U mdu@s$ UddlmZddlZddlmZddlmZddlZddlZddlZddl Z ddl m Z ddl m Z mZmZmZmZmZddlZddlmZmZmZddlmZmZmZdd lmZdd lm Z m!Z!m"Z"m#Z#m$Z$m%Z%ddl&Z'dd l&m(Z(m)Z)m*Z*m+Z+m,Z,m-Z-m.Z.m/Z/m0Z0m1Z1m2Z2dd l3m4Z4m5Z5m6Z6m7Z7m8Z8m9Z9dd l:m;Z;mZ>m?Z?ddl@mAZAmBZBmCZCmDZDmEZEmFZFmGZGmHZHmIZImJZJmKZKmLZLmMZMmNZNmOZOmPZPmQZQmRZRmSZSmTZTmUZUmVZVmWZWddlXmYZYmZZZddl[m\Z\m]Z]m^Z^m_Z_m`Z`maZambZbddlcmdZdmeZemfZfddlgmhZhddlimjZje r8ddl&mkZkmlZlddlcmmZmdZndZoddddgZpdeqd<dd d!d"gZrd#eqd$<esd%d&d'd(gZtdeqd)<d*d+d,d-gZud#eqd.<epetZvereuZwevewZxd#eqd/<eyd0d1gZzdeqd2<d3d4gZ{d#eqd5<eze{Z|d#eqd6<e}d7d8gZ~d#eqd9<ed:d;gZd#eqd<<d=d>gZd#eqd?<d@dAgZd#eqdB<edCgZd#eqdD<edEgZd#eqdF<edGgZd#eqdH<ezevZe{ewZeeZd#eqdI<ee~Zd#eqdJ<ee~eeeeeeZejejejejejejejejgZdKdLdMe Zdeje'jeydNe'jedOgZdPdQejejfDZes.ddlZeeeegZeeeegZeeZdRdQeDZeegZdSdQeDZedTdUgZe gZegZedVedWedXedYgZeegZdZdQd[DZd\dQd[DZegZeeeeeeeeeeZn gZgZgZed]Zd^d_d`daZdCd_dbdcZd-dCdedfdgZdhdiZd:d_djdkZd.dmdndodpdqZd/dmdmdrdsdtduZd0dmdvdodwdxZÐd1dmdndodydzZĐd2dd{dmd|dnd}d~dZŐd3dd(ddmddnd}ddZƐd4ddddmddnd}ddZǐd5dmddoddZȐd6dd1ddmddnd}ddZɐd7dmdddddZʐd8dmdddddZːd9dmddoddZ̐d:dmdddZddZΐd;dmddoddZdejfdd_ddZАddd_ddZdd_ddZԐd?dddddZՐd@dd_ddZ֐dAdddddZאdBdd_ddZؐdCdddddZdd_ddZddZdd_ddZܐdDdd_ddZݐdEd:ddndÜddńZސdFdddmdmddȜddʄZߐdGdd̜dd΄ZdHdddМdd҄ZGddԄde1ZGddքde+ZGdd؄de)ZdIddڄZdd:dܜddބZdddddZe'jjjZddZd:ddddZddZddZddZddZddZddZdCd_ddZddddddddddddddddddd d d d d dddddddDdgdFddd9dd?ddddddcdd5d2dkdddddddddddddddzdudddddddxddddddddddddqddddddddd d!dHd"d#dad$d%d&d'dd(d)dd.d)d)littlebignanNaNcCs g|]}dD]}|d|q qS)) YMWDhmsmsusnsZpsfsasNaT).0clsunitrrQ/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/pandas/_testing/__init__.py srcCsg|]}tt|qSrrkrrtyprrrrscCsg|]}tt|qSrrrrrrrsrrrrcCs$g|]}dD]}tj||dq qS))NUTCz US/Pacificz US/Eastern)rtz)pa timestamp)rrrrrrrs)rrrrcCsg|]}t|qSr)rduration)rrrrrrsz^$None)returncCstjddddS)zJ Reset the display options for printing and representing objects. z ^display.T)ZsilentN)pdZ reset_optionrrrrreset_display_optionssrcCst|t|kS)zO Checks if the set of unique elements of arr1 and arr2 are equivalent. ) frozenset)Zarr1Zarr2rrr equalContentssrT) transposecCs|tjkr6t|tr&tt|j}qtj|dd}n|tkrHt|}n|t krZt |}nn|t krt | }|r|j }tj |gddd}n:|tjks|tjkrt|}n|tkrt|}nt||S)z Helper function to wrap the expected output of a test in a given box_class. Parameters ---------- expected : np.ndarray, Index, Series box_cls : {Index, Series, DataFrame} Returns ------- subclass of box_cls FcopyT)Z ignore_index)rarray isinstancer!rPnpasarray_valuesrr"rZto_frameTconcatndarrayto_arrayNotImplementedError)expectedZbox_clsrrrr box_expecteds&       rcCs*t|dd}|dkrt|St|ddS)zQ Similar to pd.array, but does not cast numpy dtypes to nullable dtypes. dtypeNT)Z extract_numpy)getattrrrrR)objrrrrr@s  rcCstjd|SN)stringascii_uppercasekrrrgetColsQsr intr)rrcCsttd|d|dS)Nr)ncharssizename)rr+rrrrrmakeStringIndexVsrr)rnrcKs6td|dd}ttjt|||dfd|i|S)z%make a length k index or n categoriesrWF)rrreplace) categoriesr)r+rrZ from_codesrarange)rrrkwargsxrrrmakeCategoricalIndexZsrrcKs*tjdd|dd}tj|fd|i|S)zmake a length k IntervalIndexrd)numr)rZlinspacerZ from_breaks)rrrrrrrmakeIntervalIndexdsrcCsL|dkrtdg|dS|dkr.tddg|dStddgdg|d|dS)NrTrrF)rrrrr makeBoolIndexjs rrz Dtype | None)rrrcCst|}t|tjstt|rNtj||d}t|r|d|jdd7}nNt |rtj |tj d}| |dtj dd}ntd|t|||d S) Nrrrrr z wrong dtype )rr)rrrrAssertionErrorrrritemsizerrandomZ random_samplesortrandintrr)rrrvaluesrrrmakeNumericIndexrsrrrrcCs,t|}t|std|t|||dSNz Wrong dtype r)rr TypeErrorrrrrrrr makeIntIndexsrcCs,t|}t|std|t|||dSr)rrrrrrrr makeUIntIndexsrr!cKstd|dfd|i|S)Nrrr)r!)rrrrrrmakeRangeIndexsrcCs,t|}t|std|t|||dSr)rrrrrrrrmakeFloatIndexsrBrr)rfreqrcKs0tddd}t||||d}t|fd|i|S)Nr)periodsrrr)rr#r)rrrrdtZdrrrr makeDateIndexs rrrTcKstjfd|||d|S)Nz1 daystartrrr)rZtimedelta_range)rrrrrrrmakeTimedeltaIndexsrrScKs&tddd}tjf||d|d|S)Nrrrr)rrZ period_range)rrrrrrrmakePeriodIndexs rrcKsJ|dd}t|}tjd|gfd|i|}t||ks>t|d|S)Nrr)Zfoobarnames)ranger Z from_productlenr)rrrNrngmirrrmakeMultiIndexs  rccs tttttttg}|EdHdSr)rrrrrrr)make_index_funcsrrrindex_subclass_makers_generators rzIterable[Index]ccs$tttg}|D]}||dVqdS)z Generator which can be iterated over to get instances of all the classes which represent time-series. Parameters ---------- k: length of each of the index instances rN)rrr)rrZmake_index_funcrrrall_timeseries_index_generators rr"c CsHtt}tjt}tjdd|j|dd}W5QRXt|||dS)Nignore)invalidFrindexr)r_NrrrandnZerrstateastyper")rrrdatarrrmake_rand_seriess  rcCs t|dSNrrrrrrmakeFloatSeriessrcCs t|dSrrrrrrmakeStringSeriessrcCs*tt}t|td}tt}t|||dS)Nrr)rrrrtr")rrrrrrmakeObjectSeriess rzdict[str, Series]csttfddttDS)Ncs"i|]}|ttjtdqS)r)r"rrrrrcrrr sz!getSeriesData..)rrr_Krrrr getSeriesDatasr)rrcCs*|dkr t}ttj|t||d|dS)N)rr)rr"rrrr)nperrrrrrmakeTimeSeriess r cCs&|dkr t}ttj|t||dS)Nr)rr"rrrr)r rrrrmakePeriodSeriessr csfddttDS)Ncsi|]}|tqSr)r rrr rrrsz%getTimeSeriesData..rr)r rrr rgetTimeSeriesDatasrcsfddttDS)Ncsi|]}|tqSr)r rr rrrsz!getPeriodData..r rrrr getPeriodDatasrrcCst||}t|Sr)rr)r rrrrrmakeTimeDataFrame s rcCst}t|Sr)rr)rrrr makeDataFramesrcCsNtdddddg}dddd d gdddddgd d d ddgtdddd}||fS)Nabrdeg?g@g@g@Zfoo1Zfoo2Zfoo3Zfoo4Zfoo5z1/1/2009)r)ArCr)rr#)rrrrrgetMixedTypeDicts    rcCsttdS)Nr)rrrrrrmakeMixedDataFrame"srcCst|}t|Sr)rr)r rrrrmakePeriodFrame&sr#Fzbool | str | list[str] | None)prefixrrcsd|dkrdg|}t|r&t||ks*t|dksR|dksR|dksRt||ksRt|dksn|dkrj|dksnt|dkrfddt|D}|dkrd}t|tr|dkr|g}tttt t t d}| |}|r||}|r|d |_ |S|dk rtt|d t||kr,|dg|t|t||ks>ttd d |DsVtg} t|D]x} d d} ||| d} t} t| D]&}d| d|}|| | |<qt| | dd|}| |qbtt| }|dkr|dkrdn|d }t|d |d}nF|dkrR|dkr2dn|d }tdd |D|d}ntj||d}|S)a Create an index/multindex with given dimensions, levels, names, etc' nentries - number of entries in index nlevels - number of levels (> 1 produces multindex) prefix - a string prefix for labels names - (Optional), bool or list of strings. if True will use default names, if false will use no names, if a list is given, the name of each level in the index will be taken from the list. ndupe_l - (Optional), list of ints, the number of rows for which the label will repeated at the corresponding level, you can specify just the first few, the rest will use the default ndupe_l of 1. len(ndupe_l) <= nlevels. idx_type - "i"/"f"/"s"/"dt"/"p"/"td". If idx_type is not None, `idx_nlevels` must be 1. "i"/"f" creates an integer/float index, "s" creates a string "dt" create a datetime index. "td" create a datetime index. if unspecified, string labels will be generated. NrFT)ifrurptdcsg|]}t|qSr)rk)rr rrrrSsz#makeCustomIndex..)r r!rrr$r#rzE is not a legal value for `idx_type`, use 'i'/'f'/'s'/'dt'/'p'/'td'.css|]}|dkVqdSrNrrrrrr vsz"makeCustomIndex..cSs"tdd|d}dd|DS)Nz[^\d_]_?_cSsg|] }t|qSr)r)rrrrrr}sz4makeCustomIndex..keyfunc..)resubsplit)rZ numeric_tuplerrrkeyfunc{sz makeCustomIndex..keyfuncZ_lZ_g)keyrcss|]}|dVqdSr&rr'rrrr(s)r)rrrrrrkrrrrrrgetr ValueErrorreprextendall collectionsr sortedelementsappendlistziprr from_tuples)Znentriesnlevelsrrndupe_lidx_typeZ idx_func_dictZidx_funcidxZ list_of_listsr r.Z div_factorZcntjlabelresultZtuplesrrrr%rmakeCustomIndex+sn (         rCrzbool | list[str]) c_idx_names r_idx_names c_idx_nlevels r_idx_nlevelsrc s|dks t|dkst| dks4| dkr0|dks4t| dksP| dkrL|dksPtt|d||| d} t||d||| d} dkrdd fd d t|D}t|| | | d S) a Create a DataFrame using supplied parameters. Parameters ---------- nrows, ncols - number of data rows/cols c_idx_names, r_idx_names - False/True/list of strings, yields No names , default names or uses the provided names for the levels of the corresponding index. You can provide a single string when c_idx_nlevels ==1. c_idx_nlevels - number of levels in columns index. > 1 will yield MultiIndex r_idx_nlevels - number of levels in rows index. > 1 will yield MultiIndex data_gen_f - a function f(row,col) which return the data value at that position, the default generator used yields values of the form "RxCy" based on position. c_ndupe_l, r_ndupe_l - list of integers, determines the number of duplicates for each label at a given level of the corresponding index. The default `None` value produces a multiplicity of 1 across all levels, i.e. a unique index. Will accept a partial list of length N < idx_nlevels, for just the first N levels. If ndupe doesn't divide nrows/ncol, the last label might have lower multiplicity. dtype - passed to the DataFrame constructor as is, in case you wish to have more control in conjunction with a custom `data_gen_f` r_idx_type, c_idx_type - "i"/"f"/"s"/"dt"/"td". If idx_type is not None, `idx_nlevels` must be 1. "i"/"f" creates an integer/float index, "s" creates a string index "dt" create a datetime index. "td" create a timedelta index. if unspecified, string labels will be generated. Examples -------- # 5 row, 3 columns, default names on both, single index on both axis >> makeCustomDataframe(5,3) # make the data a random int between 1 and 100 >> mkdf(5,3,data_gen_f=lambda r,c:randint(1,100)) # 2-level multiindex on rows with each label duplicated # twice on first level, default names on both axis, single # index on both axis >> a=makeCustomDataframe(5,3,r_idx_nlevels=2,r_ndupe_l=[2]) # DatetimeIndex on row, index with unicode labels on columns # no names on either axis >> a=makeCustomDataframe(5,3,c_idx_names=False,r_idx_names=False, r_idx_type="dt",c_idx_type="u") # 4-level multindex on rows with names provided, 2-level multindex # on columns with default labels and default names. >> a=makeCustomDataframe(5,3,r_idx_nlevels=4, r_idx_names=["FEE","FIH","FOH","FUM"], c_idx_nlevels=2) >> a=mkdf(5,3,r_idx_nlevels=2,c_idx_nlevels=4) rN)r r!rrr#r$rr)r<rrr=r>RcSsd|d|S)NrHrr)rrrrrz%makeCustomDataframe..cs$g|]fddtDqS)csg|]}|qSrrr) data_gen_frIrrrsz2makeCustomDataframe...)r)rrLncols)rIrrsz'makeCustomDataframe..r)rrCrr)nrowsrNrDrErFrGrLZ c_ndupe_lZ r_ndupe_lrZ c_idx_typeZ r_idx_typecolumnsrrrrMrmakeCustomDataframes@H   rQfloat)densityc s|dkrtj}n tj|}td|d}d}t||}fdd}|||}|jkr|d9}|||}qdt|dt} || t} | | fS)NrrgRQ?cs.|t|}tt|dSr)Zrandrruniquefloor)rZ _extra_sizeindrNrOrrr_gen_unique_randsz-_create_missing_idx.._gen_unique_randg?r) rrZ RandomStateroundminrrUrrtolist) rOrNrS random_stateZmin_rowsZfac extra_sizerXrVr@r rrWr_create_missing_idxs    r^?)rSrcCs0t}t|j||d\}}tj|j||f<|S)N)rSr\)rr^shaperr|iloc)rSr\Zdfr r@rrrmakeMissingDataframe!srbc@s,eZdZddgZeddZeddZdS)SubclassedSeriestestattrrcCsddS)Nc_s t||SrrcargsrrrrrJ2rKz/SubclassedSeries._constructor..rselfrrr _constructor+szSubclassedSeries._constructorcCsddS)Nc_s t||SrSubclassedDataFramerfrrrrJ6rKz9SubclassedSeries._constructor_expanddim..rrhrrr_constructor_expanddim4sz'SubclassedSeries._constructor_expanddimN)__name__ __module__ __qualname__ _metadatapropertyrjrmrrrrrc(s  rcc@s*eZdZdgZeddZeddZdS)rlrdcCsddS)Nc_s t||SrrkrfrrrrJ>rKz2SubclassedDataFrame._constructor..rrhrrrrj<sz SubclassedDataFrame._constructorcCsddS)Nc_s t||SrrerfrrrrJBrKz9SubclassedDataFrame._constructor_sliced..rrhrrr_constructor_sliced@sz'SubclassedDataFrame._constructor_slicedN)rnrorprqrrrjrsrrrrrl9s  rlc@seZdZeddZdS)SubclassedCategoricalcCstSr)rtrhrrrrjFsz"SubclassedCategorical._constructorN)rnrorprrrjrrrrrtEsrtcs"rfdd}n fdd}|S)a` Create a function for calling on an array. Parameters ---------- alternative : function The function to be called on the array with no NaNs. Only used when 'skipna_alternative' is None. skipna_alternative : function The function to be called on the original array Returns ------- function cs |jSr)rr)skipna_alternativerrskipna_wrapper]sz,_make_skipna_wrapper..skipna_wrappercs"|}t|dkrtjS|S)Nr)Zdropnarrr|)rZnona) alternativerrrwbs r)rxrvrwr)rxrvr_make_skipna_wrapperKs ryz list[str]) rows_listrcCstj}|||S)aW Convert list of CSV rows to single CSV-formatted string for current OS. This method is used for creating expected value of to_csv() method. Parameters ---------- rows_list : List[str] Each element represents the row of csv. Returns ------- str Expected output of to_csv() in current OS. )oslinesepjoin)rzseprrrconvert_rows_list_to_csv_strksrztype[Exception]r)expected_exceptionrcCsddl}|j|ddS)a$ Helper function to mark pytest.raises that have an external error message. Parameters ---------- expected_exception : Exception Expected error to raise. Returns ------- Callable Regular `pytest.raises` function with `match` equal to `None`. rN)match)pytestZraises)rrrrrexternal_error_raisedsrcs@g}|D]2\|f|fddtD7}q|S)a Combine frame, functions from com._cython_table keys and expected result. Parameters ---------- ndframe : DataFrame or Series func_names_and_expected : Sequence of two items The first item is a name of a NDFrame method ('sum', 'prod') etc. The second item is the expected return value. Returns ------- list List of three items (DataFrame, function, expected result) cs"g|]\}}|kr|fqSrr)rfuncrr func_namendframerrrsz+get_cython_table_params..)r8 cython_table)rZfunc_names_and_expectedresultsrrrget_cython_table_paramss  rr)op_namercsP|d}ztt|}Wn2tk rJtt|ddfdd}YnX|S)z The operator function for a given op name. Parameters ---------- op_name : str The op name, in form of "add" or "__add__". Returns ------- function A function performing the operation. r*rNcs ||Srr)ryZroprrrJrKz"get_op_from_name..)striproperatorAttributeError)rZ short_opnameoprrrget_op_from_names rcCs|SrrrurrrgetitemsrcCs|SrrrurrrsetitemsrcCs|jSr)locrurrrrsrcCs|jSr)rarurrrrasracCs|jSr)atrurrrrsrcCs|jSr)iatrurrrrsrcCst|tjr$t|tjr$t||St|tjr:t||St|trHdSt|tr^t|j|St|ttfrxt|j |St|t rt|j |St|t j jjrt|j|St|t j jjrt|j|pt|j|St|trN|jdkrNtd|}t|trN|jdkrNtd|}|j}|j}|dd}|dd}||kSt|trt|trt|j|jpt|j|jSt|trt|jjdkr|jjd}t||Stt |t |dS)z- Pandas-compat for np.shares_memory. Fzstring[pyarrow]rUrrN)!rrr shares_memoryr!r _codesrr"rrQZ_ndarrayrcoreZarraysZ SparseArrayZ sp_valuesZ IntervalArray_left_rightrOrr _datachunkbuffersrNZ_maskrrZ_mgrrtype)leftrightZ left_pa_dataZ right_pa_dataZ left_buf1Z right_buf1ZarrrrrrsD              rALL_INT_EA_DTYPESALL_INT_NUMPY_DTYPESALL_NUMPY_DTYPESALL_REAL_NUMPY_DTYPESr.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@r,rArBrCr r$rGEMPTY_STRING_PATTERNENDIANrHrIrEr rFr-NARROW_NP_DTYPESr%NP_NAT_OBJECTS NULL_OBJECTSrDr*rJr&r'r(rrKrLrMr))T)rN)rrN)rN)rN)r)r)r)rN)r)rrN)rrN)rN)rN)r)N)N)N)NrN)NN)Nr)N)Nr)N)rFNN) TTrrNNNNNN)N)r_N)N) __future__rr5rdecimalrrr{r+rsysrtypingrrrr r r numpyrZpandas._config.localizationr r rZpandas._typingrrrZ pandas.compatrZpandas.core.dtypes.commonrrrrrrZpandasrrrrrrrrr r!r"r#Zpandas._testing._ior$r%r&r'r(r)Zpandas._testing._randomr*r+Zpandas._testing._warningsr,r-Zpandas._testing.assertersr.r/r0r1r2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rArBrCrDZpandas._testing.compatrErFZpandas._testing.contextsrGrHrIrJrKrLrMZpandas.core.arraysrNrOrPZpandas.core.arrays._mixinsrQZpandas.core.constructionrRrSrTrUrrr\__annotations__r]rrbrcrrrdrRrgrhricomplexrjrkrmrnrorprqrrrsrtrurZALL_REAL_EXTENSION_DTYPESrvrwrZfloat16rer^r_r`rXrYrZrrr|rZNArZ datetime64Z timedelta64rZpyarrowrr[ZUNSIGNED_INT_PYARROW_DTYPESraZSIGNED_INT_PYARROW_DTYPESZALL_INT_PYARROW_DTYPESZALL_INT_PYARROW_DTYPES_STR_REPRrfZFLOAT_PYARROW_DTYPESZFLOAT_PYARROW_DTYPES_STR_REPRZ decimal128ZDECIMAL_PYARROW_DTYPESZSTRING_PYARROW_DTYPESbinaryZBINARY_PYARROW_DTYPESZtime32Ztime64ZTIME_PYARROW_DTYPESZdate32Zdate64ZDATE_PYARROW_DTYPESZDATETIME_PYARROW_DTYPESZTIMEDELTA_PYARROW_DTYPESZbool_ZBOOL_PYARROW_DTYPESZALL_PYARROW_DTYPEScompilerrrrrrrrrrrrrrrrrrrrrrrrrrr r rrrrrrrrCrQr^rbrcrlrtryrrrcommonZ _cython_tableitemsrrrrrrrarrr__all__rrrrs       4 d$              )    sk  2