ó ‡ˆ\c@südZddlmZmZmZddlmZmZddlZddl Z ddl Z ddl m Z ddl mZddl mZdd l mZd d lmZd d lmZed dddddƒZe jeƒZdeed„ZdS(s:California housing dataset. The original database is available from StatLib http://lib.stat.cmu.edu/datasets/ The data contains 20,640 observations on 9 variables. This dataset contains the average house value as target variable and the following input variables (features): average income, housing average age, average rooms, average bedrooms, population, average occupation, latitude, and longitude in that order. References ---------- Pace, R. Kelley and Ronald Barry, Sparse Spatial Autoregressions, Statistics and Probability Letters, 33 (1997) 291-297. i˙˙˙˙(tdirnametexiststjoin(tmakedirstremoveNi(t get_data_home(t _fetch_remote(t _pkl_filepath(tRemoteFileMetadatai(tBunch(t_joblibtfilenamescal_housing.tgzturls.https://ndownloader.figshare.com/files/5976036tchecksumt@aaa5c9a6afe2225cc2aed2723682ae403280c4a3695a2ddda4ffb5d8215ea681c Csƒtd|ƒ}t|ƒs(t|ƒnt|dƒ}t|ƒs|sXtdƒ‚ntjdjtj |ƒƒt td|ƒ}t j ddd|ƒr}t j|jd ƒd d ƒ}d d dddddddg }|dd…|f}tj||ddƒWdQXt|ƒntj|ƒ}ddddddddg}|dd…df|dd…dd…f} } | dd…dfc| dd…df:<| dd…dfc| dd…df:<| dd…df| dd…df| dd…df<| d} ttƒ} t t| d d!ƒƒ} | jƒ} WdQX|rd| | fStd"| d#| d$|d%| ƒS(&sVLoad the California housing dataset (regression). ============== ============== Samples total 20640 Dimensionality 8 Features real Target real 0.15 - 5. ============== ============== Read more in the :ref:`User Guide `. Parameters ---------- data_home : optional, default: None Specify another download and cache folder for the datasets. By default all scikit-learn data is stored in '~/scikit_learn_data' subfolders. download_if_missing : optional, default=True If False, raise a IOError if the data is not locally available instead of trying to download the data from the source site. return_X_y : boolean, default=False. If True, returns ``(data.data, data.target)`` instead of a Bunch object. .. versionadded:: 0.20 Returns ------- dataset : dict-like object with the following attributes: dataset.data : ndarray, shape [20640, 8] Each row corresponding to the 8 feature values in order. dataset.target : numpy array of shape (20640,) Each value corresponds to the average house value in units of 100,000. dataset.feature_names : array of length 8 Array of ordered feature names used in the dataset. dataset.DESCR : string Description of the California housing dataset. (data, target) : tuple if ``return_X_y`` is True .. versionadded:: 0.20 Notes ------ This dataset consists of 20,640 samples and 9 features. t data_homescal_housing.pkzs1Data not found and `download_if_missing` is Falses&Downloading Cal. housing from {} to {}Rtmodesr:gztnames"CaliforniaHousing/cal_housing.datat delimitert,iiiiiiiiiNtcompresstMedInctHouseAgetAveRoomst AveBedrmst PopulationtAveOccuptLatitudet Longitudegjř@tdescrscalifornia_housing.rsttdatattargett feature_namestDESCR(RRRRtIOErrortloggertinfotformattARCHIVER Rttarfiletopentnptloadtxtt extractfileR tdumpRtloadRt__file__RtreadR (Rtdownload_if_missingt return_X_ytfilepatht archive_pathtft cal_housingt columns_indexR RRt module_pathtdfileR((sBlib/python2.7/site-packages/sklearn/datasets/california_housing.pytfetch_california_housing1sF7     !  3,,:    (t__doc__tos.pathRRRtosRRR'tnumpyR)tloggingtbaseRRRRtutilsR R R&t getLoggert__name__R#tNonetTruetFalseR9(((sBlib/python2.7/site-packages/sklearn/datasets/california_housing.pyts$