o ŀgp @s*ddlmZddlmZmZddlmZmZmZm 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/m0Z0erddl1m2Z2m3Z3m4Z4m5Z5ddl6m7Z7edee$dddddddddddej8df dRd)dZ9dSd+d,Z:  dTdUd/d0Z; dVdWd1d2Z< dVdXd3d4Z= dVdYd5d6Z>d7d8Z?edee$d9ddej8ej8d:dZd@d9Z@        d[d\dCdDZA dVd]dEdFZBd^d_dJdKZCd`dPdQZDdS)a) 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)indentsmeanFTAlldatar!aggfuncrmarginsbooldropna margins_namerobservedbool | lib.NoDefaultsortreturnc Cst|}t|}t|trAg} g} |D]} t|||||| |||| | d }| || t| d| qt| | dd}|j|ddSt|||||||||| | }|j|ddS)N) valuesindexcolumns fill_valuer(r)r+r,r-r/__name__r#)keysaxisr")method) _convert_by isinstancelist__internal_pivot_tableappendgetattrr __finalize__)r'r1r2r3r(r4r)r+r,r-r/piecesr6func_tabletablerDM/var/www/html/myenv/lib/python3.10/site-packages/pandas/core/reshape/pivot.pyr"=sJ   !AggFuncTypeBase | AggFuncTypeDictc  Csv||} |du} | rZt|rd} t|}nd} |g}|D] }||vr&t|qg}| |D]}t|tr7|j}z ||vrA||Wq-tyKYq-wt|t|j krY||}n|j }| D]}z| |}Wq_tt tfytYq_wt|}| t j urdn| }|j| || |d}| t j urtdd|jjDrtjdttd||}|rt|trt|j r|jd d }|}|jjd kr|r|jjdt|}g}tt|t| D]}|jj|}|dus||vr||q||q|j||d }|s8t|jtrtjt |jj!|jjd }|j"|d|d}t|j tr8tjt |j j!|j jd }|j"|d |d}| durIt|trI|j#d d}|durg|$|}|turg| sgt %|rg|&t'j(}|r|rw||)j*d d}t+|||||||||d }| r| s|j jd kr|j ,d|_ t|dkrt|dkr|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)_passed_categorical).0pingrDrDrE s z)__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#r4namesr)r7r4r7)rowscolsr(r-r,r4)rOr7).rr;KeyErrorr:rkeyr= TypeErrorlenr3drop ValueErrorr no_defaultgroupbyany_grouper groupingswarningswarn FutureWarningr aggrr+r2nlevelsrRrangeunstackr from_arraysrlevelsreindex sort_indexfillna is_integerastypenpint64notnarN _add_margins droplevelT)r'r1r2r3r(r4r)r+r,r-r/r6 values_passed values_multii to_filterxrW observed_boolgroupedaggedrC index_names to_unstacknamemrDrDrEr<vs               r<rCDataFrame | Seriesc  Cst|ts tdd|d} |jjD]} ||j| vr!t| qt||||} |jdkrE|jjddD]} ||j| vrDt| q6t |dkrW|fdt |d} n|} |slt|t rl| | | | |iS|rt ||||||||} t| ts| S| \}}}nt|tsJt|||||||} t| ts| S| \}}}|j|j|d}|D]}t|tr| |||<q| |d||<qdd lm}||t| gd j}|jj}t|jD]}t|trq||gj}||jt|fd ||<q| |}||j_|S) Nz&margins_name argument must be a stringzConflicting name "z " in marginsr#rPrr )r3)args)r:strr[r2rRget_level_values_compute_grand_marginndimr3rYr_append _constructor_generate_marginal_resultstupler)_generate_marginal_results_without_valuesrjpandasr!rrtsetdtypesr select_dtypesapplyr )rCr'r1rTrUr(r-r,r4msglevel grand_marginrWmarginal_result_setresult margin_keys row_marginkr! margin_dummy row_namesdtyperDrDrErrsd             rrc Cs|rPi}||D]C\}}z6t|trt||||<n&t|tr=t||tr4t|||||<n|||||<n||||<Wq tyMYq w|S|||jiSrG)itemsr:rr>dictrXr2)r'r1r(r,rrvrDrDrErUs"    rcs tdkrg}g} fdd} t|dkrP|||j||d|} d} |jjd|dD]\} }|j}| | }|}| | ||<||| |q/nWddlm}d} |jd|dD]G\} }tdkrn| | }n}|||||j}t |j t rt j |g|j j dgd|_ n t|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)Nrr#rY)rWrUr,rDrE_all_key|sz,_generate_marginal_results.._all_keyr-r#)rr-r rQrrST) future_stackcsg|]}jj|qSrD)r2rRrIrw)rrDrE z._generate_marginal_results..r2)rYr]rdrtcopyr=rr!rr:r2r from_tuplesrRrrrr3stackr;rfreorder_levels_constructor_slicedronan)rCr'r1rTrUr(r-r, table_piecesrrmargincat_axisrWpieceall_keyr!transformed_piecernew_order_indicesnew_order_namesrD)rUr,rrErls\                  rc stdkrKg}fdd}t|dkr0|j||d||} |} | || <|} || n |jdd|d|} |} | || <|} || | S|} |j}tra|j|d|} nttj| jd} | || fS)Nrcs&tdkrSfdtdS)Nr#rrrDrrDrErs z;_generate_marginal_results_without_values.._all_keyr)rr7r-r)rYr]rr=r3rror) rCr'rTrUr(r-r,rrrrrrrDrrErs*     rcCsJ|durg}|St|st|tjtttfst|r|g}|St|}|SrG) rr:rondarrayrrrcallabler;)byrDrDrEr9s r9pivot)r2r1r3rr2IndexLabel | lib.NoDefaultr1c srt|}jddj_ddjjDj_|tjur=|tjur,t|}ng}|tju}j|||d}nj|tjurbtjt rVfddt jj D}nj jjj dg}n fddt|D}fd d|D} || t |} t|rt|tsttt|}j|j| |d }n j |j| d }||} d d| jjD| j_| S) NF)deepcSsg|] }|dur |ntjqSrGr r\rIrrDrDrEr zpivot..)r=csg|]}j|qSrD)r2rrr'rDrEr!s rcg|]}|qSrDrD)rIidxrrDrEr)crrDrD)rIcolrrDrEr+r)r2r3rcSsg|] }|tjur |ndqSrGrrrDrDrEr;r)comconvert_to_list_likerr2rRr r\ set_indexr:rrfrerrextendrhrrrrrr_valuesrg) r'r3r2r1columns_listlikerUr=indexed index_list data_columns multiindexrrDrrErsH                normalize/bool | Literal[0, 1, 'all', 'index', 'columns']c  Cs^|dur |dur td|dur|durtdt|s|g}t|s&|g}d} dd||D} | r:t| ddd} t||d d }t||d d }t||\} } }}d d lm}itt| |tt||}||| d}|dur{d |d<t d d}n||d<d|i}|j d| ||||dd|}| durt || ||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|qSrD)r:rr)rIryrDrDrErszcrosstab..TF) intersectr/row)prefixrrr r __dummy__)r(r4r()r2r3r)r,r+r-)rr)r,)r2r7r#)r3r7)r) r[rr _get_names_build_names_mapperrr!rziprYr" _normalize rename_axis)r2r3r1rownamescolnamesr(r)r,r+r common_idx pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesr!r'dfkwargsrCrDrDrEcrosstabBsfj      rc Cs,t|ttfs$ddd}z||}Wnty#}ztd|d}~ww|dur]ddddd dd }|d |d <z||}WntyQ}ztd|d}~ww||}|d }|S|d ur|j}|j} |jdddfj } || v|| k@rt|d|jdddf} |jdddf} |jddddf}t ||dd}|dkr| | } t || gdd}|d }| |_|S|dkr| | } | | }|d }||_|S|d ks|d ur| | } | | } d| j|<t || gdd}| | }|d }||_| |_|Stdtd)Nr2r3)rr#zNot a valid normalize argumentFcSs||jddjddSNr#rSrsumryrDrDrErz_normalize..cSs ||SrGrrrDrDrErs cSs|j|jddddSr)divrrrDrDrErs)rNr3r2rNTrz not in pivoted DataFrame)rr)r#rSzNot a valid margins argument)r:r*rrVr[rlr2r3ilocrrrrrloc) rCrr)r, axis_subserr normalizersf table_index table_columnslast_ind_or_col column_margin index_marginrDrDrErsr       3           rrrrcCs|dur,g}t|D]\}}t|tr|jdur||jq ||d|q |St|t|kr8tdt|tsAt|}|S)N_z*arrays and names must have the same length) enumerater:rrr=rYAssertionErrorr;)arrsrRrrwarrrDrDrEr?s rr list[str]r;tuple[dict[str, str], list[str], dict[str, str], list[str]]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|qSrDrDrseenrDrE prz>_build_names_mapper..get_duplicates..)rrQrDrrEget_duplicatesnsz+_build_names_mapper..get_duplicatesc$i|]\}}|vrd||qSrow_rDrIrwr dup_namesrDrE uz'_build_names_mapper..c&g|]\}}|vrd|n|qSrrDrr rDrErxz'_build_names_mapper..crcol_rDrr rDrEr |r cr rrDrr rDrErr)r intersectionr)rrr shared_namesrrrrrDr rErPs      r)r'r!r(rr)r*r+r*r,rr-r.r/r*r0r!)r'r!r(rFr)r*r+r*r,rr-r.r/r*r0r!)r&N)rCrr'r!r-r*r,r)r&)r'r!r,r)r'r!r-r*r,r)rCr!r'r!r-r*r,r) r'r!r3rr2rr1rr0r!)NNNNFr&TF) r)r*r,rr+r*rrr0r!)rCr!r)r*r,rr0r!)r)rr)rrrrr0r)E __future__rcollections.abcrrtypingrrrrranumpyro pandas._libsr pandas.util._decoratorsr r pandas.util._exceptionsr pandas.core.dtypes.castr pandas.core.dtypes.commonrrrpandas.core.dtypes.dtypesrpandas.core.dtypes.genericrrpandas.core.commoncorecommonrpandas.core.framerpandas.core.groupbyrpandas.core.indexes.apirrrpandas.core.reshape.concatrpandas.core.reshape.utilrpandas.core.seriesrpandas._typingrrrrrr!r\r"r<rrrrrr9rrrrrrDrDrDrEs            7 V  [ -H / P