From 5792b54bc6cd90b698d29116da7948db53adfe8d Mon Sep 17 00:00:00 2001
From: Fabian Pedregosa <fabian.pedregosa@inria.fr>
Date: Wed, 6 Jan 2010 08:46:59 +0000
Subject: [PATCH] Set correct name for datasets packages (data->datasets) in
the setup, and trivial changes in datasets info message
From: cdavid <cdavid@cb17146a-f446-4be1-a4f7-bd7c5bb65646>
git-svn-id: https://scikit-learn.svn.sourceforge.net/svnroot/scikit-learn/trunk@220 22fbfee3-77ab-4535-9bad-27d1bd3bc7d8
---
scikits/learn/datasets/setup.py | 2 +-
scikits/learn/utils/attrselect.py | 30 +++++++++++++++++++++---------
2 files changed, 22 insertions(+), 10 deletions(-)
diff --git a/scikits/learn/datasets/setup.py b/scikits/learn/datasets/setup.py
index b8e587a6fc..4d18e8e113 100644
--- a/scikits/learn/datasets/setup.py
+++ b/scikits/learn/datasets/setup.py
@@ -2,7 +2,7 @@
def configuration(parent_package='',top_path=None):
from numpy.distutils.misc_util import Configuration
- config = Configuration('data',parent_package,top_path)
+ config = Configuration('datasets',parent_package,top_path)
config.add_subpackage('oldfaithful')
config.add_subpackage('pendigits')
config.add_subpackage('iris')
diff --git a/scikits/learn/utils/attrselect.py b/scikits/learn/utils/attrselect.py
index 39eb9b62f2..b5526ee6a1 100644
--- a/scikits/learn/utils/attrselect.py
+++ b/scikits/learn/utils/attrselect.py
@@ -1,5 +1,5 @@
#! /usr/bin/env python
-# Last Change: Sat Jul 21 07:00 PM 2007 J
+# Last Change: Sat Jul 21 09:00 PM 2007 J
"""This module implements function to extract attributes and/or classes from
datasets."""
@@ -8,7 +8,7 @@ import numpy as N
def print_dataset_info(data, label = None, cl = None):
# Attributes info
attr = get_attributes(data)
- msg = "data Iris has: \n" + "\t%d attributes: " % len(attr)
+ msg = "data has: \n" + "\t%d attributes: " % len(attr)
if len(attr) > 0:
msg += ", ".join([i for i in attr[:-1]])
msg += " and " + attr[-1]
@@ -20,18 +20,22 @@ def print_dataset_info(data, label = None, cl = None):
if len(cl) > 0:
msg += "\t%d classes: " % len(cl)
msg += ", ".join([i for i in cl])
- else:
- msg += "\tNo classes"
+ else:
+ msg += "\tNo classes"
- msg += '\n'
- # Number of samples
- ns = len(data)
- msg += "\t%d samples in the dataset:\n" % ns
+ msg += '\n'
+
+ # Number of samples
+ ns = len(data)
+ if label is not None:
if cl is not None and len(cl) > 0:
+ msg += "\t%d samples in the dataset:\n" % ns
c2ind = get_c2ind(cl, label)
msg += "".join(["\t\t%d samples for class %s\n" \
% (len(c2ind[cname]), cname) \
for cname in cl])
+ else:
+ msg += "\t%d samples in the dataset\n" % ns
print msg
@@ -89,7 +93,7 @@ def get_c2ind(cl, label):
return c2ind
if __name__ == '__main__':
- from scikits.learn.datasets import iris, german
+ from scikits.learn.datasets import iris, german, pendigits, oldfaithful
d = iris.load()
data, lab, cl = d['data'], d['label'], d['class']
print_dataset_info(data, lab, cl)
@@ -97,3 +101,11 @@ if __name__ == '__main__':
d = german.load()
data, lab, cl = d['data'], d['label'], d['class']
print_dataset_info(data, lab, cl)
+
+ d = oldfaithful.load()
+ data = d['data']
+ print_dataset_info(data)
+
+ d = pendigits.load()
+ data, lab, cl = d['data'], d['label'], d['class']
+ print_dataset_info(data, lab, cl)
--
GitLab