arbitrary positions. Examples -------- >>> cat = pd.Categorical(['a', 'b', 'c']) >>> cat ['a', 'b', 'c'] Categories (3, object): ['a', 'b', 'c'] >>> cat.repeat(2) ['a', 'a', 'b', 'b', 'c', 'c'] Categories (3, object): ['a', 'b', 'c'] >>> cat.repeat([1, 2, 3]) ['a', 'b', 'b', 'c', 'c', 'c'] Categories (3, object): ['a', 'b', 'c'] repeat)klassrepeatsint | Sequence[int]axiscCs.tdd|itt||}||S)NrBr)rvalidate_repeatrarangersrtake)rDrrindrBrBrErss zExtensionArray.repeat) allow_fillrindicesrrcCrW)a Take elements from an array. Parameters ---------- indices : sequence of int or one-dimensional np.ndarray of int Indices to be taken. allow_fill : bool, default False How to handle negative values in `indices`. * False: negative values in `indices` indicate positional indices from the right (the default). This is similar to :func:`numpy.take`. * True: negative values in `indices` indicate missing values. These values are set to `fill_value`. Any other other negative values raise a ``ValueError``. fill_value : any, optional Fill value to use for NA-indices when `allow_fill` is True. This may be ``None``, in which case the default NA value for the type, ``self.dtype.na_value``, is used. For many ExtensionArrays, there will be two representations of `fill_value`: a user-facing "boxed" scalar, and a low-level physical NA value. `fill_value` should be the user-facing version, and the implementation should handle translating that to the physical version for processing the take if necessary. Returns ------- ExtensionArray Raises ------ IndexError When the indices are out of bounds for the array. ValueError When `indices` contains negative values other than ``-1`` and `allow_fill` is True. See Also -------- numpy.take : Take elements from an array along an axis. api.extensions.take : Take elements from an array. Notes ----- ExtensionArray.take is called by ``Series.__getitem__``, ``.loc``, ``iloc``, when `indices` is a sequence of values. Additionally, it's called by :meth:`Series.reindex`, or any other method that causes realignment, with a `fill_value`. Examples -------- Here's an example implementation, which relies on casting the extension array to object dtype. This uses the helper method :func:`pandas.api.extensions.take`. .. code-block:: python def take(self, indices, allow_fill=False, fill_value=None): from pandas.core.algorithms import take # If the ExtensionArray is backed by an ndarray, then # just pass that here instead of coercing to object. data = self.astype(object) if allow_fill and fill_value is None: fill_value = self.dtype.na_value # fill value should always be translated from the scalar # type for the array, to the physical storage type for # the data, before passing to take. result = take(data, indices, fill_value=fill_value, allow_fill=allow_fill) return self._from_sequence(result, dtype=self.dtype) r)rDrrrrBrBrErs]zExtensionArray.takecCrW)ze Return a copy of the array. Returns ------- ExtensionArray rrnrBrBrErUrpzExtensionArray.copycCs|durt||ddS)a) Return a view on the array. Parameters ---------- dtype : str, np.dtype, or ExtensionDtype, optional Default None. Returns ------- ExtensionArray or np.ndarray A view on the :class:`ExtensionArray`'s data. N)rj)rDrTrBrBrEviews zExtensionArray.viewcCsf|jdkr |Sddlm}|||ddd}dt|jd}||d t|d |j S) Nrrformat_object_summaryFindent_for_name,  z Length: , dtype: ) r_repr_2dpandas.io.formats.printingr _formatterrstriprkrIrsrT)rDrdata class_namerBrBrE__repr__s   zExtensionArray.__repr__csZddlmfddD}d|}dtjd}|d|d jd jS) Nrrcs$g|]}|dddqS)Frr)rr.0xrrDrBrE s z+ExtensionArray._repr_2d..z, r>z [ z ] Shape: r)rrjoinrkrIrrT)rDlinesrrrBrrErs   zExtensionArray._repr_2dboxedCallable[[Any], str | None]cCs |rtStS)aY Formatting function for scalar values. This is used in the default '__repr__'. The returned formatting function receives instances of your scalar type. Parameters ---------- boxed : bool, default False An indicated for whether or not your array is being printed within a Series, DataFrame, or Index (True), or just by itself (False). This may be useful if you want scalar values to appear differently within a Series versus on its own (e.g. quoted or not). Returns ------- Callable[[Any], str] A callable that gets instances of the scalar type and returns a string. By default, :func:`repr` is used when ``boxed=False`` and :func:`str` is used when ``boxed=True``. )rrepr)rDrrBrBrEr"szExtensionArray._formatteraxescGs |ddS)z Return a transposed view on this array. Because ExtensionArrays are always 1D, this is a no-op. It is included for compatibility with np.ndarray. NrB)rDr rBrBrE transposeBrzExtensionArray.transposecCs|SrA)r rnrBrBrETKzExtensionArray.TCorder"Literal['C', 'F', 'A', 'K'] | NonecCs|S)ax Return a flattened view on this array. Parameters ---------- order : {None, 'C', 'F', 'A', 'K'}, default 'C' Returns ------- ExtensionArray Notes ----- - Because ExtensionArrays are 1D-only, this is a no-op. - The "order" argument is ignored, is for compatibility with NumPy. rB)rDrrBrBrEravelOszExtensionArray.ravelrXtype[ExtensionArrayT] to_concatSequence[ExtensionArrayT]cCrW)z Concatenate multiple array of this dtype. Parameters ---------- to_concat : sequence of this type Returns ------- ExtensionArray r)rXrrBrBrErbr[z ExtensionArray._concat_same_typecCs|jjSrA)rTrxrnrBrBrErx}rzExtensionArray._can_hold_nar<rcKsJt||d}|durtdt|jd|jd|d|dd|i|S)a Return a scalar result of performing the reduction operation. Parameters ---------- name : str Name of the function, supported values are: { any, all, min, max, sum, mean, median, prod, std, var, sem, kurt, skew }. skipna : bool, default True If True, skip NaN values. **kwargs Additional keyword arguments passed to the reduction function. Currently, `ddof` is the only supported kwarg. Returns ------- scalar Raises ------ TypeError : subclass does not define reductions N'z ' with dtype z does not support reduction 'r=rB)r TypeErrorrkrIrT)rDrr=rmethrBrBrE_reduces zExtensionArray._reducezClassVar[None]__hash__listcCs |jdkr dd|DSt|S)z Return a list of the values. These are each a scalar type, which is a Python scalar (for str, int, float) or a pandas scalar (for Timestamp/Timedelta/Interval/Period) Returns ------- list rcSsg|]}|qSrB)tolistrrBrBrErsz)ExtensionArray.tolist..)rrrnrBrBrErs zExtensionArray.tolistloccCs ttt||}||SrA)rdeleterrsr)rDrindexerrBrBrErs zExtensionArray.deletecCsHt|t|}t|j|g|jd}t||d||||dgS)a Insert an item at the given position. Parameters ---------- loc : int item : scalar-like Returns ------- same type as self Notes ----- This method should be both type and dtype-preserving. If the item cannot be held in an array of this type/dtype, either ValueError or TypeError should be raised. The default implementation relies on _from_sequence to raise on invalid items. rN)r#rsrkrZrTr)rDrraitem_arrrBrBrEinserts$zExtensionArray.insertrcCs"t|r ||}n|}|||<dS)a Analogue to np.putmask(self, mask, value) Parameters ---------- mask : np.ndarray[bool] value : scalar or listlike If listlike, must be arraylike with same length as self. Returns ------- None Notes ----- Unlike np.putmask, we do not repeat listlike values with mismatched length. 'value' should either be a scalar or an arraylike with the same length as self. N)r&)rDrrhvalrBrBrE_putmasks  zExtensionArray._putmaskcCs.|}t|r||}n|}|||<|S)z Analogue to np.where(mask, self, value) Parameters ---------- mask : np.ndarray[bool] value : scalar or listlike Returns ------- same type as self )rUr&)rDrrhrr"rBrBrE_wheres   zExtensionArray._wherecCsFt|}|t}||||d|j||jd}||||<dS)z Replace values in locations specified by 'mask' using pad or backfill. See also -------- ExtensionArray.fillna rrN)r0rrrvrUrZrT)rDrrrrrrrBrBrE_fill_mask_inplaces  z!ExtensionArray._fill_mask_inplaceraveragekeeprr na_optionrpctr)r*cCs |dkrtt||||||dS)z* See Series.rank.__doc__. rr()rjr5)rDrrr)rr*rBrBrE_rank!s zExtensionArray._rankrcCsV|jg|d}ttd|}|j|dd}t||r!||jkr)td|d|S)z Create an ExtensionArray with the given shape and dtype. See also -------- ExtensionDtype.empty ExtensionDtype.empty is the 'official' public version of this API. rT)rz5Default 'empty' implementation is invalid for dtype='r)rZr broadcast_tointprrzrTrj)rXrrTobjtakerrrBrBrE_empty;s  zExtensionArray._emptyqsnpt.NDArray[np.float64] interpolationcCs<t|}t|}tj}t|||||}t||S)z Compute the quantiles of self for each quantile in `qs`. Parameters ---------- qs : np.ndarray[float64] interpolation: str Returns ------- same type as self )rrr.rr8rkrZ)rDr2r4rrr res_valuesrBrBrE _quantileRs  zExtensionArray._quantilercCs t||dS)aT Returns the mode(s) of the ExtensionArray. Always returns `ExtensionArray` even if only one value. Parameters ---------- dropna : bool, default True Don't consider counts of NA values. Returns ------- same type as self Sorted, if possible. )r)r4)rDrrBrBrE_modehs zExtensionArray._modeufuncnp.ufunccOstdd|Dr tStj|||g|Ri|}|tur|Sd|vr1tj|||g|Ri|S|dkrItj|||g|Ri|}|turI|Stj|||g|Ri|S)Ncss |] }t|tttfVqdSrA)rzr,r+r*)rr}rBrBrE }s z1ExtensionArray.__array_ufunc__..outreduce)rFNotImplementedr/!maybe_dispatch_ufunc_to_dunder_opdispatch_ufunc_with_outdispatch_reduction_ufuncdefault_array_ufunc)rDr8rinputsrrrBrBrE__array_ufunc__|s@zExtensionArray.__array_ufunc__)rTrV)rarr?r)rDrPrarr?rP)rDrPrarr?re)rfrgrhrr?ri)r?rm)r?rq)rarvr?rw)r}rr?r)r?ri)rTrrUr>ryrvr?r)r?r))r?r).)rTrrUr>r?r)rTr)rUr>r?rL)rTrrUr>r?r)T)r?r)r?r>)r?r)Trr)rr>rrrrr?r)r=r>r?rm)NNN) rDrPrhrrrrrr?rP)rDrPr?rP)rN)rrmrrvr?rL)rN)rhrrrrrMr?r)r}rvr?r>)r?r)r?r)rrrrr?rrA)rDrPrrrrr?rP) rDrPrrrr>rrr?rP)rTrVr?r)r?r)F)rr>r?r )r rmr?rL)r?rL)r)rrr?rL)rXrrrr?rP)rrr=r>)r?r)rDrPrrr?rP)rDrPrrmr?rP)rrr?ri)rDrPrrr?rP)rrrrr?ri) rrmrrr)rrr>r*r>)rrrTr))rDrPr2r3r4rr?rP)rDrPrr>r?rP)r8r9rr)IrIrJrK__doc___typ classmethodrZr]r`r rcrlrorur|rrrr rrpropertyrTrrrrrr.r{rrrrrrrrr7rrr3rrrOrrrrrUrrrrr r rrrrxr__annotations__rrr!r#r$r%r+r1r6r7rCrBrBrBrErLps      # -   *        !   /  7 2 6 " C,  _     #       c@sXeZdZdZeddZeddZeddZedd Zed d Z ed d Z dS)ExtensionOpsMixinz A base class for linking the operators to their dunder names. .. note:: You may want to set ``__array_priority__`` if you want your implementation to be called when involved in binary operations with NumPy arrays. cCrWrArrXoprBrBrE_create_arithmetic_methodrz+ExtensionOpsMixin._create_arithmetic_methodcCsBt|d|tjt|d|tjt|d|tjt|d|tjt|d|tjt|d|tj t|d|tj t|d|tj t|d |tj t|d |tj t|d |tjt|d |tjt|d |tjt|d|tjt|d|tt|d|tjdS)N__add____radd____sub____rsub____mul____rmul____pow____rpow____mod____rmod__ __floordiv__ __rfloordiv__ __truediv__ __rtruediv__ __divmod__ __rdivmod__)setattrrLoperatoraddr1raddsubrsubmulrmulpowrpowmodrmodfloordiv rfloordivtruedivrtruedivdivmodrdivmodrXrBrBrE_add_arithmetic_opss$z%ExtensionOpsMixin._add_arithmetic_opscCrWrArrJrBrBrE_create_comparison_methodrz+ExtensionOpsMixin._create_comparison_methodcCs|t|d|tjt|d|tjt|d|tjt|d|tjt|d|tjt|d|tjdS)Nrr__lt____gt____le____ge__) r]rqr^eqneltgtlegerorBrBrE_add_comparison_ops z%ExtensionOpsMixin._add_comparison_opscCrWrArrJrBrBrE_create_logical_methodrz(ExtensionOpsMixin._create_logical_methodcCs|t|d|tjt|d|tjt|d|tjt|d|tjt|d|tjt|d|tj dS)N__and____rand____or____ror____xor____rxor__) r]r~r^and_r1rand_or_ror_xorrxorrorBrBrE_add_logical_opsr}z"ExtensionOpsMixin._add_logical_opsN) rIrJrKrDrFrLrprqr|r~rrBrBrBrErIs     rIc@s6eZdZdZed ddZeddZedd ZdS) ExtensionScalarOpsMixina A mixin for defining ops on an ExtensionArray. It is assumed that the underlying scalar objects have the operators already defined. Notes ----- If you have defined a subclass MyExtensionArray(ExtensionArray), then use MyExtensionArray(ExtensionArray, ExtensionScalarOpsMixin) to get the arithmetic operators. After the definition of MyExtensionArray, insert the lines MyExtensionArray._add_arithmetic_ops() MyExtensionArray._add_comparison_ops() to link the operators to your class. .. note:: You may want to set ``__array_priority__`` if you want your implementation to be called when involved in binary operations with NumPy arrays. TNcs*fdd}djd}t|||S)a A class method that returns a method that will correspond to an operator for an ExtensionArray subclass, by dispatching to the relevant operator defined on the individual elements of the ExtensionArray. Parameters ---------- op : function An operator that takes arguments op(a, b) coerce_to_dtype : bool, default True boolean indicating whether to attempt to convert the result to the underlying ExtensionArray dtype. If it's not possible to create a new ExtensionArray with the values, an ndarray is returned instead. Returns ------- Callable[[Any, Any], Union[ndarray, ExtensionArray]] A method that can be bound to a class. When used, the method receives the two arguments, one of which is the instance of this class, and should return an ExtensionArray or an ndarray. Returning an ndarray may be necessary when the result of the `op` cannot be stored in the ExtensionArray. The dtype of the ndarray uses NumPy's normal inference rules. Examples -------- Given an ExtensionArray subclass called MyExtensionArray, use __add__ = cls._create_method(operator.add) in the class definition of MyExtensionArray to create the operator for addition, that will be based on the operator implementation of the underlying elements of the ExtensionArray c sfdd}t|tttfrtS}||}fddt||D}fdd}jdvr=t|\}}||||fS||S)Ncs,t|ts t|r |}|S|gt}|SrA)rzrLr&rs)paramovaluesrnrBrEconvert_valuess zNExtensionScalarOpsMixin._create_method.._binop..convert_valuescsg|] \}}||qSrBrB)rrr)rKrBrEr)szJExtensionScalarOpsMixin._create_method.._binop..cs@rtt|}t|tst|}|Stj|d}|S)Nr)r$rkrzrr)rres)coerce_to_dtype result_dtyperDrBrE_maybe_convert+s zNExtensionScalarOpsMixin._create_method.._binop.._maybe_convert>rmrn)rzr,r+r*r=ziprI) rDr}rlvaluesrvaluesrrrrrrKrrnrE_binops  z6ExtensionScalarOpsMixin._create_method.._binop__)rIr)rXrKrrrop_namerBrrE_create_methods(& z&ExtensionScalarOpsMixin._create_methodcCs ||SrA)rrJrBrBrErLAs z1ExtensionScalarOpsMixin._create_arithmetic_methodcCs|j|dtdS)NF)rr)rr>rJrBrBrErqEsz1ExtensionScalarOpsMixin._create_comparison_method)TN)rIrJrKrDrFrrLrqrBrBrBrErs P r)ZrD __future__rrr^typingrrrrrrr r r r rnumpyr pandas._libsr pandas._typingrrrrrrrrrr pandas.compatrpandas.compat.numpyrr pandas.errorsrpandas.util._decoratorsrrrrpandas.util._exceptionsr pandas.util._validatorsr!r"r#pandas.core.dtypes.castr$pandas.core.dtypes.commonr%r&r'r(pandas.core.dtypes.dtypesr)pandas.core.dtypes.genericr*r+r,pandas.core.dtypes.missingr. pandas.corer/r0r1pandas.core.algorithmsr2r3r4r5r6r7 pandas.core.array_algos.quantiler8pandas.core.sortingr9r:r;rMrNrOrHrPrLrIrrBrBrBrEsX 0  0          3?