U f/ef @s ddlmZddlmZmZmZmZmZddlZ ddl m Z m Z m Z mZmZddlmZmZddlmZddlmZmZmZddlmZmZddlmmZdd l m!Z!dd l"m#Z#dd l$m%Z%m&Z&m'Z'dd l(m)Z)dd l*m+Z+ddl,m-Z-erddl.m/Z/edee!ddddBddddddZ0dddddddddd d!Z1dCd"dd#d$d%Z2dDdd&d'd(Z3dEdd&d)d*Z4dFddd#d+d,Z5d-d.Z6edee!d/dddGdd0d0d0dd1d2d/Z7dHdddd3d4d5Z8dIdd6d7d8Z9dJdd:d;d<Z:d=d=d>d?d@dAZ;dS)K) annotations) TYPE_CHECKINGCallableHashableSequencecastN) AggFuncTypeAggFuncTypeBaseAggFuncTypeDictFrameOrSeriesUnion IndexLabel)Appender Substitution)maybe_downcast_to_dtype)is_integer_dtype is_list_like is_scalar) ABCDataFrame ABCSeries) _shared_docs)Grouper)Index MultiIndexget_objs_combined_axis)concat)cartesian_product)Series DataFramez data : DataFrame pivot_table)indentsmeanFTAllrr)dataaggfuncreturnc Cst|}t|}t|trg} g} |D]>} t|||||| |||| | d }| || t| d| q&t| | dd}|j|ddSt|||||||||| | }|j|ddS)N) valuesindexcolumns fill_valuer%marginsdropna margins_nameobservedsort__name__r )keysaxisr)method) _convert_by isinstancelist__internal_pivot_tableappendgetattrrZ __finalize__)r$r'r(r)r%r*r+r,r-r.r/piecesr1func_tabletabler>=/tmp/pip-unpacked-wheel-tiezk1ph/pandas/core/reshape/pivot.pyr6sJ   z!AggFuncTypeBase | AggFuncTypeDictboolstr)r$r%r+r,r-r.r/r&c  Cs||} |dk } | rt|r*d} t|}n d} |g}|D]}||kr8t|q8g}| |D]@}t|trn|j}z||kr||WqZtk rYqZXqZt|t|j kr||}nB|j }| D].}z| |}Wqtt tfk rYqXqt|}|j | | | d}| |}|rt|trt|j r|jdd}|D]l}||krBt||rB||krBt||sBt||tr||||<nt||||j||<qB|}|jjdkr:|r:|jjdt|}g}tt|t| D]<}|jj|}|dks||kr"||n ||q||}|st|jtrvtjt|jj|jjd}|j|d d }t|j trtjt|j j|j jd}|j|dd }t|tr|jdd }|dk r|j|d d }|dk st|}|r(|r|| j!dd }t"|||||||||d }| rP| sP|j jdkrP|j#d dd }t|d krrt|d krr|j$}t|tr|r|jddd}|S)zL Helper of :func:`pandas.pivot_table` for any non-list ``aggfunc``. NTF)r.r/all)howr namesrr2Zinfer)Zdowncast)rowscolsr%r.r-r*)rCr2)%rr6KeyErrorr5rkeyr8 TypeErrorlenr)Zdrop ValueErrorgroupbyaggrr,rrdtyper(ZnlevelsrErangeunstackr from_arraysrlevelsreindexZ sort_indexfillnaAssertionErrorZnotnarB _add_marginsZ droplevelT)r$r'r(r)r%r*r+r,r-r.r/r1Z values_passedZ values_multiiZ to_filterxrJZgroupedZaggedvr=Z index_namesZ to_unstacknamemr<r>r>r?r7os                  r7r )r=r-c  Cst|tstdd|d} |jjD]} ||j| kr&t| q&t||||} |jdkr|jjddD]} ||j| krlt| qlt |dkr|fdt |d} n|} |st|t r| t | | |iS|rt ||||||||} t| ts| S| \}}}n>t|tstt|||||||} t| tsB| S| \}}}|j|j|d}|D]0}t|tr~| |||<n| |d||<q`dd lm}||| gd j}|jj}t|jD],}||gj}||jt|fd ||<q| |}||j_|S) Nz&margins_name argument must be a stringzConflicting name "z " in marginsr )r*rr)r))args)r5rArMr(rEZget_level_values_compute_grand_marginndimr)rLrr8r_generate_marginal_resultstuplerrW)_generate_marginal_results_without_valuesrUpandasrrYsetZdtypesZ select_dtypesapplyr)r=r$r'rGrHr%r.r-r*msglevel grand_marginrJZmarginal_result_setresult margin_keys row_marginkrZ margin_dummyZ row_namesrPr>r>r?rXsx              rX)r-c Cs|ri}||D]\}}zlt|tr:t||||<nLt|trzt||trht|||||<q|||||<n ||||<Wqtk rYqXq|S|||jiSdSN)itemsr5rAr9dictrKr()r$r'r%r-rmrqr\r>r>r?rcPs  rccstdkrBg}g} fdd} t|dkr|||j||d|} d} |jd| |dD]8\} }| | }|}| | ||<||| |q`nddlm}d} |jd| |dD]d\} }tdkr| | }n}|||||j}t |g|j j d|_ ||| |qt || d }t|dkrL|Sn |}|j } tdkr||j|d|}|}tgttt}|j ||_ nttj|j d }|| |fS) Nrcs|fdtdS)Nr`r rL)rJrHr-r>r?_all_keynsz,_generate_marginal_results.._all_keyr.r rlr2r.rr]rFr()rLrNrOcopyr8rhrrjrYrr(r]rr)stackr6rQZreorder_levelsrnpnan)r=r$r'rGrHr%r.r-Z table_piecesrorwmarginZcat_axisrJZpieceall_keyrZtransformed_piecernrpZ new_orderr>rvr?refsH          rec stdkrg}fdd}t|dkr`||j||d|} |} | || <|} || q|jdd|d|} |} | || <|} || | Sn |} |j}tr|j|d|} nttj| jd} | || fS)Nrcs&tdkrSfdtdS)Nr r`rur>rvr>r?rws z;_generate_marginal_results_without_values.._all_keyrxryr{)rLrNrjr8r)rr~r) r=r$rGrHr%r.r-rorwrrrnrpr>rvr?rgs*    rgcCsF|dkrg}n4t|s2t|tjtttfs2t|r:|g}nt|}|Srr) rr5r~Zndarrayrrrcallabler6)Zbyr>r>r?r4sr4pivotzIndexLabel | None)r$r(r)r'r&c s|dkrtdt|}|dkrV|dk r6t|}ng}|dk}j|||d}n|dkrttjjjdg}nfddt|D}fdd|D} || t |} t |rt |t st tt|}j|j| |d}nj|j| d}||S) Nz.pivot() missing 1 required argument: 'columns')r8rzcsg|] }|qSr>r>).0idxr$r>r? szpivot..csg|] }|qSr>r>)rcolrr>r?rs)r(r)r{)rKcomZconvert_to_list_likeZ set_indexrr(r]extendrrSrr5rfrrrZ _constructorZ_valuesZ_constructor_slicedrR) r$r(r)r'Zcolumns_listlikerHr8ZindexedZ index_listZ data_columnsZ multiindexr>rr?rs6    )r-r,r&c CsP|dkr|dk rtd|dk r0|dkr0tdt|}t|}d} dd||D} | rlt| ddd} t||d d }t||d d }t||\} } }}d d lm}tt | |tt ||}||| d}|dkrd |d<t d d}n||d<d|i}|j d| ||||d|}| dk r0t || ||d}|j | d d}|j |dd}|S)ac 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. 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|qSr>)r5rr)rr[r>r>r?ryszcrosstab..TF)Z intersectr/rowprefixrrrr{ __dummy__)r%r*r%)r(r)r+r-r,) normalizer+r-)r(r2r )r)r2)r)rMrZmaybe_make_listr _get_names_build_names_mapperrhrrtziprLr _normalizeZ rename_axis)r(r)r'rownamescolnamesr%r+r-r,rZ common_idxZ pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesrr$Zdfkwargsr=r>r>r?crosstabsbg        r)r+c CsHt|ttfsRddd}z ||}Wn,tk rP}ztd|W5d}~XYnX|dkrddddd dd }|d |d <z ||}Wn,tk r}ztd|W5d}~XYnX||}|d }nv|d kr<|j}|j} |jdddfj } || k|| k@rt|d|jdddf} |jdddf} |jddddf}t ||dd}|dkr| | } t || gdd}|d }| |_n|dkr| | } | | }|d }||_np|d ks|d kr2| | } | | } d| j|<t || gdd}| | }|d }||_| |_ntdntd|S)Nr(r))rr zNot a valid normalize argumentFcSs||jddjddSNr rFrsumr[r>r>r?z_normalize..cSs ||Srrrrr>r>r?rrcSs|j|jddddSr)divrrr>r>r?rr)rBr)r(rBTrz not in pivoted DataFrame)rr+r rFzNot a valid margins argument)r5r@rArIrMrVr(r)Zilocr]rrrr8loc) r=rr+r-Z axis_subserrZ normalizersfZ table_indexZ table_columnsZlast_ind_or_colZ column_marginZ index_marginr>r>r?rsd                  rrrcCs|dkrVg}t|D]>\}}t|tr>|jdk r>||jq||d|qn*t|t|krntdt|tst|}|S)N_z*arrays and names must have the same length) enumerater5rr]r8rLrWr6)ZarrsrErrZZarrr>r>r?rs 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|]}|kr|qSr>r>)rr]seenr>r? .sz>_build_names_mapper..get_duplicates..)rirDr>rr?get_duplicates,sz+_build_names_mapper..get_duplicatescs$i|]\}}|krd||qSZrow_r>rrZr]Z dup_namesr>r? 3sz'_build_names_mapper..cs&g|]\}}|krd|n|qSrr>rrr>r?r6sz'_build_names_mapper..cs$i|]\}}|krd||qSZcol_r>rrr>r?r:scs&g|]\}}|krd|n|qSrr>rrr>r?r=s)ri intersectionr)rrrZ shared_namesrrrrr>rr?rs     r) NNNr"NFTr#FT)Nr#N)r#)r#)r#)NNN)NNNNFr#TF)r#)r)< __future__rtypingrrrrrZnumpyr~Zpandas._typingrr r r r Zpandas.util._decoratorsr rZpandas.core.dtypes.castrZpandas.core.dtypes.commonrrrZpandas.core.dtypes.genericrrZpandas.core.commoncorecommonrZpandas.core.framerZpandas.core.groupbyrZpandas.core.indexes.apirrrZpandas.core.reshape.concatrZpandas.core.reshape.utilrZpandas.core.seriesrrhrrr7rXrcrergr4rrrrrr>r>r>r?sx        7PA&/&P