U ck @s@ddlmZddlmZmZmZmZmZddlZ ddl m Z m Z m Z mZddlmZmZmZddlmZddlmZddlmZmZmZmZdd lmZmZddlm m!Z"dd l#m$Z$dd l%m&Z&dd l'm(Z(m)Z)m*Z*dd l+m,Z,ddl-m.Z.ddl/m0Z0erddl1m2Z2edee$ddddFdddddddddddZ3dddddddddd d!Z4dGd"ddd#d$d%Z5dHddd&d'd(Z6dIdd)d*d+Z7dJddd,d-d.Z8d/d0Z9edee$d1ddedd2gd3dKdd4d4d4dd5d6d1Z:dLddddd7d8d9Z;dMdddd:d;d<Zd?d@Z=dAdAdBdCdDdEZ>dS)O) annotations) TYPE_CHECKINGCallableHashableSequencecastN) AggFuncTypeAggFuncTypeBaseAggFuncTypeDict IndexLabel)Appender Substitutiondeprecate_nonkeyword_arguments)rewrite_warning)maybe_downcast_to_dtype)is_integer_dtype is_list_likeis_nested_list_like is_scalar) ABCDataFrame ABCSeries) _shared_docs)Grouper)Index MultiIndexget_objs_combined_axis)concat)cartesian_product)Series DataFramez data : DataFrame pivot_table)indentsmeanFTAllr rboolstr)dataaggfuncmarginsdropna margins_nameobservedsortreturnc Cst|}t|}t|trg} g} |D]>} t|||||| |||| | d }| || t| d| q&t| | dd}|j|ddSt|||||||||| | }|j|ddS)N) valuesindexcolumns fill_valuer)r*r+r,r-r.__name__r")keysaxisr!)method) _convert_by isinstancelist__internal_pivot_tableappendgetattrrZ __finalize__)r(r0r1r2r)r3r*r+r,r-r.piecesr5funcZ_tabletablerA=/tmp/pip-unpacked-wheel-g7fro6k3/pandas/core/reshape/pivot.pyr!8sJ   z!AggFuncTypeBase | AggFuncTypeDictc  Cs||} |dk } | rt|r*d} t|}n d} |g}|D]}||kr8t|q8g}| |D]@}t|trn|j}z||kr||WqZtk rYqZXqZt|t|j kr||}nB|j }| D].}z| |}Wqtt tfk rYqXqt|}|j | | | d}d}t dt|d||}W5QRX|rt|trt|j r|jdd }|D]r}||kr`t||r`||kr`t||s`t||ts`t||jtjr`t||||j||<q`|}|jjd kr^|r^|jjdt|}g}tt|t| D]<}|jj|}|dks:||krF||n ||q||}|st|jtrtjt|jj|jjd }|j|d d }t|j trtjt|j j|j jd }|j|d d }| dkrt|tr|j d d }|dk r |j!|dd}|rD|r*||"j#d d }t$|||||||||d }| rl| sl|j jd krl|j%d d d }t|d krt|d kr|j&}t|tr|r|jdd d}|S)zL Helper of :func:`pandas.pivot_table` for any non-list ``aggfunc``. NTF)r-r.zpivot_table dropped a column because it failed to aggregate. This behavior is deprecated and will raise in a future version of pandas. Select only the columns that can be aggregated.z!The default value of numeric_only)Ztarget_messageZtarget_categoryZ new_messageall)howr"namesrr6Zinfer)Zdowncast)rowscolsr)r-r,r3)rDr6)'rr:KeyErrorr9rkeyr< TypeErrorlenr2Zdrop ValueErrorgroupbyr FutureWarningaggrr+rdtypenprr1nlevelsrFrangeunstackr from_arraysrlevelsreindexZ sort_indexfillnaZnotnarC _add_marginsZ droplevelT)r(r0r1r2r)r3r*r+r,r-r.r5Z values_passedZ values_multiiZ to_filterxrKZgroupedmsgZaggedvr@Z index_namesZ to_unstacknamemrArArBr;qs                r;zDataFrame | Series)r@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}||t| gd j}|jj}t|jD],}||gj}||jt|fd ||<q| |}||j_|S) Nz&margins_name argument must be a stringzConflicting name "z " in marginsr")r3rr)r2)args)r9r'rNr1rFget_level_values_compute_grand_marginndimr2rMr_appendr_generate_marginal_resultstuplerAssertionError)_generate_marginal_results_without_valuesrYpandasr rr\setZdtypesZ select_dtypesapplyr)r@r(r0rHrIr)r-r,r3r_level grand_marginrKZmarginal_result_setresult margin_keys row_marginkr Z margin_dummyZ row_namesrRrArArBr[ sx              r[)r(r,c Cs|ri}||D]\}}zlt|tr:t||||<nLt|trzt||trht|||||<q|||||<n ||||<Wqtk rYqXq|S|||jiSdSN)itemsr9r'r=dictrLr1)r(r0r)r,rsrwr`rArArBrh\s  rh)r,cstdkrBg}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)Nrdr"rM)rKrIr,rArB_all_keyzsz,_generate_marginal_results.._all_keyr-r"rrr6r-rrarGr1)rMrOrQcopyr<ror rqr\rr1rarr2stackr:rUZreorder_levelsrrSnan)r@r(r0rHrIr)r-r,Z table_piecesrur}marginZcat_axisrKZpieceall_keyr Ztransformed_piecertrvZ new_orderrAr|rBrkrsH          rk)r@r,c stdkrg}fdd}t|dkr`||j||d|} |} | || <|} || q|jdd|d|} |} | || <|} || | Sn |} |j}tr|j|d|} nttj| jd} | || fS)Nrcs&tdkrSfdtdS)Nr"rdr{rAr|rArBr}s z;_generate_marginal_results_without_values.._all_keyr~rr)rMrOrqr<r2rrSr) r@r(rHrIr)r-r,rur}rrrtrvrAr|rBrns*    rncCsF|dkrg}n4t|s2t|tjtttfs2t|r:|g}nt|}|Srx) rr9rSZndarrayrrrcallabler:)ZbyrArArBr8sr8pivotr()versionZ allowed_argszIndexLabel | None)r(r1r2r0r/c s4|dkrtdt|}|dkrV|dk r6t|}ng}|dk}j|||d}n|dkrtjtrfddtjjD}qt jjj dg}nfddt|D}fdd|D} | | t |} t |rt|tsttt|}j|j| |d}nj|j| d }||S) Nz.pivot() missing 1 required argument: 'columns')r<csg|]}j|qSrA)r1rg).0r]r(rArB szpivot..rcsg|] }|qSrArA)ridxrrArBr scsg|] }|qSrArA)rcolrrArBr s)r1r2r)rLcomZconvert_to_list_likeZ set_indexr9r1rrUrTrraextendrWrrlrrrZ _constructorZ_valuesZ_constructor_slicedrV) r(r1r2r0Zcolumns_listlikerIr<ZindexedZ index_listZ data_columnsZ multiindexrArrBrs>        )r*r,r+r/c CsX|dkr|dk rtd|dk r0|dkr0tdt|s>|g}t|sL|g}d} dd||D} | rtt| 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 r8t || ||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|qSrA)r9rr)rr^rArArBrszcrosstab..TF)Z intersectr.rowprefixrrrr __dummy__)r)r3r))r1r2r*r,r+) normalizer*r,)r1r6r")r2r6)r) rNrr _get_names_build_names_mapperror rzziprMr! _normalizeZ rename_axis)r1r2r0rownamescolnamesr)r*r,r+rZ common_idxZ pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesr r(Zdfkwargsr@rArArBcrosstabsfj      r)r@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)Nr1r2)rr"zNot a valid normalize argumentFcSs||jddjddSNr"rGrsumr^rArArBz_normalize..cSs ||SrxrrrArArBrrcSs|j|jddddSr)divrrrArArBrr)rCr2r1rCTrz not in pivoted DataFrame)rr*r"rGzNot a valid margins argument)r9r&r'rJrNrZr1r2Zilocrarrrrjloc) r@rr*r,Z axis_subserrZ normalizersfZ table_indexZ table_columnsZlast_ind_or_colZ column_marginZ index_marginrArArBrsd                  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) enumerater9rrar<rMrmr:)ZarrsrFrr]ZarrrArArBrs 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|qSrArA)rraseenrArB Lsz>_build_names_mapper..get_duplicates..)rprErArrBget_duplicatesJsz+_build_names_mapper..get_duplicatescs$i|]\}}|krd||qSZrow_rArr]raZ dup_namesrArB Qsz'_build_names_mapper..cs&g|]\}}|krd|n|qSrrArrrArBrTsz'_build_names_mapper..cs$i|]\}}|krd||qSZcol_rArrrArBrXscs&g|]\}}|krd|n|qSrrArrrArBr[s)rp intersectionr)rrrZ shared_namesrrrrrArrBr,s     r) NNNr$NFTr%FT)Nr%N)r%)r%)r%)NNN)NNNNFr%TF)r%)r)? __future__rtypingrrrrrZnumpyrSZpandas._typingrr r r Zpandas.util._decoratorsr r rZpandas.util._exceptionsrZpandas.core.dtypes.castrZpandas.core.dtypes.commonrrrrZpandas.core.dtypes.genericrrZpandas.core.commoncorecommonrZpandas.core.framerZpandas.core.groupbyrZpandas.core.indexes.apirrrZpandas.core.reshape.concatrZpandas.core.reshape.utilrZpandas.core.seriesrror r!r;r[rhrkrnr8rrrrrrArArArBs~         "7#PA& 9,R