1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
|
"""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.
"""
# Authors: Peter Prettenhofer
# License: BSD 3 clause
from os.path import dirname, exists, join
from os import makedirs, remove
import tarfile
import numpy as np
import logging
from .base import get_data_home
from .base import _fetch_remote
from .base import _pkl_filepath
from .base import RemoteFileMetadata
from ..utils import Bunch
from ..utils import _joblib
# The original data can be found at:
# http://www.dcc.fc.up.pt/~ltorgo/Regression/cal_housing.tgz
ARCHIVE = RemoteFileMetadata(
filename='cal_housing.tgz',
url='https://ndownloader.figshare.com/files/5976036',
checksum=('aaa5c9a6afe2225cc2aed2723682ae40'
'3280c4a3695a2ddda4ffb5d8215ea681'))
logger = logging.getLogger(__name__)
def fetch_california_housing(data_home=None, download_if_missing=True,
return_X_y=False):
"""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 <california_housing_dataset>`.
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.
"""
data_home = get_data_home(data_home=data_home)
if not exists(data_home):
makedirs(data_home)
filepath = _pkl_filepath(data_home, 'cal_housing.pkz')
if not exists(filepath):
if not download_if_missing:
raise IOError("Data not found and `download_if_missing` is False")
logger.info('Downloading Cal. housing from {} to {}'.format(
ARCHIVE.url, data_home))
archive_path = _fetch_remote(ARCHIVE, dirname=data_home)
with tarfile.open(mode="r:gz", name=archive_path) as f:
cal_housing = np.loadtxt(
f.extractfile('CaliforniaHousing/cal_housing.data'),
delimiter=',')
# Columns are not in the same order compared to the previous
# URL resource on lib.stat.cmu.edu
columns_index = [8, 7, 2, 3, 4, 5, 6, 1, 0]
cal_housing = cal_housing[:, columns_index]
_joblib.dump(cal_housing, filepath, compress=6)
remove(archive_path)
else:
cal_housing = _joblib.load(filepath)
feature_names = ["MedInc", "HouseAge", "AveRooms", "AveBedrms",
"Population", "AveOccup", "Latitude", "Longitude"]
target, data = cal_housing[:, 0], cal_housing[:, 1:]
# avg rooms = total rooms / households
data[:, 2] /= data[:, 5]
# avg bed rooms = total bed rooms / households
data[:, 3] /= data[:, 5]
# avg occupancy = population / households
data[:, 5] = data[:, 4] / data[:, 5]
# target in units of 100,000
target = target / 100000.0
module_path = dirname(__file__)
with open(join(module_path, 'descr', 'california_housing.rst')) as dfile:
descr = dfile.read()
if return_X_y:
return data, target
return Bunch(data=data,
target=target,
feature_names=feature_names,
DESCR=descr)
|
