B W0df @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} xF|D]>} t|||||| |||| | d }| || t| d| q(Wt| | 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.piecesr0func_tabletabler=K/var/www/html/venv/lib/python3.7/site-packages/pandas/core/reshape/pivot.pyr6sF   z!AggFuncTypeBase | AggFuncTypeDictboolstr)r#r$r*r+r,r-r.r%c  Cs||} |dk } | rt|r*d} t|}n d} |g}x|D]}||kr:t|q:Wg}xL| |D]@}t|trt|j}y||kr||Wq`tk rYq`Xq`Wt|t|j kr||}nF|j }x6| D].}y| |}Wqtt tfk rYqXqWt|}|j | | | d}| |}|rt|trt|j r|jdd}xt|D]l}||krPt||rP||krPt||sPt||tr||||<nt||||j||<qPW|}|jjdkrN|rN|jjdt|}g}xRtt|t| D]<}|jj|}|dks(||kr4||n ||qW||}|st|jtrtjt|jj|jjd}|j|d d }t|j trtjt|j j|j jd}|j|dd }t|tr|jdd }|dk r|j|d d }|dk st|}|r<|r"|| j!dd }t"|||||||||d }| rd| sd|j jdkrd|j#d dd }t|d krt|d kr|j$}t|tr|r|jddd}|S)zL Helper of :func:`pandas.pivot_table` for any non-list ``aggfunc``. NTF)r-r.all)howr)namesr)r1Zinfer)Zdowncast)rowscolsr$r-r,r))rBr1)%rr5KeyErrorr4rkeyr7 TypeErrorlenr(Zdrop ValueErrorgroupbyaggrr+rrdtyper'ZnlevelsrCrangeunstackr from_arraysrZlevelsreindexZ sort_indexfillnaAssertionErrorZnotnarA _add_marginsZ droplevelT)r#r&r'r(r$r)r*r+r,r-r.r0Z values_passedZ values_multiiZ to_filterxrGgroupedZaggedvr<Z index_namesZ to_unstacknamemr;r=r=r>r6os                   r6r )r<r,c  Cst|tstdd|d} x(|jjD]} ||j| kr(t| q(Wt||||} |jdkrx0|jjddD]} ||j| krrt| qrWt |dkr|fdt |d} n|} |st|t r| t | | |iS|rt ||||||||} t| ts | S| \}}}n>t|ts&tt|||||||} t| tsJ| S| \}}}|j|j|d}x8|D]0}t|tr| |||<n| |d||<qjWdd lm}||| gd j}|jj}x:t|jD],}||gj}||jt|fd ||<qW| |}||j_|S) Nz&margins_name argument must be a stringzConflicting name "z " in marginsr))r)r)r)r()args)r4r@rJr'rCZget_level_values_compute_grand_marginndimr(rIrr7r_generate_marginal_resultstuplerrS)_generate_marginal_results_without_valuesrQpandasrrUsetZdtypesZ select_dtypesapplyr)r<r#r&rDrEr$r-r,r)msglevel grand_marginrGZmarginal_result_setresult margin_keys row_marginkrZ margin_dummyZ row_namesrMr=r=r>rTsV              rT)r,c Cs|ri}x||D]\}}ylt|trr_Ps   r_cstdkrJg}g} fdd} t|dkr|||j||d|} d} x|jd| |dD]8\} }| | }|}| | ||<||| |qbWnddlm}d} xx|jd| |dD]d\} }tdkr| | }n}|||||j}t |g|j j d|_ ||| |qWt || d }t|dkrT|Sn |}|j } tdkr||j|d|}|}tgttt}|j ||_ nttj|j d }|| |fS) Nrcs|fdtdS)N)r]r)rI)rG)rEr,r=r>_all_keynsz,_generate_marginal_results.._all_key)r-r)rhr1r-)r)rZ)r1)r')rIrKrLcopyr7rdrrfrUrr'rZrr(stackr5rNZreorder_levelsrnpnan)r<r#r&rDrEr$r-r,Z table_piecesrkrpmarginZcat_axisrGZpieceall_keyrZtransformed_piecerjrlZ new_orderr=)rEr,r>rafsH         rac stdkrg}fdd}t|dkr`||j||d|} |} | || <|} || q|jdd|d|} |} | || <|} || | Sn |} |j}tr|j|d|} nttj| jd} | || fS)Nrcs&tdkrSfdtdS)Nr)r])rIr=)rEr,r=r>rps z;_generate_marginal_results_without_values.._all_key)r-)rhr1r-)r')rIrKrfr7r(rrsrt) r<r#rDrEr$r-r,rkrprurvrjrlr=)rEr,r>rcs*    rccCsF|dkrg}n4t|s2t|tjtttfs2t|r:|g}nt|}|S)N) rr4rsZndarrayrrrcallabler5)Zbyr=r=r>r3sr3pivotzIndexLabel | 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')r7)rZcsg|] }|qSr=r=).0idx)r#r=r> szpivot..csg|] }|qSr=r=)rycol)r#r=r>r{s)r'r()r')rHcomZconvert_to_list_likeZ set_indexrr'rZextendrrPrr4rbrrrZ _constructorZ_valuesZ_constructor_slicedrO) r#r'r(r&Zcolumns_listlikerEr7ZindexedZ index_listZ data_columnsZ multiindexr=)r#r>rxs,    )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=)r4rr)ryrWr=r=r>r{yszcrosstab..TF)Z intersectr.row)prefixr|r)r)r' __dummy__)r$r)r$)r'r(r*r,r+) normalizer*r,)r'r1r)r(r1)r)rJr}Zmaybe_make_listr _get_names_build_names_mapperrdrroziprIr _normalizeZ rename_axis)r'r(r&rownamescolnamesr$r*r,r+rZ common_idxZ pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesrr#Zdfkwargsr<r=r=r>crosstabsHg       r)r*c CsHt|ttfsRddd}y ||}Wn,tk rP}ztd|Wdd}~XYnX|dkrddddd dd }|d |d <y ||}Wn,tk r}ztd|Wdd}~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()rrzNot a valid normalize argumentFcSs||jddjddS)Nr)r1r)sum)rWr=r=r>z_normalize..cSs ||S)N)r)rWr=r=r>rrcSs|j|jddddS)Nr)r1r)divr)rWr=r=r>rr)rAr(r'rATrz not in pivoted DataFrame)rr*r)r1zNot a valid margins argument)r4r?r@rFrJrRr'r(ZilocrZrrrr7loc) r<rr*r,Z axis_subserrZ normalizersfZ table_index table_columnsZlast_ind_or_colZ column_marginZ index_marginr=r=r>rsb                   rr)rcCs|dkrZg}xvt|D]>\}}t|tr@|jdk r@||jq||d|qWn*t|t|krrtdt|tst|}|S)N_z*arrays and names must have the same length) enumerater4rrZr7rIrSr5)ZarrsrCrrVZarrr=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=)ryrZ)seenr=r> .sz>_build_names_mapper..get_duplicates..)re)rCr=)rr>get_duplicates,sz+_build_names_mapper..get_duplicatescs$i|]\}}|kr|d|qS)row_r=)ryrVrZ) dup_namesr=r> 3sz'_build_names_mapper..cs&g|]\}}|krd|n|qS)rr=)ryrVrZ)rr=r>r{7sz'_build_names_mapper..cs$i|]\}}|kr|d|qS)col_r=)ryrVrZ)rr=r>r:scs&g|]\}}|krd|n|qS)rr=)ryrVrZ)rr=r>r{>s)re intersectionr)rrrZ shared_namesrrrrr=)rr>rs    r) NNNr!NFTr"FT)Nr"N)r")r")r")NNN)NNNNFr"TF)r")r)< __future__rtypingrrrrrnumpyrsZpandas._typingrr r r r Zpandas.util._decoratorsr rZpandas.core.dtypes.castrZpandas.core.dtypes.commonrrrZpandas.core.dtypes.genericrrZpandas.core.commoncorecommonr}Zpandas.core.framerZpandas.core.groupbyrZpandas.core.indexes.apirrrZpandas.core.reshape.concatrZpandas.core.reshape.utilrZpandas.core.seriesrrdrrr6rTr_rarcr3rxrrrrr=r=r=r>sl        ,G@%+P