Pi6ddlmZddlZddlmZmZmZddlZddl m Z ddl m Z ddl mZddlmZmZmZddlmZdd lmZmZddlmcmZdd lmZdd lmZm Z m!Z!dd l"m#Z#dd l$m%Z%erddl&m'Z'm(Z(ddl)m*Z*m+Z+m,Z,m-Z-m.Z.ddl/m0Z0e d dAdBd"Z1dCd$Z2 dDdEd'Z3 dFdGd(Z4 dHdId)Z5 dHdJd*Z6d+Z7e de j8e j8d,dKd2Z9e d dLdMd5Z: dFdNd6Z;dOdPd;Z` for more examples. Examples -------- >>> df = pd.DataFrame( ... { ... "A": ["foo", "foo", "foo", "foo", "foo", "bar", "bar", "bar", "bar"], ... "B": ["one", "one", "one", "two", "two", "one", "one", "two", "two"], ... "C": [ ... "small", ... "large", ... "large", ... "small", ... "small", ... "large", ... "small", ... "small", ... "large", ... ], ... "D": [1, 2, 2, 3, 3, 4, 5, 6, 7], ... "E": [2, 4, 5, 5, 6, 6, 8, 9, 9], ... } ... ) >>> df A B C D E 0 foo one small 1 2 1 foo one large 2 4 2 foo one large 2 5 3 foo two small 3 5 4 foo two small 3 6 5 bar one large 4 6 6 bar one small 5 8 7 bar two small 6 9 8 bar two large 7 9 This first example aggregates values by taking the sum. >>> table = pd.pivot_table( ... df, values="D", index=["A", "B"], columns=["C"], aggfunc="sum" ... ) >>> table C large small A B bar one 4.0 5.0 two 7.0 6.0 foo one 4.0 1.0 two NaN 6.0 We can also fill missing values using the `fill_value` parameter. >>> table = pd.pivot_table( ... df, values="D", index=["A", "B"], columns=["C"], aggfunc="sum", fill_value=0 ... ) >>> table C large small A B bar one 4 5 two 7 6 foo one 4 1 two 0 6 The next example aggregates by taking the mean across multiple columns. >>> table = pd.pivot_table( ... df, values=["D", "E"], index=["A", "C"], aggfunc={"D": "mean", "E": "mean"} ... ) >>> table D E A C bar large 5.500000 7.500000 small 5.500000 8.500000 foo large 2.000000 4.500000 small 2.333333 4.333333 We can also calculate multiple types of aggregations for any given value column. >>> table = pd.pivot_table( ... df, ... values=["D", "E"], ... index=["A", "C"], ... aggfunc={"D": "mean", "E": ["min", "max", "mean"]}, ... ) >>> table D E mean max mean min A C bar large 5.500000 9 7.500000 6 small 5.500000 9 8.500000 8 foo large 2.000000 5 4.500000 4 small 2.333333 6 4.333333 2 ) valuesindexcolumns fill_valuer#r$r&r'r(r)kwargs__name__)keysaxis pivot_table)method) _convert_by isinstancelist__internal_pivot_tableappendgetattrr __finalize__)r"r,r-r.r#r/r$r&r'r(r)r0piecesr3func_tabletables m/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/pandas/core/reshape/pivot.pyr5r56s2t   E'""G'4  >"$ 9 9D+%)!   F MM& ! ! ! KKj$77 8 8 8 8vDq111!!$}!=== "     E   d=  9 99!AggFuncTypeBase | AggFuncTypeDictc ||z} |du} | rt|rd}t|}nd}|g}|D]}||vrt|g}| |zD]H}t|tr|j} ||vr||9#t$rYEwxYwt|t|j kr||}nN|j }| D]5} | |}#tttf$rY2wxYwt|}| | | | |}| r||}|j |fi| }|r?t|tr*t|j r|d}|}|jjdkr|r|jjdt|}g}t't|t| D]E}|jj|}|||vr||0||F|||}|st|jt*rBt+j|jj|jj }||d | }t|j t*rBt+j|j j|j j }||d| }| dur+t|tr|d }|S||}|tur5| s3t7j|r|t<j}|rJ|r.|| !d }tE||||||| |||| }| r1|s/|j jdkr|j #d |_ t|d krt|d kr|j$}t|tr|r|dd}|S)zL Helper of :func:`pandas.pivot_table` for any non-list ``aggfunc``. NTF)r(r)r&all)howr2r/namesr)r4r/r4)rowscolsr#r0r(r'r/r&)rGr4)%r r9KeyErrorr8rkeyr; TypeErrorlenr.drop ValueErrorgroupbyaggrr&r-nlevelsrJrangeunstackr from_productlevelsreindex sort_indexfillnar is_integerastypenpint64notnarF _add_margins droplevelT)r"r,r-r.r#r/r$r&r'r(r)r0r3 values_passed values_multii to_filterxrOgroupedaggedrA index_names to_unstacknamems rBr:r:s" 7?D$&M     L&\\FF LXF " "A}}qkk!   A!W%% E 99$$Q'''     y>>C -- - - ?D  C S))z84    fll4(flMMG"&/ GK * *6 * *E (*UL11(c%-6H6H(  '' E {Q5k' #e** 5  s5zz3t99-- ( (A;$Q'D|t{22!!!$$$$!!$'''' jZ @@ D ek: . . D' (:%+BSTTTAMM!! MCCE emZ 0 0 D' (>(>s~j/I/I>LL**E  2 ((a(001D   %!    3\3em.Ca.G.G //22  5zzQ3w<> > >S// ! ?)vw UUL zQ](, & &Eu}==eDDDD oo%E 4yy1}}oTQ 77 >j 22>%%   \,%?@ A A    >8             -u55 '& &*=' ZZ%.....G 4tWfh f  -u55 '& &*=' Z##FNz#JJJ // a   /(OJqMM(1.JqMM      9Zu>>>@L "IV]##   e^ , ,  ##UG,,4)$/55 #5(6  TV\* + +F"FL MrCc|ri}||D]\}} t|trt||di|||<not|trNt||tr t|||di|||<n|||fi|||<n ||fi|||<#t $rYwxYw|S|||jfi|iS)N)itemsr8rwr<dictrPr-)r"r,r#r0r'rrvs rBryrysD= L&&((  DAq gs++;&9ga&9&9&C&CF&C&CLOO..;!'!*c22B*@'!WQZ*@*@*J*J6*J*J Q*4'!*Q*A*A&*A*A Q&-ga&:&:6&:&:LO    ggdj;;F;;<._all_key*s"&#d))a-)@@ @rCr(r&r2)rr(rIrorKc4g|]}jj|Sr)r-rJ).0rhrs rB z._generate_marginal_results..ps$PPP:+1!4PPPrCr-)rQrTrUrer;to_framer8r-r from_tuplesrJrrorr.stack itertoolschainrWreorder_levels_constructor_slicedr`nan)rAr"r,rLrMr#r0r(r'r& table_piecesrrmargincat_axisrOpieceall_keytransformed_piecernew_order_indicesnew_order_namesrs ` ` @rBr}r}s 4yy1}}   A A A A A A t99q==TF]#@@W(( &((  H#gooAoII , , U"(3--!'g##E***""7++++ ,T"1"X&'bqbHVDDW(( &(( H#mm!hmGG , , Ut99q==&hsmmGG*G##E***$*3K$8$8$:$:$<!ek:66V.8.D 8 1848///%++ /4WIEKDT.U.U.U%+##$5666""7++++ 9LLx888F t99>>M m  4yy1}} D  WTHVW < <  $ $" $ $   %%'' &OSYYKs4yy9I9IJJPPPP>OPPP%+::?KK --bfFN-KK ; **rCc ltdkrg} fd} t|dkrQ|||||j|fi|} | } | || <|} | | nU|d||j|fi|} | } | || <|} | | | S|} |j} tr+|||j|fi|}n t t j| j}| | |fS)Nrc`tdkrSfdtdz zzS)Nr2rtr)rMr'srBrz;_generate_marginal_results_without_values.._all_keys44yyA~~## ?Uc$ii!m%<< ` for more on reshaping. Parameters ---------- data : DataFrame Input pandas DataFrame object. columns : Hashable or a sequence of the previous Column to use to make new frame's columns. index : Hashable or a sequence of the previous, optional Column to use to make new frame's index. If not given, uses existing index. values : Hashable or a sequence of the previous, optional Column(s) to use for populating new frame's values. If not specified, all remaining columns will be used and the result will have hierarchically indexed columns. Returns ------- DataFrame Returns reshaped DataFrame. Raises ------ ValueError: When there are any `index`, `columns` combinations with multiple values. `DataFrame.pivot_table` when you need to aggregate. See Also -------- DataFrame.pivot_table : Generalization of pivot that can handle duplicate values for one index/column pair. DataFrame.unstack : Pivot based on the index values instead of a column. wide_to_long : Wide panel to long format. Less flexible but more user-friendly than melt. Notes ----- For finer-tuned control, see hierarchical indexing documentation along with the related stack/unstack methods. Reference :ref:`the user guide ` for more examples. Examples -------- >>> df = pd.DataFrame( ... { ... "foo": ["one", "one", "one", "two", "two", "two"], ... "bar": ["A", "B", "C", "A", "B", "C"], ... "baz": [1, 2, 3, 4, 5, 6], ... "zoo": ["x", "y", "z", "q", "w", "t"], ... } ... ) >>> df foo bar baz zoo 0 one A 1 x 1 one B 2 y 2 one C 3 z 3 two A 4 q 4 two B 5 w 5 two C 6 t >>> df.pivot(index="foo", columns="bar", values="baz") bar A B C foo one 1 2 3 two 4 5 6 >>> df.pivot(index="foo", columns="bar")["baz"] bar A B C foo one 1 2 3 two 4 5 6 >>> df.pivot(index="foo", columns="bar", values=["baz", "zoo"]) baz zoo bar A B C A B C foo one 1 2 3 x y z two 4 5 6 q w t You could also assign a list of column names or a list of index names. >>> df = pd.DataFrame( ... { ... "lev1": [1, 1, 1, 2, 2, 2], ... "lev2": [1, 1, 2, 1, 1, 2], ... "lev3": [1, 2, 1, 2, 1, 2], ... "lev4": [1, 2, 3, 4, 5, 6], ... "values": [0, 1, 2, 3, 4, 5], ... } ... ) >>> df lev1 lev2 lev3 lev4 values 0 1 1 1 1 0 1 1 1 2 2 1 2 1 2 1 3 2 3 2 1 2 4 3 4 2 1 1 5 4 5 2 2 2 6 5 >>> df.pivot(index="lev1", columns=["lev2", "lev3"], values="values") lev2 1 2 lev3 1 2 1 2 lev1 1 0.0 1.0 2.0 NaN 2 4.0 3.0 NaN 5.0 >>> df.pivot(index=["lev1", "lev2"], columns=["lev3"], values="values") lev3 1 2 lev1 lev2 1 1 0.0 1.0 2 2.0 NaN 2 1 4.0 3.0 2 NaN 5.0 A ValueError is raised if there are any duplicates. >>> df = pd.DataFrame( ... { ... "foo": ["one", "one", "two", "two"], ... "bar": ["A", "A", "B", "C"], ... "baz": [1, 2, 3, 4], ... } ... ) >>> df foo bar baz 0 one A 1 1 one A 2 2 two B 3 3 two C 4 Notice that the first two rows are the same for our `index` and `columns` arguments. >>> df.pivot(index="foo", columns="bar", values="baz") Traceback (most recent call last): ... ValueError: Index contains duplicate entries, cannot reshape c3K|]}|duV dSrrrros rB zpivot..Zs& 5 5D44< 5 5 5 5 5 5rCF)deepc.g|]}||n tjSrr no_defaultrs rBrzpivot..\s0   =AD$DD#.   rC)r;cDg|]}j|Sr)r-rx)rrhr"s rBrzpivot..ss678DJ//22rCrc g|] }| Srr)ridxr"s rBrzpivot..{sOOO$s)OOOrCc g|] }| Srr)rcolr"s rBrzpivot..}s>>>cS >>>rCr)r-r.rrc2g|]}|tjur|ndSrrrs rBrzpivot..s59=CN**rC)comconvert_to_list_likeanyr-rJcopyrr set_indexr8rrWrVrroextend from_arraysr r~r|_valuesrrX) r"r.r-r,columns_listlikerMr;indexed index_list data_columns multiindexrs ` rBpivotrst/88  5 5DJ$4 5 5 555 yyey$$  EIZEU       & &+E22DDD#.(.. # #!   CN " "$*j11 >>>-=>>> ,'''+J77    W 65(A(A W''V $ -v66(GG ..tF|/C:.VVG +w/?@@ A AFAGASFL MrC normalize/bool | Literal[0, 1, 'all', 'index', 'columns']c ||td||tdt|s|g}t|s|g}d} d||zD} | rt| dd} t||d }t||d }t ||\} } }}d d lm}itt| |d tt||d }||| }|d |d<td d}n ||d<d|i}|j d| |||||d|}| durt|| ||}| | d }| |d}|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.cJg|] }t|ttf|!Sr)r8rr)rrjs rBrzcrosstab..6s,XXXqz!i=V/W/WXXXXrCTF) intersectr)row)prefixrrr)strictr __dummy__)r#r/r#)r-r.r$r'r&r()rr$r')r-r4r2)r.r4)r) rSr r _get_names_build_names_mapperrrrziprQr5 _normalize rename_axis)r-r.r,rownamescolnamesr#r$r'r&r common_idx pass_objsrownames_mapperunique_rownamescolnames_mapperunique_colnamesrr"dfr0rAs rBcrosstabrs$h~'-ABBB goDEEE u % % w ' ')JXXEGOXXXIS+IERRR %%888H'8E:::H Hh// !       s?E$777 8 8  s?GD999 : : D 4z * * *B ~; 22 ;W% BN !     E Yl      O!  < >E LrCct|ttfs1ddd} ||}n"#t$r}t d|d}~wwxYw|durbdddd }|d |d < ||}n"#t$r}t d|d}~wwxYw||}|d }n|d ur|j}|j} |jd ddfj } || v|| kzrt |d|jdd d f} |jd dd f} |jdd dd f}t||d}|dkrG| | z } t|| gd}|d }| |_n|dkrK| | z } | | d }|d }||_n|d ks|d ur| | z } | | z } d| j|<t|| gd}| | d }|d }||_| |_nt dt d|S)Nr-r.)rr2zNot a valid normalize argumentFc\||ddz SNr2rKrsumrjs rBz_normalize..zs(QA!2!2!2!:!::rCc0||z Srrrs rBrz_normalize..{sQUUWWrCcX||ddSr)divrrs rBrz_normalize..|s"quuQUUU]]u;;rC)rFr.r-rFTrz not in pivoted DataFrame)rr$r2rK) ignore_indexzNot a valid margins argument)r8r%rwrNrSr]r-r.ilocrorrrr{loc) rArr$r' axis_subserr normalizersf table_index table_columnslast_ind_or_col column_margin index_margins rBrrms/ i$ - -HI..  H!),II H H H=>>C G H%;:,,;;3 3 (. D HI&AA H H H=>>C G H% Q Dk  *RU+0  /LO4S T I GGGHH H 3B37+ z"crc'*  3B38$5IuEEE  ! !)M,=,=,?,??ME=1:::ELLOOE)EMM ' ! !',*:*:*<*<> >7888 Ls,, A AA 'A00 B:B  Brrrwr9c|ig}t|D]V\}}t|tr"|j||j<||d|WnSt |t |krt dt|tst|}|S)N_z*arrays and names must have the same length) enumerater8rror;rQAssertionErrorr9)arrsrJrrharrs rBrrs }oo . .FAs#y)) .ch.B SX&&&& ____----  . u::T " " !MNN N%&& KKE LrCr list[str]r;tuple[dict[str, str], list[str], dict[str, str], list[str]]c&t|t|zfdt|D}fdt|D}fdt|D}fdt|D}||||fS)a Given the names of a DataFrame's rows and columns, returns a set of unique row and column names and mappers that convert to original names. A row or column name is replaced if it is duplicate among the rows of the inputs, among the columns of the inputs or between the rows and the columns. Parameters ---------- rownames: list[str] colnames: list[str] Returns ------- Tuple(Dict[str, str], List[str], Dict[str, str], List[str]) rownames_mapper: dict[str, str] a dictionary with new row names as keys and original rownames as values unique_rownames: list[str] a list of rownames with duplicate names replaced by dummy names colnames_mapper: dict[str, str] a dictionary with new column names as keys and original column names as values unique_colnames: list[str] a list of column names with duplicate names replaced by dummy names c*i|]\}}|v d||Srow_rrrhro dup_namess rB z'_build_names_mapper..6$Qty?P?P q D?P?P?PrCc,g|]\}}|vrd|n|Sr rr s rBrz'_build_names_mapper..>6=adi'' q TrCc*i|]\}}|v d||Scol_rr s rBrz'_build_names_mapper..rrCc,g|]\}}|vrd|n|Srrr s rBrz'_build_names_mapper..rrC)rr)rrrrrrrs @rBrrs:H H -I(1((;(;OAJ8ATATO(1((;(;OAJ8ATATO O_o MMrC) NNNr NFTr!TT)r"rr#rr$r%r&r%r'rr(r%r)r%r*r)r"rr#rDr$r%r&r%r'rr(r%r)r%r*r)r!NT) rArqr"rr(r%r'rr&r%)r!)r"rr'r)r!T)r"rr(r%r'rr&r%) rArr"rr(r%r'rr&r%) r"rr.rr-rr,rr*r)NNNNFr!TF) r$r%r'rr&r%rrr*r)rArr$r%r'rr*r)r)rrwr*r9)rrrrr*r)> __future__rrtypingrrrnumpyr` pandas._libsrpandas.util._decoratorsrpandas.core.dtypes.castr pandas.core.dtypes.commonr r r pandas.core.dtypes.dtypesr pandas.core.dtypes.genericrrpandas.core.commoncorecommonrpandas.core.groupbyrpandas.core.indexes.apirrrpandas.core.reshape.concatrpandas.core.seriesrcollections.abcrrpandas._typingrrrrrrrr5r:rcryr}rr7rrrrrrrrCrBr)s%"""""" ......;;;;;; 544444 ! '''''' .-----%%%%%%! !      H   !"b:b:b:b:b:J@@@@X#_____FHM=====@#]+]+]+]+]+P#2+2+2+2+2+j    H ),), WWWWWWt H    "AFSSSSSnJOMMMMM`"-N-N-N-N-N-NrC