def load_credit_data():
sk_data_dir = get_data_home()
archive = RemoteFileMetadata(
filename='default of credit card clients.xls',
url='https://archive.ics.uci.edu/ml/machine-learning-databases/'
'00350/default%20of%20credit%20card%20clients.xls',
checksum=('30c6be3abd8dcfd3e6096c828bad8c2f'
'011238620f5369220bd60cfc82700933'))
if not exists(join(sk_data_dir, archive.filename)):
_fetch_remote(archive, dirname=sk_data_dir)
data = pd.read_excel(join(sk_data_dir, archive.filename),
sheet_name='Data',
header=1)
dataset = Bunch(data=(data.drop('default payment next month', axis=1)),
target=np.array(data['default payment next month']))
return dataset
from sklearn.utils import Bunch, check_random_state
from skimage.io import imread
from skimage.transform import resize as imresize, estimate_transform
import Polygon
from .poly_utils import isSelfIntersecting
# CONSTANTS
################################################################################
################################################################################
ARCHIVE_BASE_URL = 'https://github.com/jchazalon/smartdoc15-ch1-dataset/releases/download/v2.0.0'
ARCHIVE_MODELS_FILENAME = 'models.tar.gz'
ARCHIVE_MODELS = RemoteFileMetadata(
filename=ARCHIVE_MODELS_FILENAME,
url=ARCHIVE_BASE_URL + '/' + ARCHIVE_MODELS_FILENAME,
checksum=(
'6f9068624073f76b20f88352b2bac60b9e5de5a59819fc9db37fba1ee07cce8a'))
ARCHIVE_FRAMES_FILENAME = 'frames.tar.gz'
ARCHIVE_FRAMES = RemoteFileMetadata(
filename=ARCHIVE_FRAMES_FILENAME,
url=ARCHIVE_BASE_URL + '/' + ARCHIVE_FRAMES_FILENAME,
checksum=(
'3acb8be143fc86c507d90d298097cba762e91a3abf7e2d35ccd5303e13a79eae'))
DATASET_CONTENT = {
"models": (ARCHIVE_MODELS, "390MB", "Model images"),
"frames": (ARCHIVE_FRAMES, "972MB", "Dataset content and metadata")
}
@author: David Diaz Vico
@license: MIT
"""
import os
from scipy.io import loadmat
from sklearn.datasets.base import (_fetch_remote, get_data_home, Bunch,
RemoteFileMetadata)
DATASETS = {
'banana', 'breast_cancer', 'diabetis', 'flare_solar', 'german', 'heart',
'image', 'ringnorm', 'splice', 'thyroid', 'titanic', 'twonorm', 'waveform'
}
ARCHIVE = RemoteFileMetadata(
filename='benchmarks.mat',
url=
'https://github.com/tdiethe/gunnar_raetsch_benchmark_datasets/raw/master/benchmarks.mat',
checksum=(
'47c19e4bc4716edc4077cfa5ea61edf4d02af4ec51a0ecfe035626ae8b561c75'))
def fetch_raetsch(name, data_home=None):
"""Fetch Gunnar Raetsch's dataset.
Fetch a Gunnar Raetsch's benchmark dataset by name. Availabe datasets are
'banana', 'breast_cancer', 'diabetis', 'flare_solar', 'german', 'heart',
'image', 'ringnorm', 'splice', 'thyroid', 'titanic', 'twonorm' and
'waveform'. More info at
https://github.com/tdiethe/gunnar_raetsch_benchmark_datasets.
Parameters
----------
from os.path import dirname, exists, join
from os import makedirs, remove
import numpy as np
from scipy.io.matlab import loadmat
from sklearn.datasets.base import get_data_home
from sklearn.datasets.base import _fetch_remote
from sklearn.datasets.base import RemoteFileMetadata
from sklearn.datasets.base import _pkl_filepath
import joblib as _joblib
from sklearn.utils import check_random_state, Bunch
GLASS = RemoteFileMetadata(
filename='glass.data',
url=
'https://archive.ics.uci.edu/ml/machine-learning-databases/glass/glass.data',
checksum=('dd67373f4baf2807345df02cbfef2093'
'd342e61ad0d82a4fb79af43ef8ce449d'))
def fetch_uci_glass_outlier(data_home=None,
shuffle=False,
random_state=0,
download_if_missing=True):
"""Load the UCI glass data-set from AT&T (classification).
Download it if necessary.
================= =====================
Classes 6
Samples total 214
Dimensionality 9
Features real
from os.path import exists, join
from os import makedirs, remove
import tarfile
import arff
import pandas as pd
import numpy as np
from sklearn.datasets.base import RemoteFileMetadata
from sklearn.datasets.base import get_data_home, _fetch_remote
Lymphography = RemoteFileMetadata(
filename = 'Lymphography.tar.gz',
url='http://www.dbs.ifi.lmu.de/research/outlier-evaluation/input/Lymphography.tar.gz',
checksum='1ecb8fc1cc86960bbbe604d8fbf058f01bf4035af1165cc32470f9dced77a8f8'
)
def fetch_or_load_lymphography():
global Lymphography
data_home = get_data_home()
if not exists(data_home):
makedirs(data_home)
file_path = join(data_home, 'Lymphography', 'Lymphography_withoutdupl_idf.arff')
if not exists(file_path):
data_archive_path = _fetch_remote(Lymphography)
tf = tarfile.open(data_archive_path)
tf.extractall(data_home)
remove(data_archive_path)
f_descriptor = open(file_path, 'r')
dataset = arff.load(f_descriptor)
df = pd.DataFrame(dataset['data'])
feature = df.iloc[:,1:19].to_numpy()
ground_truth = np.ones(148)
for i in [43, 44, 45, 103, 132, 147]:
from os.path import dirname, exists, join
from os import makedirs, remove
import numpy as np
from sklearn.datasets.base import get_data_home
from sklearn.datasets.base import _fetch_remote
from sklearn.datasets.base import RemoteFileMetadata
from sklearn.datasets.base import _pkl_filepath
from sklearn.utils import _joblib
from sklearn.utils import check_random_state, Bunch
LIBRAS = RemoteFileMetadata(
filename='libras.data',
url=
'https://archive.ics.uci.edu/ml/machine-learning-databases/libras/movement_libras.data',
checksum=('97ebdaa6a9b28ab4a2cdd84b14f19a95'
'a7456a46137c362b65a0669eca3c3c4d'))
def fetch_uci_libras(data_home=None,
shuffle=False,
random_state=0,
download_if_missing=True):
"""Load the UCI libra data-set from AT&T (classification).
Download it if necessary.
================= =====================
Classes 15
Samples total 360
Dimensionality 90
from sklearn.datasets.base import _pkl_filepath
from sklearn.datasets.base import _fetch_remote
from sklearn.datasets.base import RemoteFileMetadata
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.preprocessing import normalize
from sklearn.utils import deprecated
from sklearn.utils import _joblib
from sklearn.utils import check_random_state, Bunch
logger = logging.getLogger(__name__)
# The original data can be found at:
# https://people.csail.mit.edu/jrennie/20Newsgroups/20news-bydate.tar.gz
ARCHIVE = RemoteFileMetadata(
filename='20news-bydate.tar.gz',
url='https://ndownloader.figshare.com/files/5975967',
checksum=('8f1b2514ca22a5ade8fbb9cfa5727df9'
'5fa587f4c87b786e15c759fa66d95610'))
CACHE_NAME = "20news-bydate.pkz"
TRAIN_FOLDER = "20news-bydate-train"
TEST_FOLDER = "20news-bydate-test"
@deprecated("Function 'download_20newsgroups' was renamed to "
"'_download_20newsgroups' in version 0.20 and will be removed in "
"release 0.22.")
def download_20newsgroups(target_dir, cache_path):
return _download_20newsgroups(target_dir, cache_path)