Cd1.ddlmZddlZddlZddlmZmZddl Z ddl m Z ddl m Z ddlmZmZmZmZddlmZddlmZmZe renejZdd d dd d efd Zdd Z ddZdS)) annotationsN) is_list_like is_scalar)methods) PANDAS_GT_200) DataFrameSeriesapply_concat_applymap_partitionshas_known_categories)Mget_meta_library_Fc Tttjtjfrtjf|||||||d|Sd} d} ttrBt jst| tst| nttr|zj dk rt| j dk rt| j dgj }n*tfd |Dst| tfd |Dst| 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 uint8 uint8 uint8 2 ... ... ... 3 ... ... ... Dask Name: get_dummies, 2 graph layers >>> dd.get_dummies(s).compute() # doctest: +ELLIPSIS a b c 0 1 0 0 1 0 1 0 2 0 0 1 3 1 0 0 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 categoriesNobjectstringcategory)includec3LK|]}tj|VdSN)ris_categorical_dtype.0cdatas 6lib/python3.11/site-packages/dask/dataframe/reshape.py zget_dummies..s2NNw3DG<<NNNNNNc3BK|]}t|VdSrr r s r$r%zget_dummies..s0BBQ'Q00BBBBBBr&) isinstancepdr r get_dummiesrrNotImplementedErrorr dtypesany_meta select_dtypesrallr r) r#rrrrrrrkwargs not_cat_msgunknown_cat_msgs ` r$r*r*s t$BL122  ~   !!       ( $7+D11 3%k22 2#D)) 7%o66 6 7 D) $ $ 7 ? x',,.. 7)+666 x',,.. 7)+666j.. |.DDLGGNNNNgNNNNN 7)+666BBBB'BBBBB 7%o66 6 *        r&meanct|r|tdt|r|tdtj||stdt ||stdt |rt d|Dst|stdgd}t|r||vr/td d d |Dztj ||j j | }t|r|}n2tj t||fd|g }|dvrt|r@tj|||jtj|j|}ntj|tj|j|}|D]1} || ||j| || <2n>tj|t*jtj|j|}|||d} |dvr*t/|gtjtj|d| } |dvr*t/|gtjtj|d| } |dkr| S|dkr| S|dkr| | z S|dkr*t/|gtjtj|d| S|dkr*t/|gtjtj|d| St)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 categoriesc,g|]}t|S)r)r!vs r$ zpivot_table..s...!1...r&z4'values' must refer to an existing column or columns)r4sumcountfirstlastzaggfunc must be either z, c3"K|] }d|dV dS)'Nr7)r!xs r$r%zpivot_table..s*1W1Wq(a(((1W1W1W1W1W1Wr&)name)names)r<r=)rrindex)rrC)rCrvalues)r:r4pivot_table_sum)chunk aggregatemetatoken chunk_kwargs)r;r4pivot_table_countr:r;r4r<pivot_table_firstr=pivot_table_last)r ValueErrorrrr rr0joinr)CategoricalIndexcat categories MultiIndex from_productsortedrrIndexr.astyper,npfloat64r pivot_sum pivot_agg pivot_count pivot_firstpivot_agg_first pivot_lastpivot_agg_last) dfrCrrDaggfuncavailable_aggfuncscolumns_contents new_columnsrH value_colr1pv_sumpv_counts r$ pivot_tableris6 U  Ku}IJJJ W  MKLLL  '7 4 4=;<<< 7 , ,     VQ ..v... / /Q V  Q OPPPBBB W   0B!B!B % 1W1WDV1W1W1W(W(W W   *2g;?+EGTTT & m00 F^^- .tWo1  ### V   W<#j&hrx//DD <#hrx//D$ W W "&y/"8"8F9J99U"V"VY W|rz"(5/9R9R   F C CF/!!# D#'#    ###% D%'%    % G   F    G  ! D%-%      F  ! D$,$     r&valuec ddlm}tjddi5|t j||||||dcdddS#1swxYwYdS)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 r) no_defaultzdataframe.convert-stringFmelt)rHid_vars value_varsvar_name value_name col_levelrIN)dask.dataframe.corerldaskconfigsetr rrm)framernrorprqrrrls r$rmrm<sR/..... 4e< = =   ## F!!$                      s'AA #A )NNNr4)NNNrjN) __future__rnumpyrXpandasr)pandas.api.typesrrrtdask.dataframerdask.dataframe._compatrrsrr r r dask.dataframe.utilsr dask.utilsrrbooluint8_get_dummies_dtype_defaultr*rirmr7r&r$rsM""""""44444444 """"""000000UUUUUUUUUUUU555555********&3@TT     $RRRRtDDDD\   6 6 6 6 6 6 r&