&`i@ ZddlmZmZmZmZmZmZmZddlZ ddl Z ddl m Z mZddlmZddlmZerddlmZGddeZed Gd d eZed Gd deZdedeeefdefdZdededededeef dZdS)) TYPE_CHECKINGDictIterableListOptionalTypeUnionN)MaxMin) Preprocessor) PublicAPI)Datasetc4eZdZdZdejfdZdZdZdS)_AbstractKBinsDiscretizerzAbstract base class for all KBinsDiscretizers. Essentially a thin wraper around ``pd.cut``. Expects either ``self.stats_`` or ``self.bins`` to be set and contain {column:list_of_bin_intervals}. dfcdtjdtjffd }||d}|j|j<|S)Nsreturnc |jjvr|Sjrj|jnd}d}|r8t |t jr|j}t|j }nd}j rj nj }t j |t |tr ||jn|j||djjS)NFT)rightlabelsorderedretbinsinclude_lowest duplicates)namecolumnsdtypesget isinstancepdCategoricalDtyperlist categories _is_fittablestats_binscutdictrrr)rrrr'selfs v/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/ray/data/preprocessors/discretizer.py bin_valuesz?_AbstractKBinsDiscretizer._transform_pandas..bin_valuessvT\))04 FT[__QV,,,FG #fb&9::#$nG!&"344FF"F"&"3B4;;D6 *4 6 6@QV Dj#2?    r)axis)r!Seriesapplyroutput_columns)r*rr, binned_dfs` r+_transform_pandasz+_AbstractKBinsDiscretizer._transform_pandassc ")        0HHZaH00 "+DL"94  r-ctjtr/tfdjDst ddSdS)Nc3*K|] }|jvVdSN)r').0colr*s r+ zC_AbstractKBinsDiscretizer._validate_bins_columns..5s;3 3 !$C49 3 3 3 3 3 3 r-zKIf `bins` is a dictionary, all elements of `columns` must be present in it.)r r'r)allr ValueErrorr*s`r+_validate_bins_columnsz0_AbstractKBinsDiscretizer._validate_bins_columns4s} di & & s3 3 3 3 (, 3 3 3 0 0       r-cddt|D}|jjd|dS)Nz, cLg|]!\}}|d|d|"S)_=) startswith)r7 attr_name attr_values r+ z6_AbstractKBinsDiscretizer.__repr__..?sN   )Iz ++C00 --z--   r-())joinvarsitems __class____name__)r*attr_strs r+__repr__z"_AbstractKBinsDiscretizer.__repr__=sa99  -1$ZZ-=-=-?-?     .)77H7777r-N) rL __module__ __qualname____doc__r! DataFramer3r=rNr-r+rrsYBL:88888r-ralpha) stabilityceZdZdZdddddddeedeeee j e eeeee j fffd e d e d ed e e eee jeejffd e eefdZdZdS)CustomKBinsDiscretizerakBin values into discrete intervals using custom bin edges. Columns must contain numerical values. Examples: Use :class:`CustomKBinsDiscretizer` to bin continuous features. >>> import pandas as pd >>> import ray >>> from ray.data.preprocessors import CustomKBinsDiscretizer >>> df = pd.DataFrame({ ... "value_1": [0.2, 1.4, 2.5, 6.2, 9.7, 2.1], ... "value_2": [10, 15, 13, 12, 23, 25], ... }) >>> ds = ray.data.from_pandas(df) >>> discretizer = CustomKBinsDiscretizer( ... columns=["value_1", "value_2"], ... bins=[0, 1, 4, 10, 25] ... ) >>> discretizer.transform(ds).to_pandas() value_1 value_2 0 0 2 1 1 3 2 1 3 3 2 3 4 2 3 5 1 3 :class:`CustomKBinsDiscretizer` can also be used in append mode by providing the name of the output_columns that should hold the encoded values. >>> discretizer = CustomKBinsDiscretizer( ... columns=["value_1", "value_2"], ... bins=[0, 1, 4, 10, 25], ... output_columns=["value_1_discretized", "value_2_discretized"] ... ) >>> discretizer.fit_transform(ds).to_pandas() # doctest: +SKIP value_1 value_2 value_1_discretized value_2_discretized 0 0.2 10 0 2 1 1.4 15 1 3 2 2.5 13 1 3 3 6.2 12 2 3 4 9.7 23 2 3 5 2.1 25 1 3 You can also specify different bin edges per column. >>> discretizer = CustomKBinsDiscretizer( ... columns=["value_1", "value_2"], ... bins={"value_1": [0, 1, 4], "value_2": [0, 18, 35, 70]}, ... ) >>> discretizer.transform(ds).to_pandas() value_1 value_2 0 0.0 0 1 1.0 0 2 1.0 0 3 NaN 0 4 NaN 1 5 1.0 1 Args: columns: The columns to discretize. bins: Defines custom bin edges. Can be an iterable of numbers, a ``pd.IntervalIndex``, or a dict mapping columns to either of them. Note that ``pd.IntervalIndex`` for bins must be non-overlapping. right: Indicates whether bins include the rightmost edge. include_lowest: Indicates whether the first interval should be left-inclusive. duplicates: Can be either 'raise' or 'drop'. If bin edges are not unique, raise ``ValueError`` or drop non-uniques. dtypes: An optional dictionary that maps columns to ``pd.CategoricalDtype`` objects or ``np.integer`` types. If you don't include a column in ``dtypes`` or specify it as an integer dtype, the outputted column will consist of ordered integers corresponding to bins. If you use a ``pd.CategoricalDtype``, the outputted column will be a ``pd.CategoricalDtype`` with the categories being mapped to bins. You can use ``pd.CategoricalDtype(categories, ordered=True)`` to preserve information about bin order. output_columns: The names of the transformed columns. If None, the transformed columns will be the same as the input columns. If not None, the length of ``output_columns`` must match the length of ``columns``, othwerwise an error will be raised. .. seealso:: :class:`UniformKBinsDiscretizer` If you want to bin data into uniform width bins. TFraiseNrrrrr1rr'rrrrr1c||_||_||_||_||_||_t j|||_| dSr6) rr'rrrrr #_derive_and_validate_output_columnsr1r=)r*rr'rrrrr1s r+__init__zCustomKBinsDiscretizer.__init__sc"   ,$ *N ^   ##%%%%%r-)rLrOrPrQrstrr rfloatr! IntervalIndexrboolrr"rnpintegerr\r%rSr-r+rWrWHsWWD$! .2&&&c& UO   eHUOR-==>> ? A &&&& eB/bj1AABB C &!c+&&&&:LLLr-rWceZdZdZdddddddeedeeeeeffd e d e d ed e eeee j e ejffd e eeffdZdddefdZdZddZxZS)UniformKBinsDiscretizerarBin values into discrete intervals (bins) of uniform width. Columns must contain numerical values. Examples: Use :class:`UniformKBinsDiscretizer` to bin continuous features. >>> import pandas as pd >>> import ray >>> from ray.data.preprocessors import UniformKBinsDiscretizer >>> df = pd.DataFrame({ ... "value_1": [0.2, 1.4, 2.5, 6.2, 9.7, 2.1], ... "value_2": [10, 15, 13, 12, 23, 25], ... }) >>> ds = ray.data.from_pandas(df) >>> discretizer = UniformKBinsDiscretizer( ... columns=["value_1", "value_2"], bins=4 ... ) >>> discretizer.fit_transform(ds).to_pandas() value_1 value_2 0 0 0 1 0 1 2 0 0 3 2 0 4 3 3 5 0 3 :class:`UniformKBinsDiscretizer` can also be used in append mode by providing the name of the output_columns that should hold the encoded values. >>> discretizer = UniformKBinsDiscretizer( ... columns=["value_1", "value_2"], ... bins=4, ... output_columns=["value_1_discretized", "value_2_discretized"] ... ) >>> discretizer.fit_transform(ds).to_pandas() # doctest: +SKIP value_1 value_2 value_1_discretized value_2_discretized 0 0.2 10 0 0 1 1.4 15 0 1 2 2.5 13 0 0 3 6.2 12 2 0 4 9.7 23 3 3 5 2.1 25 0 3 You can also specify different number of bins per column. >>> discretizer = UniformKBinsDiscretizer( ... columns=["value_1", "value_2"], bins={"value_1": 4, "value_2": 3} ... ) >>> discretizer.fit_transform(ds).to_pandas() value_1 value_2 0 0 0 1 0 0 2 0 0 3 2 0 4 3 2 5 0 2 Args: columns: The columns to discretize. bins: Defines the number of equal-width bins. Can be either an integer (which will be applied to all columns), or a dict that maps columns to integers. The range is extended by .1% on each side to include the minimum and maximum values. right: Indicates whether bins includes the rightmost edge or not. include_lowest: Whether the first interval should be left-inclusive or not. duplicates: Can be either 'raise' or 'drop'. If bin edges are not unique, raise ``ValueError`` or drop non-uniques. dtypes: An optional dictionary that maps columns to ``pd.CategoricalDtype`` objects or ``np.integer`` types. If you don't include a column in ``dtypes`` or specify it as an integer dtype, the outputted column will consist of ordered integers corresponding to bins. If you use a ``pd.CategoricalDtype``, the outputted column will be a ``pd.CategoricalDtype`` with the categories being mapped to bins. You can use ``pd.CategoricalDtype(categories, ordered=True)`` to preserve information about bin order. output_columns: The names of the transformed columns. If None, the transformed columns will be the same as the input columns. If not None, the length of ``output_columns`` must match the length of ``columns``, othwerwise an error will be raised. .. seealso:: :class:`CustomKBinsDiscretizer` If you want to specify your own bin edges. TFrXNrYrr'rrrrr1ct||_||_||_||_||_||_tj |||_ dSr6) superr\rr'rrrrr r[r1) r*rr'rrrrr1rKs r+r\z UniformKBinsDiscretizer.__init__sf    ,$ *N ^  r-datasetrrc|t|jtr|j}n|j}|D]W}t|jtr |j|n|j}t|t std|X|j t||j t||S)Nz5`bins` must be an integer or a dict of integers, got ) aggregator_fnr) _validate_on_fitr r'r)keysrint TypeErrorstat_computation_planadd_aggregatorr r )r*rgrcolumnr's r+_fitzUniformKBinsDiscretizer._fit7s  di & & #inn&&GGlG  F(249d(C(CR49V$$DdC(( RDRR  "11 2    "11 2    r-c.|dSr6)r=r<s r+rjz(UniformKBinsDiscretizer._validate_on_fitQs ##%%%%%r-cz|j|}t||j|j|_|Sr6)rncomputepost_fit_processorr'rr&)r*rgstatss r+ _fit_executez$UniformKBinsDiscretizer._fit_executeTs4*227;;( 4:FF  r-)rgr)rLrOrPrQrr]r rlrr`rr!r"rrarbr\r rqrjrw __classcell__)rKs@r+rdrds5XX~$! .2   c Cc3h'(       eB/bj1AABB C  !c+      0I,4&&&r-rdaggregate_statsr'rc niii}}}|D]C\}}|dd}|dr|||<|dr|||<D|D]A} t|| || t |t r|| n|||| <B|S)Nminmax)mnmxr'r)rJrBrk._translate_min_max_number_of_bins_to_bin_edgesr r)) ryr'rminsmaxesrvkeyvalue column_namerps r+ruruZsR%D%++--'' U!B$i >>%  & %D  >>%  '!&E+ ))++  FF|V}!+D$!7!7AfT    f  Lr-rrrc||f}d|D\}}tj|stj|rtd||krV||dkrdt|zndz}||dkrdt|zndz }tj|||dzd}nFtj|||dzd}||z dz}|r|dxx|zcc<n|dxx|z cc<|S) zETranslates a range and desired number of bins into list of bin edges.c3 K|] }|dzV dS)gNrS)r7mis r+r9zA_translate_min_max_number_of_bins_to_bin_edges..s& % %2b3h % % % % % %r-z@Cannot specify integer `bins` when input data contains infinity.rgMbP?T)endpointr|)raisinfr;abslinspace)rrr'rrngadjs r+rrs$ r(C % % % % %FB x||rx|| N    r qec"ggooe3 qec"ggooe3{2r4!8d;;;{2r4!8d;;;Bw%   GGGsNGGGG HHHOHHH Kr-)typingrrrrrrr numpyrapandasr!ray.data.aggregater r ray.data.preprocessorr ray.util.annotationsr ray.data.datasetrrrWrdr)r]r`rur^rlrrSr-r+rsMMMMMMMMMMMMMMMMMM''''''''......******)((((((7878787878 787878t Wwwwww6wwwt WSSSSS7SSSlE#t)4DTn  #,0 %[r-