a j% @s0dZddlZddlmZddlmZmZddlmZm Z m Z ddl m Z ddl Z ddlZddlmZdd lmZmZd d lmZd d lmZmZmZed dddZeddddZdZeeZ dej!fddZ"ddZ#ddZ$ee%edgdgeed dddgeeddd dgd!d"d#dd"d$d%d!d&d'Z&dS)(a ============================= Species distribution dataset ============================= This dataset represents the geographic distribution of species. The dataset is provided by Phillips et. al. (2006). The two species are: - `"Bradypus variegatus" `_ , the Brown-throated Sloth. - `"Microryzomys minutus" `_ , also known as the Forest Small Rice Rat, a rodent that lives in Peru, Colombia, Ecuador, Peru, and Venezuela. References ---------- `"Maximum entropy modeling of species geographic distributions" `_ S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling, 190:231-259, 2006. N)BytesIO)IntegralReal)PathLikemakedirsremove)exists)Bunch)Intervalvalidate_params) get_data_home)RemoteFileMetadata _fetch_remote _pkl_filepathz samples.zipz.https://ndownloader.figshare.com/files/5976075Z@abb07ad284ac50d9e6d20f1c4211e0fd3c098f7f85955e89d321ee8efe37ac28)filenameurlZchecksumz coverages.zipz.https://ndownloader.figshare.com/files/5976078Z@4d862674d72e79d6cee77e63b98651ec7926043ba7d39dcb31329cf3f6073807zspecies_coverage.pkzcsbfddt|D}ddtfdd|D}tj|d}t|d}|dkr^d||<|S) zjLoad a coverage file from an open file object. This will return a numpy array of the given dtype csg|] }qS)readline).0_)FrME:\soccer\ml_env\Lib\site-packages\sklearn/datasets/_species_distributions.py Hz"_load_coverage..cSs|dt|dfS)Nrr )splitfloat)trrrIrz _load_coverage..csg|] }|qSrr)rline) make_tuplerrrJrdtypes NODATA_valuei)rangedictnploadtxtint)r header_lengthr$headerMZnodatar)rr"r_load_coverageCs r-cCs6|dd}tj|dddd}||j_|S)zLoad csv file. Parameters ---------- F : file object CSV file open in byte mode. Returns ------- rec : np.ndarray record array representing the data ascii,rz S22,f4,f4)Zskiprows delimiterr$)rdecodestriprr'r(r$names)rr3Zrecrrr _load_csvSs r4cCs`|j|j}||j|j}|j|j}||j|j}t|||j}t|||j}||fS)a%Construct the map grid from the batch object Parameters ---------- batch : Batch object The object returned by :func:`fetch_species_distributions` Returns ------- (xgrid, ygrid) : 1-D arrays The grid corresponding to the values in batch.coverages )x_left_lower_corner grid_sizeNxy_left_lower_cornerNyr'Zarange)batchZxminZxmaxZyminZymaxZxgridZygridrrrconstruct_gridsgs  r;booleanleft)closedgZneither) data_homedownload_if_missing n_retriesdelayT)Zprefer_skip_nested_validationg?cCst|}t|st|tdddddd}tj}t|t}t|s|sPtdt dt j |ft t |||d }t|H}|jD]0} t|| } d | vrt| } d | vrt| } qWd n1s0Yt|t d tj |ft t|||d } t| Z}g}|jD]0} t|| } t d| |t| qtj||d}Wd n1sn0Yt| tf|| | d|}tj||ddn t|}|S)a Loader for species distribution dataset from Phillips et. al. (2006). 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. 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 ------- data : :class:`~sklearn.utils.Bunch` Dictionary-like object, with the following attributes. coverages : array, shape = [14, 1592, 1212] These represent the 14 features measured at each point of the map grid. The latitude/longitude values for the grid are discussed below. Missing data is represented by the value -9999. train : record array, shape = (1624,) The training points for the data. Each point has three fields: - train['species'] is the species name - train['dd long'] is the longitude, in degrees - train['dd lat'] is the latitude, in degrees test : record array, shape = (620,) The test points for the data. Same format as the training data. Nx, Ny : integers The number of longitudes (x) and latitudes (y) in the grid x_left_lower_corner, y_left_lower_corner : floats The (x,y) position of the lower-left corner, in degrees grid_size : float The spacing between points of the grid, in degrees Notes ----- This dataset represents the geographic distribution of species. The dataset is provided by Phillips et. al. (2006). The two species are: - `"Bradypus variegatus" `_ , the Brown-throated Sloth. - `"Microryzomys minutus" `_ , also known as the Forest Small Rice Rat, a rodent that lives in Peru, Colombia, Ecuador, Peru, and Venezuela. References ---------- * `"Maximum entropy modeling of species geographic distributions" `_ S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling, 190:231-259, 2006. Examples -------- >>> from sklearn.datasets import fetch_species_distributions >>> species = fetch_species_distributions() >>> species.train[:5] array([(b'microryzomys_minutus', -64.7 , -17.85 ), (b'microryzomys_minutus', -67.8333, -16.3333), (b'microryzomys_minutus', -67.8833, -16.3 ), (b'microryzomys_minutus', -67.8 , -16.2667), (b'microryzomys_minutus', -67.9833, -15.9 )], dtype=[('species', 'S22'), ('dd long', 'sN