From 8994d0ef61f66228fadb142bba2a809178b81b39 Mon Sep 17 00:00:00 2001
From: Manvendra Singh <manu-chroma@users.noreply.github.com>
Date: Sun, 7 Aug 2016 18:37:07 +0530
Subject: [PATCH] [MRG+1] added return_X_y option to toy datasets in
sklearn.datasets (#7154)
* added return_X_y support to more dataset loaders
* fix typo
* updated whats_new.rst
* fix indentation for version added tag
* call astype before the branching
* better formatting in whats_new.rst
* better formatting
* updated what's new
---
doc/whats_new.rst | 13 +++--
sklearn/datasets/base.py | 79 +++++++++++++++++++++++++----
sklearn/datasets/tests/test_base.py | 26 ++++++++++
3 files changed, 104 insertions(+), 14 deletions(-)
diff --git a/doc/whats_new.rst b/doc/whats_new.rst
index a4154de9bd..eef97a178e 100644
--- a/doc/whats_new.rst
+++ b/doc/whats_new.rst
@@ -230,11 +230,16 @@ Enhancements
(`#6846 <https://github.com/scikit-learn/scikit-learn/pull/6846>`_)
By `Sebastian Säger`_ and `YenChen Lin`_.
- - Added new return type ``(data, target)`` : tuple option to
- :func:`load_iris` dataset,
- (`#7049 <https://github.com/scikit-learn/scikit-learn/pull/7049>`_)
+ - Added parameter ``return_X_y`` and return type ``(data, target) : tuple`` option to
+ :func:`load_iris` dataset
+ `#7049 <https://github.com/scikit-learn/scikit-learn/pull/7049>`_,
:func:`load_breast_cancer` dataset
- (`#7152 <https://github.com/scikit-learn/scikit-learn/pull/7152>`_) by
+ `#7152 <https://github.com/scikit-learn/scikit-learn/pull/7152>`_,
+ :func:`load_digits` dataset,
+ :func:`load_diabetes` dataset,
+ :func:`load_linnerud` dataset,
+ :func:`load_boston` dataset
+ `#7154 <https://github.com/scikit-learn/scikit-learn/pull/7154>`_ by
`Manvendra Singh`_.
Bug fixes
diff --git a/sklearn/datasets/base.py b/sklearn/datasets/base.py
index 3d6107268b..b5c7b4cd4f 100644
--- a/sklearn/datasets/base.py
+++ b/sklearn/datasets/base.py
@@ -264,7 +264,7 @@ def load_iris(return_X_y=False):
If True, returns ``(data, target)`` instead of a Bunch object.
See below for more information about the `data` and `target` object.
- .. versionadded:: 0.18
+ .. versionadded:: 0.18
Returns
-------
@@ -277,7 +277,7 @@ def load_iris(return_X_y=False):
(data, target) : tuple if ``return_X_y`` is True
- .. versionadded:: 0.18
+ .. versionadded:: 0.18
Examples
--------
@@ -338,7 +338,7 @@ def load_breast_cancer(return_X_y=False):
If True, returns ``(data, target)`` instead of a Bunch object.
See below for more information about the `data` and `target` object.
- .. versionadded:: 0.18
+ .. versionadded:: 0.18
Returns
-------
@@ -351,7 +351,7 @@ def load_breast_cancer(return_X_y=False):
(data, target) : tuple if ``return_X_y`` is True
- .. versionadded:: 0.18
+ .. versionadded:: 0.18
The copy of UCI ML Breast Cancer Wisconsin (Diagnostic) dataset is
downloaded from:
@@ -411,7 +411,7 @@ def load_breast_cancer(return_X_y=False):
feature_names=feature_names)
-def load_digits(n_class=10):
+def load_digits(n_class=10, return_X_y=False):
"""Load and return the digits dataset (classification).
Each datapoint is a 8x8 image of a digit.
@@ -431,6 +431,12 @@ def load_digits(n_class=10):
n_class : integer, between 0 and 10, optional (default=10)
The number of classes to return.
+ return_X_y : boolean, default=False.
+ If True, returns ``(data, target)`` instead of a Bunch object.
+ See below for more information about the `data` and `target` object.
+
+ .. versionadded:: 0.18
+
Returns
-------
data : Bunch
@@ -440,6 +446,10 @@ def load_digits(n_class=10):
sample, 'target_names', the meaning of the labels, and 'DESCR',
the full description of the dataset.
+ (data, target) : tuple if ``return_X_y`` is True
+
+ .. versionadded:: 0.18
+
Examples
--------
To load the data and visualize the images::
@@ -458,7 +468,7 @@ def load_digits(n_class=10):
delimiter=',')
with open(join(module_path, 'descr', 'digits.rst')) as f:
descr = f.read()
- target = data[:, -1]
+ target = data[:, -1].astype(np.int)
flat_data = data[:, :-1]
images = flat_data.view()
images.shape = (-1, 8, 8)
@@ -468,14 +478,17 @@ def load_digits(n_class=10):
flat_data, target = flat_data[idx], target[idx]
images = images[idx]
+ if return_X_y:
+ return flat_data, target
+
return Bunch(data=flat_data,
- target=target.astype(np.int),
+ target=target,
target_names=np.arange(10),
images=images,
DESCR=descr)
-def load_diabetes():
+def load_diabetes(return_X_y=False):
"""Load and return the diabetes dataset (regression).
============== ==================
@@ -487,20 +500,36 @@ def load_diabetes():
Read more in the :ref:`User Guide <datasets>`.
+ Parameters
+ ----------
+ return_X_y : boolean, default=False.
+ If True, returns ``(data, target)`` instead of a Bunch object.
+ See below for more information about the `data` and `target` object.
+
+ .. versionadded:: 0.18
+
Returns
-------
data : Bunch
Dictionary-like object, the interesting attributes are:
'data', the data to learn and 'target', the regression target for each
sample.
+
+ (data, target) : tuple if ``return_X_y`` is True
+
+ .. versionadded:: 0.18
"""
base_dir = join(dirname(__file__), 'data')
data = np.loadtxt(join(base_dir, 'diabetes_data.csv.gz'))
target = np.loadtxt(join(base_dir, 'diabetes_target.csv.gz'))
+
+ if return_X_y:
+ return data, target
+
return Bunch(data=data, target=target)
-def load_linnerud():
+def load_linnerud(return_X_y=False):
"""Load and return the linnerud dataset (multivariate regression).
Samples total: 20
@@ -508,6 +537,14 @@ def load_linnerud():
Features: integer
Targets: integer
+ Parameters
+ ----------
+ return_X_y : boolean, default=False.
+ If True, returns ``(data, target)`` instead of a Bunch object.
+ See below for more information about the `data` and `target` object.
+
+ .. versionadded:: 0.18
+
Returns
-------
data : Bunch
@@ -515,6 +552,10 @@ def load_linnerud():
'targets', the two multivariate datasets, with 'data' corresponding to
the exercise and 'targets' corresponding to the physiological
measurements, as well as 'feature_names' and 'target_names'.
+
+ (data, target) : tuple if ``return_X_y`` is True
+
+ .. versionadded:: 0.18
"""
base_dir = join(dirname(__file__), 'data/')
# Read data
@@ -529,13 +570,16 @@ def load_linnerud():
with open(dirname(__file__) + '/descr/linnerud.rst') as f:
descr = f.read()
+ if return_X_y:
+ return data_exercise, data_physiological
+
return Bunch(data=data_exercise, feature_names=header_exercise,
target=data_physiological,
target_names=header_physiological,
DESCR=descr)
-def load_boston():
+def load_boston(return_X_y=False):
"""Load and return the boston house-prices dataset (regression).
============== ==============
@@ -545,6 +589,14 @@ def load_boston():
Targets real 5. - 50.
============== ==============
+ Parameters
+ ----------
+ return_X_y : boolean, default=False.
+ If True, returns ``(data, target)`` instead of a Bunch object.
+ See below for more information about the `data` and `target` object.
+
+ .. versionadded:: 0.18
+
Returns
-------
data : Bunch
@@ -552,6 +604,10 @@ def load_boston():
'data', the data to learn, 'target', the regression targets,
and 'DESCR', the full description of the dataset.
+ (data, target) : tuple if ``return_X_y`` is True
+
+ .. versionadded:: 0.18
+
Examples
--------
>>> from sklearn.datasets import load_boston
@@ -580,6 +636,9 @@ def load_boston():
data[i] = np.asarray(d[:-1], dtype=np.float64)
target[i] = np.asarray(d[-1], dtype=np.float64)
+ if return_X_y:
+ return data, target
+
return Bunch(data=data,
target=target,
# last column is target value
diff --git a/sklearn/datasets/tests/test_base.py b/sklearn/datasets/tests/test_base.py
index 6be9b399e1..523d5fcd8c 100644
--- a/sklearn/datasets/tests/test_base.py
+++ b/sklearn/datasets/tests/test_base.py
@@ -128,6 +128,13 @@ def test_load_digits():
assert_equal(digits.data.shape, (1797, 64))
assert_equal(numpy.unique(digits.target).size, 10)
+ # test return_X_y option
+ X_y_tuple = load_digits(return_X_y=True)
+ bunch = load_digits()
+ assert_true(isinstance(X_y_tuple, tuple))
+ assert_array_equal(X_y_tuple[0], bunch.data)
+ assert_array_equal(X_y_tuple[1], bunch.target)
+
def test_load_digits_n_class_lt_10():
digits = load_digits(9)
@@ -165,6 +172,13 @@ def test_load_diabetes():
assert_equal(res.data.shape, (442, 10))
assert_true(res.target.size, 442)
+ # test return_X_y option
+ X_y_tuple = load_diabetes(return_X_y=True)
+ bunch = load_diabetes()
+ assert_true(isinstance(X_y_tuple, tuple))
+ assert_array_equal(X_y_tuple[0], bunch.data)
+ assert_array_equal(X_y_tuple[1], bunch.target)
+
def test_load_linnerud():
res = load_linnerud()
@@ -173,6 +187,12 @@ def test_load_linnerud():
assert_equal(len(res.target_names), 3)
assert_true(res.DESCR)
+ # test return_X_y option
+ X_y_tuple = load_linnerud(return_X_y=True)
+ bunch = load_linnerud()
+ assert_true(isinstance(X_y_tuple, tuple))
+ assert_array_equal(X_y_tuple[0], bunch.data)
+ assert_array_equal(X_y_tuple[1], bunch.target)
def test_load_iris():
res = load_iris()
@@ -211,6 +231,12 @@ def test_load_boston():
assert_equal(res.feature_names.size, 13)
assert_true(res.DESCR)
+ # test return_X_y option
+ X_y_tuple = load_boston(return_X_y=True)
+ bunch = load_boston()
+ assert_true(isinstance(X_y_tuple, tuple))
+ assert_array_equal(X_y_tuple[0], bunch.data)
+ assert_array_equal(X_y_tuple[1], bunch.target)
def test_loads_dumps_bunch():
bunch = Bunch(x="x")
--
GitLab