OwgUdZddlmZddlZddlmZmZmZmZm 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/m0Z0m1Z1ddl2m3Z3m4Z4ddl5m6Z6m7Z7m8Z8ddl9m:Z:ddl;mZ>ddl?m@Z@mAZAerddlBmCZCmDZDddlmEZEmFZFmGZGmHZHddlImJZJmKZKmLZLiZMdeNd<dddddZOGdd e:ZPGd!d"ZQGd#d$eeZRGd%de<ZSy)&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 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 duplicatedcReZdZUdZded<edZddZd d dZd fd Z xZ S) PandasObjectz/ Baseclass for various pandas objects. zdict[str, Any]_cachect|S)zK Class constructor (for this class it's just `__class__`). )typeselfs G/var/www/horilla/myenv/lib/python3.12/site-packages/pandas/core/base.py _constructorzPandasObject._constructorls Dzc,tj|S)zI Return a string representation for a particular object. )object__repr__rAs rCrHzPandasObject.__repr__ss t$$rEct|dsy||jjy|jj|dy)zV Reset cached properties. If ``key`` is passed, only clears that key. r>N)hasattrr>clearpop)rBkeys rC _reset_cachezPandasObject._reset_cachezs8tX&  ; KK    KKOOC &rEct|dd}|r3|d}tt|r|S|jSt|S)zx Generates the total memory usage for an object that returns either a value or Series of values memory_usageNTdeep)getattrintrsumsuper __sizeof__)rBrPmem __class__s rCrWzPandasObject.__sizeof__sO t^T: D)Cins< <#'')< <w!##rE)returnstrN)rMz str | NonerZNonerZrT) __name__ __module__ __qualname____doc____annotations__propertyrDrHrNrW __classcell__)rYs@rCr=r=ds6   % ' $ $rEr=c eZdZdZddZddZy)NoNewAttributesMixina Mixin which prevents adding new attributes. Prevents additional attributes via xxx.attribute = "something" after a call to `self.__freeze()`. Mainly used to prevent the user from using wrong attributes on an accessor (`Series.cat/.str/.dt`). If you really want to add a new attribute at a later time, you need to use `object.__setattr__(self, key, value)`. c2tj|ddy)z9 Prevents setting additional attributes. __frozenTN)rG __setattr__rAs rC_freezezNoNewAttributesMixin._freezes 4T2rEct|ddr8|dk(s3|t|jvst||dtd|dtj |||y)NriFr>z"You cannot add any new attribute '')rSr@__dict__AttributeErrorrGrj)rBrMvalues rCrjz NoNewAttributesMixin.__setattr__s_ 4U + 8Od4j)))tS$'3 #EcU!!LM M4e,rEN)rZr])rMr[rZr])r_r`rarbrkrjrErCrgrgs 3 -rErgceZdZUdZded<dZded<ded<d d gZeeZe e d Z e d Z e e dd Ze e dZdZdddZe ddZdZeZy)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\) isinstancerulisttupler!r npndarrayrAs rC_selection_listzSelectionMixin._selection_lists= OOdE9h K OO$ $rEc|jt|jtr |jS|j|jSr\)ruryrtr!rAs rC _selected_objzSelectionMixin._selected_objs5 ?? "j9&E88O88DOO, ,rEc.|jjSr\)rndimrAs rCrzSelectionMixin.ndims!!&&&rEcHt|jtr |jS|j%|jj |j St |jdkDr(|jj|jddS|jS)NrT)axis only_slice) ryrtr!ru_getitem_nocopyr~lenrv _drop_axisrAs rC_obj_with_exclusionsz#SelectionMixin._obj_with_exclusionss| dhh *88O ?? &88++D,@,@A A t ! # 88&&tQ4&P P88OrEc|jtd|jdt|ttt t tjfrt|jjj|tt|k7rQtt|j|jj}tdt!|dd|j#t|dS||jvrtd||j|j$}|j#||S) Nz Column(s) z already selectedzColumns not found: r)rzColumn not found: )ru IndexErrorryrzr{r!r r|r}rrtcolumns intersectionset differenceKeyErrorr[_gotitemr)rBrMbad_keysrs rC __getitem__zSelectionMixin.__getitem__s  ?? &z$//)::KLM M cD%HbjjI J488##0056#c#h-GC 3 3DHH4D4D EF!4S]1R5H4IJKK==c=3 3$(("!3C59::88C=%%D==4=0 0rEct|)a sub-classes to define return a sliced object Parameters ---------- key : str / list of selections ndim : {1, 2} requested ndim of result subset : object, default None subset to act on r)rBrMrsubsets rCrzSelectionMixin._gotitems"$''rEcd}|jdk(r2tj|r||vstj|r|}|S|jdk(r&tj|r||jk(r|}|S)zO Infer the `selection` to pass to our constructor in _gotitem. Nrr)rr r is_list_likename)rBrMr selections rC_infer_selectionzSelectionMixin._infer_selectionsp  ;;!  ]]3 C6Mc6F6Fs6KI[[A #--"4 9KIrEct|r\r)rBfuncargskwargss rC aggregatezSelectionMixin.aggregates !$''rEr^r\)rrT)rzSeries | DataFrame)r_r`rarbrcru_internal_namesr_internal_names_setr rdr~rrrrrrrraggrqrErCrsrss M$(J!(##0Oo.   --  ' '   1 (    ( CrErsc eZdZUdZdZedgZded<ed9dZ ed:dZ e d;dZ ee d Z edd Ze dZed=dZed=dZed?dZe ddej,f d@dZe edAdZeddd dB dCdZeeddd dB dCdZdZeZdDdZedAdZ e dBdEd Z!e dF dGd!Z"d"Z#e dHdId#Z$edAd$Z%edAd%Z&edAd&Z'e dJdKd'Z(ee)jTd(d(d(e+jXd)* dL dMd+Z*d,e-d-<e. dN dOd.Z/e. dN dPd/Z/ee-d-d01 dQ dRd2Z/d3d4dSd5Z0e dTdUd6Z1d7Z2d8Z3y)Vr6zS Common ops mixin to support a unified interface / docs for Series / Index itolistzfrozenset[str] _hidden_attrsct|r\rrAs rCdtypezIndexOpsMixin.dtype'"$''rEct|r\rrAs rC_valueszIndexOpsMixin._values,rrEc2tj|||S)zw Return the transpose, which is by definition self. Returns ------- %(klass)s )nvvalidate_transpose)rBrrs rC transposezIndexOpsMixin.transpose1s dF+ rEa 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') )rc.|jjS)z Return a tuple of the shape of the underlying data. Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.shape (3,) )rshaperAs rCrzIndexOpsMixin.shapeZs||!!!rEct|r\rrAs rC__len__zIndexOpsMixin.__len__gs !$''rEcy)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 rrqrAs rCrzIndexOpsMixin.ndimks0rEc\t|dk(rtt|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 ValueErrorrAs rCitemzIndexOpsMixin.items*6 t9>T # #QRRrEc.|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 )rnbytesrAs rCrzIndexOpsMixin.nbytess4||"""rEc,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 )rrrAs rCsizezIndexOpsMixin.sizes44<<  rEct|)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'] rrAs rCarrayzIndexOpsMixin.arrays~"$''rENFc lt|jtr |jj|f||d|S|r1t t |j}td|d|tjuxrC|tjuxr.tj|jtj }|j}|rUt!||stj"||}n|j%}||tj&t)|<tj"||}|r|r |sot+retj,|jdd|ddr?t+r%|s#|j/}d|j0_|S|j%}|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]') )copyna_valuez/to_numpy() got an unexpected keyword argument 'rm)rNrF)ryrrrto_numpyrrkeys TypeErrorr no_defaultr|nan issubdtypefloatingrrasarrayr asanyarrayr"r shares_memoryviewflags writeable) rBrrrrrfillnavaluesresults rCrzIndexOpsMixin.to_numpysi~ djj. 1&4::&&uU4(UfU U D/0HA(1M  CNN * T'RBMM$**bkk,RS   #FH5F%808F2==d, -F%0 2E2G Ra 0&!*=&(#[[]F-2FLL* $[[]F rEc|j Sr\)rrAs rCemptyzIndexOpsMixin.emptys99}rEmaxminlargest)opopposerpc|j}tj|tj|||}t |t rl|sZ|j jr>> 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. stacklevelrskipna)rrvalidate_minmax_axisvalidate_argmax_with_skipnaryr)r"anywarningswarnr@r_ FutureWarningrargmaxr% nanargmaxrBrrrrdelegaters rCrzIndexOpsMixin.argmaxsl<< %//fE h /hmmo113 &tDz':':&;F| &tDz':':&;F| &tDz':':&;>> 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] )rrrAs rCrzIndexOpsMixin.tolistsD||""$$rEct|jtjst |jSt |jj t|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 ) ryrr|r}rmaprrangerrAs rC__iter__zIndexOpsMixin.__iter__DsK,$,, 3 % %t||((% 0A0A*BC CrEcFtt|jS)ak Return True if there are any NaNs. Enables various performance speedups. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 3, None]) >>> s 0 1.0 1 2.0 2 3.0 3 NaN dtype: float64 >>> s.hasnans True )boolr"rrAs rChasnanszIndexOpsMixin.hasnans`s2DJNN$%%rEc|j}t|tr|j||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)rconvert)rryr)rr$ map_array)rBmapperrrarrs rC _map_valueszIndexOpsMixin._map_values{sA2ll c> *776Y77 7##C9gVVrEc8tj||||||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 )sort ascending normalizebinsdropna)r$value_counts_internal)rBrrrrrs rC value_countszIndexOpsMixin.value_countss*n//    rEc|j}t|tjs|j }|St j |}|Sr\)rryr|r}r:r$unique1d)rBrrs rCr:zIndexOpsMixin.uniquesB&"**-]]_F  ((0F rEcR|j}|r t|}t|S)a Return number of unique elements in the object. Excludes NA values by default. Parameters ---------- dropna : bool, default True Don't include NaN in the count. Returns ------- int See Also -------- DataFrame.nunique: Method nunique for DataFrame. Series.count: Count non-NA/null observations in the Series. Examples -------- >>> s = pd.Series([1, 3, 5, 7, 7]) >>> s 0 1 1 3 2 5 3 7 4 7 dtype: int64 >>> s.nunique() 4 )r:r#r)rBruniqss rCnuniquezIndexOpsMixin.nuniques'F  '.E5zrEc>|jdt|k(S)a. Return boolean if values in the object are unique. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.is_unique True >>> s = pd.Series([1, 2, 3, 1]) >>> s.is_unique False F)r)r rrAs rC is_uniquezIndexOpsMixin.is_unique,s&||5|)SY66rEc2ddlm}||jS)aY Return boolean if values in the object are monotonically increasing. Returns ------- bool Examples -------- >>> s = pd.Series([1, 2, 2]) >>> s.is_monotonic_increasing True >>> s = pd.Series([3, 2, 1]) >>> s.is_monotonic_increasing False rr3)pandasr3is_monotonic_increasingrBr3s rCrz%IndexOpsMixin.is_monotonic_increasingA& !T{222rEc2ddlm}||jS)a\ Return boolean if values in the object are monotonically decreasing. Returns ------- bool Examples -------- >>> s = pd.Series([3, 2, 2, 1]) >>> s.is_monotonic_decreasing True >>> s = pd.Series([1, 2, 3]) >>> s.is_monotonic_decreasing False rr)rr3is_monotonic_decreasingrs rCrz%IndexOpsMixin.is_monotonic_decreasingXrrEcHt|jdr|jj|S|jj}|rWt |j rBt s>> idx = pd.Index([1, 2, 3]) >>> idx.memory_usage() 24 rPrQ) rJrrPrrrrrr|r}rr memory_usage_of_objects)rBrRvrs rC _memory_usagezIndexOpsMixin._memory_usageos> 4::~ .::**+  JJ   ODJJ/"**dll3F ,,V4 4ArEr7z sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. )rorder size_hintrc2tj|j||\}}|jtj k(r|j tj}t|tr|j|}||fSddl m }||}||fS)N)ruse_na_sentinelrr) r$ factorizerrr|float16astypefloat32ryr rDrr3)rBrrcodesuniquesr3s rCr zIndexOpsMixin.factorizes$$-- LLt_ w ==BJJ &nnRZZ0G dH %''0G g~ %GnGg~rEa 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 searchsortedcyr\rqrBrpsidesorters rCr&zIndexOpsMixin.searchsorted# rEcyr\rqr(s rCr&zIndexOpsMixin.searchsorted,r+rEr3)r8ct|tr$dt|jd}t ||j }t|t js|j|||Stj||||S)Nz(Value must be 1-D array-like or scalar, z is not supported)r)r*) ryrr@r_rrr|r}r&r$)rBrpr)r*msgrs rCr&zIndexOpsMixin.searchsorted5s e\ *:;''((9; S/ !&"**-&&u4&G G&&     rEfirstkeepc2|j|}||SNr0) _duplicated)rBr1r;s rCdrop_duplicateszIndexOpsMixin.drop_duplicatesOs"%%4%0 ZK  rEc|j}t|tr|j|St j||Sr3)rryr)r;r$)rBr1rs rCr4zIndexOpsMixin._duplicatedTs9ll c> *>>t>, ,$$St44rEctj||}|j}t|dd}tj||j }t |}t|tr5tj|j|j|j}tjd5tj|||}ddd|j!|S#1swYxYw)NT) extract_numpy extract_rangeignore)all)r)r&get_op_result_namerr+maybe_prepare_scalar_for_oprr*ryrr|arangestartstopsteperrstate arithmetic_op_construct_result)rBotherrres_namelvaluesrvaluesrs rC _arith_methodzIndexOpsMixin._arith_method[s))$6,,TN11'7==I09 gu %ii w||W\\JG [[X & =&&w((((       A: " "(2 S S<##6!!6>(>(@ '+>> C#CC C  C CJ    E%y1:>Q"Q37Q Q2Qf E%z::>"37 ;B"%HGD8&&4 W W>    ] ] ]  ]  ]  ]  ] ~ % %N77(33,33, ' 'R  X__   $ ,  ,` R*-!   '      *-!  - '       n %W5*0%)  3 ' #  (  6 23:!  5 5 =(rE)Trb __future__rrQtypingrrrrrr 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!pandas.core.dtypes.missingr"r# pandas.corer$r%r&pandas.core.accessorr'pandas.core.arrayliker(pandas.core.arraysr)pandas.core.constructionr*r+collections.abcr,r-r.r/r0r1rr2r3r4r5rc_indexops_doc_kwargsr=rgrsr6rqrErCrjs#..-545   /*-   " n! ! ,$=,$^--DdWX&dNS(HS(rE