o Q i;_@snddlmZmZmZmZmZmZmZmZm 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@mAZAmBZBmCZCmDZDmEZEmFZFmGZGmHZHmIZImJZJmKZKmLZLmMZMmNZNmOZOmPZPddlQmRZRddlSZSddlTmUZUddlVZVddlWZXddlWmYZYddlZm[Z[ddZ\eRd d Z]d d Z^d dZ_ddZ`ddZaddZbddZcddZdddZeeeefdZgZhd3ddZid4dddd Zjd!dd"d#d$Zkd%d&Zld5ddd'd(Zmd5ddd)d*Znd+ddd,d-d.Zod/d0Zpd1d2ZqdS)6)PFunctionFunctionOptionsFunctionRegistryHashAggregateFunctionHashAggregateKernelKernelScalarAggregateFunctionScalarAggregateKernelScalarFunction ScalarKernelVectorFunction VectorKernelArraySortOptionsAssumeTimezoneOptions CastOptions CountOptionsCumulativeOptionsCumulativeSumOptionsDayOfWeekOptionsDictionaryEncodeOptionsRunEndEncodeOptionsElementWiseAggregateOptionsExtractRegexOptionsExtractRegexSpanOptions FilterOptions IndexOptionsInversePermutationOptions JoinOptionsListSliceOptionsListFlattenOptionsMakeStructOptionsMapLookupOptionsMatchSubstringOptions ModeOptions NullOptions PadOptionsPairwiseOptionsPartitionNthOptionsPivotWiderOptionsQuantileOptions RandomOptions RankOptionsRankQuantileOptionsReplaceSliceOptionsReplaceSubstringOptionsRoundBinaryOptions RoundOptionsRoundTemporalOptionsRoundToMultipleOptionsScalarAggregateOptionsScatterOptionsSelectKOptionsSetLookupOptions SkewOptions SliceOptions SortOptions SplitOptionsSplitPatternOptionsStrftimeOptionsStrptimeOptionsStructFieldOptions TakeOptionsTDigestOptions TrimOptionsUtf8NormalizeOptionsVarianceOptions WeekOptionsWinsorizeOptionsZeroFillOptions call_functionfunction_registry get_functionlist_functionscall_tabular_functionregister_scalar_functionregister_tabular_functionregister_aggregate_functionregister_vector_function UdfContext Expression) namedtupleN)dedent)_compute_docstrings) docscrapecCs|jjSN)_doc arg_names)funcrZC/home/ubuntu/.local/lib/python3.10/site-packages/pyarrow/compute.py_get_arg_namesssr\_OptionsClassDoc)paramscCs"|jsdSt|j}t|dS)N Parameters)__doc__rUNumpyDocStringr]) options_classdocrZrZr[_scrape_options_class_doczs  rdc Cs|j}t|j|j|j|jd|_||_||_g}|j }|s/|jdkr$dnd}d|jd|}| |d|j }|rD| |dt j |j} | td t|} | D]} |jd vrbd } nd } | | d | d| dqX|durt|} | r| jD]}| |jd |jd|jD] }| d|dqqn,td|jdtt|}|jD]}| td|jd|jd|jdq| td|jd| td| durt| d}| d|dd||_|S)N)namearityrboptions_required argumentsargumentzCall compute function z with the given z. z z. Parameters ---------- )vectorscalar_aggregatez Array-likezArray-like or scalar-likez :  z" Argument to compute function. z zOptions class z does not have a docstringz z. : optional Parameter for z7 constructor. Either `options` or `z@` 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. ) rWdictrerfrbrg__arrow_compute_function____name__ __qualname__summaryappend descriptionrTfunction_doc_additionsgetrSr\kindrdr^typedescwarningswarnRuntimeWarninginspect signature parametersvaluesstripjoinr`)wrapper exposed_namerYrbcpp_doc doc_piecesrsarg_strru doc_additionrXarg_namearg_typeoptions_class_docps options_sigstrippedrZrZr[_decorate_compute_functionsr       rcCsF|jj}|sdSzt|WSty"td|dtYdSw)NzPython binding for z not exposed)rWrbglobalsKeyErrorr{r|r})rY class_namerZrZr[_get_options_classs  rcCs~|s|r|durtd|d||i|S|dur=t|tr'|di|St||r.|Std|d|dt|dS)Nz Function z@ called with both an 'options' argument and additional argumentsz expected a z parameter, got rZ) TypeError isinstancerory)rerboptionsargskwargsrZrZr[_handle_optionss"   rcs@durddfdd }|Sdddfdd }|S)N memory_poolcsbturt|krtddt|d|r*t|dtr*tt|S|d|S)N takes  positional argument(s), but were givenr)EllipsislenrrrQ_calllistcall)rr)rfrY func_namerZr[rs z&_make_generic_wrapper..wrapper)rrcstur&t|krtddt|d|d}|d}nd}t|||}|rBt|dtrBtt||S|||S)NrrrrZr) rrrrrrQrrr)rrrr option_argsrfrYrrbrZr[rs    rZ)rrYrbrfrrZrr[_make_generic_wrappers rcCsddlm}g}|D] }||||jq |D] }||||jq|durYt|}|jD]}|j|j |j fvs?J|rH|j |j d}||q2||d|j dd||d|j ddt |S)Nr) Parameter)rxr)defaultr) r~rrtPOSITIONAL_ONLYVAR_POSITIONALrrrrxPOSITIONAL_OR_KEYWORD KEYWORD_ONLYreplace Signature)rX var_arg_namesrbrr^rerrrZrZr[_make_signatures,       rcCsjt|}t|}|o|dd}|r|dg}ng}t||||jd}t||||_t ||||S)N*)rf) rr\ startswithpoplstriprrfr __signature__r)rerYrbrX has_varargrrrZrZr[_wrap_function*s rcCst}t}ddd}|D]1}|||}||}|jdkr"q|jdkr-|jdkr-q||vs5J|t||||<||<qdS)z Make global functions wrapping each compute function. Note that some of the automatically-generated wrappers may be overridden by custom versions below. and_or_)andorhash_aggregaterlrN)rrHrJrwrIrxrfr)gregrewritescpp_namererYrZrZr[_make_global_functions:s    rutf8_zero_fillcCsh|dup|du}|r|durtd|dur,tjj|}|dur't|}nt|}td|g||S)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'Fcast) ValueErrorpatypeslib ensure_typerunsafesaferG)arr target_typerrrsafe_vars_passedrZrZr[r\s6   rrcCs|dur|dur||||}n||}n |dur!|d|}t|tjs0tj||jd}n|j|jkr@tj||jd}t|d}td|g||}|durd|dkrdtj||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 Examples -------- >>> import pyarrow as pa >>> import pyarrow.compute as pc >>> arr = pa.array(["Lorem", "ipsum", "dolor", "sit", "Lorem", "ipsum"]) >>> pc.index(arr, "ipsum") >>> pc.index(arr, "ipsum", start=2) >>> pc.index(arr, "amet") Nrryvalueindex) slicerrScalarscalarryas_pyrrGint64)datarstartendrrresultrZrZr[rs     rT) boundscheckrcCst|d}td||g||S)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 ] )rtake)r?rG)rindicesrrrrZrZr[rs (rcCsVt|tjtjtjfstj||jd}n|j|jkr$tj||jd}td||gS)aeReplace each null element in values with a corresponding element from fill_value. If fill_value is scalar-like, then every null element in values will be replaced with fill_value. If fill_value is array-like, then the i-th element in values will be replaced with the i-th element in fill_value. The fill_value's type must be the same as that of values, or it must be 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 values, 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 ] >>> arr = pa.array([1, 2, None, 4, None]) >>> arr.fill_null(pa.array([10, 20, 30, 40, 50])) [ 1, 2, 30, 4, 50 ] rcoalesce) rrArray ChunkedArrayrrryrrG)r fill_valuerZrZr[ fill_nulls 3 rcCR|durg}t|tjtjfr|dntdd|}t||}td|g||S)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)dummy descendingcS|dfS)NrrZkey_namerZrZr[dz top_k_unstable..select_k_unstablerrrrrtmapr5rGrk sort_keysrrrZrZr[top_k_unstable:%  rcCr)a 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)r ascendingcSr)NrrZrrZrZr[rrz#bottom_k_unstable..rrrrZrZr[bottom_k_unstableirrsystem) initializerrrcCst|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. )rrandom)length)r*rG)nrrrrZrZr[rs rcGslt|}|dkr1t|dttfrt|dSt|dtr&t|dStdt |dt|S)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@rArBrCrDrErFrGrHrIrJrKrLrMrNrOrPrQ collectionsrRr~textwraprSr{pyarrowrrTpyarrow.vendoredrUr\r]rdrrrrrrrr utf8_zfillrrrrrrrrrrrZrZrZr[s<J W    S  E2,;// 1