riT HdZddlZddlZddlmZmZddlmZmZddl m Z ddl Z ddl Z ddlmZddlmZmZmZmZmZddlmZdd lmZmZed d d Zej8eZeeedgdgdgdgeedddgeedddgddddddddddZ y)a8California 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 median 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, 33:291-297, 1997. N)IntegralReal)PathLikeremove)exists) get_data_home)RemoteFileMetadata_convert_data_dataframe _fetch_remote _pkl_filepath load_descr)Bunch)Intervalvalidate_paramszcal_housing.tgzz.https://ndownloader.figshare.com/files/5976036@aaa5c9a6afe2225cc2aed2723682ae403280c4a3695a2ddda4ffb5d8215ea681)filenameurlchecksumbooleanleft)closedgneither) data_homedownload_if_missing return_X_yas_frame n_retriesdelayT)prefer_skip_nested_validationFg?clt|}t|d}t|s|s tdtj dj tj|tt|||}tjd|5}tj|jdd } gd } | d d | f} tj | |d d d d t#|ntj$|} gd}  d d df| d d dd f} } | d d dfxx| d d dfzcc<| d d dfxx| d d dfzcc<| d d df| d d dfz | d d df<| dz } t'd}| }| }d }dg}|rt)d| | | |\}}}|r||fSt+||||| |S#1swYxYw)a Load 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 : str or path-like, 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 : bool, default=True If False, raise an OSError if the data is not locally available instead of trying to download the data from the source site. return_X_y : bool, default=False If True, returns ``(data.data, data.target)`` instead of a Bunch object. .. versionadded:: 0.20 as_frame : bool, default=False If True, the data is a pandas DataFrame including columns with appropriate dtypes (numeric, string or categorical). The target is a pandas DataFrame or Series depending on the number of target_columns. .. versionadded:: 0.23 n_retries : int, default=3 Number of retries when HTTP errors are encountered. .. versionadded:: 1.5 delay : float, default=1.0 Number of seconds between retries. .. versionadded:: 1.5 Returns ------- dataset : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. data : ndarray, shape (20640, 8) Each row corresponding to the 8 feature values in order. If ``as_frame`` is True, ``data`` is a pandas object. target : numpy array of shape (20640,) Each value corresponds to the median house value in units of 100,000. If ``as_frame`` is True, ``target`` is a pandas object. feature_names : list of length 8 Array of ordered feature names used in the dataset. DESCR : str Description of the California housing dataset. frame : pandas DataFrame Only present when `as_frame=True`. DataFrame with ``data`` and ``target``. .. versionadded:: 0.23 (data, target) : tuple if ``return_X_y`` is True A tuple of two ndarray. The first containing a 2D array of shape (n_samples, n_features) with each row representing one sample and each column representing the features. The second ndarray of shape (n_samples,) containing the target samples. .. versionadded:: 0.20 Notes ----- This dataset consists of 20,640 samples and 9 features. Examples -------- >>> from sklearn.datasets import fetch_california_housing >>> housing = fetch_california_housing() >>> print(housing.data.shape, housing.target.shape) (20640, 8) (20640,) >>> print(housing.feature_names[0:6]) ['MedInc', 'HouseAge', 'AveRooms', 'AveBedrms', 'Population', 'AveOccup'] )rzcal_housing.pkzz1Data not found and `download_if_missing` is Falsez&Downloading Cal. housing from {} to {})dirnamerrzr:gz)modenamez"CaliforniaHousing/cal_housing.data,) delimiter) r!rrNr-)compress)MedIncHouseAgeAveRooms AveBedrms PopulationAveOccupLatitude Longituderrr*r,r!r+gj@zcalifornia_housing.rst MedHouseValfetch_california_housing)datatargetframe target_names feature_namesDESCR)rr rOSErrorloggerinfoformatARCHIVErr tarfileopennploadtxt extractfilejoblibdumprloadr r r)rrrrrrfilepath archive_pathf cal_housing columns_indexr=r:r9descrXyr;r<s b/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/sklearn/datasets/_california_housing.pyr8r88sX 2IY(9:H ( "MN N 4 ; ;GKK S %   \\vL 9 ;Q** BCsK 8M%a&67K KK X : ; |kk(+  Mq!t$k!QR%&8DF AJ$q!t*J AJ$q!t*Jadd1a4j(DAJh F / 0E AA EL- &fm\ q!!t  !#  s ; ;s A F**F3)!__doc__loggingrDnumbersrrosrros.pathrrInumpyrFsklearn.datasetsrsklearn.datasets._baser r r r r sklearn.utilsrsklearn.utils._param_validationrrrC getLogger__name__r@strr8rTrds0" * E  8 O    8 $8T* ){ kKxD@A4d9=> #'   s src