tf\.ddlmZddlZddlZddlmZmZddl Z ddl m Z ddl m Z ddlmZmZmZmZddlmZddlmZdd lmZmZe ren ej6Zdd d dd d efd Zdd Z ddZy)) annotationsN) is_list_like is_scalar)methods) PANDAS_GE_200) DataFrameSeriesapply_concat_applymap_partitionshas_known_categories) no_default)Mget_meta_library_Fc ttjtjfrtjf|||||||d|Sd} d} ttr6t j s t| tst| ttr|xjdk(jr t| jdk(jr t| jjdgj}ntfd|Ds t| tfd |Ds t| tt!jf|||||||d|S) a Convert categorical variable into dummy/indicator variables. Data must have category dtype to infer result's ``columns``. Parameters ---------- data : Series, or DataFrame For Series, the dtype must be categorical. For DataFrame, at least one column must be categorical. prefix : string, list of strings, or dict of strings, default None String to append DataFrame column names. Pass a list with length equal to the number of columns when calling get_dummies on a DataFrame. Alternatively, `prefix` can be a dictionary mapping column names to prefixes. prefix_sep : string, default '_' If appending prefix, separator/delimiter to use. Or pass a list or dictionary as with `prefix.` dummy_na : bool, default False Add a column to indicate NaNs, if False NaNs are ignored. columns : list-like, default None Column names in the DataFrame to be encoded. If `columns` is None then all the columns with `category` dtype will be converted. sparse : bool, default False Whether the dummy columns should be sparse or not. Returns SparseDataFrame if `data` is a Series or if all columns are included. Otherwise returns a DataFrame with some SparseBlocks. .. versionadded:: 0.18.2 drop_first : bool, default False Whether to get k-1 dummies out of k categorical levels by removing the first level. dtype : dtype, default bool Data type for new columns. Only a single dtype is allowed. .. versionadded:: 0.18.2 Returns ------- dummies : DataFrame Examples -------- Dask's version only works with Categorical data, as this is the only way to know the output shape without computing all the data. >>> import pandas as pd >>> import dask.dataframe as dd >>> s = dd.from_pandas(pd.Series(list('abca')), npartitions=2) >>> dd.get_dummies(s) Traceback (most recent call last): ... NotImplementedError: `get_dummies` with non-categorical dtypes is not supported... With categorical data: >>> s = dd.from_pandas(pd.Series(list('abca'), dtype='category'), npartitions=2) >>> dd.get_dummies(s) # doctest: +NORMALIZE_WHITESPACE Dask DataFrame Structure: a b c npartitions=2 0 bool bool bool 2 ... ... ... 3 ... ... ... Dask Name: get_dummies, 2 graph layers >>> dd.get_dummies(s).compute() # doctest: +ELLIPSIS a b c 0 True False False 1 False True False 2 False False True 3 True False False See Also -------- pandas.get_dummies )prefix prefix_sepdummy_nacolumnssparse drop_firstdtypez`get_dummies` with non-categorical dtypes is not supported. Please use `df.categorize()` beforehand to convert to categorical dtype.z`get_dummies` with unknown categories is not supported. Please use `column.cat.as_known()` or `df.categorize()` beforehand to ensure known categoriesobjectstringcategory)includec3NK|]}tj|ywN)ris_categorical_dtype.0cdatas `/var/www/html/software/conda/envs/higlass/lib/python3.12/site-packages/dask/dataframe/reshape.py zget_dummies..s Nw33DG<Ns"%c3:K|]}t|ywrr r!s r%r&zget_dummies..sBQ'Q0Bs) isinstancepdr r get_dummiesrr NotImplementedErrorr dtypesany_meta select_dtypesrallr r) r$rrrrrrrkwargs not_cat_msgunknown_cat_msgs ` r%r*r*st$BLL12~~   !!     ( $++D1%k2 2#D)%o6 6 D) $ ? x',,.)+66 x',,.)+66jj.. |.DLLGNgNN)+66B'BB%o6 6 **      ct|r| tdt|r| tdtj||s tdt ||s tdt |r"t |Dcgc] }t|c}st|s tdgd}t|r||vr$tdd jd |Dztj||jj| }t|r|}n.tjjt||fd|g }|d vrt|rFtj|||j tj"|j$|} ntj|tj"|j$|} |D])} | | j'||j(| | | <+nFtj|t*j,tj"|j$|} |||d} |dvr.t/|gtj0tj2| d| } |dvr.t/|gtj4tj2| d| } |dk(r S|dk(r S|dk(r  z S|dk(r.t/|gtj6tj8| d| S|dk(r.t/|gtj:tj<| d| Stcc}w)a Create a spreadsheet-style pivot table as a DataFrame. Target ``columns`` must have category dtype to infer result's ``columns``. ``index``, ``columns``, and ``aggfunc`` must be all scalar. ``values`` can be scalar or list-like. Parameters ---------- df : DataFrame index : scalar column to be index columns : scalar column to be columns values : scalar or list(scalar) column(s) to aggregate aggfunc : {'mean', 'sum', 'count', 'first', 'last'}, default 'mean' Returns ------- table : DataFrame See Also -------- pandas.DataFrame.pivot_table Nz.'index' must be the name of an existing columnz0'columns' must be the name of an existing columnz 'columns' must be category dtypezs'columns' must have known categories. Please use `df[columns].cat.as_known()` beforehand to ensure known categoriesz4'values' must refer to an existing column or columns)meansumcountfirstlastzaggfunc must be either z, c3(K|] }d|d yw)'N)r"xs r%r&zpivot_table..s1WqAaS(1Ws)name)names)r9r:)rrindex)rrA)rArvalues)r7r6pivot_table_sum)chunk aggregatemetatoken chunk_kwargs)r8r6pivot_table_countr7r8r6r9pivot_table_firstr:pivot_table_last)r ValueErrorrr r rr0joinr)CategoricalIndexcat categories MultiIndex from_productsortedrrIndexr.astyper,npfloat64r pivot_sum pivot_agg pivot_count pivot_firstpivot_agg_first pivot_lastpivot_agg_last)dfrArrBaggfuncvavailable_aggfuncscolumns_contents new_columnsrF value_colr1pv_sumpv_counts r% pivot_tablerhs,6 U u}IJJ W KLL  ' '7 4;<< 7 ,   V v.!1. / V OPPB W 0B!B % 1WDV1W(W W  **2g;??+E+EGT& mm00 F^- .tWo1 ## V <<#j&&hhrxx/D <<#hhrxx/D$ W "&y/"8"8F9J9J99U"VY W||rzz"((5/9R F CF/!# D##''#  ##% D%%''%  % G  F   G ! D%%--%    F ! D$$,,$   w/sMc tjjddi5|jtj t |||||dcdddS#1swYyxYw)a Unpivots a DataFrame from wide format to long format, optionally leaving identifier variables set. This function is useful to massage a DataFrame into a format where one or more columns are identifier variables (``id_vars``), while all other columns, considered measured variables (``value_vars``), are "unpivoted" to the row axis, leaving just two non-identifier columns, 'variable' and 'value'. Parameters ---------- frame : DataFrame id_vars : tuple, list, or ndarray, optional Column(s) to use as identifier variables. value_vars : 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 Name to use for the 'variable' column. If None it uses ``frame.columns.name`` or 'variable'. value_name : scalar, default 'value' Name to use for the 'value' column. col_level : int or string, optional If columns are a MultiIndex then use this level to melt. Returns ------- DataFrame Unpivoted DataFrame. See Also -------- pandas.DataFrame.melt zdataframe.convert-stringFmelt)rFid_vars value_varsvar_name value_name col_levelrGN)daskconfigsetr rrjr)framerkrlrmrnros r%rjrj=s_R 4e< =  ## FF!!$      s +AA )NNNr6)NNNvalueN) __future__rnumpyrVpandasr)pandas.api.typesrrrpdask.dataframerdask.dataframe._compatrdask.dataframe.corerr r r dask.dataframe.utilsr dask.typingr dask.utilsrrbooluint8_get_dummies_dtype_defaultr*rhrjr=r4r%rst"4 "0UU5"*&3T     $RtD\   3 r4