python decision tree based on ID3 thought
- 2020-06-23 00:48:39
- OfStack
This is a decision tree based on ID3 to determine whether Marine biological data is fish, for your reference, the specific content is as follows
# coding=utf-8
import operator
from math import log
import time
def createDataSet():
dataSet = [[1, 1, 'yes'],
[1, 1, 'yes'],
[1, 0, 'no'],
[0, 1, 'no'],
[0, 1, 'no'],
[0,0,'maybe']]
labels = ['no surfaceing', 'flippers']
return dataSet, labels
# Calculate the Shannon entropy
def calcShannonEnt(dataSet):
numEntries = len(dataSet)
labelCounts = {}
for feaVec in dataSet:
currentLabel = feaVec[-1]
if currentLabel not in labelCounts:
labelCounts[currentLabel] = 0
labelCounts[currentLabel] += 1
shannonEnt = 0.0
for key in labelCounts:
prob = float(labelCounts[key]) / numEntries
shannonEnt -= prob * log(prob, 2)
return shannonEnt
def splitDataSet(dataSet, axis, value):
retDataSet = []
for featVec in dataSet:
if featVec[axis] == value:
reducedFeatVec = featVec[:axis]
reducedFeatVec.extend(featVec[axis + 1:])
retDataSet.append(reducedFeatVec)
return retDataSet
def chooseBestFeatureToSplit(dataSet):
numFeatures = len(dataSet[0]) - 1 # Because at the end of the data set 1 Is the label
baseEntropy = calcShannonEnt(dataSet)
bestInfoGain = 0.0
bestFeature = -1
for i in range(numFeatures):
featList = [example[i] for example in dataSet]
uniqueVals = set(featList)
newEntropy = 0.0
for value in uniqueVals:
subDataSet = splitDataSet(dataSet, i, value)
prob = len(subDataSet) / float(len(dataSet))
newEntropy += prob * calcShannonEnt(subDataSet)
infoGain = baseEntropy - newEntropy
if infoGain > bestInfoGain:
bestInfoGain = infoGain
bestFeature = i
return bestFeature
# Because we recursively build the decision tree based on the cost of the attributes, there may be some cases where the last attributes run out, but the classification
# If the calculation is still incomplete, the node classification will be calculated by majority vote
def majorityCnt(classList):
classCount = {}
for vote in classList:
if vote not in classCount.keys():
classCount[vote] = 0
classCount[vote] += 1
return max(classCount)
def createTree(dataSet, labels):
classList = [example[-1] for example in dataSet]
if classList.count(classList[0]) == len(classList): # If the categories are the same, the division is stopped
return classList[0]
if len(dataSet[0]) == 1: # All the features are used up
return majorityCnt(classList)
bestFeat = chooseBestFeatureToSplit(dataSet)
bestFeatLabel = labels[bestFeat]
myTree = {bestFeatLabel: {}}
del (labels[bestFeat])
featValues = [example[bestFeat] for example in dataSet]
uniqueVals = set(featValues)
for value in uniqueVals:
subLabels = labels[:] # The contents of the original list were copied in order not to change 1 Under the
myTree[bestFeatLabel][value] = createTree(splitDataSet(dataSet,
bestFeat, value), subLabels)
return myTree
def main():
data, label = createDataSet()
t1 = time.clock()
myTree = createTree(data, label)
t2 = time.clock()
print myTree
print 'execute for ', t2 - t1
if __name__ == '__main__':
main()
Finally, we can test the script 1. If we want to draw the generated decision tree with an image, we only need to define an plottree function in the script.