σ ¦–Υ\c@`sκddlmZmZmZddlZddlZddlm Z m Z m Z m Z ddl mZddlmZmZmZmZddlmZdd edeeejd „Zdddd d „Zdddd dd„ZdS(i(tabsolute_importtdivisiontprint_functionNi(tSeriest DataFrametmap_partitionstapply_concat_apply(tmethods(tis_categorical_dtypet is_scalarthas_known_categoriestPANDAS_VERSIONi(tMt_c `stdkri|d6}n-|tjkrCtdjtƒƒ‚ni}tˆtjtjfƒr˜tj ˆd|d|d|d|d|d ||Sd } d } tˆtƒrμt ˆƒsΞt | ƒ‚nt ˆƒs’t | ƒ‚q’nΆtˆtƒr’|dkrIˆjd kjƒr+t | ƒ‚nˆjjd dgƒj}n+t‡fd†|Dƒƒstt | ƒ‚nt‡fd†|Dƒƒs’t | ƒ‚q’ntj ˆjd|d|d|d|d|d ||} ttj ˆd|d|d|d|d|d |d| |S(sΕ 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 np.uint8 Data type for new columns. Only a single dtype is allowed. Only valid if pandas is 0.23.0 or newer. .. 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, 4 tasks >>> dd.get_dummies(s).compute() a b c 0 1 0 0 1 0 1 0 2 0 0 1 3 1 0 0 See Also -------- pandas.get_dummies s0.23.0tdtypesOYour version of pandas is '{}'. The 'dtype' keyword was added in pandas 0.23.0.tprefixt prefix_septdummy_natcolumnstsparset drop_firsts„`get_dummies` with non-categorical dtypes is not supported. Please use `df.categorize()` beforehand to convert to categorical dtype.s•`get_dummies` with unknown categories is not supported. Please use `column.cat.as_known()` or `df.categorize()` beforehand to ensure known categoriestobjecttincludetcategoryc3`s|]}tˆ|ƒVqdS(N(R(t.0tc(tdata(s5lib/python2.7/site-packages/dask/dataframe/reshape.pys Œsc3`s|]}tˆ|ƒVqdS(N(R (RR(R(s5lib/python2.7/site-packages/dask/dataframe/reshape.pys stmetaN(R tnptuint8t ValueErrortformatt isinstancetpdRRt get_dummiesRtNotImplementedErrorR tNonetdtypestanyt_metat select_dtypesRtallR( RRRRRRRRtkwargst not_cat_msgtunknown_cat_msgR((Rs5lib/python2.7/site-packages/dask/dataframe/reshape.pyR"sJS           tmeanc C`sγt|ƒ s|dkr(tdƒ‚nt|ƒ sA|dkrPtdƒ‚nt||ƒsotdƒ‚nt||ƒsŽtdƒ‚nt|ƒ s§|dkrΆtdƒ‚nt|ƒ sΟ|dkrήtd ƒ‚ntj||jjd |ƒ}tj d |d t j ƒ}||j _ i|d 6|d 6|d6}t|gdtjdtjd|ddd|ƒ}t|gdtjdtjd|ddd|ƒ} |dkr΅|S|dkrΕ| S|dkrΩ|| St‚dS(s Create a spreadsheet-style pivot table as a DataFrame. Target ``columns`` must have category dtype to infer result's ``columns``. ``index``, ``columns``, ``values`` and ``aggfunc`` must be all scalar. Parameters ---------- data : DataFrame values : scalar column to aggregate index : scalar column to be index columns : scalar column to be columns aggfunc : {'mean', 'sum', 'count'}, default 'mean' Returns ------- table : DataFrame s.'index' must be the name of an existing columns0'columns' must be the name of an existing columns 'columns' must be category dtypess'columns' must have known categories. Please use `df[columns].cat.as_known()` beforehand to ensure known categoriess/'values' must be the name of an existing columnR-tsumtcounts/aggfunc must be either 'mean', 'sum' or 'count'tnameRRtindextvaluestchunkt aggregateRttokentpivot_table_sumt chunk_kwargstpivot_table_countN(R-R.R/(R R$RRR R!tCategoricalIndextcatt categoriesRRtfloat64R1R0RRt pivot_sumt pivot_aggt pivot_count( tdfR1RR2taggfunct new_columnsRR*tpv_sumtpv_count((s5lib/python2.7/site-packages/dask/dataframe/reshape.pyt pivot_table₯sF            tvaluecC`sJddlm}|jtjd|d|d|d|d|d|d d ƒS( Ni(t no_defaultRtid_varst value_varstvar_namet value_namet col_levelR5tmelt(tdask.dataframe.coreRGRR RM(tframeRHRIRJRKRLRG((s5lib/python2.7/site-packages/dask/dataframe/reshape.pyRMοs  (t __future__RRRtnumpyRtpandasR!tcoreRRRRtRtutilsRR R R R R$tFalseRR"RERM(((s5lib/python2.7/site-packages/dask/dataframe/reshape.pyts  ""  I