\c@svdZddlZddlZddlmZddlmZddZied6Z edddd Z dS( sBGlue code to load http://mlcomp.org data as a scikit.learn datasetiN(t load_files(t deprecatedcKs=|dk r$tjj||}nt||jd|S(Nt description(tNonetostpathtjoinRtget(t dataset_pathtmetadatatset_tkwargs((s6lib/python2.7/site-packages/sklearn/datasets/mlcomp.pyt_load_document_classification s tDocumentClassificationssince the http://mlcomp.org/ website will shut down in March 2017, the load_mlcomp function was deprecated in version 0.19 and will be removed in 0.21.trawc Ks|dkr@ytjd}Wq@tk r<tdq@Xntjj|}tjj|}tjj|}tjj |std|nt |t j rtjj |t|}nd}d|}xtj|D]}tjj ||d}tjj |s!qnt|C}x9|D]1} | j|kr7tjj ||}Pq7q7WWdQXqW|dkrtd|nt} tjj |d}tjj |st|dnt|U}xK|D]C} d | kr| jd d \} } | j| | j`. Parameters ---------- name_or_id : int or str The integer id or the string name metadata of the MLComp dataset to load set\_ : str, default='raw' Select the portion to load: 'train', 'test' or 'raw' mlcomp_root : str, optional The filesystem path to the root folder where MLComp datasets are stored, if mlcomp_root is None, the MLCOMP_DATASETS_HOME environment variable is looked up instead. **kwargs : domain specific kwargs to be passed to the dataset loader. Returns ------- data : Bunch Dictionary-like object, the interesting attributes are: 'filenames', the files holding the raw to learn, 'target', the classification labels (integer index), 'target_names', the meaning of the labels, and 'DESCR', the full description of the dataset. Note on the lookup process: depending on the type of name_or_id, will choose between integer id lookup or metadata name lookup by looking at the unzipped archives and metadata file. TODO: implement zip dataset loading too tMLCOMP_DATASETS_HOMEs.MLCOMP_DATASETS_HOME env variable is undefinedsCould not find folder: sname: R Ns+Could not find dataset with metadata line: s is not a valid MLComp datasett:itformattunknows"No loader implemented for format: R (RRtenvirontKeyErrort ValueErrorRt expandusertabspathtnormpathtexistst isinstancetnumberstIntegralRtstrtlistdirtopentstriptdicttsplitRtLOADERS(t name_or_idR t mlcomp_rootR Rtexpected_name_linetdatasett metadata_filetftlineR tkeytvalueRtloader((s6lib/python2.7/site-packages/sklearn/datasets/mlcomp.pyt load_mlcompsP*         # ( t__doc__RRtsklearn.datasets.baseRt sklearn.utilsRRR R#R.(((s6lib/python2.7/site-packages/sklearn/datasets/mlcomp.pyts