a Ofp @sddlmZddlmZmZddlmZmZmZm Z ddl Z ddl Z ddl mZddlmZmZddlmZddlmZdd lmZmZmZdd lmZdd lmZmZddlm m!Z"dd l#m$Z$dd l%m&Z&ddl'm(Z(m)Z)m*Z*ddl+m,Z,ddl-m.Z.ddl/m0Z0er4ddl1m2Z2m3Z3m4Z4m5Z5ddl6m7Z7edee$dddddddddddej8df dddddd ddd!d"dZ9dd#dddd ddd!d$d%Z:dKd&dddd'd(d)Z;dLddd*d+d,Zd2d3Z?edee$d4ddej8ej8d5dd6d7d7dd8d9d4Z@dOdddd:dd;dd?d@ZBdQdBdCdDdEZCdFdFdGdHdIdJZDdS)R) annotations)HashableSequence) TYPE_CHECKINGCallableLiteralcastN)lib)Appender Substitution)find_stack_level)maybe_downcast_to_dtype) is_list_likeis_nested_list_like is_scalar)ExtensionDtype) ABCDataFrame ABCSeries) _shared_docs)Grouper)Index MultiIndexget_objs_combined_axis)concat)cartesian_product)Series) AggFuncTypeAggFuncTypeBaseAggFuncTypeDict IndexLabel DataFramez data : DataFrame pivot_table)indentsmeanFTAllr!rboolrzbool | lib.NoDefault)dataaggfuncmarginsdropna margins_nameobservedsortreturnc Cst|}t|}t|trg} g} |D]>} t|||||| |||| | d }| || t| d| q&t| | dd}|j|ddSt|||||||||| | }|j|ddS)N) valuesindexcolumns fill_valuer)r*r+r,r-r.__name__r#)keysaxisr")method) _convert_by isinstancelist__internal_pivot_tableappendgetattrrZ __finalize__)r(r0r1r2r)r3r*r+r,r-r.piecesr5func_tabletablerBR/var/www/ai-form-bot/venv/lib/python3.9/site-packages/pandas/core/reshape/pivot.pyr"=sJ   z!AggFuncTypeBase | AggFuncTypeDictc  Cs||} |du} | rt|r*d} t|}n d} |g}|D]}||vr8t|q8g}| |D]>}t|trn|j}z||vr||WqZtyYqZ0qZt|t|j kr||}n@|j }| D],}z| |}Wqtt tfyYq0qt|}| t j urdn| }|j| || |d}| t j urRtdd|jjDrRtjdttd||}|rt|trt|j r|jd d }|}|jjd kr|r|jjdt|}g}tt|t| D]<}|jj|}|dus||vr||n ||q|j||d }|st|jtrRtjt |jj!|jjd }|j"|d|d}t|j trtjt |j j!|j jd }|j"|d |d}| durt|tr|j#d d}|dur|$|}|tur| st %|r|&t'j(}|r"|r||)j*d d}t+|||||||||d }| rJ| sJ|j jd krJ|j ,d|_ t|dkrlt|dkrl|j-}t|tr|r|jd d d}|S)zL Helper of :func:`pandas.pivot_table` for any non-list ``aggfunc``. NTF)r-r.r+css|] }|jVqdSN)Z_passed_categorical).0ZpingrBrBrC sz)__internal_pivot_table..zThe default value of observed=False is deprecated and will change to observed=True in a future version of pandas. Specify observed=False to silence this warning and retain the current behavior)category stacklevelall)howr#r3namesr)r6r3r6)rowscolsr)r-r,r3)rJr6).rr:KeyErrorr9rkeyr< TypeErrorlenr2Zdrop ValueErrorr no_defaultgroupbyany_grouperZ groupingswarningswarn FutureWarningr aggrr+r1nlevelsrMrangeunstackr from_arraysrZlevelsreindexZ sort_indexfillna is_integerZastypenpZint64ZnotnarI _add_marginsZ droplevelT)r(r0r1r2r)r3r*r+r,r-r.r5Z values_passedZ values_multiiZ to_filterxrRZ observed_boolgroupedZaggedrAZ index_namesZ to_unstacknamemrBrBrCr;vs                r;zDataFrame | Series)rAr(r-r,c  Cst|tstdd|d} |jjD]} ||j| vr&t| q&t||||} |jdkr|jjddD]} ||j| vrlt| qlt |dkr|fdt |d} n|} |st|t r| | | | |iS|rt ||||||||} t| ts| S| \}}}n>t|ts Jt|||||||} t| tsD| S| \}}}|j|j|d}|D]0}t|tr| |||<n| |d||<qbdd lm}||t| gd j}|jj}t|jD]<}t|trڐq||gj}||jt|fd ||<q| |}||j_|S) Nz&margins_name argument must be a stringzConflicting name "z " in marginsr#rKrr )r2)args)r9strrUr1rMget_level_values_compute_grand_marginndimr2rTr_append _constructor_generate_marginal_resultstupler)_generate_marginal_results_without_valuesrbpandasr!rrgsetZdtypesrZ select_dtypesapplyr )rAr(r0rOrPr)r-r,r3msglevel grand_marginrRZmarginal_result_setresult margin_keys row_marginkr!Z margin_dummyZ row_namesZdtyperBrBrCrfs`               rf)r(r,c Cs|ri}||D]\}}zlt|tr:t||||<nLt|trzt||trht|||||<q|||||<n ||||<WqtyYq0q|S|||jiSdSrD)itemsr9rqr=dictrSr1)r(r0r)r,rrvrBrBrCrsUs   rs)r(r-r,cstdkr|g}g} fdd} t|dkr|||j||d|} d} |jjd|dD]>\} }|j}| | }|}| | ||<||| |q`nddlm}d} |jd|dD]\} }tdkr| | }n}|||||j}t |j t r(t j |g|j j dgd|_ nt|g|j jd |_ ||| |q|s\|St|| d }t|dkr|Sn |}|j} tdkr||j|d|jd d tgttt}fd d|D}j |_ n|jtj|jd|| fS)Nrcs|fdtdS)Nrnr#rT)rRrPr,rBrC_all_key|sz,_generate_marginal_results.._all_keyr-r#)r~r-r rLrkrNT)Z future_stackcsg|]}jj|qSrB)r1rMrErh)rrBrC z._generate_marginal_results..r1)rTrWr]rgcopyr<rzr!r|r9r1r from_tuplesrMrrkrr2stackr:r_Zreorder_levels_constructor_slicedrenan)rAr(r0rOrPr)r-r,Z table_piecesrrmarginZcat_axisrRZpieceall_keyr!Ztransformed_piecerZnew_order_indicesZnew_order_namesrB)rPr,rrCrwlsX             rwc stdkrg}fdd}t|dkr`|j||d||} |} | || <|} || q|jdd|d|} |} | || <|} || | Sn |} |j}tr|j|d|} nttj| jd} | || fS)Nrcs&tdkrSfdtdS)Nr#rnrrBrrBrCrs z;_generate_marginal_results_without_values.._all_keyr)r~r6r-r)rTrWr|r<r2rrer) rAr(rOrPr)r-r,rrrrrrrBrrCrys*    rycCsF|durg}n4t|s2t|tjtttfs2t|r:|g}nt|}|SrD) rr9reZndarrayrrrcallabler:)ZbyrBrBrCr8sr8pivot)r1r0rzIndexLabel | lib.NoDefault)r(r2r1r0r/c svt|}jddj_ddjjDj_|tjurz|tjurXt|}ng}|tju}j|||d}n|tjurtjt rfddt jj D}q܈j jjj dg}nfddt|D}fd d|D} || t |} t|r>t|ts>ttt|}j|j| |d }nj |j| d }||} d d| jjD| j_| S) NF)deepcSsg|]}|dur|ntjqSrDr rVrErkrBrBrCr szpivot..)r<csg|]}j|qSrB)r1rrrr(rBrCr!srcsg|] }|qSrBrB)rEidxrrBrCr)rcsg|] }|qSrBrB)rEcolrrBrCr+r)r1r2rcSsg|]}|tjur|ndqSrDrrrBrBrCr;s)comZconvert_to_list_likerr1rMr rVZ set_indexr9rr_r^rrkextendrarrxrrrrvZ_valuesr`) r(r2r1r0Zcolumns_listlikerPr<ZindexedZ index_listZ data_columnsZ multiindexrrBrrCrsH                 z/bool | Literal[0, 1, 'all', 'index', 'columns'])r*r,r+ normalizer/c  Cs^|dur|durtd|dur0|dur0tdt|s>|g}t|sL|g}d} dd||D} | rtt| ddd} t||d d }t||d d }t||\} } }}d d lm}itt| |tt||}||| d}|durd |d<t d d}n||d<d|i}|j d| ||||dd|}| dur>t || ||d}|j | d d}|j |dd}|S)a Compute a simple cross tabulation of two (or more) factors. By default, computes a frequency table of the factors unless an array of values and an aggregation function are passed. Parameters ---------- index : array-like, Series, or list of arrays/Series Values to group by in the rows. columns : array-like, Series, or list of arrays/Series Values to group by in the columns. values : array-like, optional Array of values to aggregate according to the factors. Requires `aggfunc` be specified. rownames : sequence, default None If passed, must match number of row arrays passed. colnames : sequence, default None If passed, must match number of column arrays passed. aggfunc : function, optional If specified, requires `values` be specified as well. margins : bool, default False Add row/column margins (subtotals). margins_name : str, default 'All' Name of the row/column that will contain the totals when margins is True. dropna : bool, default True Do not include columns whose entries are all NaN. normalize : bool, {'all', 'index', 'columns'}, or {0,1}, default False Normalize by dividing all values by the sum of values. - If passed 'all' or `True`, will normalize over all values. - If passed 'index' will normalize over each row. - If passed 'columns' will normalize over each column. - If margins is `True`, will also normalize margin values. Returns ------- DataFrame Cross tabulation of the data. See Also -------- DataFrame.pivot : Reshape data based on column values. pivot_table : Create a pivot table as a DataFrame. Notes ----- Any Series passed will have their name attributes used unless row or column names for the cross-tabulation are specified. Any input passed containing Categorical data will have **all** of its categories included in the cross-tabulation, even if the actual data does not contain any instances of a particular category. In the event that there aren't overlapping indexes an empty DataFrame will be returned. Reference :ref:`the user guide ` for more examples. Examples -------- >>> a = np.array(["foo", "foo", "foo", "foo", "bar", "bar", ... "bar", "bar", "foo", "foo", "foo"], dtype=object) >>> b = np.array(["one", "one", "one", "two", "one", "one", ... "one", "two", "two", "two", "one"], dtype=object) >>> c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny", ... "shiny", "dull", "shiny", "shiny", "shiny"], ... dtype=object) >>> pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c']) b one two c dull shiny dull shiny a bar 1 2 1 0 foo 2 2 1 2 Here 'c' and 'f' are not represented in the data and will not be shown in the output because dropna is True by default. Set dropna=False to preserve categories with no data. >>> foo = pd.Categorical(['a', 'b'], categories=['a', 'b', 'c']) >>> bar = pd.Categorical(['d', 'e'], categories=['d', 'e', 'f']) >>> pd.crosstab(foo, bar) col_0 d e row_0 a 1 0 b 0 1 >>> pd.crosstab(foo, bar, dropna=False) col_0 d e f row_0 a 1 0 0 b 0 1 0 c 0 0 0 Nz&aggfunc cannot be used without values.z)values cannot be used without an aggfunc.cSsg|]}t|ttfr|qSrB)r9rr)rErirBrBrCrrzcrosstab..TF)Z intersectr.rowprefixrrr r __dummy__)r)r3r))r1r2r*r,r+r-)rr*r,)r1r6r#)r2r6)r) rUrr _get_names_build_names_mapperrzr!rziprTr" _normalizeZ rename_axis)r1r2r0rownamescolnamesr)r*r,r+rZ common_idxZ pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesr!r(ZdfkwargsrArBrBrCcrosstabBsfj      r)rAr*r,r/c CsLt|ttfsTddd}z ||}Wn.tyR}ztd|WYd}~n d}~00|durddddd dd }|d |d <z ||}Wn.ty}ztd|WYd}~n d}~00||}|d }nv|d ur@|j}|j} |jdddfj } || v|| k@rt|d|jdddf} |jdddf} |jddddf}t ||dd}|dkr| | } t || gdd}|d }| |_n|dkr| | } | | }|d }||_np|d ks|d ur6| | } | | } d| j|<t || gdd}| | }|d }||_| |_ntdntd|S)Nr1r2)rr#zNot a valid normalize argumentFcSs||jddjddSNr#rNrsumrirBrBrCrz_normalize..cSs ||SrDrrrBrBrCrrcSs|j|jddddSr)divrrrBrBrCrr)rIr2r1rITrz not in pivoted DataFrame)rr*r#rNzNot a valid margins argument)r9r'rqrQrUrcr1r2Zilocrkrrrruloc) rArr*r,Z axis_subserrZ normalizersfZ table_index table_columnsZlast_ind_or_colZ column_marginZ index_marginrBrBrCrsd                    rrrqrcCs|durVg}t|D]>\}}t|tr>|jdur>||jq||d|qn*t|t|krntdt|tst|}|S)N_z*arrays and names must have the same length) enumerater9rrkr<rTAssertionErrorr:)ZarrsrMrrhZarrrBrBrCr?s rz list[str]z;tuple[dict[str, str], list[str], dict[str, str], list[str]])rrr/csdd}t|t|}||||B|Bfddt|D}fddt|D}fddt|D}fddt|D}||||fS) a Given the names of a DataFrame's rows and columns, returns a set of unique row and column names and mappers that convert to original names. A row or column name is replaced if it is duplicate among the rows of the inputs, among the columns of the inputs or between the rows and the columns. Parameters ---------- rownames: list[str] colnames: list[str] Returns ------- Tuple(Dict[str, str], List[str], Dict[str, str], List[str]) rownames_mapper: dict[str, str] a dictionary with new row names as keys and original rownames as values unique_rownames: list[str] a list of rownames with duplicate names replaced by dummy names colnames_mapper: dict[str, str] a dictionary with new column names as keys and original column names as values unique_colnames: list[str] a list of column names with duplicate names replaced by dummy names cstfdd|DS)Ncsh|]}|vr|qSrBrBrseenrBrC prz>_build_names_mapper..get_duplicates..)r{rLrBrrCget_duplicatesnsz+_build_names_mapper..get_duplicatescs$i|]\}}|vrd||qSZrow_rBrErhrkZ dup_namesrBrC usz'_build_names_mapper..cs&g|]\}}|vrd|n|qSrrBrrrBrCrxsz'_build_names_mapper..cs$i|]\}}|vrd||qSZcol_rBrrrBrCr|scs&g|]\}}|vrd|n|qSrrBrrrBrCrs)r{ intersectionr)rrrZ shared_namesrrrrrBrrCrPs     r)r&N)r&)r&)r&)NNNNFr&TF)r&)r)E __future__rcollections.abcrrtypingrrrrrZnumpyreZ pandas._libsr Zpandas.util._decoratorsr r Zpandas.util._exceptionsr Zpandas.core.dtypes.castr Zpandas.core.dtypes.commonrrrZpandas.core.dtypes.dtypesrZpandas.core.dtypes.genericrrZpandas.core.commoncorecommonrZpandas.core.framerZpandas.core.groupbyrZpandas.core.indexes.apirrrZpandas.core.reshape.concatrZpandas.core.reshape.utilrZpandas.core.seriesrZpandas._typingrrrrrzr!rVr"r;rfrsrwryr8rrrrrrBrBrBrCs           "7V[-H/P