U md@sdZddlmZddlmZmZddlZddlZddl Z ddl Z ddl m Z ddl mZddl mZdd l mZdd l mZdd l mZd d lmZeddddZe eZdddddddZdS)a: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. )exists)makedirsremoveN) get_data_home)_convert_data_dataframe) _fetch_remote) _pkl_filepath)RemoteFileMetadata) load_descr)Bunchzcal_housing.tgzz.https://ndownloader.figshare.com/files/5976036Z@aaa5c9a6afe2225cc2aed2723682ae403280c4a3695a2ddda4ffb5d8215ea681)filenameurlZchecksumTF) data_homedownload_if_missing return_X_yas_framec Cst|d}t|st|t|d}t|s|s8tdtdtj |t t|d}t j d|dP}t j|dd d }d d d ddddddg }|dd|f}tj||ddW5QRXt|n t|}ddddddddg} |dddf|ddddf} } | ddd f| dddf<| dddf| dddf<| dddf| dddf| dddf<| d} td} | } | }d}d g}|rtd!| | | |\}} }|r| |fSt| |||| | d"S)#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, 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 a IOError 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 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 average 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. )rzcal_housing.pkzz1Data not found and `download_if_missing` is Falsez&Downloading Cal. housing from {} to {})dirnamezr:gz)modenamez"CaliforniaHousing/cal_housing.data,) delimiterr rrN)compressZMedIncZHouseAgeZAveRoomsZ AveBedrmsZ PopulationZAveOccupZLatitudeZ Longitudegj@zcalifornia_housing.rstZ MedHouseValfetch_california_housing)datatargetframe target_names feature_namesZDESCR)rrrr IOErrorloggerinfoformatARCHIVErrtarfileopennpZloadtxt extractfilejoblibdumprloadr rr )rrrrfilepath archive_pathfZ cal_housingZ columns_indexr%r"r!descrXyr#r$r8]/home/sam/Atlas/atlas_env/lib/python3.8/site-packages/sklearn/datasets/_california_housing.pyr 5svH       &$$, r )__doc__os.pathrosrrr+numpyr-loggingr/r_baserrr r r utilsr r* getLogger__name__r'r r8r8r8r9s0