o ?HhX:@sddlZddlmZddlmZmZddlZddlm Z ddl m Z ddl m Z dd lmZd d Zd d ZeGdddeZGdddZGdddZGdddZeZeeeeddZd'ddZd'ddZddZddZd d!ZGd"d#d#Zdd$d%d&ZdS)(Nwraps)Protocolruntime_checkable)issparse) get_config) available_if)2_create_pandas_dataframe_from_non_pandas_containerc Cs>zt|WSty}z td|d|d|d}~ww)zCheck library is installed.zSetting output container to 'z ' requires z to be installedN) importlib import_module ImportError)libraryexcrY/home/air/sanwanet/gpt-api/venv/lib/python3.10/site-packages/sklearn/utils/_set_output.pycheck_library_installeds rcCs*t|rz|WStyYdSw|SN)callable Exceptioncolumnsrrr get_columnss rc@s8eZdZUeed<d ddZddZddZd d Zd S) ContainerAdapterProtocol container_libFcCdS)aCreate container from `X_output` with additional metadata. Parameters ---------- X_output : {ndarray, dataframe} Data to wrap. X_original : {ndarray, dataframe} Original input dataframe. This is used to extract the metadata that should be passed to `X_output`, e.g. pandas row index. columns : callable, ndarray, or None The column names or a callable that returns the column names. The callable is useful if the column names require some computation. If `None`, then no columns are passed to the container's constructor. inplace : bool, default=False Whether or not we intend to modify `X_output` in-place. However, it does not guarantee that we return the same object if the in-place operation is not possible. Returns ------- wrapped_output : container_type `X_output` wrapped into the container type. Nr)selfX_output X_originalrinplacerrrcreate_container(z)ContainerAdapterProtocol.create_containercCr)a Return True if X is a supported container. Parameters ---------- Xs: container Containers to be checked. Returns ------- is_supported_container : bool True if X is a supported container. Nr)rXrrris_supported_containerDr"z/ContainerAdapterProtocol.is_supported_containercCr)aQRename columns in `X`. Parameters ---------- X : container Container which columns is updated. columns : ndarray of str Columns to update the `X`'s columns with. Returns ------- updated_container : container Container with new names. Nrrr#rrrrrename_columnsRr"z'ContainerAdapterProtocol.rename_columnscCr)aStack containers horizontally (column-wise). Parameters ---------- Xs : list of containers List of containers to stack. Returns ------- stacked_Xs : container Stacked containers. Nr)rXsrrrhstackcr"zContainerAdapterProtocol.hstackN)F) __name__ __module__ __qualname__str__annotations__r!r$r&r(rrrrr$s   rc@2eZdZdZd ddZddZddZd d Zd S) PandasAdapterpandasTcCsttd}t|}|rt||js.t||jr|j}n t||jr$|j}nd}t||| d}|dur8|||S|S)Nr0)r#indexcopy)rr isinstance DataFramer1r r&)rrrrr pdr1rrrr!us   zPandasAdapter.create_containercCtd}t||jS)Nr0rr3r4)rr#r5rrrr$ z$PandasAdapter.is_supported_containercC ||_|Srrr%rrrr&zPandasAdapter.rename_columnscCtd}|j|ddS)Nr0r )axisrconcat)rr'r5rrrr(zPandasAdapter.hstackNTr)r*r+rr!r$r&r(rrrrr/rs   r/c@r.) PolarsAdapterpolarsTcCs`td}t|}t|tjr|n|}|rt||js$|j||ddS|dur.|||S|S)NrCrow)schemaorient)rrr3npndarraytolistr4r&)rrrrr plrrrr!s zPolarsAdapter.create_containercCr6)NrCr7)rr#rJrrrr$r8z$PolarsAdapter.is_supported_containercCr9rrr%rrrr&r:zPolarsAdapter.rename_columnscCr;)NrC horizontal)howr=)rr'rJrrrr(r?zPolarsAdapter.hstackNr@rArrrrrBs    rBc@s(eZdZddZeddZddZdS)ContainerAdaptersManagercCs i|_dSr)adaptersrrrr__init__s z!ContainerAdaptersManager.__init__cCsdht|jBS)Ndefault)setrNrOrrrsupported_outputssz*ContainerAdaptersManager.supported_outputscCs||j|j<dSr)rNr)radapterrrrregistersz!ContainerAdaptersManager.registerN)r)r*r+rPpropertyrSrUrrrrrMs   rMc Cs^|jjdd}ztj|WSty.}zttj}td|d|d|d}~ww)zGet the adapter that knows how to handle such container. See :class:`sklearn.utils._set_output.ContainerAdapterProtocol` for more details. .rzZThe container does not have a registered adapter in scikit-learn. Available adapters are: z" while the container provided is: N) __class__r*splitADAPTERS_MANAGERrNKeyErrorlistkeys ValueError) container module_nameravailable_adaptersrrr_get_adapter_from_containers  rbcCs0t||d}ztj|WStyYdSw)zGet container adapter.denseN)_get_output_configrZrNr[)method estimator dense_configrrr_get_container_adapters   rhcCs\t|di}||vr||}nt|d}tj}||vr*tdt|d|d|iS)aGet output config based on estimator and global configuration. Parameters ---------- method : {"transform"} Estimator's method for which the output container is looked up. estimator : estimator instance or None Estimator to get the output configuration from. If `None`, check global configuration is used. Returns ------- config : dict Dictionary with keys: - "dense": specifies the dense container for `method`. This can be `"default"` or `"pandas"`. _sklearn_output_config_outputzoutput config must be in z, got rc)getattrrrZrSr^sorted)rerfest_sklearn_output_configrgrSrrrrds  rdcCsbt||}|ddkst|s|S|d}t|r#td|dtj|}|j|||jdS)aWrap output with container based on an estimator's or global config. Parameters ---------- method : {"transform"} Estimator's method to get container output for. data_to_wrap : {ndarray, dataframe} Data to wrap with container. original_input : {ndarray, dataframe} Original input of function. estimator : estimator instance Estimator with to get the output configuration from. Returns ------- output : {ndarray, dataframe} If the output config is "default" or the estimator is not configured for wrapping return `data_to_wrap` unchanged. If the output config is "pandas", return `data_to_wrap` as a pandas DataFrame. rcrQzmThe transformer outputs a scipy sparse matrix. Try to set the transformer output to a dense array or disable z- output with set_output(transform='default').r) rd_auto_wrap_is_configuredrr^ capitalizerZrNr!get_feature_names_out)re data_to_wraporiginal_inputrf output_configrgrTrrr_wrap_data_with_container s  rtcstfdd}|S)z@Wrapper used by `_SetOutputMixin` to automatically wrap methods.csr||g|Ri|}t|tr2t|d||g|ddR}tt|dr0t||S|St|||S)Nrr _make)r3tuplerthasattrtyperu)rr#argskwargsrq return_tuplefrerrwrapped=s  z$_wrap_method_output..wrappedr)r}rer~rr|r_wrap_method_output:srcCs t|dt}t|dod|vS)zReturn True if estimator is configured for auto-wrapping the transform method. `_SetOutputMixin` sets `_sklearn_auto_wrap_output_keys` to `set()` if auto wrapping is manually disabled. _sklearn_auto_wrap_output_keysrp transform)rkrRrw)rfauto_wrap_output_keysrrrrnQs rncs8eZdZdZdfdd ZeeddddZZS) _SetOutputMixina\Mixin that dynamically wraps methods to return container based on config. Currently `_SetOutputMixin` wraps `transform` and `fit_transform` and configures it based on `set_output` of the global configuration. `set_output` is only defined if `get_feature_names_out` is defined and `auto_wrap_output_keys` is the default value. rc stjdi|t|ts|dustd|dur t|_dSddd}t|_|D](\}}t||r:||vr;q-|j |||j vrGq-t t |||}t |||q-dS)Nz6auto_wrap_output_keys must be None or a tuple of keys.r)r fit_transformr)super__init_subclass__r3rvr^rRritemsrwadd__dict__rrksetattr)clsrrz method_to_keyrekeywrapped_methodrXrrrhs*  z!_SetOutputMixin.__init_subclass__NcCs*|dur|St|dsi|_||jd<|S)aSet output container. See :ref:`sphx_glr_auto_examples_miscellaneous_plot_set_output.py` for an example on how to use the API. Parameters ---------- transform : {"default", "pandas", "polars"}, default=None Configure output of `transform` and `fit_transform`. - `"default"`: Default output format of a transformer - `"pandas"`: DataFrame output - `"polars"`: Polars output - `None`: Transform configuration is unchanged .. versionadded:: 1.4 `"polars"` option was added. Returns ------- self : estimator instance Estimator instance. Nrir)rwri)rrrrr set_outputs   z_SetOutputMixin.set_output)r) r)r*r+__doc__rr rnr __classcell__rrrrr^s   rrcCsJt|dp t|do |du}|sdSt|dstd|d|j|dS)a)Safely call estimator.set_output and error if it not available. This is used by meta-estimators to set the output for child estimators. Parameters ---------- estimator : estimator instance Estimator instance. transform : {"default", "pandas", "polars"}, default=None Configure output of the following estimator's methods: - `"transform"` - `"fit_transform"` If `None`, this operation is a no-op. Returns ------- estimator : estimator instance Estimator instance. rrNrzUnable to configure output for z' because `set_output` is not available.r)rwr^r)rfrset_output_for_transformrrr_safe_set_outputs     rr) r functoolsrtypingrrnumpyrG scipy.sparser_configr _available_ifr fixesr rrrr/rBrMrZrUrbrhrdrtrrnrrrrrrs4       M,    #. M