OwgRdZddlmZddlZddlZddlmZddlmZm Z m Z ddl Z ddl Z ddlmZmZmZmZddlmZmZmZmZmZmZddlmZdd lmZdd lm Z m!Z!dd l"m#Z#m$Z$m%Z%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1dd l2m3Z3dd l4m5Z5m6Z6m7Z7m8Z8ddl9m:Z:m;Z;mZ>m?Z?ddl@mAZAmBZBddlCmDZDddlEmFZGmHZHmIZIddlJmKZKerddlmLZLmMZMmNZNddlOmPZPmQZQmRZRddlSmTZTmUZUd6dZV d7dZWd8dZXejejejejejejejejejejejejejejdZgd9dZhd:dZidZjd;dZkdd Zo d? d@d!Zpeed"ed#ed$% dA dBd&Zq dC dDd'Zr dC dDd(Zs d< dEd)Zt dF dGd*Zu dH dId+Zv dJ dKd,Zw dL dMd-Zx dN dOd.Zyhd/ZzdPdQd0Z{ dR dSd1Z|dTd2Z}dUd3Z~ dVd4Z dW dXd5Zy)Yzl Generic data algorithms. This module is experimental at the moment and not intended for public consumption ) annotationsN)dedent) TYPE_CHECKINGLiteralcast)algos hashtableiNaTlib) AnyArrayLike ArrayLikeAxisIntDtypeObj TakeIndexernpt)doc)find_stack_level)'construct_1d_object_array_from_listlikenp_find_common_type)ensure_float64 ensure_objectensure_platform_int is_array_like is_bool_dtypeis_complex_dtype is_dict_likeis_extension_array_dtypeis_float_dtype is_integeris_integer_dtype is_list_likeis_object_dtypeis_signed_integer_dtypeneeds_i8_conversion) concat_compat)BaseMaskedDtypeCategoricalDtypeExtensionDtype NumpyEADtype)ABCDatetimeArrayABCExtensionArrayABCIndex ABCMultiIndex ABCSeriesABCTimedeltaArray)isnana_value_for_dtype)take_nd)arrayensure_wrapped_if_datetimelike extract_array)validate_indices)ListLike NumpySorterNumpyValueArrayLike) CategoricalIndexSeries)BaseMaskedArrayExtensionArrayct|ts t|d}t|jrt t j|St|jtrBtd|}|jst|jSt j|St|jtrtd|}|jSt|jrdt|t j r$t j|j#dSt j|j%ddSt'|jrt j|St)|jr8|jj*dvr t-|St j|St/|jrtt j |St1|jr-|j#d }tt j |}|St j|t2 }t |S) a routine to ensure that our data is of the correct input dtype for lower-level routines This will coerce: - ints -> int64 - uint -> uint64 - bool -> uint8 - datetimelike -> i8 - datetime64tz -> i8 (in local tz) - categorical -> codes Parameters ---------- values : np.ndarray or ExtensionArray Returns ------- np.ndarray T extract_numpyr=r:uint8Fcopy) i8dtype) isinstancer-r5r"rJrnpasarrayr&r_hasna _ensure_data_datar'codesrndarrayviewastyper ritemsizerrr$object)valuesnpvaluess M/var/www/horilla/myenv/lib/python3.12/site-packages/pandas/core/algorithms.pyrOrOjs, fm ,vT:v||$RZZ/00 FLL/ 2'0}}  - -zz&!! FLL"2 3mV,|| v|| $ fbjj )::f%**73 3::f%,,W5,A A &,, 'zz&!!  % << K /!&) )zz&!! &,, 'BJJ'' V\\ *;;t$ H-ZZf -F   ct|tr|j|k(r|St|tjs%|j }|j ||}|S|j |d}|S)z reverse of _ensure_data Parameters ---------- values : np.ndarray or ExtensionArray dtype : np.dtype or ExtensionDtype original : AnyArrayLike Returns ------- ExtensionArray or np.ndarray rIFrC)rKr+rJrLconstruct_array_type_from_sequencerT)rWrJoriginalclss rY_reconstruct_datar`sr &+,1F eRXX &((*##F%#8 Mu51 MrZcbt|ttttj fs|dk7r't j|dtttj|d}|dvr(t|tr t|}t|}|St j|}|S)z5 ensure that we are arraylike if not already isin-targetsz with argument that is not not a Series, Index, ExtensionArray, or np.ndarray is deprecated and will raise in a future version. stacklevelFskipna)mixedstring mixed-integer)rKr,r.r+rLrRwarningswarn FutureWarningrr infer_dtypetuplelistrrM)rW func_nameinferreds rY_ensure_arraylikerrs fx4ErzzR S  & MM+""+-  ??6%8 ; ;&%(f>> pd.unique(pd.Series([2, 1, 3, 3])) array([2, 1, 3]) >>> pd.unique(pd.Series([2] + [1] * 5)) array([2, 1]) >>> pd.unique(pd.Series([pd.Timestamp("20160101"), pd.Timestamp("20160101")])) array(['2016-01-01T00:00:00.000000000'], dtype='datetime64[ns]') >>> pd.unique( ... pd.Series( ... [ ... pd.Timestamp("20160101", tz="US/Eastern"), ... pd.Timestamp("20160101", tz="US/Eastern"), ... ] ... ) ... ) ['2016-01-01 00:00:00-05:00'] Length: 1, dtype: datetime64[ns, US/Eastern] >>> pd.unique( ... pd.Index( ... [ ... pd.Timestamp("20160101", tz="US/Eastern"), ... pd.Timestamp("20160101", tz="US/Eastern"), ... ] ... ) ... ) DatetimeIndex(['2016-01-01 00:00:00-05:00'], dtype='datetime64[ns, US/Eastern]', freq=None) >>> pd.unique(np.array(list("baabc"), dtype="O")) array(['b', 'a', 'c'], dtype=object) An unordered Categorical will return categories in the order of appearance. >>> pd.unique(pd.Series(pd.Categorical(list("baabc")))) ['b', 'a', 'c'] Categories (3, object): ['a', 'b', 'c'] >>> pd.unique(pd.Series(pd.Categorical(list("baabc"), categories=list("abc")))) ['b', 'a', 'c'] Categories (3, object): ['a', 'b', 'c'] An ordered Categorical preserves the category ordering. >>> pd.unique( ... pd.Series( ... pd.Categorical(list("baabc"), categories=list("abc"), ordered=True) ... ) ... ) ['b', 'a', 'c'] Categories (3, object): ['a' < 'b' < 'c'] An array of tuples >>> pd.unique(pd.Series([("a", "b"), ("b", "a"), ("a", "c"), ("b", "a")]).values) array([('a', 'b'), ('b', 'a'), ('a', 'c')], dtype=object) )unique_with_mask)rWs rYuniquer3s| F ##rZct|dk(ryt|}tj|j j ddk7j }|S)aH Return the number of unique values for integer array-likes. Significantly faster than pandas.unique for long enough sequences. No checks are done to ensure input is integral. Parameters ---------- values : 1d array-like Returns ------- int : The number of unique values in ``values`` rintp)lenrOrLbincountravelrTsum)rWresults rY nunique_intsrsO 6{a & !Fkk&,,.//78A= B B DF MrZct|d}t|jtr|j S|}t |\}}|t |}|*|j |}t||j|}|S|j ||\}}t||j|}|J||jdfS)z?See algorithms.unique for docs. Takes a mask for masked arrays.rrpmaskbool) rrrKrJr(rrrr`rT)rWrr^r tableuniquess rYrrs v :F&,,/}}H+F3Iv c&k "E |,,v&#GX^^XF V$ 7 #GX^^XF F+++rZi@Bct|s"tdt|jdt|s"tdt|jdt |t t ttjfsUt|}t|d}t|dkDrc|jjdvrKt|s@t!|}n4t |t"rtj$|}nt'|dd}t|d }t'|d }t |tjs|j)|St+|jrt-|j)|St+|jr:t/|js%tj0|j2t4 St+|jrt)||j7t8St |jt:r2t)tj<|tj<|St|t>kDrBt|d kr4|jt8k7r!tA|jCrd }nZd}nVtE|j|j}|j7|d}|j7|d}tFjH}|||S)z Compute the isin boolean array. Parameters ---------- comps : list-like values : list-like Returns ------- ndarray[bool] Same length as `comps`. zIonly list-like objects are allowed to be passed to isin(), you passed a ``rbrriufcbT)rA extract_rangeisinr@rIctjtj||jtj|SN)rL logical_orrrisnan)cvs rYfzisin..fs.}}RWWQ]%8%8%:BHHQKHHrZcJtj||jSr)rLrr)abs rYzisin..sRWWQ]002rZFrC)%r! TypeErrortype__name__rKr,r.r+rLrRrorrrrJkindr#rr-r3r5rr$pd_arrayr"zerosshaperrTrVr(rM_MINIMUM_COMP_ARR_LENr0anyrhtableismember)compsrW orig_values comps_arrayrcommons rYrrsj   ((,U (<(<'=Q @     ((,V (=(='>a A  fx4ErzzR S6l ";.I K!O !!W,+E2=[IF FM *&!vTN#EVrZz values : sequence A 1-D sequence. Sequences that aren't pandas objects are coerced to ndarrays before factorization. zt sort : bool, default False Sort `uniques` and shuffle `codes` to maintain the relationship. zG size_hint : int, optional Hint to the hashtable sizer. )rWsortrct|ttfr|j||St |d}|}t|t t fr%|j|j|\}}||fSt|tjs|j|\}}ntj|}|s\|jtk(rIt|}|jr.t|jd}tj |||}t#|||\}}|r!t%|d kDrt'|||d d \}}t)||j|}||fS) aN Encode the object as an enumerated type or categorical variable. This method is useful for obtaining a numeric representation of an array when all that matters is identifying distinct values. `factorize` is available as both a top-level function :func:`pandas.factorize`, and as a method :meth:`Series.factorize` and :meth:`Index.factorize`. Parameters ---------- {values}{sort} use_na_sentinel : bool, default True If True, the sentinel -1 will be used for NaN values. If False, NaN values will be encoded as non-negative integers and will not drop the NaN from the uniques of the values. .. versionadded:: 1.5.0 {size_hint} Returns ------- codes : ndarray An integer ndarray that's an indexer into `uniques`. ``uniques.take(codes)`` will have the same values as `values`. uniques : ndarray, Index, or Categorical The unique valid values. When `values` is Categorical, `uniques` is a Categorical. When `values` is some other pandas object, an `Index` is returned. Otherwise, a 1-D ndarray is returned. .. note:: Even if there's a missing value in `values`, `uniques` will *not* contain an entry for it. See Also -------- cut : Discretize continuous-valued array. unique : Find the unique value in an array. Notes ----- Reference :ref:`the user guide ` for more examples. Examples -------- These examples all show factorize as a top-level method like ``pd.factorize(values)``. The results are identical for methods like :meth:`Series.factorize`. >>> codes, uniques = pd.factorize(np.array(['b', 'b', 'a', 'c', 'b'], dtype="O")) >>> codes array([0, 0, 1, 2, 0]) >>> uniques array(['b', 'a', 'c'], dtype=object) With ``sort=True``, the `uniques` will be sorted, and `codes` will be shuffled so that the relationship is the maintained. >>> codes, uniques = pd.factorize(np.array(['b', 'b', 'a', 'c', 'b'], dtype="O"), ... sort=True) >>> codes array([1, 1, 0, 2, 1]) >>> uniques array(['a', 'b', 'c'], dtype=object) When ``use_na_sentinel=True`` (the default), missing values are indicated in the `codes` with the sentinel value ``-1`` and missing values are not included in `uniques`. >>> codes, uniques = pd.factorize(np.array(['b', None, 'a', 'c', 'b'], dtype="O")) >>> codes array([ 0, -1, 1, 2, 0]) >>> uniques array(['b', 'a', 'c'], dtype=object) Thus far, we've only factorized lists (which are internally coerced to NumPy arrays). When factorizing pandas objects, the type of `uniques` will differ. For Categoricals, a `Categorical` is returned. >>> cat = pd.Categorical(['a', 'a', 'c'], categories=['a', 'b', 'c']) >>> codes, uniques = pd.factorize(cat) >>> codes array([0, 0, 1]) >>> uniques ['a', 'c'] Categories (3, object): ['a', 'b', 'c'] Notice that ``'b'`` is in ``uniques.categories``, despite not being present in ``cat.values``. For all other pandas objects, an Index of the appropriate type is returned. >>> cat = pd.Series(['a', 'a', 'c']) >>> codes, uniques = pd.factorize(cat) >>> codes array([0, 0, 1]) >>> uniques Index(['a', 'c'], dtype='object') If NaN is in the values, and we want to include NaN in the uniques of the values, it can be achieved by setting ``use_na_sentinel=False``. >>> values = np.array([1, 2, 1, np.nan]) >>> codes, uniques = pd.factorize(values) # default: use_na_sentinel=True >>> codes array([ 0, 1, 0, -1]) >>> uniques array([1., 2.]) >>> codes, uniques = pd.factorize(values, use_na_sentinel=False) >>> codes array([0, 1, 0, 2]) >>> uniques array([ 1., 2., nan]) )rrrr)r)rF)compat)rrrT)r assume_uniqueverify)rKr,r.rrrr*r/freqrLrRrMrJrVr0rr1whererr safe_sortr`) rWrrrr^rQr null_maskrs rYrrbsVp&8Y/0T?KK v =FH 6,.?@A KK # ))t)4wg~  +))/)JwF#6<<6#9 V I}}-fll5I)Xv>( + w  G q "  +   BG '>rZcltjdttt ||||||S)aK Compute a histogram of the counts of non-null values. Parameters ---------- values : ndarray (1-d) sort : bool, default True Sort by values ascending : bool, default False Sort in ascending order normalize: bool, default False If True then compute a relative histogram bins : integer, optional Rather than count values, group them into half-open bins, convenience for pd.cut, only works with numeric data dropna : bool, default True Don't include counts of NaN Returns ------- Series zupandas.value_counts is deprecated and will be removed in a future version. Use pd.Series(obj).value_counts() instead.rc)r ascending normalizebinsdropna)rjrkrlrvalue_counts_internal)rWrrrrrs rY value_countsr/s@< MM E#%  !    rZcddlm}m}t|dd}|rdnd} |ddlm} t ||r |j} | ||d} | j| } | | _ | | jj} | jjd | _ | j} |r,| jdk(jr| j dd} t#j$t'| g}nt)|rz||d jj| } | | _ || j_ | j}t |t"j*st#j,|}n{t |t.rot1t3|j4}||| j7||j9} |j:| j_| j}nt=|d}t?||\}}}|j@t"jBk(r|jt"jD}||}|j@tFk(r)|j@tHk(r|jtH}nL|j@|j@k7r3|j@dk7r$tKjLdtNtQ||_ |||| d } |r| jS|} |r| |jUz } | S#t$r} td | d} ~ wwxYw)Nr)r;r<r proportioncount)cutT)include_lowestz+bins argument only works with numeric data.rintervalFrC)indexr)levelrrrzstring[pyarrow_numpy]zThe behavior of value_counts with object-dtype is deprecated. In a future version, this will *not* perform dtype inference on the resulting index. To retain the old behavior, use `result.index = result.index.infer_objects()`rc)rrrD)r)+pandasr;r<getattrpandas.core.reshape.tilerrK_valuesrrrrnotnarT sort_indexallilocrLr3rrrRrMr-rorangenlevelsgroupbysizenamesrrvalue_counts_arraylikerJfloat16rvrrVrjrkrlr sort_valuesr)rWrrrrrr;r< index_namerriierrrcountslevelskeys_idxs rYrr^s .J$<'D 0 ff %^^F TVT$7B /  **,-||**:6 ""$ v~~*//1[[1%F3r7)$ $F +F/77DDFDSFFK *FLL ^^Ffbjj1F+  .%/0FV$/vf5  "(FLL ^^F'vHF4VVDOD&!zzRZZ'{{2::.+CyyD TZZ6%9jj( TZZ'II!88 D"/1"CHF#DuEF ##i#8&**,& MS TIJPS S Ts L(( M1 L==Mc|}t|}tj|||\}}}t|jr|r|t k7}||||}}t ||j|}|||fS)z Parameters ---------- values : np.ndarray dropna : bool mask : np.ndarray[bool] or None, default None Returns ------- uniques : np.ndarray counts : np.ndarray[np.int64] r)rOr value_countr$rJr r`)rWrrr^rr na_counterres_keyss rYrrsxH & !F%11&&tLD&*8>>* 4r)rrNzUnable to sort modes: rc)rrr$rJr4r_moderOrrrLrrrjrkrr`)rWrrr^npresultres_maskrrs rYrrs"v 8FH6<<(/7&/||6|** & !FVFFHh!! 778$x BF M   $SE *')   s;B)) C2"CCc  t|j}t|}|jdk(rt j ||||||}|S|jdk(rt j |||||||}|Std)a Rank the values along a given axis. Parameters ---------- values : np.ndarray or ExtensionArray Array whose values will be ranked. The number of dimensions in this array must not exceed 2. axis : int, default 0 Axis over which to perform rankings. method : {'average', 'min', 'max', 'first', 'dense'}, default 'average' The method by which tiebreaks are broken during the ranking. na_option : {'keep', 'top'}, default 'keep' The method by which NaNs are placed in the ranking. - ``keep``: rank each NaN value with a NaN ranking - ``top``: replace each NaN with either +/- inf so that they there are ranked at the top ascending : bool, default True Whether or not the elements should be ranked in ascending order. pct : bool, default False Whether or not to the display the returned rankings in integer form (e.g. 1, 2, 3) or in percentile form (e.g. 0.333..., 0.666..., 1). )is_datetimelike ties_methodr na_optionpctrE)axisrrrrrz&Array with ndim > 2 are not supported.)r$rJrOndimrrank_1drank_2dr)rWrmethodrrrrrankss rYrankr +s>*&,,7O & !F {{a +  * L   +  L@AArZcxt|tjttt fs$t jdttt|stj|}t|}|r+t||j|t|||d|}|S|j!||}|S)ak Take elements from an array. Parameters ---------- arr : array-like or scalar value Non array-likes (sequences/scalars without a dtype) are coerced to an ndarray. .. deprecated:: 2.1.0 Passing an argument other than a numpy.ndarray, ExtensionArray, Index, or Series is deprecated. indices : sequence of int or one-dimensional np.ndarray of int Indices to be taken. axis : int, default 0 The axis over which to select values. allow_fill : bool, default False How to handle negative values in `indices`. * False: negative values in `indices` indicate positional indices from the right (the default). This is similar to :func:`numpy.take`. * True: negative values in `indices` indicate missing values. These values are set to `fill_value`. Any other negative values raise a ``ValueError``. fill_value : any, optional Fill value to use for NA-indices when `allow_fill` is True. This may be ``None``, in which case the default NA value for the type (``self.dtype.na_value``) is used. For multi-dimensional `arr`, each *element* is filled with `fill_value`. Returns ------- ndarray or ExtensionArray Same type as the input. Raises ------ IndexError When `indices` is out of bounds for the array. ValueError When the indexer contains negative values other than ``-1`` and `allow_fill` is True. Notes ----- When `allow_fill` is False, `indices` may be whatever dimensionality is accepted by NumPy for `arr`. When `allow_fill` is True, `indices` should be 1-D. See Also -------- numpy.take : Take elements from an array along an axis. Examples -------- >>> import pandas as pd With the default ``allow_fill=False``, negative numbers indicate positional indices from the right. >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1]) array([10, 10, 30]) Setting ``allow_fill=True`` will place `fill_value` in those positions. >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1], allow_fill=True) array([10., 10., nan]) >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1], allow_fill=True, ... fill_value=-10) array([ 10, 10, -10]) zpd.api.extensions.take accepting non-standard inputs is deprecated and will raise in a future version. Pass either a numpy.ndarray, ExtensionArray, Index, or Series instead.rcT)r allow_fill fill_value)r)rKrLrRr+r,r.rjrkrlrrrMrr6rr2take)arrindicesrrrrs rYrrksj cBJJ(98YO P  8 ')    jjo!'*G#))D/2 t  M'- MrZc| t|}t|tjr(|jj dvrt |s t|rtj|jj}t |rtj|gntj|}||jk\jr*||jkjr |j}n |j}t |r tt|j|}n't!tt"||}n t%|}|j'|||S)a Find indices where elements should be inserted to maintain order. Find the indices into a sorted array `arr` (a) such that, if the corresponding elements in `value` were inserted before the indices, the order of `arr` would be preserved. Assuming that `arr` is sorted: ====== ================================ `side` returned index `i` satisfies ====== ================================ left ``arr[i-1] < value <= self[i]`` right ``arr[i-1] <= value < self[i]`` ====== ================================ Parameters ---------- arr: np.ndarray, ExtensionArray, Series Input array. If `sorter` is None, then it must be sorted in ascending order, otherwise `sorter` must be an array of indices that sort it. value : array-like or scalar Values to insert into `arr`. side : {'left', 'right'}, optional If 'left', the index of the first suitable location found is given. If 'right', return the last such index. If there is no suitable index, return either 0 or N (where N is the length of `self`). sorter : 1-D array-like, optional Optional array of integer indices that sort array a into ascending order. They are typically the result of argsort. Returns ------- array of ints or int If value is array-like, array of insertion points. If value is scalar, a single integer. See Also -------- numpy.searchsorted : Similar method from NumPy. iurI)sidesorter)rrKrLrRrJrrr iinforr3minrmaxrintrr r4 searchsorted)rvaluerrr value_arrrJs rYrrs`$V, 3 # IINNd "  "25"9 ()3E):BHHeW%  " ' ' )yEII/E.J.J.LIIEOOE e ejj/0ET)U35AE-S1   EV  <r}r|r{rzrvruc\t|}tj}|j}t |}|rt j }nt j}t|tr|j}|j}t|tjs|t|d|jdrA|dk7r$tdt|jd||||j!|St#t|jdd}|jj$dvr*tj&}|j)d}t*}d }nZ|rtj,}nG|j$d vr9|jj.d vrtj0}ntj2}|j4}|d k(r|j7d d }tj|}tj8|j:|} t=dgdz} |dk\r t=d|n t=|d| |<|| t?| <|jj.t@vrtCjD|| |||nt=dgdz} |dk\r t=|dn t=d|| |<t?| } t=dgdz} |dkDr t=d| n t=| d| |<t?| }||| ||| | <|r| j)d} |d k(r | dddf} | S)aQ difference of n between self, analogous to s-s.shift(n) Parameters ---------- arr : ndarray or ExtensionArray n : int number of periods axis : {0, 1} axis to shift on stacklevel : int, default 3 The stacklevel for the lost dtype warning. Returns ------- shifted __rz cannot diff z on axis=zK has no 'diff' method. Convert to a suitable dtype prior to calling 'diff'.FrrHTr)r}r|rrrINrE) datetimelikeztimedelta64[ns])#rrLnanrJroperatorxorsubrKr)to_numpyrRhasattrr ValueErrorrshiftrrrzrSr object_rrvrurreshapeemptyrslicern _diff_specialrdiff_2d)rnrnarJis_boolop is_timedelta orig_ndimout_arr na_indexer _res_indexer res_indexer _lag_indexer lag_indexers rYdiffr;;s( AA B IIEE"G \\ \\%&lln  c2:: & 3"R[[M, -qy <S 0B0B/C9TF!STTc399Q<( (9%%&'GG  L yy~~hhtn    t  99>>. .JJEJJEIA~kk"a  HHUOEhhsyy.G+"J)*auT1~U1d^Jt!#GE*  yy~~&  c7At,Gd }q( /0AvU1d^5q> TL) d }q( 01AU4!_5!T? TL) !#k"2C 4DE ,,01A~!Q$- NrZc8t|tjttfs t dd}t|j ts&tj|ddk(r t|}n" |j}|j|}||St%|s t dt'tj(|}|s+t+t-|t+|k(s t/d|Jt1|\}}|t+|}|j3|t'|j5|}|rG|j} |r$|t+| k|t+|k\z} d|| <nd} t7| |d } ntj8t+|t: } | j=|tj>t+|| j|d } |r(|d k(} |r!| |t+| kz|t+|k\z} |r tj@| | d |t'| fS#t tjf$r:|jrt|dt r t#|}n t|}YwxYw)a Sort ``values`` and reorder corresponding ``codes``. ``values`` should be unique if ``codes`` is not None. Safe for use with mixed types (int, str), orders ints before strs. Parameters ---------- values : list-like Sequence; must be unique if ``codes`` is not None. codes : np.ndarray[intp] or None, default None Indices to ``values``. All out of bound indices are treated as "not found" and will be masked with ``-1``. use_na_sentinel : bool, default True If True, the sentinel -1 will be used for NaN values. If False, NaN values will be encoded as non-negative integers and will not drop the NaN from the uniques of the values. assume_unique : bool, default False When True, ``values`` are assumed to be unique, which can speed up the calculation. Ignored when ``codes`` is None. verify : bool, default True Check if codes are out of bound for the values and put out of bound codes equal to ``-1``. If ``verify=False``, it is assumed there are no out of bound codes. Ignored when ``codes`` is None. Returns ------- ordered : AnyArrayLike Sorted ``values`` new_codes : ndarray Reordered ``codes``; returned when ``codes`` is not None. Raises ------ TypeError * If ``values`` is not list-like or if ``codes`` is neither None nor list-like * If ``values`` cannot be sorted ValueError * If ``codes`` is not None and ``values`` contain duplicates. zbOnly np.ndarray, ExtensionArray, and Index objects are allowed to be passed to safe_sort as valuesNFrerirzMOnly list-like objects or None are allowed to be passed to safe_sort as codesz,values should be unique if codes is not NonerrrIwrap)r)!rKrLrRr+r,rrJr(r rm _sort_mixedargsortrdecimalInvalidOperationrrn _sort_tuplesr!rrMrrr'r map_locationslookupr2r+rputarangeputmask) rWrQrrrrorderedrtorder2r new_codesreverse_indexers rYrrsZ` frzz+Hh("G**VG_-K**VG_-K #((5H #((5H  "1%I >>8Xy9 :D ;;t <1s D! D&cPddlm}ddlm}||d\}}||d}||S)a Convert array of tuples (1d) to array of arrays (2d). We need to keep the columns separately as they contain different types and nans (can't use `np.sort` as it may fail when str and nan are mixed in a column as types cannot be compared). r) to_arrays)lexsort_indexerNT)orders)"pandas.core.internals.constructionr]pandas.core.sortingr^)rWr]r^arraysrindexers rYrCrC=s0=3&$'IFAfT2G '?rZcddlm}tj5tjddt t |d}t |d}dddjd \}}tj|j|j}|||jd d }t|tr0t|tr |j|j}n[t|t r |j"}t|t r |j"}t%||g}t|}t'|}|j)|j}tj*||S#1swY,xYw) a Extracts the union from lvals and rvals with respect to duplicates and nans in both arrays. Parameters ---------- lvals: np.ndarray or ExtensionArray left values which is ordered in front. rvals: np.ndarray or ExtensionArray right values ordered after lvals. Returns ------- np.ndarray or ExtensionArray Containing the unsorted union of both arrays. Notes ----- Caller is responsible for ensuring lvals.dtype == rvals.dtype. rr<ignorez.s10$Q.288A; DE rZrrerIrfFrC)convert)rr})r'rrKdictr&rr<rrLrur.rr get_indexerr2rrDrTrVr map_infermap_infer_maskr0rSrB) rmapper na_actionr}msgr<rc new_valuesrWr|s @rY map_arrayrs@6((;I;kRo F fd # (F!' F &6{abjj9&)$  FLL..01F,,**3/V^^W5  s8xxzZZUZ +F}}VVW==!! Ff!2!2288!rOr`rrComplex128HashTableComplex64HashTableFloat64HashTableFloat32HashTableUInt64HashTableUInt32HashTableUInt16HashTableUInt8HashTableInt64HashTableInt32HashTableInt16HashTable Int8HashTableStringHashTablePyObjectHashTablerrrrrrunique1drrrrrrrrrr rrr-r;rr?rCrwrrZrYrs#  (4"4  1 2  K!\ &2>B8,,**&&&&$$$$$$  " "  " "  " "  " "  $$&& $$6^$B.,0 "X"z! )- ; ;;; ; ' ; - ;|       0  t tt t + t-,tr  , ,, ,  , ,b  a aa a  a aLLP( ( $(,H(1(B-4)-; ; ); '; ;<RV) )#)2N))\ 8 8 8 8 8  8  88F m m m mp&,!% Q= Q= /Q= #Q=  Q= $ Q=pJ gf*.  3 3 &33 3  3 4 3D  4+ 4+%64+4+t+/ P P (P  P ) P rZ