classifying_.idea_.name

classifying

classifying_.idea_classifying.iml

<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
  <component name="NewModuleRootManager">
    <content url="file://$MODULE_DIR$" />
    <orderEntry type="inheritedJdk" />
    <orderEntry type="sourceFolder" forTests="false" />
  </component>
</module>

classifying_.idea_encodings.xml

<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
  <component name="Encoding" useUTFGuessing="true" native2AsciiForPropertiesFiles="false" />
</project>

classifying_.idea_misc.xml

<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
  <component name="ProjectRootManager" version="2" project-jdk-name="Python 2.7.3 (/usr/bin/python)" project-jdk-type="Python SDK" />
</project>

classifying_.idea_modules.xml

<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
  <component name="ProjectModuleManager">
    <modules>
      <module fileurl="file://$PROJECT_DIR$/.idea/classifying.iml" filepath="$PROJECT_DIR$/.idea/classifying.iml" />
    </modules>
  </component>
</project>

classifying_.idea_scopes_scope_settings.xml

<component name="DependencyValidationManager">
  <state>
    <option name="SKIP_IMPORT_STATEMENTS" value="false" />
  </state>
</component>

classifying_.idea_vcs.xml

<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
  <component name="VcsDirectoryMappings">
    <mapping directory="" vcs="" />
  </component>
</project>

classifying_bucket - 00.data

['6.1', '3.0', '4.9', '1.8', 'Iris-virginica']
['5.8', '2.8', '5.1', '2.4', 'Iris-virginica']
['6.3', '2.9', '5.6', '1.8', 'Iris-virginica']
['6.7', '2.5', '5.8', '1.8', 'Iris-virginica']
['6.3', '2.5', '5.0', '1.9', 'Iris-virginica']
['4.4', '2.9', '1.4', '0.2', 'Iris-setosa']
['4.9', '3.1', '1.5', '0.1', 'Iris-setosa']
['4.8', '3.0', '1.4', '0.3', 'Iris-setosa']
['4.5', '2.3', '1.3', '0.3', 'Iris-setosa']
['5.1', '3.8', '1.6', '0.2', 'Iris-setosa']
['5.8', '2.7', '4.1', '1.0', 'Iris-versicolor']
['5.5', '2.4', '3.7', '1.0', 'Iris-versicolor']
['5.5', '2.6', '4.4', '1.2', 'Iris-versicolor']
['6.5', '2.8', '4.6', '1.5', 'Iris-versicolor']
['6.0', '2.9', '4.5', '1.5', 'Iris-versicolor']

classifying_bucket - 01.data

['6.3', '3.4', '5.6', '2.4', 'Iris-virginica']
['6.3', '3.3', '6.0', '2.5', 'Iris-virginica']
['6.2', '2.8', '4.8', '1.8', 'Iris-virginica']
['6.9', '3.2', '5.7', '2.3', 'Iris-virginica']
['7.9', '3.8', '6.4', '2.0', 'Iris-virginica']
['5.1', '3.7', '1.5', '0.4', 'Iris-setosa']
['4.8', '3.1', '1.6', '0.2', 'Iris-setosa']
['5.4', '3.4', '1.7', '0.2', 'Iris-setosa']
['5.8', '4.0', '1.2', '0.2', 'Iris-setosa']
['5.5', '4.2', '1.4', '0.2', 'Iris-setosa']
['5.5', '2.3', '4.0', '1.3', 'Iris-versicolor']
['6.6', '3.0', '4.4', '1.4', 'Iris-versicolor']
['5.6', '3.0', '4.1', '1.3', 'Iris-versicolor']
['7.0', '3.2', '4.7', '1.4', 'Iris-versicolor']
['5.7', '3.0', '4.2', '1.2', 'Iris-versicolor']

classifying_bucket - 02.data

['6.3', '2.7', '4.9', '1.8', 'Iris-virginica']
['7.6', '3.0', '6.6', '2.1', 'Iris-virginica']
['6.0', '3.0', '4.8', '1.8', 'Iris-virginica']
['7.2', '3.2', '6.0', '1.8', 'Iris-virginica']
['6.9', '3.1', '5.4', '2.1', 'Iris-virginica']
['4.9', '3.0', '1.4', '0.2', 'Iris-setosa']
['5.0', '3.5', '1.6', '0.6', 'Iris-setosa']
['5.3', '3.7', '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']
['6.9', '3.1', '4.9', '1.5', 'Iris-versicolor']
['6.2', '2.9', '4.3', '1.3', 'Iris-versicolor']
['5.9', '3.2', '4.8', '1.8', 'Iris-versicolor']
['6.6', '2.9', '4.6', '1.3', 'Iris-versicolor']
['6.2', '2.2', '4.5', '1.5', 'Iris-versicolor']

classifying_bucket - 03.data

['5.8', '2.7', '5.1', '1.9', 'Iris-virginica']
['7.1', '3.0', '5.9', '2.1', 'Iris-virginica']
['6.7', '3.1', '5.6', '2.4', 'Iris-virginica']
['7.7', '2.6', '6.9', '2.3', 'Iris-virginica']
['6.3', '2.8', '5.1', '1.5', 'Iris-virginica']
['5.0', '3.5', '1.3', '0.3', 'Iris-setosa']
['5.1', '3.4', '1.5', '0.2', 'Iris-setosa']
['5.0', '3.0', '1.6', '0.2', 'Iris-setosa']
['4.6', '3.4', '1.4', '0.3', 'Iris-setosa']
['4.8', '3.4', '1.9', '0.2', 'Iris-setosa']
['5.7', '2.8', '4.1', '1.3', 'Iris-versicolor']
['6.1', '2.8', '4.0', '1.3', 'Iris-versicolor']
['6.1', '2.8', '4.7', '1.2', 'Iris-versicolor']
['5.6', '3.0', '4.5', '1.5', 'Iris-versicolor']
['6.8', '2.8', '4.8', '1.4', 'Iris-versicolor']

classifying_bucket - 04.data

['5.6', '2.8', '4.9', '2.0', 'Iris-virginica']
['7.7', '2.8', '6.7', '2.0', 'Iris-virginica']
['6.5', '3.0', '5.8', '2.2', 'Iris-virginica']
['7.7', '3.0', '6.1', '2.3', 'Iris-virginica']
['5.7', '2.5', '5.0', '2.0', 'Iris-virginica']
['5.0', '3.6', '1.4', '0.2', 'Iris-setosa']
['4.6', '3.2', '1.4', '0.2', 'Iris-setosa']
['5.0', '3.3', '1.4', '0.2', 'Iris-setosa']
['4.9', '3.1', '1.5', '0.1', 'Iris-setosa']
['4.7', '3.2', '1.3', '0.2', 'Iris-setosa']
['6.4', '2.9', '4.3', '1.3', 'Iris-versicolor']
['6.3', '3.3', '4.7', '1.6', 'Iris-versicolor']
['5.8', '2.6', '4.0', '1.2', 'Iris-versicolor']
['5.5', '2.5', '4.0', '1.3', 'Iris-versicolor']
['5.9', '3.0', '4.2', '1.5', 'Iris-versicolor']

classifying_bucket - 05.data

['7.7', '3.8', '6.7', '2.2', 'Iris-virginica']
['6.4', '2.8', '5.6', '2.1', 'Iris-virginica']
['6.2', '3.4', '5.4', '2.3', 'Iris-virginica']
['6.7', '3.3', '5.7', '2.1', 'Iris-virginica']
['6.7', '3.0', '5.2', '2.3', 'Iris-virginica']
['5.2', '4.1', '1.5', '0.1', 'Iris-setosa']
['5.4', '3.9', '1.3', '0.4', 'Iris-setosa']
['4.6', '3.1', '1.5', '0.2', 'Iris-setosa']
['5.1', '3.8', '1.9', '0.4', 'Iris-setosa']
['5.4', '3.9', '1.7', '0.4', 'Iris-setosa']
['4.9', '2.4', '3.3', '1.0', 'Iris-versicolor']
['5.0', '2.3', '3.3', '1.0', 'Iris-versicolor']
['5.5', '2.4', '3.8', '1.1', 'Iris-versicolor']
['5.4', '3.0', '4.5', '1.5', 'Iris-versicolor']
['6.0', '3.4', '4.5', '1.6', 'Iris-versicolor']

classifying_bucket - 06.data

['6.4', '2.8', '5.6', '2.2', 'Iris-virginica']
['6.5', '3.0', '5.2', '2.0', 'Iris-virginica']
['4.9', '2.5', '4.5', '1.7', 'Iris-virginica']
['7.2', '3.0', '5.8', '1.6', 'Iris-virginica']
['6.4', '2.7', '5.3', '1.9', 'Iris-virginica']
['5.0', '3.2', '1.2', '0.2', 'Iris-setosa']
['5.0', '3.4', '1.5', '0.2', 'Iris-setosa']
['5.2', '3.5', '1.5', '0.2', 'Iris-setosa']
['4.6', '3.6', '1.0', '0.2', 'Iris-setosa']
['5.1', '3.5', '1.4', '0.2', 'Iris-setosa']
['5.7', '2.6', '3.5', '1.0', 'Iris-versicolor']
['6.1', '2.9', '4.7', '1.4', 'Iris-versicolor']
['6.7', '3.0', '5.0', '1.7', 'Iris-versicolor']
['5.8', '2.7', '3.9', '1.2', 'Iris-versicolor']
['6.3', '2.5', '4.9', '1.5', 'Iris-versicolor']

classifying_bucket - 07.data

['6.7', '3.3', '5.7', '2.5', 'Iris-virginica']
['7.4', '2.8', '6.1', '1.9', 'Iris-virginica']
['7.2', '3.6', '6.1', '2.5', 'Iris-virginica']
['6.8', '3.0', '5.5', '2.1', 'Iris-virginica']
['6.8', '3.2', '5.9', '2.3', 'Iris-virginica']
['4.4', '3.2', '1.3', '0.2', 'Iris-setosa']
['5.7', '4.4', '1.5', '0.4', 'Iris-setosa']
['5.1', '3.8', '1.5', '0.3', 'Iris-setosa']
['4.4', '3.0', '1.3', '0.2', 'Iris-setosa']
['5.0', '3.4', '1.6', '0.4', 'Iris-setosa']
['5.1', '2.5', '3.0', '1.1', 'Iris-versicolor']
['5.6', '2.5', '3.9', '1.1', 'Iris-versicolor']
['6.7', '3.1', '4.7', '1.5', 'Iris-versicolor']
['5.7', '2.9', '4.2', '1.3', 'Iris-versicolor']
['6.1', '3.0', '4.6', '1.4', 'Iris-versicolor']

classifying_bucket - 08.data

['6.5', '3.0', '5.5', '1.8', 'Iris-virginica']
['6.4', '3.1', '5.5', '1.8', 'Iris-virginica']
['6.1', '2.6', '5.6', '1.4', 'Iris-virginica']
['6.9', '3.1', '5.1', '2.3', 'Iris-virginica']
['6.5', '3.2', '5.1', '2.0', 'Iris-virginica']
['4.9', '3.1', '1.5', '0.1', 'Iris-setosa']
['4.8', '3.0', '1.4', '0.1', 'Iris-setosa']
['5.7', '3.8', '1.7', '0.3', 'Iris-setosa']
['4.8', '3.4', '1.6', '0.2', 'Iris-setosa']
['5.4', '3.7', '1.5', '0.2', 'Iris-setosa']
['5.6', '2.9', '3.6', '1.3', 'Iris-versicolor']
['6.3', '2.3', '4.4', '1.3', 'Iris-versicolor']
['6.4', '3.2', '4.5', '1.5', 'Iris-versicolor']
['6.0', '2.7', '5.1', '1.6', 'Iris-versicolor']
['5.0', '2.0', '3.5', '1.0', 'Iris-versicolor']

classifying_bucket - 09.data

['7.3', '2.9', '6.3', '1.8', 'Iris-virginica']
['6.4', '3.2', '5.3', '2.3', 'Iris-virginica']
['6.0', '2.2', '5.0', '1.5', 'Iris-virginica']
['5.9', '3.0', '5.1', '1.8', 'Iris-virginica']
['5.8', '2.7', '5.1', '1.9', 'Iris-virginica']
['4.3', '3.0', '1.1', '0.1', 'Iris-setosa']
['5.5', '3.5', '1.3', '0.2', 'Iris-setosa']
['5.1', '3.3', '1.7', '0.5', 'Iris-setosa']
['5.4', '3.4', '1.5', '0.4', 'Iris-setosa']
['5.1', '3.5', '1.4', '0.3', 'Iris-setosa']
['6.0', '2.2', '4.0', '1.0', 'Iris-versicolor']
['5.7', '2.8', '4.5', '1.3', 'Iris-versicolor']
['5.2', '2.7', '3.9', '1.4', 'Iris-versicolor']
['6.7', '3.1', '4.4', '1.4', 'Iris-versicolor']
['5.6', '2.7', '4.2', '1.3', 'Iris-versicolor']

classifying_cc.data

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

classifying_classifier.py

import random

class classifier:

    def buckets (self, fileName, classColumn, bucketsNo):

        data = {}
        buckets = []

        f = open(fileName)
        lines = f.readlines()
        f.close()


        for line in lines:
            cur_line = line.strip().split(',')
            cur_class = cur_line[classColumn]
            data.setdefault(cur_class,[])
            data[cur_class].append(cur_line[0:classColumn])


        for i in range(bucketsNo):
            buckets.append([])

        for key in data:

            buNum = 0
            random.shuffle(data[key])

            for values in data[key]:
                values.append(key)
                buckets[buNum].append(values)
                buNum = (buNum + 1) % bucketsNo

            for cc in range(bucketsNo):
                f = open ("%s - %02i.data" % ('bucket',cc),'w')
                for values in buckets[cc]:
                    f.write(str(values) + '\n')
                f.close()

classifying_standard.py

class Classifier:

    def __init__(self, filename):

        self.medianAndDeviation = []
        
        # reading the data in from the file
        f = open(filename)
        lines = f.readlines()
        f.close()
        self.format = lines[0].strip().split('\t')
        self.data = []
        for line in lines[1:]:
            fields = line.strip().split('\t')
            ignore = []
            vector = []
            for i in range(len(fields)):
                if self.format[i] == 'num':
                    vector.append(float(fields[i]))
                elif self.format[i] == 'comment':
                    ignore.append(fields[i])
                elif self.format[i] == 'class':
                    classification = fields[i]
            self.data.append((classification, vector, ignore))
        self.rawData = list(self.data)
        # get length of instance vector
        self.vlen = len(self.data[0][1])
        # now normalize the data
        for i in range(self.vlen):
            self.normalizeColumn(i)
        

        
    
    ##################################################
    ###
    ###  CODE TO COMPUTE THE MODIFIED STANDARD SCORE

    def getMedian(self, alist):
        """return median of alist"""
        if alist == []:
            return []
        blist = sorted(alist)
        length = len(alist)
        if length % 2 == 1:
            # length of list is odd so return middle element
            return blist[int(((length + 1) / 2) -  1)]
        else:
            # length of list is even so compute midpoint
            v1 = blist[int(length / 2)]
            v2 =blist[(int(length / 2) - 1)]
            return (v1 + v2) / 2.0
        

    def getAbsoluteStandardDeviation(self, alist, median):
        """given alist and median return absolute standard deviation"""
        sum = 0
        for item in alist:
            sum += abs(item - median)
        return sum / len(alist)


    def normalizeColumn(self, columnNumber):
       """given a column number, normalize that column in self.data"""
       # first extract values to list
       col = [v[1][columnNumber] for v in self.data]
       median = self.getMedian(col)
       asd = self.getAbsoluteStandardDeviation(col, median)
       #print("Median: %f   ASD = %f" % (median, asd))
       self.medianAndDeviation.append((median, asd))
       for v in self.data:
           v[1][columnNumber] = (v[1][columnNumber] - median) / asd


    def normalizeVector(self, v):
        """We have stored the median and asd for each column.
        We now use them to normalize vector v"""
        vector = list(v)
        for i in range(len(vector)):
            (median, asd) = self.medianAndDeviation[i]
            vector[i] = (vector[i] - median) / asd
        return vector

    
    ###
    ### END NORMALIZATION
    ##################################################



    def manhattan(self, vector1, vector2):
        """Computes the Manhattan distance."""
        return sum(map(lambda v1, v2: abs(v1 - v2), vector1, vector2))


    def nearestNeighbor(self, itemVector):
        """return nearest neighbor to itemVector"""
        return min([ (self.manhattan(itemVector, item[1]), item)
                     for item in self.data])
    
    def classify(self, itemVector):
        """Return class we think item Vector is in"""
        return(self.nearestNeighbor(self.normalizeVector(itemVector))[1][0])

def test(training_filename, test_filename):
    """Test the classifier on a test set of data"""
    classifier = Classifier(training_filename)
    f = open(test_filename)
    lines = f.readlines()
    f.close()
    numCorrect = 0.0
    for line in lines:
        data = line.strip().split('\t')
        vector = []
        classInColumn = -1
        for i in range(len(classifier.format)):
              if classifier.format[i] == 'num':
                  vector.append(float(data[i]))
              elif classifier.format[i] == 'class':
                  classInColumn = i
        theClass= classifier.classify(vector)
        prefix = '-'
        if theClass == data[classInColumn]:
            # it is correct
            numCorrect += 1
            prefix = '+'
        print("%s  %12s  %s" % (prefix, theClass, line))
    print("%4.2f%% correct" % (numCorrect * 100/ len(lines)))
        

##
##  Here are examples of how the classifier is used on different data sets
##  in the book.
#  test('athletesTrainingSet.txt', 'athletesTestSet.txt')
#  test("irisTrainingSet.data", "irisTestSet.data")
#  test("mpgTrainingSet.txt", "mpgTestSet.txt")