yhh>UdZddlmZddlZddlmZmZmZmZm Z m Z m Z ddl Z ddl ZddlmZddlmZddlmZmZmZmZmZmZmZddlmZdd lmZdd l m!Z!dd l"m#Z#m$Z$dd l%m&Z&dd l'm(Z(ddl)m*Z*m+Z+ddl,m-Z-ddl.m/Z/m0Z0m1Z1m2Z2ddl3m4Z4m5Z5ddl6m7Z7m8Z8m9Z9ddl:m;Z;ddlm?Z?ddl@mAZAmBZBerddlCmDZDmEZEddlmFZFmGZGmHZHmIZIddlJmKZKmLZLmMZMiZNdeOd<dddddZPGdd e;ZQGd!d"ZRGd#d$eeZSGd%de=ZTdS)&z. Base and utility classes for pandas objects. ) annotationsN) TYPE_CHECKINGAnyGenericLiteralcastfinaloverload)using_copy_on_write)lib)AxisIntDtypeObj IndexLabelNDFrameTSelfShapenpt)PYPY)functionAbstractMethodError)cache_readonlydoc)find_stack_level)can_hold_element)is_object_dtype is_scalar)ExtensionDtype) ABCDataFrameABCIndex ABCMultiIndex ABCSeries)isnaremove_na_arraylike) algorithmsnanopsops) DirNamesMixin)OpsMixin)ExtensionArray)ensure_wrapped_if_datetimelike extract_array)HashableIterator)DropKeep NumpySorterNumpyValueArrayLike ScalarLike_co) DataFrameIndexSerieszdict[str, str] _shared_docs IndexOpsMixin)klassinplaceunique duplicatedcXeZdZUdZded<edZddZddd Zdfd Z xZ S) PandasObjectz/ Baseclass for various pandas objects. zdict[str, Any]_cachec t|S)zK Class constructor (for this class it's just `__class__`). )typeselfs G/var/www/histauto/venv/lib/python3.11/site-packages/pandas/core/base.py _constructorzPandasObject._constructorms Dzzreturnstrc6t|S)zI Return a string representation for a particular object. )object__repr__rBs rDrKzPandasObject.__repr__ts t$$$rFNkey str | NoneNonect|dsdS||jdS|j|ddS)zV Reset cached properties. If ``key`` is passed, only clears that key. r?N)hasattrr?clearpop)rCrLs rD _reset_cachezPandasObject._reset_cache{sVtX&&  F ; K        KOOC & & & & &rFintct|dd}|r>|d}tt|r|n|St S)zx Generates the total memory usage for an object that returns either a value or Series of values memory_usageNTdeep)getattrrTrsumsuper __sizeof__)rCrVmem __class__s rDr\zPandasObject.__sizeof__sm t^T::  =,D)))Cinn;ss#''))<< <ww!!###rF)rGrHN)rLrMrGrNrGrT) __name__ __module__ __qualname____doc____annotations__propertyrErKrSr\ __classcell__)r^s@rDr>r>es  X %%%% ' ' ' ' ' $ $ $ $ $ $ $ $ $ $rFr>c"eZdZdZd dZd dZdS) 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)`. rGrNc>t|dddS)z9 Prevents setting additional attributes. __frozenTN)rJ __setattr__rBs rD_freezezNoNewAttributesMixin._freezes" 4T22222rFrLrHct|ddr@|dks:|t|jvs$t||dtd|dt|||dS)NrkFr?z"You cannot add any new attribute '')rYrA__dict__AttributeErrorrJrl)rCrLvalues rDrlz NoNewAttributesMixin.__setattr__s 4U + + N 8OOd4jj)))tS$''3 !Lc!L!L!LMM M4e,,,,,rFN)rGrN)rLrHrGrN)rarbrcrdrmrlrFrDririsF  3333 - - - - - -rFriceZdZUdZded<dZded<ded<d d gZeeZe e d Z e d Z e e ddZe e dZdZdddZe ddZdZeZdS)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__ct|jtttt t jfs|jgS|jSr_) isinstancerwlisttupler"r npndarrayrBs rD_selection_listzSelectionMixin._selection_lists? OdE9h K   %O$ $rFcv|jt|jtr|jS|j|jSr_)rwr{rvr"rBs rD _selected_objzSelectionMixin._selected_objs1 ? "j9&E&E "8O8DO, ,rFrGrTc|jjSr_)rndimrBs rDrzSelectionMixin.ndims!&&rFct|jtr|jS|j|j|jSt |jdkr"|j|jddS|jS)NrT)axis only_slice) r{rvr"rw_getitem_nocopyrlenrx _drop_axisrBs rD_obj_with_exclusionsz#SelectionMixin._obj_with_exclusionss} dh * * 8O ? &8++D,@AA A t  ! # # 8&&tQ4&PP P8OrFc|jtd|jdt|ttt t tjfrt|j j |tt|kr`tt||j j }tdt!|dd|t|dS||j vrtd||j |j}|||S) Nz Column(s) z already selectedzColumns not found: r)rzColumn not found: )rw IndexErrorr{r|r}r"r r~rrrvcolumns intersectionset differenceKeyErrorrH_gotitemr)rCrLbad_keysrs rD __getitem__zSelectionMixin.__getitem__s) ? &L$/LLLMM M cD%HbjI J J 148#005566#c#hh--GGC 3 3DH4D E EFFJS]]1R45HJJKKK==c=33 3$(""9C99:::8C=%D==4=00 0rFrc t|)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 r)rCrLrsubsets rDrzSelectionMixin._gotitems"$'''rFrSeries | DataFramecd}|jdkr/tj|r||vstj|r|}n,|jdkr!tj|r ||jkr|}|S)zO Infer the `selection` to pass to our constructor in _gotitem. Nrr)rr r is_list_likename)rCrLr selections rD_infer_selectionzSelectionMixin._infer_selectionsz  ;!   ]3   $'6MMc6Fs6K6KMII [A  #-"4"4  9K9KIrFc t|r_r)rCfuncargskwargss rD aggregatezSelectionMixin.aggregates!$'''rFr`r_)rrT)rr)rarbrcrdrerw_internal_namesr_internal_names_setr rfrrrrrrrrraggrsrFrDrurusG MMM$(J((((####0O#o..  X U--^-  '''^ U' ^ U 111 ( ( ( ( (     U ((( CCCrFruc eZdZUdZdZedgZded<edfdZ edgd Z e dhd Z ee d Z edidZdjdZedjdZe dZedjdZedjdZedkdZe ddejfdld"Ze edmd#Zed$d%d&' dndod,Zeed%d$d-' dndod.Zd/ZeZdpd1Zedmd2Z e dndqd4Z!e drdsd:Z"d;Z#e dtdud<Z$edmd=Z%edmd>Z&edmd?Z'e dvdwdAZ(ee)j*dBdBdBe+j,dCD dxdydGZ*dHe-dI<e. dzd{dRZ/e. dzd|dUZ/ee-dIdVW d}d~d\Z/d]d^ddaZ0e dddcZ1ddZ2deZ3dS)r7zS Common ops mixin to support a unified interface / docs for Series / Index itolistzfrozenset[str] _hidden_attrsrGrc t|r_rrBs rDdtypezIndexOpsMixin.dtype("$'''rFExtensionArray | np.ndarrayc t|r_rrBs rD_valueszIndexOpsMixin._values-rrFrc0tj|||S)zw Return the transpose, which is by definition self. Returns ------- %(klass)s )nvvalidate_transpose)rCrrs rD transposezIndexOpsMixin.transpose2s dF+++ rFa Return the transpose, which is by definition self. Examples -------- For Series: >>> s = pd.Series(['Ant', 'Bear', 'Cow']) >>> s 0 Ant 1 Bear 2 Cow dtype: object >>> s.T 0 Ant 1 Bear 2 Cow dtype: object For Index: >>> idx = pd.Index([1, 2, 3]) >>> idx.T Index([1, 2, 3], dtype='int64') )rrc|jjS)z Return a tuple of the shape of the underlying data. Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.shape (3,) )rshaperBs rDrzIndexOpsMixin.shape[s|!!rFrTc t|r_rrBs rD__len__zIndexOpsMixin.__len__hs!$'''rFcdS)a Number of dimensions of the underlying data, by definition 1. Examples -------- >>> s = pd.Series(['Ant', 'Bear', 'Cow']) >>> s 0 Ant 1 Bear 2 Cow dtype: object >>> s.ndim 1 For Index: >>> idx = pd.Index([1, 2, 3]) >>> idx Index([1, 2, 3], dtype='int64') >>> idx.ndim 1 rrsrBs rDrzIndexOpsMixin.ndimos 0qrFc~t|dkrtt|Std)a Return the first element of the underlying data as a Python scalar. Returns ------- scalar The first element of Series or Index. Raises ------ ValueError If the data is not length = 1. Examples -------- >>> s = pd.Series([1]) >>> s.item() 1 For an index: >>> s = pd.Series([1], index=['a']) >>> s.index.item() 'a' rz6can only convert an array of size 1 to a Python scalar)rnextiter ValueErrorrBs rDitemzIndexOpsMixin.items66 t99>>T ## #QRRRrFc|jjS)a Return the number of bytes in the underlying data. Examples -------- For Series: >>> s = pd.Series(['Ant', 'Bear', 'Cow']) >>> s 0 Ant 1 Bear 2 Cow dtype: object >>> s.nbytes 24 For Index: >>> idx = pd.Index([1, 2, 3]) >>> idx Index([1, 2, 3], dtype='int64') >>> idx.nbytes 24 )rnbytesrBs rDrzIndexOpsMixin.nbytess4|""rFc*t|jS)a Return the number of elements in the underlying data. Examples -------- For Series: >>> s = pd.Series(['Ant', 'Bear', 'Cow']) >>> s 0 Ant 1 Bear 2 Cow dtype: object >>> s.size 3 For Index: >>> idx = pd.Index([1, 2, 3]) >>> idx Index([1, 2, 3], dtype='int64') >>> idx.size 3 )rrrBs rDsizezIndexOpsMixin.sizes44<   rFr*c t|)ac 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 from ``.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 NumpyExtensionArray 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'] rrBs rDarrayzIndexOpsMixin.arrays~"$'''rFNFrnpt.DTypeLike | Nonecopyboolna_valuerJ np.ndarrayc pt|jtr|jj|f||d|S|rAt t |}td|d|tj uo2|tj uo#tj |jtj }|j}|r_t!||stj||}n|}||tjt)|<tj||}|r|r|s}t+rotj|jdd|ddrEt+r#|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]') )rrz/to_numpy() got an unexpected keyword argument 'rorNrF)r{rrrto_numpyrrkeys TypeErrorr no_defaultr~nan issubdtypefloatingrrasarrayr asanyarrayr#r shares_memoryviewflags writeable) rCrrrrrfillnavaluesresults rDrzIndexOpsMixin.to_numpy!s~ dj. 1 1 &4:&uU4(UUfUU U  D//00HM(MMM  CN * T'RBM$*bk,R,RS    9#FH55 'F%88808F2=d,, -F%000  + + +2E2G2G + RaR 0&!*== +&((++#[[]]F-2FL**#[[]]F rFc|j Sr_)rrBs rDemptyzIndexOpsMixin.emptys9}rFmaxminlargest)opopposerrTrAxisInt | Noneskipnac>|j}tj|tj|||}t |t r||sf|r@tj dt|j dttdS|Stj||}|dkr>tj dt|j dtt|S)ab Return int position of the {value} value in the Series. If the {op}imum is achieved in multiple locations, the first row position is returned. Parameters ---------- axis : {{None}} Unused. Parameter needed for compatibility with DataFrame. skipna : bool, default True Exclude NA/null values when showing the result. *args, **kwargs Additional arguments and keywords for compatibility with NumPy. Returns ------- int Row position of the {op}imum value. See Also -------- Series.arg{op} : Return position of the {op}imum value. Series.arg{oppose} : Return position of the {oppose}imum value. numpy.ndarray.arg{op} : Equivalent method for numpy arrays. Series.idxmax : Return index label of the maximum values. Series.idxmin : Return index label of the minimum values. Examples -------- Consider dataset containing cereal calories >>> 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. The behavior of x.argmax/argmin with skipna=False and NAs, or with all-NAs is deprecated. In a future version this will raise ValueError. stacklevelrr)rrvalidate_minmax_axisvalidate_argmax_with_skipnar{r*r#anywarningswarnrAra FutureWarningrargmaxr& nanargmaxrCrrrrdelegaters rDrzIndexOpsMixin.argmaxs6l< %%%/fEE h / /  )hmmoo1133 ) FtDzz':FFF"/11 r(((%hv>>>F|| FtDzz':FFF"/11 MrFsmallestc>|j}tj|tj|||}t |t r||sf|r@tj dt|j dttdS|Stj||}|dkr>tj dt|j dtt|S)Nrrrrr)rrrvalidate_argmin_with_skipnar{r*r#rrrrArarrargminr& nanargminrs rDrzIndexOpsMixin.argmins5< %%%/fEE h / /  )hmmoo1133 ) FtDzz':FFF"/11 r(((%hv>>>F|| FtDzz':FFF"/11 MrFc4|jS)a 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 See Also -------- numpy.ndarray.tolist : Return the array as an a.ndim-levels deep nested list of Python scalars. Examples -------- For Series >>> s = pd.Series([1, 2, 3]) >>> s.to_list() [1, 2, 3] For Index: >>> idx = pd.Index([1, 2, 3]) >>> idx Index([1, 2, 3], dtype='int64') >>> idx.to_list() [1, 2, 3] )rrrBs rDrzIndexOpsMixin.tolist"sD|""$$$rFr.ct|jtjst |jSt |jjt|jjS)a Return an iterator 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 ------- iterator Examples -------- >>> s = pd.Series([1, 2, 3]) >>> for x in s: ... print(x) 1 2 3 ) r{rr~rrmaprrangerrBs rD__iter__zIndexOpsMixin.__iter__HsM,$, 33 D %% %t|(% 0A*B*BCC CrFc^tt|S)ak Return True if there are any NaNs. Enables various performance speedups. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 3, None]) >>> s 0 1.0 1 2.0 2 3.0 3 NaN dtype: float64 >>> s.hasnans True )rr#rrBs rDhasnanszIndexOpsMixin.hasnansds"2DJJNN$$%%%rFconvertc|j}t|tr|||St j||||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 convert : bool, default True Try to find better dtype for elementwise function results. If False, leave as dtype=object. Note that the dtype is always preserved for some extension array dtypes, such as Categorical. 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. ) na_action)rr)rr{r*rr% map_array)rCmapperrrarrs rD _map_valueszIndexOpsMixin._map_valuessM2l c> * * 8776Y777 7#C9gVVVVrF normalizesort ascendingdropnar5c6tj||||||S)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 when True. Preserve the order of the data when False. 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 )r r r binsr )r%value_counts_internal)rCr r r rr s rD value_countszIndexOpsMixin.value_countss1n/      rFc|j}t|tjs|}nt j|}|Sr_)rr{r~rr;r%unique1d)rCrrs rDr;zIndexOpsMixin.uniquesA&"*-- 1]]__FF(00F rFcj|}|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)rCr uniqss rDnuniquezIndexOpsMixin.nuniques3F   /'..E5zzrFcP|dt|kS)a. Return boolean if values in the object are unique. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.is_unique True >>> s = pd.Series([1, 2, 3, 1]) >>> s.is_unique False F)r )rrrBs rD is_uniquezIndexOpsMixin.is_unique0s#&||5|))SYY66rFc.ddlm}||jS)aY Return boolean if values in the object are monotonically increasing. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 2]) >>> s.is_monotonic_increasing True >>> s = pd.Series([3, 2, 1]) >>> s.is_monotonic_increasing False rr4)pandasr4is_monotonic_increasingrCr4s rDrz%IndexOpsMixin.is_monotonic_increasingE'& !     uT{{22rFc.ddlm}||jS)a\ Return boolean if values in the object are monotonically decreasing. Returns ------- bool Examples -------- >>> s = pd.Series([3, 2, 2, 1]) >>> s.is_monotonic_decreasing True >>> s = pd.Series([1, 2, 3]) >>> s.is_monotonic_decreasing False rr)rr4is_monotonic_decreasingrs rDrz%IndexOpsMixin.is_monotonic_decreasing\rrFrXc$t|jdr|j|S|jj}|rQt |jr=t s6ttj |j }|tj |z }|S)a 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 Examples -------- >>> idx = pd.Index([1, 2, 3]) >>> idx.memory_usage() 24 rVrW) rPrrVrrrrrr~rrr memory_usage_of_objects)rCrXvrs rD _memory_usagezIndexOpsMixin._memory_usagess> 4:~ . . :**+  J   5ODJ// 5 5"*dl33F ,V44 4ArFr8z sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. )rorder size_hintr use_na_sentinel"tuple[npt.NDArray[np.intp], Index]cptj|j||\}}|jtjkr|tj}t|tr| |}n5ddl m } |||j}n#t$r||}YnwxYw||fS)N)r r&rrr)r% factorizerrr~float16astypefloat32r{r!rErr4NotImplementedError)rCr r&codesuniquesr4s rDr)zIndexOpsMixin.factorizes$$- Lt_   w =BJ & &nnRZ00G dM * * )''00GG $ $ $ $ $ $ )%tz:::& ) ) ) %.. )g~sBB10B1a 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.rrr2sideLiteral['left', 'right']sorterr0np.intpcdSr_rsrCrrr1r3s rDr0zIndexOpsMixin.searchsorted,  rFnpt.ArrayLike | ExtensionArraynpt.NDArray[np.intp]cdSr_rsr6s rDr0zIndexOpsMixin.searchsorted5r7rFr4)r9left$NumpyValueArrayLike | ExtensionArrayNumpySorter | Nonenpt.NDArray[np.intp] | np.intpct|tr'dt|jd}t ||j}t|t js||||Stj||||S)Nz(Value must be 1-D array-like or scalar, z is not supported)r1r3) r{rrArarrr~rr0r%)rCrrr1r3msgrs rDr0zIndexOpsMixin.searchsorted>s e\ * * ";;;';;; S// !&"*-- H&&u4&GG G&       rFfirstkeeprCr/c@||}||SNrB) _duplicated)rCrCr<s rDdrop_duplicateszIndexOpsMixin.drop_duplicatesXs%%%4%00 ZK  rFnpt.NDArray[np.bool_]c|j}t|tr||St j||SrE)rr{r*r<r%)rCrCrs rDrFzIndexOpsMixin._duplicated]sEl c> * * ->>t>,, ,$St4444rFctj||}|j}t|dd}tj||j}t |}t|tr%tj |j |j |j }tjd5tj|||}dddn #1swxYwY|||S)NT) extract_numpy extract_rangeignore)all)r)r'get_op_result_namerr,maybe_prepare_scalar_for_oprr+r{rr~arangestartstopsteperrstate arithmetic_op_construct_result)rCotherrres_namelvaluesrvaluesrs rD _arith_methodzIndexOpsMixin._arith_methodds)$66,TNNN1'7=II099 gu % % Ki w|W\JJG [X & & & = =&w<)rCr/)rA)rCr/rGrH)4rarbrcrd__array_priority__ frozensetrrerfrrr rTrrrrrrrr rrrrrrrto_listrrrrrr;rrrrr#r%r)textwrapdedentr6r r0rGrFr\rWrsrFrDr7r7sp $-I  %%M(((X((((X(     U      A: " " "X "((((X2 SS US<###X#6!!!X!6>(>(>(X>(@ '+> CCCC UCJ  X U SE%y111:>QQQQ21Qf SE%z::::>;:B"%"%"%HGDDDD8&&&^&4 WWWW UW>    ] ] ] ]  U] ~ %%%% U%N777X7(333X3,333X3, '''' U'R S X_      $  6` R*-!     X *-!     X  Sn %W555*0%)     65 23:!!!!!!  5555 U5 = = =(((((rF)Urd __future__rrbtypingrrrrrr r rnumpyr~pandas._configr pandas._libsr pandas._typingr rrrrrr pandas.compatrpandas.compat.numpyrr pandas.errorsrpandas.util._decoratorsrrpandas.util._exceptionsrpandas.core.dtypes.castrpandas.core.dtypes.commonrrpandas.core.dtypes.dtypesrpandas.core.dtypes.genericrr r!r"pandas.core.dtypes.missingr#r$ pandas.corer%r&r'pandas.core.accessorr(pandas.core.arrayliker)pandas.core.arraysr*pandas.core.constructionr+r,collections.abcr-r.r/r0r1r2rr3r4r5r6re_indexops_doc_kwargsr>rirur7rsrFrDr{sn#"""""............------544444444444544444   /.....******------   " !!!! ! ,$,$,$,$,$=,$,$,$^--------DdddddWX&dddN[([([([([(H[([([([([(rF