o d]@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)boundcsNeZdZUdZded<eddZddd ZddddZdfdd Z Z S) PandasObjectz/ Baseclass for various pandas objects. zdict[str, Any]_cachecCst|S)zJ Class constructor (for this class it's just `__class__`. )typeselfrCD/app/.heroku/python/lib/python3.10/site-packages/pandas/core/base.py _constructorlzPandasObject._constructorreturnstrcCs t|S)zI Return a string representation for a particular object. )object__repr__rArCrCrDrJs zPandasObject.__repr__Nkey str | NoneNonecCs6t|dsdS|dur|jdS|j|ddS)zV Reset cached properties. If ``key`` is passed, only clears that key. r?N)hasattrr?clearpop)rBrLrCrCrD _reset_cachezs zPandasObject._reset_cacheintcs>t|dd}|r|dd}tt|r|S|StS)zx Generates the total memory usage for an object that returns either a value or Series of values memory_usageNTdeep)getattrrSr!sumsuper __sizeof__)rBrTZmem __class__rCrDrZs   zPandasObject.__sizeof__)rGrHN)rLrMrGrNrGrS) __name__ __module__ __qualname____doc____annotations__propertyrErJrRrZ __classcell__rCrCr[rDr>ds     r>c@s$eZdZdZd ddZd dd Zd S) NoNewAttributesMixina Mixin which prevents adding new attributes. Prevents additional attributes via xxx.attribute = "something" after a call to `self.__freeze()`. Mainly used to prevent the user from using wrong attributes on an accessor (`Series.cat/.str/.dt`). If you really want to add a new attribute at a later time, you need to use `object.__setattr__(self, key, value)`. rGrNcCst|dddS)z9 Prevents setting additional attributes. __frozenTN)rI __setattr__rArCrCrD_freezeszNoNewAttributesMixin._freezerLrHcCsTt|ddr!|dks!|t|jvs!t||ddus!td|dt|||dS)NrgFr?z"You cannot add any new attribute '')rWr@__dict__AttributeErrorrIrh)rBrLvaluerCrCrDrhs  z NoNewAttributesMixin.__setattr__N)rGrN)rLrHrGrN)r_r`rarbrirhrCrCrCrDrfs rfc@seZdZUdZded<dZded<ded<d d gZeeZe e d d Z e d dZ e e dddZe e ddZddZddddZddZeZdS)SelectionMixinz mixin implementing the selection & aggregation interface on a group-like object sub-classes need to define: obj, exclusions robjNzIndexLabel | None _selectionzfrozenset[Hashable] exclusionsr? __setstate__cCs&t|jtttttjfs|jgS|jSr]) isinstancerplisttupler$r#npndarrayrArCrCrD_selection_lists zSelectionMixin._selection_listcCs(|jdus t|jtr|jS|j|jSr])rprsror$rArCrCrD _selected_objs zSelectionMixin._selected_objrGrScC|jjSr])ryndimrArCrCrDr{zSelectionMixin.ndimcCsRt|jtr |jS|jdur|j|jSt|jdkr&|jj|jdddS|jS)NrT)axisZ only_slice) rsror$rpZ_getitem_nocopyrxlenrqZ _drop_axisrArCrCrD_obj_with_exclusionss  z#SelectionMixin._obj_with_exclusionscCs|jdurtd|jdt|tttttjfrIt |j j |t t |kr@tt ||j j }tdt|dd|jt|ddS||j vrUtd||j |j}|j||dS) Nz Column(s) z already selectedzColumns not found: r})r{zColumn not found: )rp IndexErrorrsrtrur$r#rvrwrrocolumns intersectionset differenceKeyErrorrH_gotitemr{)rBrLbad_keysr{rCrCrD __getitem__s   zSelectionMixin.__getitem__r{cCt|)a sub-classes to define return a sliced object Parameters ---------- key : str / list of selections ndim : {1, 2} requested ndim of result subset : object, default None subset to act on r)rBrLr{ZsubsetrCrCrDrs zSelectionMixin._gotitemcOrr]r)rBfuncargskwargsrCrCrD aggregateszSelectionMixin.aggregater^r])r{rS)r_r`rarbrcrpZ_internal_namesrZ_internal_names_setr rdrxrryr{rrrrZaggrCrCrCrDrns,      rnc@seZdZUdZdZedgZded<eddd Z edd d Z e dddZ ee ddZ edddZdddZedddZe ddZedddZedd d!Zedd#d$Ze d%d&ejfdd.d/Ze edd0d1Zddd6d7Zed8d9d:d; 2dddd?Zeed9d8d@d; 2dddAdBZdCdDZeZddFdGZ e!ddHdIZ"ddKdLZ#dMd2d%d%dNddRdSZ$e ddTdUZ%e & 2 & % 2ddd[d\Z&d]d^Z'e ddd_d`Z(eddadbZ)eddcddZ*eddedfZ+e dddhdiZ,ee-j.djdjdje/0dkdl & 2dddodpZ.dqe1dr<e2 s sddd{d|Z3e2 s sdddd|Z3ee1drdd %dddd|Z3dddddZ4e ddddZ5ddZ6ddZ7d%S)r7zS Common ops mixin to support a unified interface / docs for Series / Index itolistzfrozenset[str] _hidden_attrsrGrcCrr]rrArCrCrDdtyper|zIndexOpsMixin.dtypeExtensionArray | np.ndarraycCrr]rrArCrCrD_valuesr|zIndexOpsMixin._valuesrBr<cOst|||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. )rrcCrz)z Return a tuple of the shape of the underlying data. Examples -------- >>> s = pd.Series([1, 2, 3]) >>> s.shape (3,) )rshaperArCrCrDr5s zIndexOpsMixin.shaperScCrr]rrArCrCrD__len__BszIndexOpsMixin.__len__ Literal[1]cCsdS)zO Number of dimensions of the underlying data, by definition 1. r}rCrArCrCrDr{FszIndexOpsMixin.ndimcCs t|dkr tt|Std)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. r}z6can only convert an array of size 1 to a Python scalar)rnextiter ValueErrorrArCrCrDitemMs  zIndexOpsMixin.itemcCrz)zD Return the number of bytes in the underlying data. )rnbytesrArCrCrDr`rFzIndexOpsMixin.nbytescC t|jS)zG Return the number of elements in the underlying data. )rrrArCrCrDsizegrKzIndexOpsMixin.sizer,cCr)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'] rrArCrCrDarrayns?zIndexOpsMixin.arrayNFrnpt.DTypeLike | Nonecopyboolna_valuerI np.ndarraycKst|jr|jj|f||d|S|r$t|d}td|d|tjurG|j }t ||s9t j ||d}n| }||t |<n|j }t j ||d}|rX|tjus]|strt |j dd|ddrtr{|s{|}d|j_|S| }|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 'rjrNrF)rrrto_numpyrtkeys TypeErrorr no_defaultrrrvZasarrayrZ asanyarrayr%r Z shares_memoryviewflagsZ writeable)rBrrrrrvaluesresultrCrCrDrs6 _    zIndexOpsMixin.to_numpycCs|j Sr])rrArCrCrDempty3r|zIndexOpsMixin.emptyTr~AxisInt | NoneskipnacO&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(ZnanmaxrrBr~rrrrCrCrDmax8 ( zIndexOpsMixin.maxrminZlargest)opZopposermcOR|j}t|t|||}t|tr"|s|rdS|St j ||dS)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. rr) rrrZvalidate_argmax_with_skipnarsr,r%anyargmaxr(Z nanargmaxrBr~rrrZdelegaterCrCrDrds6  zIndexOpsMixin.argmaxcOr)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(ZnanminrrrCrCrDrrzIndexOpsMixin.minZsmallestcOr)Nrr) rrrZvalidate_argmin_with_skipnarsr,r%rargminr(Z nanargminrrCrCrDrs  zIndexOpsMixin.argmincCs |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. )rrrArCrCrDrs zIndexOpsMixin.tolistrcCs.t|jtjs t|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 ) rsrrvrwrmaprrangerrArCrCrD__iter__s zIndexOpsMixin.__iter__cCstt|S)z Return True if there are any NaNs. Enables various performance speedups. Returns ------- bool )rr%rrArCrCrDhasnanss zIndexOpsMixin.hasnansnpt.NDArray[np.bool_]cCrr])r%rrArCrCrDr%!s zIndexOpsMixin.isnar)r~r numeric_only filter_typenamerHrc Ks>t||d}|durtt|jd||dd|i|S)zA Perform the reduction type operation if we can. Nz cannot perform the operation rrC)rWrr@r_) rBrrr~rrrkwdsrrCrCrD_reduce$s zIndexOpsMixin._reducec s`t|r/t|trt|dr|fdd}nddlm}t|dkr+||tjd}n||}t|t ro|dvrBd|d }t ||d krM||j }t |jr]td |j}||S|j}|j |}t|j|}|St|jrt|jd r|j}|d urtdd} n!|jt}|d krdd} n|d urtj} n d|d }t || ||}|S)a An internal function that maps values using the input correspondence (which can be a dict, Series, or function). Parameters ---------- mapper : function, dict, or Series The input correspondence object na_action : {None, 'ignore'} If 'ignore', propagate NA values, without passing them to the mapping function Returns ------- Union[Index, MultiIndex], inferred The output of the mapping function applied to the index. If the function returns a tuple with more than one element a MultiIndex will be returned. __missing__cs$t|trt|rtjS|Sr])rsfloatrvisnannan)xZdict_with_defaultrCrDVs z+IndexOpsMixin._map_values..r)r5r)Nignorez+na_action must either be 'ignore' or None, z was passedrr3rNcSs ||Sr])rrfrCrCrDrs cSst||t|tjSr])rZmap_infer_maskr%rrvZuint8rrCrCrDrs)rrsdictrOpandasr5rrvZfloat64r$rindexZnotnarrr rrZ get_indexerr'Ztake_ndrNotImplementedErrorastyperIrZ map_infer) rBZmapperZ na_actionr5msgcatrZindexer new_valuesZmap_frCrrD _map_values9sR          zIndexOpsMixin._map_values normalizesort ascendingdropnar5cCstj||||||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|}|St|}|Sr])rrsrvrwr:r'Zunique1d)rBrrrCrCrDr:s   zIndexOpsMixin.uniquecCs|}|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)rBrZuniqsrCrCrDnunique s#zIndexOpsMixin.nuniquecCs|jddt|kS)zr Return boolean if values in the object are unique. Returns ------- bool F)r)rrrArCrCrD is_unique1s zIndexOpsMixin.is_uniquecCddlm}||jS)z Return boolean if values in the object are monotonically increasing. Returns ------- bool rr4)rr4is_monotonic_increasingrBr4rCrCrDr< z%IndexOpsMixin.is_monotonic_increasingcCr)z Return boolean if values in the object are monotonically decreasing. Returns ------- bool rr)rr4is_monotonic_decreasingrrCrCrDrIrz%IndexOpsMixin.is_monotonic_decreasingrVcCsRt|jdr |jj|dS|jj}|r't|r'ts'ttj|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 rTrU) rOrrTrr rr rvrwrrZmemory_usage_of_objects)rBrVvrrCrCrD _memory_usageVs zIndexOpsMixin._memory_usager8z sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. )rorderZ size_hintruse_na_sentinel"tuple[npt.NDArray[np.intp], Index]cCsftj|j||d\}}|jtjkr|tj}t|t r%| |}||fSddl m }||}||fS)N)rrrr) r' factorizerrrvZfloat16rZfloat32rsr#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.rmr2sideLiteral['left', 'right']sorterr0np.intpcCdSr]rCrBrmrrrCrCrDrs zIndexOpsMixin.searchsortednpt.ArrayLike | ExtensionArraynpt.NDArray[np.intp]cCrr]rCrrCrCrDrsr4)r9left$NumpyValueArrayLike | ExtensionArraynpt.NDArray[np.intp] | np.intpcCsXt|trdt|jd}t||j}t|tjs#|j|||dSt j||||dS)Nz(Value must be 1-D array-like or scalar, z is not supported)rr) rsr"r@r_rrrvrwrr')rBrmrrrrrCrCrDrs  firstkeeprr/cCs|j|d}||SNr) _duplicated)rBrr;rCrCrDdrop_duplicates2s  zIndexOpsMixin.drop_duplicatescCstj|j|dSr)r'r;r)rBrrCrCrDr7szIndexOpsMixin._duplicatedcCs~t||}|j}t|ddd}t||j}t|}tjddt |||}Wdn1s3wY|j ||dS)NT)Z extract_numpyZ extract_ranger)all)r) r)Zget_op_result_namerr.Zmaybe_prepare_scalar_for_oprr-rvZerrstateZ arithmetic_op_construct_result)rBotherrZres_nameZlvaluesZrvaluesrrCrCrD _arith_method;s zIndexOpsMixin._arith_methodcCr)z~ Construct an appropriately-wrapped result from the ArrayLike result of an arithmetic-like operation. r)rBrrrCrCrDrHrFzIndexOpsMixin._construct_result)rGr)rGr)rBr<rGr<)rGrr^)rGr)rGr,)rrrrrrIrGr)rGr)NT)r~rrr)r~rrrrGrS)rGr)rGr)rrHr~rrrr])FTFNT) rrrrrrrrrGr5)T)rrrGrS)F)rVrrGrS)FT)rrrrrGr)..)rmr2rrrr0rGr)rmrrrrr0rGr)rN)rmrrrrr0rGr)rr/)r)rr/rGr)8r_r`rarbZ__array_priority__ frozensetrrcrdrrr rTrrr{rrrrrrrrrrrrrrZto_listrrrr%rrrr:rrrrrr'rtextwrapdedentr6r rrrrrrCrCrCrDr7 s             @  , E,    f_ '    #g )Srb __future__rr typingrrrrrrr r r r numpyrvZpandas._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/r0r1r2rr3r4r5r6rcZ_indexops_doc_kwargsr<r>rfrnr7rCrCrCrDsF 0  $        /"X