B ln¦d+Xã@s<ddlmZmZmZmZmZmZmZmZm Z m Z m Z m Z m Z mZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZm 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,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2m3Z3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9m:Z:m;Z;mZ>m?Z?m@Z@mAZAmBZBmCZCddlDmEZEddlFZFddlGmHZHddlIZIddlJZKddlJmLZLddlMmNZNdd„ZOeEd d ƒZPd d „ZQd d„ZRdd„ZSdd„ZTdd„ZUdd„ZVdd„ZWdd„ZXeXƒddddfdd„ZYddfddœdd„ZZd dd!œd"d#„Z[d$d%„Z\dfddœd&d'„Z]dfddœd(d)„Z^d*ddd+œd,d-„Z_d.d/„Z`d0d1„ZadS)2é)CÚFunctionÚFunctionOptionsÚFunctionRegistryÚHashAggregateFunctionÚHashAggregateKernelÚKernelÚScalarAggregateFunctionÚScalarAggregateKernelÚScalarFunctionÚ ScalarKernelÚVectorFunctionÚ VectorKernelÚArraySortOptionsÚAssumeTimezoneOptionsÚ CastOptionsÚ CountOptionsÚCumulativeSumOptionsÚDayOfWeekOptionsÚDictionaryEncodeOptionsÚRunEndEncodeOptionsÚElementWiseAggregateOptionsÚExtractRegexOptionsÚ FilterOptionsÚ IndexOptionsÚ JoinOptionsÚListSliceOptionsÚMakeStructOptionsÚMapLookupOptionsÚMatchSubstringOptionsÚ ModeOptionsÚ NullOptionsÚ PadOptionsÚPartitionNthOptionsÚQuantileOptionsÚ RandomOptionsÚ RankOptionsÚReplaceSliceOptionsÚReplaceSubstringOptionsÚRoundBinaryOptionsÚ RoundOptionsÚRoundTemporalOptionsÚRoundToMultipleOptionsÚScalarAggregateOptionsÚSelectKOptionsÚSetLookupOptionsÚ SliceOptionsÚ SortOptionsÚ SplitOptionsÚSplitPatternOptionsÚStrftimeOptionsÚStrptimeOptionsÚStructFieldOptionsÚ TakeOptionsÚTDigestOptionsÚ TrimOptionsÚUtf8NormalizeOptionsÚVarianceOptionsÚ WeekOptionsÚ call_functionÚfunction_registryÚ get_functionÚlist_functionsÚcall_tabular_functionÚregister_scalar_functionÚregister_tabular_functionÚScalarUdfContextÚ Expression)Ú namedtupleN)Údedent)Ú_compute_docstrings)Ú docscrapecCs|jjS)N)Ú_docÚ arg_names)Úfunc©rLú3/tmp/pip-unpacked-wheel-i2z0tf32/pyarrow/compute.pyÚ_get_arg_namesfsrNÚ_OptionsClassDoc)ÚparamscCs"|js dSt |j¡}t|dƒS)NZ Parameters)Ú__doc__rHZNumpyDocStringrO)Ú options_classÚdocrLrLrMÚ_scrape_options_class_docms rTcCsþ|j}t|j|j|j|jd|_||_||_g}|j }|sZ|jdkrHdnd}d  |j|¡}|  |›d¡|j }|r„|  |›d¡t j |j¡} |  tdƒ¡t|ƒ} x@| D]8} |jd krÂd } nd } |  | ›d | ›d ¡|  d¡q®W|dk r¼t|ƒ} | rTx | jD]D}|  |j›d |j›d ¡x"|jD]}|  d|›d ¡q0Wq WnPt d|j›dt¡t |¡}x.|j ¡D] }|  td  |j|j¡ƒ¡q€W|  td|j›dƒ¡|  tdƒ¡| dk rî|  d  t| ƒ d ¡¡¡d |¡|_ |S)N)ÚnameÚarityrRÚoptions_requiredéÚ argumentsÚargumentz,Call compute function {!r} with the given {}z. z z. Parameters ---------- )ZvectorÚscalar_aggregatez Array-likezArray-like or scalar-likez : Ú z" Argument to compute function. z zOptions class z does not have a docstringz¾ {0} : optional Parameter for {1} constructor. Either `options` or `{0}` can be passed, but not both at the same time. z& options : pyarrow.compute.zK, optional Alternative way of passing options. z‰ memory_pool : pyarrow.MemoryPool, optional If not passed, will allocate memory from the default memory pool. z {} Ú)!rIÚdictrUrVrRrWZ__arrow_compute_function__Ú__name__Ú __qualname__ÚsummaryÚformatÚappendÚ descriptionrGZfunction_doc_additionsÚgetrFrNÚkindrTrPÚtypeÚdescÚwarningsÚwarnÚRuntimeWarningÚinspectÚ signatureÚ parametersÚvaluesÚstripÚjoinrQ)ÚwrapperZ exposed_namerKrRZcpp_docZ doc_piecesraZarg_strrdZ doc_additionrJZarg_nameZarg_typeZoptions_class_docÚpÚsÚ options_sigrLrLrMÚ_decorate_compute_functiontsb           rvcCsF|jj}|sdSy tƒ|Stk r@t d |¡t¡dSXdS)Nz!Python binding for {} not exposed)rIrRÚglobalsÚKeyErrorrirjrbrk)rKÚ class_namerLrLrMÚ_get_options_classÇs  rzcCsl|s|r(|dk rtd |¡ƒ‚|||ŽS|dk rht|tƒrD|f|ŽSt||ƒrR|Std ||t|ƒ¡ƒ‚dS)NzMFunction {!r} called with both an 'options' argument and additional argumentsz-Function {!r} expected a {} parameter, got {})Ú TypeErrorrbÚ isinstancer^rg)rUrRÚoptionsÚargsÚkwargsrLrLrMÚ_handle_optionsÓs    r€cs>ˆdkr ddœ‡‡‡fdd„ }ndddœ‡‡‡‡fdd„ }|S)N)Ú memory_poolcsbˆtk r2t|ƒˆkr2tˆ›dˆ›dt|ƒ›dƒ‚|rTt|dtƒrTt ˆt|ƒ¡Sˆ |d|¡S)Nz takes z positional argument(s), but z were givenr)ÚEllipsisÚlenr{r|rDÚ_callÚlistÚcall)rr~)rVrKÚ func_namerLrMrrês z&_make_generic_wrapper..wrapper)rr}cs’ˆtk rLt|ƒˆkr2tˆ›dˆ›dt|ƒ›dƒ‚|ˆd…}|dˆ…}nd}tˆˆ|||ƒ}|r„t|dtƒr„t ˆt|ƒ|¡Sˆ |||¡S)Nz takes z positional argument(s), but z were givenrLr) r‚rƒr{r€r|rDr„r…r†)rr}r~rZ option_args)rVrKr‡rRrLrMrrôs  rL)r‡rKrRrVrrrL)rVrKr‡rRrMÚ_make_generic_wrapperès rˆcCsÞddlm}g}x|D]}| |||jƒ¡qWx|D]}| |||jƒ¡q6W|dk r¾t |¡}xD|j ¡D]6}|j|j |j fksˆt ‚|rš|j |j d}| |¡qnW| |d|j dd¡| |d|j dd¡t  |¡S)Nr)Ú Parameter)rfr})Údefaultr)rlr‰rcÚPOSITIONAL_ONLYÚVAR_POSITIONALrmrnrorfÚPOSITIONAL_OR_KEYWORDÚ KEYWORD_ONLYÚAssertionErrorÚreplaceÚ Signature)rJÚ var_arg_namesrRr‰rPrUrursrLrLrMÚ_make_signatures&        r“cCsjt|ƒ}t|ƒ}|o |d d¡}|r8| ¡ d¡g}ng}t||||jd}t|||ƒ|_t ||||ƒS)NéÿÿÿÿÚ*)rV) rzrNÚ startswithÚpopÚlstriprˆrVr“Ú __signature__rv)rUrKrRrJZ has_varargr’rrrLrLrMÚ_wrap_functionsršcCsŠtƒ}tƒ}dddœ}xn| ¡D]b}| ||¡}| |¡}|jdkrFq |jdkr\|jdkr\q ||kslt|ƒ‚t||ƒ||<||<q WdS)z« Make global functions wrapping each compute function. Note that some of the automatically-generated wrappers may be overridden by custom versions below. Úand_Úor_)ÚandÚorZhash_aggregater[rN) rwr=r?rer>rfrVrrš)ÚgÚregZrewritesZcpp_namerUrKrLrLrMÚ_make_global_functions.s   r¡cCsh|dk p|dk }|r$|dk r$tdƒ‚|dkrXtjj |¡}|dkrNt |¡}n t |¡}td|g||ƒS)a† Cast array values to another data type. Can also be invoked as an array instance method. Parameters ---------- arr : Array-like target_type : DataType or str Type to cast to safe : bool, default True Check for overflows or other unsafe conversions options : CastOptions, default None Additional checks pass by CastOptions memory_pool : MemoryPool, optional memory pool to use for allocations during function execution. Examples -------- >>> from datetime import datetime >>> import pyarrow as pa >>> arr = pa.array([datetime(2010, 1, 1), datetime(2015, 1, 1)]) >>> arr.type TimestampType(timestamp[us]) You can use ``pyarrow.DataType`` objects to specify the target type: >>> cast(arr, pa.timestamp('ms')) [ 2010-01-01 00:00:00.000, 2015-01-01 00:00:00.000 ] >>> cast(arr, pa.timestamp('ms')).type TimestampType(timestamp[ms]) Alternatively, it is also supported to use the string aliases for these types: >>> arr.cast('timestamp[ms]') [ 2010-01-01 00:00:00.000, 2015-01-01 00:00:00.000 ] >>> arr.cast('timestamp[ms]').type TimestampType(timestamp[ms]) Returns ------- casted : Array The cast result as a new Array NzRMust either pass values for 'target_type' and 'safe' or pass a value for 'options'FÚcast) Ú ValueErrorÚpaÚtypesÚlibÚ ensure_typerZunsafeÚsafer<)ZarrZ target_typer¨r}rZsafe_vars_passedrLrLrMr¢Ns6   r¢)rcCsÌ|dk r.|dk r"| |||¡}qB| |¡}n|dk rB| d|¡}t|tjƒs`tj||jd}n |j|jkr€tj| ¡|jd}t|d}td|g||ƒ}|dk rÈ| ¡dkrÈtj| ¡|t  ¡d}|S)a© Find the index of the first occurrence of a given value. Parameters ---------- data : Array-like value : Scalar-like object The value to search for. start : int, optional end : int, optional memory_pool : MemoryPool, optional If not passed, will allocate memory from the default memory pool. Returns ------- index : int the index, or -1 if not found Nr)rg)ÚvalueÚindex) Úslicer|r¤ÚScalarÚscalarrgÚas_pyrr<Zint64)Údatar©ÚstartÚendrr}ÚresultrLrLrMrª“s     rªT)Ú boundscheckrcCst|d}td||g||ƒS)a– Select values (or records) from array- or table-like data given integer selection indices. The result will be of the same type(s) as the input, with elements taken from the input array (or record batch / table fields) at the given indices. If an index is null then the corresponding value in the output will be null. Parameters ---------- data : Array, ChunkedArray, RecordBatch, or Table indices : Array, ChunkedArray Must be of integer type boundscheck : boolean, default True Whether to boundscheck the indices. If False and there is an out of bounds index, will likely cause the process to crash. memory_pool : MemoryPool, optional If not passed, will allocate memory from the default memory pool. Returns ------- result : depends on inputs Selected values for the given indices Examples -------- >>> import pyarrow as pa >>> arr = pa.array(["a", "b", "c", None, "e", "f"]) >>> indices = pa.array([0, None, 4, 3]) >>> arr.take(indices) [ "a", null, "e", null ] )r³Útake)r6r<)r¯Úindicesr³rr}rLrLrMr´¹s( r´cCsVt|tjtjtjfƒs(tj||jd}n |j|jkrHtj| ¡|jd}td||gƒS)a€ Replace each null element in values with fill_value. The fill_value must be the same type as values or able to be implicitly casted to the array's type. This is an alias for :func:`coalesce`. Parameters ---------- values : Array, ChunkedArray, or Scalar-like object Each null element is replaced with the corresponding value from fill_value. fill_value : Array, ChunkedArray, or Scalar-like object If not same type as data will attempt to cast. Returns ------- result : depends on inputs Values with all null elements replaced Examples -------- >>> import pyarrow as pa >>> arr = pa.array([1, 2, None, 3], type=pa.int8()) >>> fill_value = pa.scalar(5, type=pa.int8()) >>> arr.fill_null(fill_value) [ 1, 2, 5, 3 ] )rgZcoalesce) r|r¤ÚArrayÚ ChunkedArrayr¬r­rgr®r<)roZ fill_valuerLrLrMÚ fill_nullås # r¸cCsR|dkr g}t|tjtjfƒr*| d¡ntdd„|ƒ}t||ƒ}td|g||ƒS)a¸ Select the indices of the top-k ordered elements from array- or table-like data. This is a specialization for :func:`select_k_unstable`. Output is not guaranteed to be stable. Parameters ---------- values : Array, ChunkedArray, RecordBatch, or Table Data to sort and get top indices from. k : int The number of `k` elements to keep. sort_keys : List-like Column key names to order by when input is table-like data. memory_pool : MemoryPool, optional If not passed, will allocate memory from the default memory pool. Returns ------- result : Array Indices of the top-k ordered elements Examples -------- >>> import pyarrow as pa >>> import pyarrow.compute as pc >>> arr = pa.array(["a", "b", "c", None, "e", "f"]) >>> pc.top_k_unstable(arr, k=3) [ 5, 4, 2 ] N)ÚdummyÚ descendingcSs|dfS)NrºrL)Úkey_namerLrLrMÚ:óz top_k_unstable..Úselect_k_unstable)r|r¤r¶r·rcÚmapr-r<)roÚkÚ sort_keysrr}rLrLrMÚtop_k_unstables%  rÂcCsR|dkr g}t|tjtjfƒr*| d¡ntdd„|ƒ}t||ƒ}td|g||ƒS)aÏ Select the indices of the bottom-k ordered elements from array- or table-like data. This is a specialization for :func:`select_k_unstable`. Output is not guaranteed to be stable. Parameters ---------- values : Array, ChunkedArray, RecordBatch, or Table Data to sort and get bottom indices from. k : int The number of `k` elements to keep. sort_keys : List-like Column key names to order by when input is table-like data. memory_pool : MemoryPool, optional If not passed, will allocate memory from the default memory pool. Returns ------- result : Array of indices Indices of the bottom-k ordered elements Examples -------- >>> import pyarrow as pa >>> import pyarrow.compute as pc >>> arr = pa.array(["a", "b", "c", None, "e", "f"]) >>> pc.bottom_k_unstable(arr, k=3) [ 0, 1, 2 ] N)r¹Ú ascendingcSs|dfS)NrÃrL)r»rLrLrMr¼ir½z#bottom_k_unstable..r¾)r|r¤r¶r·rcr¿r-r<)rorÀrÁrr}rLrLrMÚbottom_k_unstable?s%  rÄÚsystem)Ú initializerr}rcCst|d}tdg|||dS)aB Generate numbers in the range [0, 1). Generated values are uniformly-distributed, double-precision in range [0, 1). Algorithm and seed can be changed via RandomOptions. Parameters ---------- n : int Number of values to generate, must be greater than or equal to 0 initializer : int or str How to initialize the underlying random generator. If an integer is given, it is used as a seed. If "system" is given, the random generator is initialized with a system-specific source of (hopefully true) randomness. Other values are invalid. options : pyarrow.compute.RandomOptions, optional Alternative way of passing options. memory_pool : pyarrow.MemoryPool, optional If not passed, will allocate memory from the default memory pool. )rÆÚrandom)Úlength)r$r<)ÚnrÆr}rrLrLrMrÇns rÇcGsrt|ƒ}|dkrdt|dttfƒr0t |d¡St|dtƒrLt |d¡Stdt |dƒ›ƒ‚n t |¡SdS)aReference a column of the dataset. Stores only the field's name. Type and other information is known only when the expression is bound to a dataset having an explicit scheme. Nested references are allowed by passing multiple names or a tuple of names. For example ``('foo', 'bar')`` references the field named "bar" inside the field named "foo". Parameters ---------- *name_or_index : string, multiple strings, tuple or int The name or index of the (possibly nested) field the expression references to. Returns ------- field_expr : Expression Reference to the given field Examples -------- >>> import pyarrow.compute as pc >>> pc.field("a") >>> pc.field(1) >>> pc.field(("a", "b")) >> pc.field("a", "b") r?r@rArBrCrDÚ collectionsrErlÚtextwraprFriZpyarrowr¤rGZpyarrow.vendoredrHrNrOrTrvrzr€rˆr“ršr¡r¢rªr´r¸rÂrÄrÇrÍr­rLrLrLrMÚs8ÿJ     S E&,+//1