Scribd Logo
Upload

Welcome to Scribd!

  • 8 views

    Lab 3 IA2

    Uploaded by

    Chad Christensen
    The document presents code for building a decision tree classifier using the ID3 algorithm. It defines functions for calculating entropy, information gain, identifying class labels, and recursively constructing the decision tree from a training dataset. The code is then executed on a sample dataset to build and output the decision tree.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd

    Lab 3 IA2

    Uploaded by

    Chad Christensen
    8 views3 pages
    The document presents code for building a decision tree classifier using the ID3 algorithm. It defines functions for calculating entropy, information gain, identifying class labels, and recursively constructing the decision tree from a training dataset. The code is then executed on a sample dataset to build and output the decision tree.

    Original Description:

    asd

    Original Title

    Lab3IA2

    Copyright

    © © All Rights Reserved

    Available Formats

    TXT, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document presents code for building a decision tree classifier using the ID3 algorithm. It defines functions for calculating entropy, information gain, identifying class labels, and recursively constructing the decision tree from a training dataset. The code is then executed on a sample dataset to build and output the decision tree.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    8 views3 pages

    Lab 3 IA2

    Uploaded by

    Chad Christensen
    The document presents code for building a decision tree classifier using the ID3 algorithm. It defines functions for calculating entropy, information gain, identifying class labels, and recursively constructing the decision tree from a training dataset. The code is then executed on a sample dataset to build and output the decision tree.

    Copyright:

    © All Rights Reserved
    Download as TXT, PDF, TXT or read online from Scribd
    Download as txt, pdf, or txt
    of 3

    import math

    from math import log


    S = [('age', 'competition', 'type', 'profit'), ('old', 'yes', 'swr', 'down'), ('
    old', 'no', 'swr', 'down'), ('old', 'no', 'hwr', 'down'),\
    ('mid', 'yes', 'swr', 'down'), ('mid', 'yes', 'hwr', 'down'), ('mid', 'no', 'hwr
    ', 'up'), ('mid', 'no', 'swr', 'up'), ('new', 'yes', 'swr', 'up'), \
    ('new', 'no', 'hwr', 'up'), ('new', 'no', 'swr', 'up')]
    class Tree(object):
    def __init__(self):
    self.children = None
    self.leg = None
    self.data = None
    def entropy(S):
    dicti = {}
    for i in range(1, len(S)):
    if dicti.get(S[i][3], None) is None:
    dicti[S[i][3]] = 1
    else:
    dicti[S[i][3]] = dicti[S[i][3]] + 1
    result = 0
    for ke in dicti.keys():
    result = result - (dicti[ke]/float(len(S) - 1))*log((dicti[ke]/f
    loat(len(S)-1)), 2)
    return result
    def gain(attrib_pos):
    dictiat = {}
    for i in range(1, len(S)):
    if dictiat.get(S[i][attrib_pos], None) is None:
    dictiat[S[i][attrib_pos]] = {}
    if dictiat[S[i][attrib_pos]].get(S[i][3], None) is None:
    dictiat[S[i][attrib_pos]][S[i][3]] = 1
    else:
    dictiat[S[i][attrib_pos]][S[i][3]] = dictiat[S[i][attrib
    _pos]][S[i][3]] + 1
    return dictiat
    def getnrcls(S):
    dicu = {}
    for i in range(1, len(S)):
    if dicu.get(S[i][3], None) is None:
    dicu[S[i][3]] = 0
    return dicu.keys()
    def gain_calc(attrib_pos, S):
    dic = gain(attrib_pos)
    result = entropy(S)
    for key in dic.keys():
    if len(dic[key].keys()) == 2:
    ceva = 0
    toate = 0
    for keyy in dic[key].keys():
    toate = toate + dic[key][keyy]
    for keyy in dic[key].keys():
    ceva = ceva - dic[key][keyy]/float(toate)*log(di
    c[key][keyy]/float(toate),2)
    ceva = ceva * toate / (len(S) - 1)
    result = result - ceva

    return result
    dicc = {}
    dicc['new'] = 0
    dicc['old'] = 0
    dicc['mid'] = 0
    dicc['yes'] = 1
    dicc['no'] = 1
    dicc['swr'] = 2
    dicc['hwr'] = 2
    def id3(S, dicc):
    maxx = -10000
    for i in range(0, 2):
    if maxx < gain_calc(i, S):
    maxx = gain_calc(i, S)
    pos = i
    id3tree = Tree()
    id3tree.data = S[0][pos]
    id3tree.children = [Tree() for i in range(3)]
    id3tree.children[0].leg = 'new'
    id3tree.children[1].leg = 'mid'
    id3tree.children[2].leg = 'old'
    for i in range(len(id3tree.children)):
    continueid3(S, id3tree.children[i], id3tree.children[i].leg, dic
    c)
    return id3tree
    def continueid3(S, id3tree, leg, dicc):
    newS = [S[0]]
    for i in range(1, len(S)):
    if S[i][dicc[leg]] == leg:
    newS.append(S[i])
    if len(getnrcls(newS)) == 1:
    id3tree.data=getnrcls(newS)[0]
    else:
    maxx = -10000
    for i in range(1,2):
    print gain_calc(i, newS)
    if maxx < gain_calc(i, newS):
    maxx = gain_calc(i, newS)
    pos = i
    id3tree.data = newS[0][pos]
    id3tree.children = [Tree() for i in range(2)]
    id3tree.children[0].leg = 'yes'
    id3tree.children[1].leg = 'no'
    for i in range(len(id3tree.children)):
    continueid3(newS, id3tree.children[i], id3tree.children[
    i].leg, dicc)
    copac = id3(S, dicc)
    print copac.data
    print copac.children[0].leg
    print copac.children[0].data
    print copac.children[1].leg
    print copac.children[1].data
    print copac.children[2].leg
    print copac.children[2].data

    print copac.children[1].children[0].leg
    print copac.children[1].children[0].data
    print copac.children[1].children[1].leg
    print copac.children[1].children[1].data
    dike = {}
    dike['up'] = []
    dike['down'] = []
    def afis(copac, dic, currentval):
    if copac.children is None:
    dic[copac.data].append(currentval+copac.leg)
    else:
    if copac.leg is None:
    currentval = currentval + copac.data + ' '
    else:
    currentval = currentval + copac.leg + ':' + copac.data +
    ' '
    for i in copac.children:
    dic = afis(i, dic, currentval)
    return dic
    print afis(copac, dike, '')

    You might also like