U md]@sUdZddlmZddlZddlmZmZmZmZm Z m Z m Z m Z m Z mZddlZddlmZddlmZddlmZmZmZmZmZmZmZddlmZdd lm Z!dd l"m#Z#dd l$m%Z%m&Z&dd l'm(Z(dd l)m*Z*m+Z+m,Z,m-Z-m.Z.ddl/m0Z0m1Z1m2Z2ddl3m4Z4m5Z5ddl6m7Z7m8Z8m9Z9ddl:m;Z;ddlm?Z?ddl@mAZAmBZBerddlmCZCmDZDmEZEmFZFddlGmHZHmIZImJZJiZKdeLd<dddddZMe dddZNGddde;ZOGd d!d!ZPGd"d#d#eeZQGd$dde=ZRdS)%z. Base and utility classes for pandas objects. ) annotationsN) TYPE_CHECKINGAnyGenericHashableIteratorLiteralTypeVarcastfinaloverload)using_copy_on_write)lib)AxisAxisIntDtypeObj IndexLabelNDFrameTShapenpt)PYPY)functionAbstractMethodError)cache_readonlydoc)can_hold_element)is_categorical_dtype is_dict_likeis_extension_array_dtypeis_object_dtype is_scalar) ABCDataFrameABCIndex ABCSeries)isnaremove_na_arraylike) algorithmsnanopsops) DirNamesMixin)OpsMixin)ExtensionArray)ensure_wrapped_if_datetimelike extract_array)DropKeep NumpySorterNumpyValueArrayLike ScalarLike_co) CategoricalIndexSerieszdict[str, str] _shared_docs IndexOpsMixin)klassZinplaceunique duplicated_T)boundcs\eZdZUdZded<eddZdddd Zdd d d ddZddfdd Z Z S) PandasObjectz/ Baseclass for various pandas objects. zdict[str, Any]_cachecCst|S)zJ Class constructor (for this class it's just `__class__`. )typeselfrCI/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/pandas/core/base.py _constructorlszPandasObject._constructorstrreturncCs t|S)zI Return a string representation for a particular object. )object__repr__rArCrCrDrJsszPandasObject.__repr__Nz str | NoneNonekeyrHcCs4t|dsdS|dkr"|jn|j|ddS)zV Reset cached properties. If ``key`` is passed, only clears that key. r?N)hasattrr?clearpop)rBrMrCrCrD _reset_cachezs   zPandasObject._reset_cacheintcs<t|dd}|r2|dd}tt|r(|n|StS)zx Generates the total memory usage for an object that returns either a value or Series of values memory_usageNTdeep)getattrrRr!sumsuper __sizeof__)rBrSZmem __class__rCrDrYs   zPandasObject.__sizeof__)N) __name__ __module__ __qualname____doc____annotations__propertyrErJrQrY __classcell__rCrCrZrDr>ds   r>c@s.eZdZdZddddZddddd Zd S) NoNewAttributesMixina Mixin which prevents adding new attributes. Prevents additional attributes via xxx.attribute = "something" after a call to `self.__freeze()`. Mainly used to prevent the user from using wrong attributes on an accessor (`Series.cat/.str/.dt`). If you really want to add a new attribute at a later time, you need to use `object.__setattr__(self, key, value)`. rKrGcCst|dddS)z9 Prevents setting additional attributes. __frozenTN)rI __setattr__rArCrCrD_freezeszNoNewAttributesMixin._freezerFrLcCsTt|ddrB|dksB|t|jksBt||ddk sBtd|dt|||dS)NrdFr?z"You cannot add any new attribute '')rVr@__dict__AttributeErrorrIre)rBrMvaluerCrCrDres  z NoNewAttributesMixin.__setattr__N)r\r]r^r_rfrerCrCrCrDrcs rcc@seZdZUdZded<dZded<ded<d d gZeeZe e d d Z e d dZ e e ddddZe e ddZddZdddddZddZeZdS)SelectionMixinz mixin implementing the selection & aggregation interface on a group-like object sub-classes need to define: obj, exclusions robjNzIndexLabel | None _selectionzfrozenset[Hashable] exclusionsr? __setstate__cCs&t|jtttttjfs |jgS|jSN) isinstancermlisttupler$r#npndarrayrArCrCrD_selection_lists zSelectionMixin._selection_listcCs,|jdkst|jtr|jS|j|jSdSrp)rmrqrlr$rArCrCrD _selected_objszSelectionMixin._selected_objrRrGcCs|jjSrp)rwndimrArCrCrDrxszSelectionMixin.ndimcCsVt|jtr|jS|jdk r*|j|jSt|jdkrL|jj|jdddS|jSdS)NrT)axisZ only_slice) rqrlr$rmZ_getitem_nocopyrvlenrnZ _drop_axisrArCrCrD_obj_with_exclusionss  z#SelectionMixin._obj_with_exclusionscCs|jdk rtd|jdt|tttttjfrt |j j |t t |krtt ||j j }tdt|dd|jt|ddS||j krtd||j |j}|j||dSdS) Nz Column(s) z already selectedzColumns not found: ryrxzColumn not found: )rm IndexErrorrqrrrsr$r#rtrur{rlcolumns intersectionset differenceKeyErrorrF_gotitemrx)rBrMbad_keysrxrCrCrD __getitem__s   zSelectionMixin.__getitem__rcCs t|dS)a sub-classes to define return a sliced object Parameters ---------- key : str / list of selections ndim : {1, 2} requested ndim of result subset : object, default None subset to act on Nr)rBrMrxZsubsetrCrCrDrs zSelectionMixin._gotitemcOs t|dSrpr)rBfuncargskwargsrCrCrD aggregateszSelectionMixin.aggregate)N)r\r]r^r_r`rmZ_internal_namesrZ_internal_names_setr rarvrrwrxr|rrrZaggrCrCrCrDrks*     rkc@s8eZdZUdZdZedgZded<edddd Z ed dd d Z e d d dddZ ee ddZ eddddZddddZeddddZe ddZeddddZeddd d!Zed"dd#d$Ze d%d&ejfd'd(d)d*d+d,d-Ze ed(dd.d/Zdd1d(d2d3d4Zed5d6d7d8dd1d(dd9d:d;Zdd1d(d2dd8dd1d(dd9d?d@ZdAdBZeZdCddDdEZ e!d(ddFdGZ"dHddIdJZ#dKd0d%d%dLdMdNd(dOdPdQZ$e ddRdSZ%e dd(d(d(d(dTdUdVdWZ&dXdYZ'e dd(ddZd[d\Z(ed(dd]d^Z)ed(dd_d`Z*ed(ddadbZ+e dd(ddcdddeZ,ee-j.dfdfdfe/0dgdhdd(d(didjdkdlZ.dme1dn<e2ddpdqdrdsdtdudvZ3e2ddwdqdrdxdtdydvZ3ee1dndzd{dd}dqdrd~dtddvZ3ddddddZ4e dddHdddZ5ddZ6ddZ7d%S)r7zS Common ops mixin to support a unified interface / docs for Series / Index itolistzfrozenset[str] _hidden_attrsrrGcCs t|dSrprrArCrCrDdtypeszIndexOpsMixin.dtypezExtensionArray | np.ndarraycCs t|dSrprrArCrCrD_valuesszIndexOpsMixin._valuesr<)rBrHcOst|||S)zw Return the transpose, which is by definition self. Returns ------- %(klass)s )nvZvalidate_transpose)rBrrrCrCrD transpose"s zIndexOpsMixin.transposezD Return the transpose, which is by definition self. )rrcCs|jjS)z Return a tuple of the shape of the underlying data. Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.shape (3,) )rshaperArCrCrDr5s zIndexOpsMixin.shaperRcCs t|dSrprrArCrCrD__len__BszIndexOpsMixin.__len__z Literal[1]cCsdS)zO Number of dimensions of the underlying data, by definition 1. ryrCrArCrCrDrxFszIndexOpsMixin.ndimcCs$t|dkrtt|StddS)a  Return the first element of the underlying data as a Python scalar. Returns ------- scalar The first element of %(klass)s. Raises ------ ValueError If the data is not length-1. ryz6can only convert an array of size 1 to a Python scalarN)r{nextiter ValueErrorrArCrCrDitemMs  zIndexOpsMixin.itemcCs|jjS)zD Return the number of bytes in the underlying data. )rnbytesrArCrCrDr`szIndexOpsMixin.nbytescCs t|jS)zG Return the number of elements in the underlying data. )r{rrArCrCrDsizegszIndexOpsMixin.sizer,cCs t|dS)aM The ExtensionArray of the data backing this Series or Index. Returns ------- ExtensionArray An ExtensionArray of the values stored within. For extension types, this is the actual array. For NumPy native types, this is a thin (no copy) wrapper around :class:`numpy.ndarray`. ``.array`` differs ``.values`` which may require converting the data to a different form. See Also -------- Index.to_numpy : Similar method that always returns a NumPy array. Series.to_numpy : Similar method that always returns a NumPy array. Notes ----- This table lays out the different array types for each extension dtype within pandas. ================== ============================= dtype array type ================== ============================= category Categorical period PeriodArray interval IntervalArray IntegerNA IntegerArray string StringArray boolean BooleanArray datetime64[ns, tz] DatetimeArray ================== ============================= For any 3rd-party extension types, the array type will be an ExtensionArray. For all remaining dtypes ``.array`` will be a :class:`arrays.NumpyExtensionArray` wrapping the actual ndarray stored within. If you absolutely need a NumPy array (possibly with copying / coercing data), then use :meth:`Series.to_numpy` instead. Examples -------- For regular NumPy types like int, and float, a PandasArray is returned. >>> pd.Series([1, 2, 3]).array [1, 2, 3] Length: 3, dtype: int64 For extension types, like Categorical, the actual ExtensionArray is returned >>> ser = pd.Series(pd.Categorical(['a', 'b', 'a'])) >>> ser.array ['a', 'b', 'a'] Categories (2, object): ['a', 'b'] NrrArCrCrDarrayns?zIndexOpsMixin.arrayNFznpt.DTypeLike | NoneboolrIz np.ndarray)rcopyna_valuerHcKst|jr$|jj|f||d|S|rHt|d}td|d|tjk r|j }t ||srt j ||d}n| }||t |<n|j }t j ||d}|r|tjks|strt |j dd|ddrtr|s|}d|j_n| }|S) a A NumPy ndarray representing the values in this Series or Index. 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 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. **kwargs Additional keywords passed through to the ``to_numpy`` method of the underlying array (for extension arrays). Returns ------- numpy.ndarray See Also -------- Series.array : Get the actual data stored within. Index.array : Get the actual data stored within. DataFrame.to_numpy : Similar method for DataFrame. Notes ----- The returned array will be the same up to equality (values equal in `self` will be equal in the returned array; likewise for values that are not equal). When `self` contains an ExtensionArray, the dtype may be different. For example, for a category-dtype Series, ``to_numpy()`` will return a NumPy array and the categorical dtype will be lost. For NumPy dtypes, this will be a reference to the actual data stored in this Series or Index (assuming ``copy=False``). Modifying the result in place will modify the data stored in the Series or Index (not that we recommend doing that). For extension types, ``to_numpy()`` *may* require copying data and coercing the result to a NumPy type (possibly object), which may be expensive. When you need a no-copy reference to the underlying data, :attr:`Series.array` should be used instead. This table lays out the different dtypes and default return types of ``to_numpy()`` for various dtypes within pandas. ================== ================================ dtype array type ================== ================================ category[T] ndarray[T] (same dtype as input) period ndarray[object] (Periods) interval ndarray[object] (Intervals) IntegerNA ndarray[object] datetime64[ns] datetime64[ns] datetime64[ns, tz] ndarray[object] (Timestamps) ================== ================================ Examples -------- >>> ser = pd.Series(pd.Categorical(['a', 'b', 'a'])) >>> ser.to_numpy() array(['a', 'b', 'a'], dtype=object) Specify the `dtype` to control how datetime-aware data is represented. Use ``dtype=object`` to return an ndarray of pandas :class:`Timestamp` objects, each with the correct ``tz``. >>> ser = pd.Series(pd.date_range('2000', periods=2, tz="CET")) >>> ser.to_numpy(dtype=object) array([Timestamp('2000-01-01 00:00:00+0100', tz='CET'), Timestamp('2000-01-02 00:00:00+0100', tz='CET')], dtype=object) Or ``dtype='datetime64[ns]'`` to return an ndarray of native datetime64 values. The values are converted to UTC and the timezone info is dropped. >>> ser.to_numpy(dtype="datetime64[ns]") ... # doctest: +ELLIPSIS array(['1999-12-31T23:00:00.000000000', '2000-01-01T23:00:00...'], dtype='datetime64[ns]') )rrrz/to_numpy() got an unexpected keyword argument 'rgrNr~F)rrrto_numpyrrkeys TypeErrorr no_defaultrrrtZasarrayrZ asanyarrayr%r Z shares_memoryviewflagsZ writeable)rBrrrrrvaluesresultrCrCrDrs4_      zIndexOpsMixin.to_numpycCs|j Srp)rrArCrCrDempty3szIndexOpsMixin.emptyTzAxisInt | None)rzskipnacOs&t|t||tj|j|dS)a Return the maximum value of the Index. Parameters ---------- axis : int, optional For compatibility with NumPy. Only 0 or None are allowed. skipna : bool, default True Exclude NA/null values when showing the result. *args, **kwargs Additional arguments and keywords for compatibility with NumPy. Returns ------- scalar Maximum value. See Also -------- Index.min : Return the minimum value in an Index. Series.max : Return the maximum value in a Series. DataFrame.max : Return the maximum values in a DataFrame. Examples -------- >>> idx = pd.Index([3, 2, 1]) >>> idx.max() 3 >>> idx = pd.Index(['c', 'b', 'a']) >>> idx.max() 'c' For a MultiIndex, the maximum is determined lexicographically. >>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)]) >>> idx.max() ('b', 2) r)rvalidate_minmax_axisZ validate_maxr(ZnanmaxrrBrzrrrrCrCrDmax8s(  zIndexOpsMixin.maxrminlargest)opZopposerj)rzrrHcOsX|j}t|t|||}t|trF|s<|r>> s = pd.Series({{'Corn Flakes': 100.0, 'Almond Delight': 110.0, ... 'Cinnamon Toast Crunch': 120.0, 'Cocoa Puff': 110.0}}) >>> s Corn Flakes 100.0 Almond Delight 110.0 Cinnamon Toast Crunch 120.0 Cocoa Puff 110.0 dtype: float64 >>> s.argmax() 2 >>> s.argmin() 0 The maximum cereal calories is the third element and the minimum cereal calories is the first element, since series is zero-indexed. r}rN) rrrZvalidate_argmax_with_skipnarqr,r%anyargmaxr(Z nanargmaxrBrzrrrZdelegaterCrCrDrds6   zIndexOpsMixin.argmaxcOs&t|t||tj|j|dS)a Return the minimum value of the Index. Parameters ---------- axis : {None} Dummy argument for consistency with Series. skipna : bool, default True Exclude NA/null values when showing the result. *args, **kwargs Additional arguments and keywords for compatibility with NumPy. Returns ------- scalar Minimum value. See Also -------- Index.max : Return the maximum value of the object. Series.min : Return the minimum value in a Series. DataFrame.min : Return the minimum values in a DataFrame. Examples -------- >>> idx = pd.Index([3, 2, 1]) >>> idx.min() 1 >>> idx = pd.Index(['c', 'b', 'a']) >>> idx.min() 'a' For a MultiIndex, the minimum is determined lexicographically. >>> idx = pd.MultiIndex.from_product([('a', 'b'), (2, 1)]) >>> idx.min() ('a', 1) r)rrZ validate_minr(ZnanminrrrCrCrDrs(  zIndexOpsMixin.minsmallestcOsX|j}t|t|||}t|trF|s<|rt||d}|dkr,tt|jd||fd|i|S)zA Perform the reduction type operation if we can. Nz cannot perform the operation r)rVrr@r\) rBrrrzrrrkwdsrrCrCrD_reduce$s  zIndexOpsMixin._reducec sjt|r^t|tr.t|dr.|fdd}n0ddlm}t|dkrV||tjd}n||}t|t r|dkrd|d }t ||d kr||j }t |jrtd |j}||S|j}|j |}t|j|}|St|jrt|jd r|j}|d k r tdd} nF|jt}|d kr6dd} n&|d krHtj} nd|d }t || ||}|S)a An internal function that maps values using the input correspondence (which can be a dict, Series, or function). Parameters ---------- mapper : function, dict, or Series The input correspondence object na_action : {None, 'ignore'} If 'ignore', propagate NA values, without passing them to the mapping function Returns ------- Union[Index, MultiIndex], inferred The output of the mapping function applied to the index. If the function returns a tuple with more than one element a MultiIndex will be returned. __missing__cs"t|trt|rtjn|Srp)rqfloatrtisnannan)xZdict_with_defaultrCrDVsz+IndexOpsMixin._map_values..r)r5r)Nignorez+na_action must either be 'ignore' or None, z was passedrr3rNcSs ||Srp)rrfrCrCrDrcSst||t|tjSrp)rZmap_infer_maskr%rrtZuint8rrCrCrDrs)rrqdictrNpandasr5r{rtZfloat64r$rindexZnotnarrr rrZ get_indexerr'Ztake_ndrNotImplementedErrorastyperIrZ map_infer) rBZmapperZ na_actionr5msgcatrZindexer new_valuesZmap_frCrrD _map_values9sJ                zIndexOpsMixin._map_valuesr5) normalizesort ascendingdropnarHcCstj||||||dS)a Return a Series containing counts of unique values. The resulting object will be in descending order so that the first element is the most frequently-occurring element. Excludes NA values by default. Parameters ---------- normalize : bool, default False If True then the object returned will contain the relative frequencies of the unique values. sort : bool, default True Sort by frequencies. ascending : bool, default False Sort in ascending order. bins : int, optional Rather than count values, group them into half-open bins, a convenience for ``pd.cut``, only works with numeric data. dropna : bool, default True Don't include counts of NaN. Returns ------- Series See Also -------- Series.count: Number of non-NA elements in a Series. DataFrame.count: Number of non-NA elements in a DataFrame. DataFrame.value_counts: Equivalent method on DataFrames. Examples -------- >>> index = pd.Index([3, 1, 2, 3, 4, np.nan]) >>> index.value_counts() 3.0 2 1.0 1 2.0 1 4.0 1 Name: count, dtype: int64 With `normalize` set to `True`, returns the relative frequency by dividing all values by the sum of values. >>> s = pd.Series([3, 1, 2, 3, 4, np.nan]) >>> s.value_counts(normalize=True) 3.0 0.4 1.0 0.2 2.0 0.2 4.0 0.2 Name: proportion, dtype: float64 **bins** Bins can be useful for going from a continuous variable to a categorical variable; instead of counting unique apparitions of values, divide the index in the specified number of half-open bins. >>> s.value_counts(bins=3) (0.996, 2.0] 2 (2.0, 3.0] 2 (3.0, 4.0] 1 Name: count, dtype: int64 **dropna** With `dropna` set to `False` we can also see NaN index values. >>> s.value_counts(dropna=False) 3.0 2 1.0 1 2.0 1 4.0 1 NaN 1 Name: count, dtype: int64 )rrrbinsr)r' value_counts)rBrrrrrrCrCrDrsWzIndexOpsMixin.value_countscCs*|j}t|tjs|}n t|}|Srp)rrqrtrur:r'Zunique1d)rBrrrCrCrDr:s    zIndexOpsMixin.unique)rrHcCs|}|rt|}t|S)a Return number of unique elements in the object. Excludes NA values by default. Parameters ---------- dropna : bool, default True Don't include NaN in the count. Returns ------- int See Also -------- DataFrame.nunique: Method nunique for DataFrame. Series.count: Count non-NA/null observations in the Series. Examples -------- >>> s = pd.Series([1, 3, 5, 7, 7]) >>> s 0 1 1 3 2 5 3 7 4 7 dtype: int64 >>> s.nunique() 4 )r:r&r{)rBrZuniqsrCrCrDnunique s#zIndexOpsMixin.nuniquecCs|jddt|kS)zr Return boolean if values in the object are unique. Returns ------- bool F)r)rr{rArCrCrD is_unique1s zIndexOpsMixin.is_uniquecCsddlm}||jS)z Return boolean if values in the object are monotonically increasing. Returns ------- bool rr4)rr4is_monotonic_increasingrBr4rCrCrDr<s z%IndexOpsMixin.is_monotonic_increasingcCsddlm}||jS)z Return boolean if values in the object are monotonically decreasing. Returns ------- bool rr)rr4is_monotonic_decreasingrrCrCrDrIs z%IndexOpsMixin.is_monotonic_decreasing)rUrHcCsRt|jdr|jj|dS|jj}|rNt|rNtsNttj|j }|t |7}|S)aN Memory usage of the values. Parameters ---------- deep : bool, default False Introspect the data deeply, interrogate `object` dtypes for system-level memory consumption. Returns ------- bytes used See Also -------- numpy.ndarray.nbytes : Total bytes consumed by the elements of the array. Notes ----- Memory usage does not include memory consumed by elements that are not components of the array if deep=False or if used on PyPy rSrT) rNrrSrr rr rtrurrZmemory_usage_of_objects)rBrUvrrCrCrD _memory_usageVs zIndexOpsMixin._memory_usager8z sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. )rorderZ size_hintrz"tuple[npt.NDArray[np.intp], Index])ruse_na_sentinelrHcCs`tj|j||d\}}|jtjkr.|tj}t|t rD| |}nddl m }||}||fS)N)rrrr) r' factorizerrrtZfloat16rZfloat32rqr#rErr4)rBrrcodesZuniquesr4rCrCrDrzs      zIndexOpsMixin.factorizea Find indices where elements should be inserted to maintain order. Find the indices into a sorted {klass} `self` such that, if the corresponding elements in `value` were inserted before the indices, the order of `self` would be preserved. .. note:: The {klass} *must* be monotonically sorted, otherwise wrong locations will likely be returned. Pandas does *not* check this for you. Parameters ---------- value : array-like or scalar Values 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 `self` into ascending order. They are typically the result of ``np.argsort``. Returns ------- int or array of int A scalar or array of insertion points with the same shape as `value`. See Also -------- sort_values : Sort by the values along either axis. numpy.searchsorted : Similar method from NumPy. Notes ----- Binary search is used to find the required insertion points. Examples -------- >>> ser = pd.Series([1, 2, 3]) >>> ser 0 1 1 2 2 3 dtype: int64 >>> ser.searchsorted(4) 3 >>> ser.searchsorted([0, 4]) array([0, 3]) >>> ser.searchsorted([1, 3], side='left') array([0, 2]) >>> ser.searchsorted([1, 3], side='right') array([1, 3]) >>> ser = pd.Series(pd.to_datetime(['3/11/2000', '3/12/2000', '3/13/2000'])) >>> ser 0 2000-03-11 1 2000-03-12 2 2000-03-13 dtype: datetime64[ns] >>> ser.searchsorted('3/14/2000') 3 >>> ser = pd.Categorical( ... ['apple', 'bread', 'bread', 'cheese', 'milk'], ordered=True ... ) >>> ser ['apple', 'bread', 'bread', 'cheese', 'milk'] Categories (4, object): ['apple' < 'bread' < 'cheese' < 'milk'] >>> ser.searchsorted('bread') 1 >>> ser.searchsorted(['bread'], side='right') array([3]) If the values are not monotonically sorted, wrong locations may be returned: >>> ser = pd.Series([2, 1, 3]) >>> ser 0 2 1 1 2 3 dtype: int64 >>> ser.searchsorted(1) # doctest: +SKIP 0 # wrong result, correct would be 1 searchsorted.r2zLiteral[('left', 'right')]r0znp.intp)rjsidesorterrHcCsdSrprCrBrjrrrCrCrDrs zIndexOpsMixin.searchsortedznpt.ArrayLike | ExtensionArrayznpt.NDArray[np.intp]cCsdSrprCrrCrCrDrsr4)r9leftz$NumpyValueArrayLike | ExtensionArrayznpt.NDArray[np.intp] | np.intpcCsXt|tr$dt|jd}t||j}t|tjsF|j|||dSt j||||dS)Nz(Value must be 1-D array-like or scalar, z is not supported)rr) rqr"r@r\rrrtrurr')rBrjrrrrrCrCrDrs  firstkeepr/cCs|j|d}||SNr) _duplicated)rBrr;rCrCrDdrop_duplicates2s zIndexOpsMixin.drop_duplicates)rrHcCstj|j|dSr)r'r;r)rBrrCrCrDr7szIndexOpsMixin._duplicatedc Csjt||}|j}t|ddd}t||j}t|}tjddt |||}W5QRX|j ||dS)NT)Z extract_numpyZ extract_ranger)all)r) r)Zget_op_result_namerr.Zmaybe_prepare_scalar_for_oprr-rtZerrstateZ arithmetic_op_construct_result)rBotherrZres_nameZlvaluesZrvaluesrrCrCrD _arith_method;s zIndexOpsMixin._arith_methodcCs t|dS)z~ Construct an appropriately-wrapped result from the ArrayLike result of an arithmetic-like operation. Nr)rBrrrCrCrDrHszIndexOpsMixin._construct_result)NT)NT)NT)NT)N)FTFNT)T)F)FT)..)..)rN)r)8r\r]r^r_Z__array_priority__ frozensetrr`rarrr rTrrrxrrrrrrrrrrrrrrZto_listrrrr%rrrr:rrrrrr'rtextwrapdedentr6r rrrrrrCrCrCrDr7 s     @, E, f_ '   #g )Sr_ __future__rrtypingrrrrrrr r r r numpyrtZpandas._configr Z pandas._libsrZpandas._typingrrrrrrrZ pandas.compatrZpandas.compat.numpyrrZ pandas.errorsrZpandas.util._decoratorsrrZpandas.core.dtypes.castrZpandas.core.dtypes.commonrrrr r!Zpandas.core.dtypes.genericr"r#r$Zpandas.core.dtypes.missingr%r&Z pandas.corer'r(r)Zpandas.core.accessorr*Zpandas.core.arrayliker+Zpandas.core.arraysr,Zpandas.core.constructionr-r.r/r0r1r2rr3r4r5r6r`Z_indexops_doc_kwargsr<r>rcrkr7rCrCrCrDsD 0   $         /"X