jXZddlmZddlZddlmZddlZddlmZddl m Z m Z ddl m Z ddlmZddlmcmZddlmZdd lmZdd lmZerdd lmZdd lmZdd lmZd(dZ ed d)d*dZ!edd+d,d!Z"ed d-d.d'Z#dS)/) annotationsN) TYPE_CHECKING) set_module) is_iterator is_list_like) concat_compat)notna) MultiIndex)concat) to_numeric)Hashable) AnyArrayLike) DataFramevariablestrreturnlistc|]t|s|gSt|tr't|tst |dt|SgS)Nz7 must be a list of tuples when columns are a MultiIndex)r isinstancer r ValueError)arg_varsrcolumnss FC:\Projects\DSCons\.venv\Lib\site-packages\pandas\core\reshape\melt.pyensure_list_varsrstH%% ":   , , "Z$5O5O "TTT >> ! pandasvalueTframer value_namer ignore_indexboolc  |jvrtd|dt|dj}|du}t|dj}tj|t|krtd|s|r|j|}nj}||z} || } | dk} | r.dt| | d D} td | |r$j ddtj | fn- d n d |j|_|tjtrtjjtt!jjkrjj}ndt#tjjD}n׉jj jjndg}nt'|rtjtr|t)|rt+|}t|tjkr8td|dt|dtjdntd|d|g}j\} }|t|z }i}|D]}|}t|jt2jsH|dkrt5|g|zd ||<Ut7|g|j|j||<~t3j|j|||<||z|gz}jddkr\t djDs>t5fdt#jdDd j||<nj d||<tC|D]5\}}j"|#| ||<6$||}|sSt3jt3j%t|}j&'||_&|S)a Unpivot a DataFrame from wide to long format, optionally leaving identifiers set. This function is useful to reshape a DataFrame into a format where one or more columns are identifier variables (`id_vars`), while all other columns are considered measured variables (`value_vars`), and are "unpivoted" to the row axis, leaving just two non-identifier columns, 'variable' and 'value'. Parameters ---------- frame : DataFrame The DataFrame to unpivot. id_vars : scalar, tuple, list, or ndarray, optional Column(s) to use as identifier variables. value_vars : scalar, tuple, list, or ndarray, optional Column(s) to unpivot. If not specified, uses all columns that are not set as `id_vars`. var_name : scalar, tuple, list, or ndarray, optional Name to use for the 'variable' column. If None it uses ``frame.columns.name`` or 'variable'. Must be a scalar if columns are a MultiIndex. value_name : scalar, default 'value' Name to use for the 'value' column, can't be an existing column label. col_level : scalar, optional If columns are a MultiIndex then use this level to melt. ignore_index : bool, default True If True, original index is ignored. If False, the original index is retained. Index labels will be repeated as necessary. Returns ------- DataFrame Unpivoted DataFrame. See Also -------- DataFrame.melt : Identical method. pivot_table : Create a spreadsheet-style pivot table as a DataFrame. DataFrame.pivot : Return reshaped DataFrame organized by given index / column values. DataFrame.explode : Explode a DataFrame from list-like columns to long format. Notes ----- Reference :ref:`the user guide ` for more examples. Examples -------- >>> df = pd.DataFrame( ... { ... "A": {0: "a", 1: "b", 2: "c"}, ... "B": {0: 1, 1: 3, 2: 5}, ... "C": {0: 2, 1: 4, 2: 6}, ... } ... ) >>> df A B C 0 a 1 2 1 b 3 4 2 c 5 6 >>> pd.melt(df, id_vars=["A"], value_vars=["B"]) A variable value 0 a B 1 1 b B 3 2 c B 5 >>> pd.melt(df, id_vars=["A"], value_vars=["B", "C"]) A variable value 0 a B 1 1 b B 3 2 c B 5 3 a C 2 4 b C 4 5 c C 6 The names of 'variable' and 'value' columns can be customized: >>> pd.melt( ... df, ... id_vars=["A"], ... value_vars=["B"], ... var_name="myVarname", ... value_name="myValname", ... ) A myVarname myValname 0 a B 1 1 b B 3 2 c B 5 Original index values can be kept around: >>> pd.melt(df, id_vars=["A"], value_vars=["B", "C"], ignore_index=False) A variable value 0 a B 1 1 b B 3 2 c B 5 0 a C 2 1 b C 4 2 c C 6 If you have multi-index columns: >>> df.columns = [list("ABC"), list("DEF")] >>> df A B C D E F 0 a 1 2 1 b 3 4 2 c 5 6 >>> pd.melt(df, col_level=0, id_vars=["A"], value_vars=["B"]) A variable value 0 a B 1 1 b B 3 2 c B 5 >>> pd.melt(df, id_vars=[("A", "D")], value_vars=[("B", "E")]) (A, D) variable_0 variable_1 value 0 a B E 1 1 b B E 3 2 c B E 5 z value_name (z3) cannot match an element in the DataFrame columns.id_varsN value_varsz)id_vars cannot contain duplicate columns.cg|] \}}|| Sr').0lab not_founds r zmelt..s1&YyrT)strictzFThe following id_vars or value_vars are not present in the DataFrame: F)deepcg|]}d|S) variable_r')r(is rr+zmelt..sUUUOOOUUUrrz var_name=z has z, items, but the dataframe columns only have z levels.z must be a scalar.r)r )namedtypec3ZK|]&}t|tj o|jV'dSN)rnpr2 _supports_2d)r(dts r zmelt..sI&&=?Jr28 $ $$8&&&&&&rc2g|]}jdd|fSr5)iloc)r(r0rs rr+zmelt.. s( = = =!UZ1  = = =rFr)(rrrlenget_indexer_forget_level_valuesanyzipKeyErrorr;algosuniquecopyrr namessetranger1rrrshapepopr2r6r typetile_valuesdtypesvaluesravel enumerate_get_level_valuesrepeat _constructorarangeindextake)rr#r$var_namer col_levelr value_vars_was_not_nonelevellabelsidxmissingmissing_labelsnum_rowsKnum_cols_adjustedmdatacolid_datamcolumnsr0resulttakers` rmeltrj,spNU]"" %: % % %   w 5=AAG(4!*lEMJJJ 5= ( ( 1 122S\\AADEEE'*'  M229==EEME:%##F++) ;;== *-fgd*K*K*KN3"033  # +Jqqq%,s"3"334EEJJEJ**EE  && 66yAA  emZ 0 0 5=&''3s5=3F/G/G+H+HHH =.UUU3u}?R;S;S5T5TUUU',m&8&D ""*HH h    emZ 0 0 ?8$$ *>>8}}s5=1111 XxXXs8}}XX;>u};M;MXXX2 ====>> >:+KHaCLL(*,E E E))C..'-22 E 1$$#WI0A$APTUUUc +T']]2GL VVVc 2CDDE#JJ!ZL0H {1~#&&CH<&&&### = = = =uU[^'<'< = = =D    j"M//44jH%%II3]44Q77>>xHHc   x  8 8F / #e**--/@AA{''.. Mrdatagroupsdictdropnac i}g}t}ttt|}|D]q\}}t||krt dfd|D} t| ||<||| |}rtj |} | D]%} tj| j||| <&|rtjt||dt" |D]} t%|| z  s fd|D}|| |zS)a Reshape wide-format data to long. Generalized inverse of DataFrame.pivot. Accepts a dictionary, ``groups``, in which each key is a new column name and each value is a list of old column names that will be "melted" under the new column name as part of the reshape. Parameters ---------- data : DataFrame The wide-format DataFrame. groups : dict {new_name : list_of_columns}. dropna : bool, default True Do not include columns whose entries are all NaN. Returns ------- DataFrame Reshaped DataFrame. See Also -------- melt : Unpivot a DataFrame from wide to long format, optionally leaving identifiers set. pivot : Create a spreadsheet-style pivot table as a DataFrame. DataFrame.pivot : Pivot without aggregation that can handle non-numeric data. DataFrame.pivot_table : Generalization of pivot that can handle duplicate values for one index/column pair. DataFrame.unstack : Pivot based on the index values instead of a column. wide_to_long : Wide panel to long format. Less flexible but more user-friendly than melt. Examples -------- >>> data = pd.DataFrame( ... { ... "hr1": [514, 573], ... "hr2": [545, 526], ... "team": ["Red Sox", "Yankees"], ... "year1": [2007, 2007], ... "year2": [2008, 2008], ... } ... ) >>> data hr1 hr2 team year1 year2 0 514 545 Red Sox 2007 2008 1 573 526 Yankees 2007 2008 >>> pd.lreshape(data, {"year": ["year1", "year2"], "hr": ["hr1", "hr2"]}) team year hr 0 Red Sox 2007 514 1 Yankees 2007 573 2 Red Sox 2008 545 3 Yankees 2008 526 z$All column lists must be same lengthc*g|]}|jSr')rN)r(rerks rr+zlreshape..\s 8883T#Y&888rr)r2c(i|]\}}||Sr'r')r(kvmasks r zlreshape..ks#:::DAqQ$:::rr=)rHr>nextiterrPitemsrrappendunionrr differencer6rMrNonesr!r allrU)rkrlrnrd pivot_colsall_colsrbtargetrG to_concatid_colsrecrts` @rlreshapersx EJ!eeH Dfmmoo&& ' '((A))  u::??CDD D8888%888 %i00f &!!!>>%((4<**84455G33WT#Y.22c  ;ws5A/00=== $ $A E%(OO #DDxxzz ;::::EKKMM:::E   UGj,@  A AAr\d+dfsepsuffixc d d}dd}t|s|g}nt|}|j|rt dt|s|g}nt|}||rt dg}g} |D]H} ||| ||} | | |||| ||| |It|d } |j | } || }t|d kr(| | | S|| |  g||S)aV! Unpivot a DataFrame from wide to long format. Less flexible but more user-friendly than melt. With stubnames ['A', 'B'], this function expects to find one or more group of columns with format A-suffix1, A-suffix2,..., B-suffix1, B-suffix2,... You specify what you want to call this suffix in the resulting long format with `j` (for example `j='year'`) Each row of these wide variables are assumed to be uniquely identified by `i` (can be a single column name or a list of column names) All remaining variables in the data frame are left intact. Parameters ---------- df : DataFrame The wide-format DataFrame. stubnames : str or list-like The stub name(s). The wide format variables are assumed to start with the stub names. i : str or list-like Column(s) to use as id variable(s). j : str The name of the sub-observation variable. What you wish to name your suffix in the long format. sep : str, default "" A character indicating the separation of the variable names in the wide format, to be stripped from the names in the long format. For example, if your column names are A-suffix1, A-suffix2, you can strip the hyphen by specifying `sep='-'`. suffix : str, default '\\d+' A regular expression capturing the wanted suffixes. '\\d+' captures numeric suffixes. Suffixes with no numbers could be specified with the negated character class '\\D+'. You can also further disambiguate suffixes, for example, if your wide variables are of the form A-one, B-two,.., and you have an unrelated column A-rating, you can ignore the last one by specifying `suffix='(!?one|two)'`. When all suffixes are numeric, they are cast to int64/float64. Returns ------- DataFrame A DataFrame that contains each stub name as a variable, with new index (i, j). See Also -------- melt : Unpivot a DataFrame from wide to long format, optionally leaving identifiers set. pivot : Create a spreadsheet-style pivot table as a DataFrame. DataFrame.pivot : Pivot without aggregation that can handle non-numeric data. 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. Notes ----- All extra variables are left untouched. This simply uses `pandas.melt` under the hood, but is hard-coded to "do the right thing" in a typical case. Examples -------- >>> np.random.seed(123) >>> df = pd.DataFrame( ... { ... "A1970": {0: "a", 1: "b", 2: "c"}, ... "A1980": {0: "d", 1: "e", 2: "f"}, ... "B1970": {0: 2.5, 1: 1.2, 2: 0.7}, ... "B1980": {0: 3.2, 1: 1.3, 2: 0.1}, ... "X": dict(zip(range(3), np.random.randn(3), strict=True)), ... } ... ) >>> df["id"] = df.index >>> df A1970 A1980 B1970 B1980 X id 0 a d 2.5 3.2 -1.085631 0 1 b e 1.2 1.3 0.997345 1 2 c f 0.7 0.1 0.282978 2 >>> pd.wide_to_long(df, ["A", "B"], i="id", j="year") ... # doctest: +NORMALIZE_WHITESPACE X A B id year 0 1970 -1.085631 a 2.5 1 1970 0.997345 b 1.2 2 1970 0.282978 c 0.7 0 1980 -1.085631 d 3.2 1 1980 0.997345 e 1.3 2 1980 0.282978 f 0.1 With multiple id columns >>> df = pd.DataFrame( ... { ... "famid": [1, 1, 1, 2, 2, 2, 3, 3, 3], ... "birth": [1, 2, 3, 1, 2, 3, 1, 2, 3], ... "ht1": [2.8, 2.9, 2.2, 2, 1.8, 1.9, 2.2, 2.3, 2.1], ... "ht2": [3.4, 3.8, 2.9, 3.2, 2.8, 2.4, 3.3, 3.4, 2.9], ... } ... ) >>> df famid birth ht1 ht2 0 1 1 2.8 3.4 1 1 2 2.9 3.8 2 1 3 2.2 2.9 3 2 1 2.0 3.2 4 2 2 1.8 2.8 5 2 3 1.9 2.4 6 3 1 2.2 3.3 7 3 2 2.3 3.4 8 3 3 2.1 2.9 >>> long_format = pd.wide_to_long(df, stubnames="ht", i=["famid", "birth"], j="age") >>> long_format ... # doctest: +NORMALIZE_WHITESPACE ht famid birth age 1 1 1 2.8 2 3.4 2 1 2.9 2 3.8 3 1 2.2 2 2.9 2 1 1 2.0 2 3.2 2 1 1.8 2 2.8 3 1 1.9 2 2.4 3 1 1 2.2 2 3.3 2 1 2.3 2 3.4 3 1 2.1 2 2.9 Going from long back to wide just takes some creative use of `unstack` >>> wide_format = long_format.unstack() >>> wide_format.columns = wide_format.columns.map("{0[0]}{0[1]}".format) >>> wide_format.reset_index() famid birth ht1 ht2 0 1 1 2.8 3.4 1 1 2 2.9 3.8 2 1 3 2.2 2.9 3 2 1 2.0 3.2 4 2 2 1.8 2.8 5 2 3 1.9 2.4 6 3 1 2.2 3.3 7 3 2 2.3 3.4 8 3 3 2.1 2.9 Less wieldy column names are also handled >>> np.random.seed(0) >>> df = pd.DataFrame( ... { ... "A(weekly)-2010": np.random.rand(3), ... "A(weekly)-2011": np.random.rand(3), ... "B(weekly)-2010": np.random.rand(3), ... "B(weekly)-2011": np.random.rand(3), ... "X": np.random.randint(3, size=3), ... } ... ) >>> df["id"] = df.index >>> df # doctest: +NORMALIZE_WHITESPACE, +ELLIPSIS A(weekly)-2010 A(weekly)-2011 B(weekly)-2010 B(weekly)-2011 X id 0 0.548814 0.544883 0.437587 0.383442 0 0 1 0.715189 0.423655 0.891773 0.791725 1 1 2 0.602763 0.645894 0.963663 0.528895 1 2 >>> pd.wide_to_long(df, ["A(weekly)", "B(weekly)"], i="id", j="year", sep="-") ... # doctest: +NORMALIZE_WHITESPACE X A(weekly) B(weekly) id year 0 2010 0 0.548814 0.437587 1 2010 1 0.715189 0.891773 2 2010 1 0.602763 0.963663 0 2011 0 0.544883 0.383442 1 2011 1 0.423655 0.791725 2 2011 1 0.645894 0.528895 If we have many columns, we could also use a regex to find our stubnames and pass that list on to wide_to_long >>> stubnames = sorted( ... set( ... [ ... match[0] ... for match in df.columns.str.findall(r"[A-B]\(.*\)").values ... if match != [] ... ] ... ) ... ) >>> list(stubnames) ['A(weekly)', 'B(weekly)'] All of the above examples have integers as suffixes. It is possible to have non-integers as suffixes. >>> df = pd.DataFrame( ... { ... "famid": [1, 1, 1, 2, 2, 2, 3, 3, 3], ... "birth": [1, 2, 3, 1, 2, 3, 1, 2, 3], ... "ht_one": [2.8, 2.9, 2.2, 2, 1.8, 1.9, 2.2, 2.3, 2.1], ... "ht_two": [3.4, 3.8, 2.9, 3.2, 2.8, 2.4, 3.3, 3.4, 2.9], ... } ... ) >>> df famid birth ht_one ht_two 0 1 1 2.8 3.4 1 1 2 2.9 3.8 2 1 3 2.2 2.9 3 2 1 2.0 3.2 4 2 2 1.8 2.8 5 2 3 1.9 2.4 6 3 1 2.2 3.3 7 3 2 2.3 3.4 8 3 3 2.1 2.9 >>> long_format = pd.wide_to_long( ... df, stubnames="ht", i=["famid", "birth"], j="age", sep="_", suffix=r"\w+" ... ) >>> long_format ... # doctest: +NORMALIZE_WHITESPACE ht famid birth age 1 1 one 2.8 two 3.4 2 one 2.9 two 3.8 3 one 2.2 two 2.9 2 1 one 2.0 two 3.2 2 one 1.8 two 2.8 3 one 1.9 two 2.4 3 1 one 2.2 two 3.3 2 one 2.3 two 3.4 3 one 2.1 two 2.9 stubrrrcdtj|tj||d}|j|jj|S)N^$)reescaperrmatch)rrrrregexs r get_var_namesz#wide_to_long..get_var_namesosK?RYt__?binn?f???z"*...u5566rcft||||||}||jt j||zdd||< t ||||<n#tttf$rYnwxYw| g||S)N)r#r$rrYrT)r) rjrstriprreplacerrr TypeErrorr OverflowError set_index)rrr0jr$rnewdfs r melt_stubzwide_to_long..melt_stubss !{{3''    8<'' $*(=(=r'NNa !%(++E!HH:}5    D wwAw'''s$A==BBz,stubname can't be identical to a column namez3the id variables need to uniquely identify each rowr3)axis)onN)rrrrrr)rrrr)rrrisinrAr duplicatedextendryr r{r>rjoinmerge reset_index)r stubnamesr0rrrrr_meltedvalue_vars_flattenedr value_varmeltedr#news r wide_to_longrps~7777((((&  " "$K OO  zy!!%%''IGHHH ?? C GG !uPNOOOGBB!M"dC88 ##I...yyT1aC@@AAAA G! $ $ $Fj##$899G W+C 1vv{{}}Q$$V,,,yy++--!y44>>wwAwGGGr)rrrr)NNNrNT)rrrr r r!rr)T)rkrrlrmrnr!rr)rr)rrrrrrrr)$ __future__rrtypingrnumpyr6pandas.util._decoratorsrpandas.core.dtypes.commonrrpandas.core.dtypes.concatrpandas.core.dtypes.missingr pandas.core.algorithmscore algorithmsrDpandas.core.indexes.apir pandas.core.reshape.concatr pandas.core.tools.numericr collections.abcr pandas._typingrrrrrjrrr'rrrs"""""" ......433333,,,,,,&&&&&&&&&......------000000!((((((++++++           H  "iiiiiX HSBSBSBSBSBl HAGsHsHsHsHsHsHsHr