diff --git a/scikits/learn/datasets/__init__.py b/scikits/learn/datasets/__init__.py
index e69de29bb2d1d6434b8b29ae775ad8c2e48c5391..d89713f7dfcbdee04d867a88c89cf1eab9e8c2b2 100644
--- a/scikits/learn/datasets/__init__.py
+++ b/scikits/learn/datasets/__init__.py
@@ -0,0 +1 @@
+from base import load
diff --git a/scikits/learn/datasets/base.py b/scikits/learn/datasets/base.py
new file mode 100644
index 0000000000000000000000000000000000000000..a92f85f73c7745e2a6db3894c4d34b2bc8ffa36c
--- /dev/null
+++ b/scikits/learn/datasets/base.py
@@ -0,0 +1,65 @@
+"""
+Base object for all datasets
+"""
+
+# Copyright (c) 2007 David Cournapeau <cournape@gmail.com>
+# 2010 Fabian Pedregosa <fabian.pedregosa@inria.fr>
+#
+
+
+import numpy as np
+
+class Bunch(dict):
+ """
+ Container for dataset.
+
+ Members
+ -------
+ - data : a record array with the actual data
+ - label : label[i] = label index of data[i]
+ - class : class[i] is the string corresponding to label index i.
+ - COPYRIGHT, TITLE, SOURCE, DESCRSHORT, DESCRLONG,
+ NOTE. Information about the dataset.
+ """
+
+ def __init__(self, **kwargs):
+ dict.__init__(self, kwargs)
+ self.__dict__ = self
+
+def load(dataset):
+ """load the data and returns them.
+
+ Returns
+ -------
+ data : Bunch
+ See docstring of bunch for a complete description of its members.
+
+ Available datasets
+ - iris
+
+ Example
+ -------
+ Let's say you are interested in the samples 10, 25, and 50, and want to
+ know their class name.
+
+ >>> data = load()
+ >>> print data.label #doctest: +ELLIPSIS
+ [ 0. 0. ...]
+ """
+ import csv
+ import os
+ DESCR = ''
+
+ firis = csv.reader(open(os.path.dirname(__file__) + '/data/%s.csv' % dataset))
+ fdescr = open(os.path.dirname(__file__) + '/descr/%s.rst' % dataset)
+ temp = firis.next()
+ nsamples = int(temp[0])
+ nfeat = int(temp[1])
+ labelnames = temp[2:]
+ data = np.empty((nsamples, nfeat))
+ label = np.empty((nsamples,))
+ for i, ir in enumerate(firis):
+ data[i] = np.asanyarray(ir[:-1], dtype=np.float)
+ label[i] = np.asanyarray(ir[-1], dtype=np.int)
+ return Bunch(data = data, label=label, labelnames=labelnames, DESCR=fdescr.read())
+
diff --git a/scikits/learn/datasets/data/iris.csv b/scikits/learn/datasets/data/iris.csv
new file mode 100644
index 0000000000000000000000000000000000000000..3f521bf33e1cf08cbe28b213fd9fc565a8e488c8
--- /dev/null
+++ b/scikits/learn/datasets/data/iris.csv
@@ -0,0 +1,151 @@
+150, 4, setosa, versicolor, virginica
+5.1,3.5,1.4,0.2,0
+4.9,3.0,1.4,0.2,0
+4.7,3.2,1.3,0.2,0
+4.6,3.1,1.5,0.2,0
+5.0,3.6,1.4,0.2,0
+5.4,3.9,1.7,0.4,0
+4.6,3.4,1.4,0.3,0
+5.0,3.4,1.5,0.2,0
+4.4,2.9,1.4,0.2,0
+4.9,3.1,1.5,0.1,0
+5.4,3.7,1.5,0.2,0
+4.8,3.4,1.6,0.2,0
+4.8,3.0,1.4,0.1,0
+4.3,3.0,1.1,0.1,0
+5.8,4.0,1.2,0.2,0
+5.7,4.4,1.5,0.4,0
+5.4,3.9,1.3,0.4,0
+5.1,3.5,1.4,0.3,0
+5.7,3.8,1.7,0.3,0
+5.1,3.8,1.5,0.3,0
+5.4,3.4,1.7,0.2,0
+5.1,3.7,1.5,0.4,0
+4.6,3.6,1.0,0.2,0
+5.1,3.3,1.7,0.5,0
+4.8,3.4,1.9,0.2,0
+5.0,3.0,1.6,0.2,0
+5.0,3.4,1.6,0.4,0
+5.2,3.5,1.5,0.2,0
+5.2,3.4,1.4,0.2,0
+4.7,3.2,1.6,0.2,0
+4.8,3.1,1.6,0.2,0
+5.4,3.4,1.5,0.4,0
+5.2,4.1,1.5,0.1,0
+5.5,4.2,1.4,0.2,0
+4.9,3.1,1.5,0.1,0
+5.0,3.2,1.2,0.2,0
+5.5,3.5,1.3,0.2,0
+4.9,3.1,1.5,0.1,0
+4.4,3.0,1.3,0.2,0
+5.1,3.4,1.5,0.2,0
+5.0,3.5,1.3,0.3,0
+4.5,2.3,1.3,0.3,0
+4.4,3.2,1.3,0.2,0
+5.0,3.5,1.6,0.6,0
+5.1,3.8,1.9,0.4,0
+4.8,3.0,1.4,0.3,0
+5.1,3.8,1.6,0.2,0
+4.6,3.2,1.4,0.2,0
+5.3,3.7,1.5,0.2,0
+5.0,3.3,1.4,0.2,0
+7.0,3.2,4.7,1.4,1
+6.4,3.2,4.5,1.5,1
+6.9,3.1,4.9,1.5,1
+5.5,2.3,4.0,1.3,1
+6.5,2.8,4.6,1.5,1
+5.7,2.8,4.5,1.3,1
+6.3,3.3,4.7,1.6,1
+4.9,2.4,3.3,1.0,1
+6.6,2.9,4.6,1.3,1
+5.2,2.7,3.9,1.4,1
+5.0,2.0,3.5,1.0,1
+5.9,3.0,4.2,1.5,1
+6.0,2.2,4.0,1.0,1
+6.1,2.9,4.7,1.4,1
+5.6,2.9,3.6,1.3,1
+6.7,3.1,4.4,1.4,1
+5.6,3.0,4.5,1.5,1
+5.8,2.7,4.1,1.0,1
+6.2,2.2,4.5,1.5,1
+5.6,2.5,3.9,1.1,1
+5.9,3.2,4.8,1.8,1
+6.1,2.8,4.0,1.3,1
+6.3,2.5,4.9,1.5,1
+6.1,2.8,4.7,1.2,1
+6.4,2.9,4.3,1.3,1
+6.6,3.0,4.4,1.4,1
+6.8,2.8,4.8,1.4,1
+6.7,3.0,5.0,1.7,1
+6.0,2.9,4.5,1.5,1
+5.7,2.6,3.5,1.0,1
+5.5,2.4,3.8,1.1,1
+5.5,2.4,3.7,1.0,1
+5.8,2.7,3.9,1.2,1
+6.0,2.7,5.1,1.6,1
+5.4,3.0,4.5,1.5,1
+6.0,3.4,4.5,1.6,1
+6.7,3.1,4.7,1.5,1
+6.3,2.3,4.4,1.3,1
+5.6,3.0,4.1,1.3,1
+5.5,2.5,4.0,1.3,1
+5.5,2.6,4.4,1.2,1
+6.1,3.0,4.6,1.4,1
+5.8,2.6,4.0,1.2,1
+5.0,2.3,3.3,1.0,1
+5.6,2.7,4.2,1.3,1
+5.7,3.0,4.2,1.2,1
+5.7,2.9,4.2,1.3,1
+6.2,2.9,4.3,1.3,1
+5.1,2.5,3.0,1.1,1
+5.7,2.8,4.1,1.3,1
+6.3,3.3,6.0,2.5,2
+5.8,2.7,5.1,1.9,2
+7.1,3.0,5.9,2.1,2
+6.3,2.9,5.6,1.8,2
+6.5,3.0,5.8,2.2,2
+7.6,3.0,6.6,2.1,2
+4.9,2.5,4.5,1.7,2
+7.3,2.9,6.3,1.8,2
+6.7,2.5,5.8,1.8,2
+7.2,3.6,6.1,2.5,2
+6.5,3.2,5.1,2.0,2
+6.4,2.7,5.3,1.9,2
+6.8,3.0,5.5,2.1,2
+5.7,2.5,5.0,2.0,2
+5.8,2.8,5.1,2.4,2
+6.4,3.2,5.3,2.3,2
+6.5,3.0,5.5,1.8,2
+7.7,3.8,6.7,2.2,2
+7.7,2.6,6.9,2.3,2
+6.0,2.2,5.0,1.5,2
+6.9,3.2,5.7,2.3,2
+5.6,2.8,4.9,2.0,2
+7.7,2.8,6.7,2.0,2
+6.3,2.7,4.9,1.8,2
+6.7,3.3,5.7,2.1,2
+7.2,3.2,6.0,1.8,2
+6.2,2.8,4.8,1.8,2
+6.1,3.0,4.9,1.8,2
+6.4,2.8,5.6,2.1,2
+7.2,3.0,5.8,1.6,2
+7.4,2.8,6.1,1.9,2
+7.9,3.8,6.4,2.0,2
+6.4,2.8,5.6,2.2,2
+6.3,2.8,5.1,1.5,2
+6.1,2.6,5.6,1.4,2
+7.7,3.0,6.1,2.3,2
+6.3,3.4,5.6,2.4,2
+6.4,3.1,5.5,1.8,2
+6.0,3.0,4.8,1.8,2
+6.9,3.1,5.4,2.1,2
+6.7,3.1,5.6,2.4,2
+6.9,3.1,5.1,2.3,2
+5.8,2.7,5.1,1.9,2
+6.8,3.2,5.9,2.3,2
+6.7,3.3,5.7,2.5,2
+6.7,3.0,5.2,2.3,2
+6.3,2.5,5.0,1.9,2
+6.5,3.0,5.2,2.0,2
+6.2,3.4,5.4,2.3,2
+5.9,3.0,5.1,1.8,2
diff --git a/scikits/learn/datasets/descr/iris.rst b/scikits/learn/datasets/descr/iris.rst
new file mode 100644
index 0000000000000000000000000000000000000000..62a2d8e48404beb4da452a71bd95a173d69dd6ee
--- /dev/null
+++ b/scikits/learn/datasets/descr/iris.rst
@@ -0,0 +1,69 @@
+Iris Plants Database
+
+Source
+------
+Creator: R.A. Fisher
+Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
+Date: July, 1988
+
+This is a copy of UCI ML iris datasets.
+
+The famous Iris database, first used by Sir R.A Fisher
+
+This is perhaps the best known database to be found in the
+pattern recognition literature. Fisher's paper is a classic in the field and
+is referenced frequently to this day. (See Duda & Hart, for example.) The
+data set contains 3 classes of 50 instances each, where each class refers to a
+type of iris plant. One class is linearly separable from the other 2; the
+latter are NOT linearly separable from each other.
+
+
+References
+----------
+
+ - Fisher,R.A. "The use of multiple measurements in taxonomic problems"
+ Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
+ Mathematical Statistics" (John Wiley, NY, 1950).
+ - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
+ (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
+ - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
+ Structure and Classification Rule for Recognition in Partially Exposed
+ Environments". IEEE Transactions on Pattern Analysis and Machine
+ Intelligence, Vol. PAMI-2, No. 1, 67-71.
+ - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
+ on Information Theory, May 1972, 431-433.
+ - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al"s AUTOCLASS II
+ conceptual clustering system finds 3 classes in the data.
+ - Many, many more ...
+
+
+Number of Instances: 150 (50 in each of three classes)
+
+Number of Attributes: 4 numeric, predictive attributes and the class
+
+Attribute Information:
+ - sepal length in cm
+ - sepal width in cm
+ - petal length in cm
+ - petal width in cm
+ - class:
+ - Iris-Setosa
+ - Iris-Versicolour
+ - Iris-Virginica
+
+Summary Statistics:
+ Min Max Mean SD Class Correlation
+ sepal length: 4.3 7.9 5.84 0.83 0.7826
+ sepal width: 2.0 4.4 3.05 0.43 -0.4194
+ petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
+ petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
+
+Missing Attribute Values: None
+
+Class Distribution: 33.3% for each of 3 classes.
+
+Example
+-------
+ >>> data = load()
+ >>> print data.label #doctest: +ELLIPSIS
+ [ 0. 0. ...][ 0. 0. ...]
diff --git a/scikits/learn/datasets/iris.py b/scikits/learn/datasets/iris.py
new file mode 100644
index 0000000000000000000000000000000000000000..59b8cac70e498e69fb093c42a17d8122c5a9dc6a
--- /dev/null
+++ b/scikits/learn/datasets/iris.py
@@ -0,0 +1,92 @@
+#! /usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# The code and descriptive text is copyrighted and offered under the terms of
+# the BSD License from the authors; see below. However, the actual dataset may
+# have a different origin and intellectual property status. See the SOURCE and
+# COPYRIGHT variables for this information.
+
+# Copyright (c) 2007 David Cournapeau <cournape@gmail.com>
+# 2010 Fabian Pedregosa <fabian.pedregosa@inria.fr>
+#
+Iris Plants Database
+
+Creator: R.A. Fisher
+Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
+Date: July, 1988
+
+This is a copy of UCI ML iris datasets.
+
+References:
+ - Fisher,R.A. 'The use of multiple measurements in taxonomic problems'
+ Annual Eugenics, 7, Part II, 179-188 (1936); also in 'Contributions to
+ Mathematical Statistics' (John Wiley, NY, 1950).
+ - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
+ (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
+ - Dasarathy, B.V. (1980) 'Nosing Around the Neighborhood: A New System
+ Structure and Classification Rule for Recognition in Partially Exposed
+ Environments'. IEEE Transactions on Pattern Analysis and Machine
+ Intelligence, Vol. PAMI-2, No. 1, 67-71.
+ - Gates, G.W. (1972) 'The Reduced Nearest Neighbor Rule'. IEEE Transactions
+ on Information Theory, May 1972, 431-433.
+ - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al's AUTOCLASS II
+ conceptual clustering system finds 3 classes in the data.
+ - Many, many more
+ """
+
+DESCR = """
+The famous Iris database, first used by Sir R.A Fisher
+
+This is perhaps the best known database to be found in the
+pattern recognition literature. Fisher's paper is a classic in the field and
+is referenced frequently to this day. (See Duda & Hart, for example.) The
+data set contains 3 classes of 50 instances each, where each class refers to a
+type of iris plant. One class is linearly separable from the other 2; the
+latter are NOT linearly separable from each other.
+
+Number of Instances: 150 (50 in each of three classes)
+
+Number of Attributes: 4 numeric, predictive attributes and the class
+
+Attribute Information:
+ - sepal length in cm
+ - sepal width in cm
+ - petal length in cm
+ - petal width in cm
+ - class:
+ - Iris-Setosa
+ - Iris-Versicolour
+ - Iris-Virginica
+
+Summary Statistics:
+ Min Max Mean SD Class Correlation
+ sepal length: 4.3 7.9 5.84 0.83 0.7826
+ sepal width: 2.0 4.4 3.05 0.43 -0.4194
+ petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
+ petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
+
+Missing Attribute Values: None
+
+Class Distribution: 33.3% for each of 3 classes.
+"""
+
+import numpy as np
+from .base import Bunch
+
+def load():
+ """load the iris data and returns them.
+
+ Returns
+ -------
+ iris : Bunch
+ See docstring of bunch for a complete description of its members.
+
+ Example
+ -------
+ Let's say you are interested in the samples 10, 25, and 50, and want to
+ know their class name.
+
+ >>> data = load()
+ >>> print data.label #doctest: +ELLIPSIS
+ [ 0. 0. ...][ 0. 0. ...]
+ """
diff --git a/scikits/learn/datasets/iris/COPYING b/scikits/learn/datasets/iris/COPYING
deleted file mode 100644
index 465e793f163956fa6218b782b8197e06677cdcdd..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/COPYING
+++ /dev/null
@@ -1,34 +0,0 @@
-# The code and descriptive text is copyrighted and offered under the terms of
-# the BSD License from the authors; see below. However, the actual dataset may
-# have a different origin and intellectual property status. See the SOURCE and
-# COPYRIGHT variables for this information.
-
-# Copyright (c) 2007 David Cournapeau <cournape@gmail.com>
-#
-# All rights reserved.
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions are
-# met:
-#
-# * Redistributions of source code must retain the above copyright
-# notice, this list of conditions and the following disclaimer.
-# * Redistributions in binary form must reproduce the above copyright
-# notice, this list of conditions and the following disclaimer in
-# the documentation and/or other materials provided with the
-# distribution.
-# * Neither the author nor the names of any contributors may be used
-# to endorse or promote products derived from this software without
-# specific prior written permission.
-#
-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
-# TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
-# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
-# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
-# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
-# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
-# ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
diff --git a/scikits/learn/datasets/iris/__init__.py b/scikits/learn/datasets/iris/__init__.py
deleted file mode 100644
index 11f79492c6bf831645979d0881e96f5666710413..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/__init__.py
+++ /dev/null
@@ -1,10 +0,0 @@
-#! /usr/bin/env python
-# Last Change: Mon Jul 02 02:00 PM 2007 J
-import data as _iris
-__doc__ = _iris.DESCRSHORT
-copyright = _iris.COPYRIGHT
-source = _iris.SOURCE
-
-load = _iris.load
-
-all = ['load', 'copyright', 'source']
diff --git a/scikits/learn/datasets/iris/data.py b/scikits/learn/datasets/iris/data.py
deleted file mode 100644
index 444a9ecbc7b7c6a434bf961c6362b0875049b382..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/data.py
+++ /dev/null
@@ -1,128 +0,0 @@
-#! /usr/bin/env python
-# -*- coding: utf-8 -*-
-# Last Change: Tue Jul 17 04:00 PM 2007 J
-
-# The code and descriptive text is copyrighted and offered under the terms of
-# the BSD License from the authors; see below. However, the actual dataset may
-# have a different origin and intellectual property status. See the SOURCE and
-# COPYRIGHT variables for this information.
-
-# Copyright (c) 2007 David Cournapeau <cournape@gmail.com>
-#
-# All rights reserved.
-#
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions are
-# met:
-#
-# * Redistributions of source code must retain the above copyright
-# notice, this list of conditions and the following disclaimer.
-# * Redistributions in binary form must reproduce the above copyright
-# notice, this list of conditions and the following disclaimer in
-# the documentation and/or other materials provided with the
-# distribution.
-# * Neither the author nor the names of any contributors may be used
-# to endorse or promote products derived from this software without
-# specific prior written permission.
-#
-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED
-# TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
-# PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
-# CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
-# EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
-# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
-# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
-# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
-# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
-# ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-"""Iris dataset."""
-
-__docformat__ = 'restructuredtext'
-
-COPYRIGHT = """See SOURCE. """
-TITLE = "Iris Plants Database"
-SOURCE = """Creator: R.A. Fisher
-Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
-Date: July, 1988
-
-This is a copy of UCI ML iris datasets, except that the data are in mm instead
-of cm, so that exact values as int can be given.
-
-References:
- - Fisher,R.A. "The use of multiple measurements in taxonomic problems"
- Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions to
- Mathematical Statistics" (John Wiley, NY, 1950).
- - Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
- (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- - Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
- Structure and Classification Rule for Recognition in Partially Exposed
- Environments". IEEE Transactions on Pattern Analysis and Machine
- Intelligence, Vol. PAMI-2, No. 1, 67-71.
- - Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE Transactions
- on Information Theory, May 1972, 431-433.
- - See also: 1988 MLC Proceedings, 54-64. Cheeseman et al's AUTOCLASS II
- conceptual clustering system finds 3 classes in the data."""
-
-DESCRSHORT = """The famous Iris database, first used by Sir R.A Fisher"""
-
-DESCRLONG = """This is perhaps the best known database to be found in the
-pattern recognition literature. Fisher's paper is a classic in the field and
-is referenced frequently to this day. (See Duda & Hart, for example.) The
-data set contains 3 classes of 50 instances each, where each class refers to a
-type of iris plant. One class is linearly separable from the other 2; the
-latter are NOT linearly separable from each other. """
-
-NOTE = """
-Number of Instances: 150 (50 in each of three classes)
-
-Number of Attributes: 4 numeric, predictive attributes and the class
-
-Attribute Information:
- - sepal length in mm
- - sepal width in mm
- - petal length in mm
- - petal width in mm
- - class:
- - Iris-Setosa
- - Iris-Versicolour
- - Iris-Virginica
-
-Missing Attribute Values: None
-
-Class Distribution: 33.3% for each of 3 classes.
-"""
-
-import numpy as np
-
-
-def load():
- """load the iris data and returns them.
-
- :returns:
- d : dict
- contains the following values:
- - 'data' : a record array with the actual data
- - 'label' : label[i] = label index of data[i]
- - 'class' : class[i] is the string corresponding to label index i.
-
- Example
- -------
-
- Let's say you are interested in the samples 10, 25, and 50, and want to
- know their class name.
-
- >>>> d = load()
- # >>>> ind = [10, 25, 50]
- # >>>> lind = d['label'][ind] # returns the label index of each sample
- # >>>> d['class'][lind] # returns the class name of each sample
-
- """
- from iris import SL, SW, PL, PW, labels, LI2LN
- PW = np.array(PW, dtype=np.float)
- PL = np.array(PL, dtype=np.float)
- SW = np.array(SW, dtype=np.float)
- SL = np.array(SL, dtype=np.float)
- labels = np.array(labels, dtype=np.int)
- return PW, PL, SW, SL, labels
diff --git a/scikits/learn/datasets/iris/iris.py b/scikits/learn/datasets/iris/iris.py
deleted file mode 100644
index 13ff411eac62740b94583fdc3c0ec517295ec6e3..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/iris.py
+++ /dev/null
@@ -1,71 +0,0 @@
-# Autogenerated by convert.py at Tue, 17 Jul 2007 06:47:17 +0000
-
-SL = ['5.1', '4.9', '4.7', '4.6', '5.0', '5.4', '4.6', '5.0', '4.4', '4.9',
-'5.4', '4.8', '4.8', '4.3', '5.8', '5.7', '5.4', '5.1', '5.7', '5.1', '5.4',
-'5.1', '4.6', '5.1', '4.8', '5.0', '5.0', '5.2', '5.2', '4.7', '4.8', '5.4',
-'5.2', '5.5', '4.9', '5.0', '5.5', '4.9', '4.4', '5.1', '5.0', '4.5', '4.4',
-'5.0', '5.1', '4.8', '5.1', '4.6', '5.3', '5.0', '7.0', '6.4', '6.9', '5.5',
-'6.5', '5.7', '6.3', '4.9', '6.6', '5.2', '5.0', '5.9', '6.0', '6.1', '5.6',
-'6.7', '5.6', '5.8', '6.2', '5.6', '5.9', '6.1', '6.3', '6.1', '6.4', '6.6',
-'6.8', '6.7', '6.0', '5.7', '5.5', '5.5', '5.8', '6.0', '5.4', '6.0', '6.7',
-'6.3', '5.6', '5.5', '5.5', '6.1', '5.8', '5.0', '5.6', '5.7', '5.7', '6.2',
-'5.1', '5.7', '6.3', '5.8', '7.1', '6.3', '6.5', '7.6', '4.9', '7.3', '6.7',
-'7.2', '6.5', '6.4', '6.8', '5.7', '5.8', '6.4', '6.5', '7.7', '7.7', '6.0',
-'6.9', '5.6', '7.7', '6.3', '6.7', '7.2', '6.2', '6.1', '6.4', '7.2', '7.4',
-'7.9', '6.4', '6.3', '6.1', '7.7', '6.3', '6.4', '6.0', '6.9', '6.7', '6.9',
-'5.8', '6.8', '6.7', '6.7', '6.3', '6.5', '6.2', '5.9']
-
-SW = ['3.5', '3.0', '3.2', '3.1', '3.6', '3.9', '3.4', '3.4', '2.9', '3.1',
-'3.7', '3.4', '3.0', '3.0', '4.0', '4.4', '3.9', '3.5', '3.8', '3.8', '3.4',
-'3.7', '3.6', '3.3', '3.4', '3.0', '3.4', '3.5', '3.4', '3.2', '3.1', '3.4',
-'4.1', '4.2', '3.1', '3.2', '3.5', '3.1', '3.0', '3.4', '3.5', '2.3', '3.2',
-'3.5', '3.8', '3.0', '3.8', '3.2', '3.7', '3.3', '3.2', '3.2', '3.1', '2.3',
-'2.8', '2.8', '3.3', '2.4', '2.9', '2.7', '2.0', '3.0', '2.2', '2.9', '2.9',
-'3.1', '3.0', '2.7', '2.2', '2.5', '3.2', '2.8', '2.5', '2.8', '2.9', '3.0',
-'2.8', '3.0', '2.9', '2.6', '2.4', '2.4', '2.7', '2.7', '3.0', '3.4', '3.1',
-'2.3', '3.0', '2.5', '2.6', '3.0', '2.6', '2.3', '2.7', '3.0', '2.9', '2.9',
-'2.5', '2.8', '3.3', '2.7', '3.0', '2.9', '3.0', '3.0', '2.5', '2.9', '2.5',
-'3.6', '3.2', '2.7', '3.0', '2.5', '2.8', '3.2', '3.0', '3.8', '2.6', '2.2',
-'3.2', '2.8', '2.8', '2.7', '3.3', '3.2', '2.8', '3.0', '2.8', '3.0', '2.8',
-'3.8', '2.8', '2.8', '2.6', '3.0', '3.4', '3.1', '3.0', '3.1', '3.1', '3.1',
-'2.7', '3.2', '3.3', '3.0', '2.5', '3.0', '3.4', '3.0']
-
-PL = ['1.4', '1.4', '1.3', '1.5', '1.4', '1.7', '1.4', '1.5', '1.4', '1.5',
-'1.5', '1.6', '1.4', '1.1', '1.2', '1.5', '1.3', '1.4', '1.7', '1.5', '1.7',
-'1.5', '1.0', '1.7', '1.9', '1.6', '1.6', '1.5', '1.4', '1.6', '1.6', '1.5',
-'1.5', '1.4', '1.5', '1.2', '1.3', '1.5', '1.3', '1.5', '1.3', '1.3', '1.3',
-'1.6', '1.9', '1.4', '1.6', '1.4', '1.5', '1.4', '4.7', '4.5', '4.9', '4.0',
-'4.6', '4.5', '4.7', '3.3', '4.6', '3.9', '3.5', '4.2', '4.0', '4.7', '3.6',
-'4.4', '4.5', '4.1', '4.5', '3.9', '4.8', '4.0', '4.9', '4.7', '4.3', '4.4',
-'4.8', '5.0', '4.5', '3.5', '3.8', '3.7', '3.9', '5.1', '4.5', '4.5', '4.7',
-'4.4', '4.1', '4.0', '4.4', '4.6', '4.0', '3.3', '4.2', '4.2', '4.2', '4.3',
-'3.0', '4.1', '6.0', '5.1', '5.9', '5.6', '5.8', '6.6', '4.5', '6.3', '5.8',
-'6.1', '5.1', '5.3', '5.5', '5.0', '5.1', '5.3', '5.5', '6.7', '6.9', '5.0',
-'5.7', '4.9', '6.7', '4.9', '5.7', '6.0', '4.8', '4.9', '5.6', '5.8', '6.1',
-'6.4', '5.6', '5.1', '5.6', '6.1', '5.6', '5.5', '4.8', '5.4', '5.6', '5.1',
-'5.1', '5.9', '5.7', '5.2', '5.0', '5.2', '5.4', '5.1']
-
-PW = ['0.2', '0.2', '0.2', '0.2', '0.2', '0.4', '0.3', '0.2', '0.2', '0.1',
-'0.2', '0.2', '0.1', '0.1', '0.2', '0.4', '0.4', '0.3', '0.3', '0.3', '0.2',
-'0.4', '0.2', '0.5', '0.2', '0.2', '0.4', '0.2', '0.2', '0.2', '0.2', '0.4',
-'0.1', '0.2', '0.1', '0.2', '0.2', '0.1', '0.2', '0.2', '0.3', '0.3', '0.2',
-'0.6', '0.4', '0.3', '0.2', '0.2', '0.2', '0.2', '1.4', '1.5', '1.5', '1.3',
-'1.5', '1.3', '1.6', '1.0', '1.3', '1.4', '1.0', '1.5', '1.0', '1.4', '1.3',
-'1.4', '1.5', '1.0', '1.5', '1.1', '1.8', '1.3', '1.5', '1.2', '1.3', '1.4',
-'1.4', '1.7', '1.5', '1.0', '1.1', '1.0', '1.2', '1.6', '1.5', '1.6', '1.5',
-'1.3', '1.3', '1.3', '1.2', '1.4', '1.2', '1.0', '1.3', '1.2', '1.3', '1.3',
-'1.1', '1.3', '2.5', '1.9', '2.1', '1.8', '2.2', '2.1', '1.7', '1.8', '1.8',
-'2.5', '2.0', '1.9', '2.1', '2.0', '2.4', '2.3', '1.8', '2.2', '2.3', '1.5',
-'2.3', '2.0', '2.0', '1.8', '2.1', '1.8', '1.8', '1.8', '2.1', '1.6', '1.9',
-'2.0', '2.2', '1.5', '1.4', '2.3', '2.4', '1.8', '1.8', '2.1', '2.4', '2.3',
-'1.9', '2.3', '2.5', '2.3', '1.9', '2.0', '2.3', '1.8']
-
-labels = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2,
-2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
-2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2]
-
-LI2LN = {0: 'Iris-setosa', 1: 'Iris-versicolor', 2: 'Iris-virginica'}
-
diff --git a/scikits/learn/datasets/iris/src/convert.py b/scikits/learn/datasets/iris/src/convert.py
deleted file mode 100755
index 86111fd77ce3b4cd9779ddf666045dc2fc287ebd..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/src/convert.py
+++ /dev/null
@@ -1,44 +0,0 @@
-#! /usr/bin/env python
-# Last Change: Tue Jul 17 03:00 PM 2007 J
-
-# This script generates a python file from the txt data
-import time
-import csv
-
-from scikits.learn.datasets.misc import dumpvar
-
-# array for equivalence label index <> label name
-ln2li = {'Iris-setosa' : 0, 'Iris-versicolor': 1, 'Iris-virginica' :2}
-li2ln = {}
-for c,i in ln2li.items():
- li2ln[i] = c
-
-# Load the data
-dataname = 'iris.data'
-f = open(dataname, 'r')
-a = csv.reader(f)
-el = [i for i in a]
-# Remove last value corresponding to empty line in data file
-el.remove(el[-1])
-assert len(el) == 150
-
-sl = [i[0] for i in el]
-sw = [i[1] for i in el]
-pl = [i[2] for i in el]
-pw = [i[3] for i in el]
-cl = [i[4] for i in el]
-
-# dcl[i] = label index of data[i]
-dcl = [ln2li[i] for i in cl]
-
-# Write the data in oldfaitful.py
-a = open("../iris.py", "w")
-a.write('# Autogenerated by convert.py at %s\n\n' %
- time.strftime("%a, %d %b %Y %H:%M:%S +0000", time.gmtime()))
-
-a.writelines(dumpvar(sl, 'SL'))
-a.writelines(dumpvar(sw, 'SW'))
-a.writelines(dumpvar(pl, 'PL'))
-a.writelines(dumpvar(pw, 'PW'))
-a.writelines(dumpvar(dcl, 'LABELS'))
-a.writelines(dumpvar(li2ln, 'LI2LN'))
diff --git a/scikits/learn/datasets/iris/src/iris.data b/scikits/learn/datasets/iris/src/iris.data
deleted file mode 100644
index 5c4316cd695e7c72f1db7ef496ffd2d2ef705b25..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/src/iris.data
+++ /dev/null
@@ -1,151 +0,0 @@
-5.1,3.5,1.4,0.2,Iris-setosa
-4.9,3.0,1.4,0.2,Iris-setosa
-4.7,3.2,1.3,0.2,Iris-setosa
-4.6,3.1,1.5,0.2,Iris-setosa
-5.0,3.6,1.4,0.2,Iris-setosa
-5.4,3.9,1.7,0.4,Iris-setosa
-4.6,3.4,1.4,0.3,Iris-setosa
-5.0,3.4,1.5,0.2,Iris-setosa
-4.4,2.9,1.4,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-5.4,3.7,1.5,0.2,Iris-setosa
-4.8,3.4,1.6,0.2,Iris-setosa
-4.8,3.0,1.4,0.1,Iris-setosa
-4.3,3.0,1.1,0.1,Iris-setosa
-5.8,4.0,1.2,0.2,Iris-setosa
-5.7,4.4,1.5,0.4,Iris-setosa
-5.4,3.9,1.3,0.4,Iris-setosa
-5.1,3.5,1.4,0.3,Iris-setosa
-5.7,3.8,1.7,0.3,Iris-setosa
-5.1,3.8,1.5,0.3,Iris-setosa
-5.4,3.4,1.7,0.2,Iris-setosa
-5.1,3.7,1.5,0.4,Iris-setosa
-4.6,3.6,1.0,0.2,Iris-setosa
-5.1,3.3,1.7,0.5,Iris-setosa
-4.8,3.4,1.9,0.2,Iris-setosa
-5.0,3.0,1.6,0.2,Iris-setosa
-5.0,3.4,1.6,0.4,Iris-setosa
-5.2,3.5,1.5,0.2,Iris-setosa
-5.2,3.4,1.4,0.2,Iris-setosa
-4.7,3.2,1.6,0.2,Iris-setosa
-4.8,3.1,1.6,0.2,Iris-setosa
-5.4,3.4,1.5,0.4,Iris-setosa
-5.2,4.1,1.5,0.1,Iris-setosa
-5.5,4.2,1.4,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-5.0,3.2,1.2,0.2,Iris-setosa
-5.5,3.5,1.3,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-4.4,3.0,1.3,0.2,Iris-setosa
-5.1,3.4,1.5,0.2,Iris-setosa
-5.0,3.5,1.3,0.3,Iris-setosa
-4.5,2.3,1.3,0.3,Iris-setosa
-4.4,3.2,1.3,0.2,Iris-setosa
-5.0,3.5,1.6,0.6,Iris-setosa
-5.1,3.8,1.9,0.4,Iris-setosa
-4.8,3.0,1.4,0.3,Iris-setosa
-5.1,3.8,1.6,0.2,Iris-setosa
-4.6,3.2,1.4,0.2,Iris-setosa
-5.3,3.7,1.5,0.2,Iris-setosa
-5.0,3.3,1.4,0.2,Iris-setosa
-7.0,3.2,4.7,1.4,Iris-versicolor
-6.4,3.2,4.5,1.5,Iris-versicolor
-6.9,3.1,4.9,1.5,Iris-versicolor
-5.5,2.3,4.0,1.3,Iris-versicolor
-6.5,2.8,4.6,1.5,Iris-versicolor
-5.7,2.8,4.5,1.3,Iris-versicolor
-6.3,3.3,4.7,1.6,Iris-versicolor
-4.9,2.4,3.3,1.0,Iris-versicolor
-6.6,2.9,4.6,1.3,Iris-versicolor
-5.2,2.7,3.9,1.4,Iris-versicolor
-5.0,2.0,3.5,1.0,Iris-versicolor
-5.9,3.0,4.2,1.5,Iris-versicolor
-6.0,2.2,4.0,1.0,Iris-versicolor
-6.1,2.9,4.7,1.4,Iris-versicolor
-5.6,2.9,3.6,1.3,Iris-versicolor
-6.7,3.1,4.4,1.4,Iris-versicolor
-5.6,3.0,4.5,1.5,Iris-versicolor
-5.8,2.7,4.1,1.0,Iris-versicolor
-6.2,2.2,4.5,1.5,Iris-versicolor
-5.6,2.5,3.9,1.1,Iris-versicolor
-5.9,3.2,4.8,1.8,Iris-versicolor
-6.1,2.8,4.0,1.3,Iris-versicolor
-6.3,2.5,4.9,1.5,Iris-versicolor
-6.1,2.8,4.7,1.2,Iris-versicolor
-6.4,2.9,4.3,1.3,Iris-versicolor
-6.6,3.0,4.4,1.4,Iris-versicolor
-6.8,2.8,4.8,1.4,Iris-versicolor
-6.7,3.0,5.0,1.7,Iris-versicolor
-6.0,2.9,4.5,1.5,Iris-versicolor
-5.7,2.6,3.5,1.0,Iris-versicolor
-5.5,2.4,3.8,1.1,Iris-versicolor
-5.5,2.4,3.7,1.0,Iris-versicolor
-5.8,2.7,3.9,1.2,Iris-versicolor
-6.0,2.7,5.1,1.6,Iris-versicolor
-5.4,3.0,4.5,1.5,Iris-versicolor
-6.0,3.4,4.5,1.6,Iris-versicolor
-6.7,3.1,4.7,1.5,Iris-versicolor
-6.3,2.3,4.4,1.3,Iris-versicolor
-5.6,3.0,4.1,1.3,Iris-versicolor
-5.5,2.5,4.0,1.3,Iris-versicolor
-5.5,2.6,4.4,1.2,Iris-versicolor
-6.1,3.0,4.6,1.4,Iris-versicolor
-5.8,2.6,4.0,1.2,Iris-versicolor
-5.0,2.3,3.3,1.0,Iris-versicolor
-5.6,2.7,4.2,1.3,Iris-versicolor
-5.7,3.0,4.2,1.2,Iris-versicolor
-5.7,2.9,4.2,1.3,Iris-versicolor
-6.2,2.9,4.3,1.3,Iris-versicolor
-5.1,2.5,3.0,1.1,Iris-versicolor
-5.7,2.8,4.1,1.3,Iris-versicolor
-6.3,3.3,6.0,2.5,Iris-virginica
-5.8,2.7,5.1,1.9,Iris-virginica
-7.1,3.0,5.9,2.1,Iris-virginica
-6.3,2.9,5.6,1.8,Iris-virginica
-6.5,3.0,5.8,2.2,Iris-virginica
-7.6,3.0,6.6,2.1,Iris-virginica
-4.9,2.5,4.5,1.7,Iris-virginica
-7.3,2.9,6.3,1.8,Iris-virginica
-6.7,2.5,5.8,1.8,Iris-virginica
-7.2,3.6,6.1,2.5,Iris-virginica
-6.5,3.2,5.1,2.0,Iris-virginica
-6.4,2.7,5.3,1.9,Iris-virginica
-6.8,3.0,5.5,2.1,Iris-virginica
-5.7,2.5,5.0,2.0,Iris-virginica
-5.8,2.8,5.1,2.4,Iris-virginica
-6.4,3.2,5.3,2.3,Iris-virginica
-6.5,3.0,5.5,1.8,Iris-virginica
-7.7,3.8,6.7,2.2,Iris-virginica
-7.7,2.6,6.9,2.3,Iris-virginica
-6.0,2.2,5.0,1.5,Iris-virginica
-6.9,3.2,5.7,2.3,Iris-virginica
-5.6,2.8,4.9,2.0,Iris-virginica
-7.7,2.8,6.7,2.0,Iris-virginica
-6.3,2.7,4.9,1.8,Iris-virginica
-6.7,3.3,5.7,2.1,Iris-virginica
-7.2,3.2,6.0,1.8,Iris-virginica
-6.2,2.8,4.8,1.8,Iris-virginica
-6.1,3.0,4.9,1.8,Iris-virginica
-6.4,2.8,5.6,2.1,Iris-virginica
-7.2,3.0,5.8,1.6,Iris-virginica
-7.4,2.8,6.1,1.9,Iris-virginica
-7.9,3.8,6.4,2.0,Iris-virginica
-6.4,2.8,5.6,2.2,Iris-virginica
-6.3,2.8,5.1,1.5,Iris-virginica
-6.1,2.6,5.6,1.4,Iris-virginica
-7.7,3.0,6.1,2.3,Iris-virginica
-6.3,3.4,5.6,2.4,Iris-virginica
-6.4,3.1,5.5,1.8,Iris-virginica
-6.0,3.0,4.8,1.8,Iris-virginica
-6.9,3.1,5.4,2.1,Iris-virginica
-6.7,3.1,5.6,2.4,Iris-virginica
-6.9,3.1,5.1,2.3,Iris-virginica
-5.8,2.7,5.1,1.9,Iris-virginica
-6.8,3.2,5.9,2.3,Iris-virginica
-6.7,3.3,5.7,2.5,Iris-virginica
-6.7,3.0,5.2,2.3,Iris-virginica
-6.3,2.5,5.0,1.9,Iris-virginica
-6.5,3.0,5.2,2.0,Iris-virginica
-6.2,3.4,5.4,2.3,Iris-virginica
-5.9,3.0,5.1,1.8,Iris-virginica
-
diff --git a/scikits/learn/datasets/iris/src/iris.names b/scikits/learn/datasets/iris/src/iris.names
deleted file mode 100644
index 7730e5d2699edf21fc3f600bba26d09962cc19fb..0000000000000000000000000000000000000000
--- a/scikits/learn/datasets/iris/src/iris.names
+++ /dev/null
@@ -1,62 +0,0 @@
-1. Title: Iris Plants Database
-
-2. Sources:
- (a) Creator: R.A. Fisher
- (b) Donor: Michael Marshall (MARSHALL%PLU@io.arc.nasa.gov)
- (c) Date: July, 1988
-
-3. Past Usage:
- - Publications: too many to mention!!! Here are a few.
- 1. Fisher,R.A. "The use of multiple measurements in taxonomic problems"
- Annual Eugenics, 7, Part II, 179-188 (1936); also in "Contributions
- to Mathematical Statistics" (John Wiley, NY, 1950).
- 2. Duda,R.O., & Hart,P.E. (1973) Pattern Classification and Scene Analysis.
- (Q327.D83) John Wiley & Sons. ISBN 0-471-22361-1. See page 218.
- 3. Dasarathy, B.V. (1980) "Nosing Around the Neighborhood: A New System
- Structure and Classification Rule for Recognition in Partially Exposed
- Environments". IEEE Transactions on Pattern Analysis and Machine
- Intelligence, Vol. PAMI-2, No. 1, 67-71.
- -- Results:
- -- very low misclassification rates (0% for the setosa class)
- 4. Gates, G.W. (1972) "The Reduced Nearest Neighbor Rule". IEEE
- Transactions on Information Theory, May 1972, 431-433.
- -- Results:
- -- very low misclassification rates again
- 5. See also: 1988 MLC Proceedings, 54-64. Cheeseman et al's AUTOCLASS II
- conceptual clustering system finds 3 classes in the data.
-
-4. Relevant Information:
- --- This is perhaps the best known database to be found in the pattern
- recognition literature. Fisher's paper is a classic in the field
- and is referenced frequently to this day. (See Duda & Hart, for
- example.) The data set contains 3 classes of 50 instances each,
- where each class refers to a type of iris plant. One class is
- linearly separable from the other 2; the latter are NOT linearly
- separable from each other.
- --- Predicted attribute: class of iris plant.
- --- This is an exceedingly simple domain.
-
-5. Number of Instances: 150 (50 in each of three classes)
-
-6. Number of Attributes: 4 numeric, predictive attributes and the class
-
-7. Attribute Information:
- 1. sepal length in cm
- 2. sepal width in cm
- 3. petal length in cm
- 4. petal width in cm
- 5. class:
- -- Iris Setosa
- -- Iris Versicolour
- -- Iris Virginica
-
-8. Missing Attribute Values: None
-
-Summary Statistics:
- Min Max Mean SD Class Correlation
- sepal length: 4.3 7.9 5.84 0.83 0.7826
- sepal width: 2.0 4.4 3.05 0.43 -0.4194
- petal length: 1.0 6.9 3.76 1.76 0.9490 (high!)
- petal width: 0.1 2.5 1.20 0.76 0.9565 (high!)
-
-9. Class Distribution: 33.3% for each of 3 classes.