Python实现的朴素贝叶斯分类器示例
本文实例讲述了Python实现的朴素贝叶斯分类器。分享给大家供大家参考，具体如下：
因工作中需要，自己写了一个朴素贝叶斯分类器。
对于未出现的属性，采取了拉普拉斯平滑，避免未出现的属性的概率为零导致整个条件概率都为零的情况出现。
朴素贝叶斯的基本原理网上很容易查到，这里不再叙述，直接附上代码
因工作中需要，自己写了一个朴素贝叶斯分类器。对于未出现的属性，采取了拉普拉斯平滑，避免未出现的属性的概率为零导致整个条件概率都为零的情况出现。
class NBClassify(object):
def __init__(self, fillNa = 1):
self.fillNa = 1
pass
def train(self, trainSet):
# 计算每种类别的概率
# 保存所有tag的所有种类，及它们出现的频次
dictTag = {}
for subTuple in trainSet:
dictTag[str(subTuple[1])] = 1 if str(subTuple[1]) not in dictTag.keys() else dictTag[str(subTuple[1])] + 1
# 保存每个tag本身的概率
tagProbablity = {}
totalFreq = sum([value for value in dictTag.values()])
for key, value in dictTag.items():
tagProbablity[key] = value / totalFreq
# print(tagProbablity)
self.tagProbablity = tagProbablity
##############################################################################
# 计算特征的条件概率
# 保存特征属性基本信息{特征1:{值1:出现5次, 值2:出现1次}, 特征2:{值1:出现1次, 值2:出现5次}}
dictFeaturesBase = {}
for subTuple in trainSet:
for key, value in subTuple[0].items():
if key not in dictFeaturesBase.keys():
dictFeaturesBase[key] = {value:1}
else:
if value not in dictFeaturesBase[key].keys():
dictFeaturesBase[key][value] = 1
else:
dictFeaturesBase[key][value] += 1
# dictFeaturesBase = {
# '职业': {'农夫': 1, '教师': 2, '建筑工人': 2, '护士': 1},
# '症状': {'打喷嚏': 3, '头痛': 3}
# }
dictFeatures = {}.fromkeys([key for key in dictTag])
for key in dictFeatures.keys():
dictFeatures[key] = {}.fromkeys([key for key in dictFeaturesBase])
for key, value in dictFeatures.items():
for subkey in value.keys():
value[subkey] = {}.fromkeys([x for x in dictFeaturesBase[subkey].keys()])
# dictFeatures = {
# '感冒 ': {'症状': {'打喷嚏': None, '头痛': None}, '职业': {'护士': None, '农夫': None, '建筑工人': None, '教师': None}},
# '脑震荡': {'症状': {'打喷嚏': None, '头痛': None}, '职业': {'护士': None, '农夫': None, '建筑工人': None, '教师': None}},
# '过敏 ': {'症状': {'打喷嚏': None, '头痛': None}, '职业': {'护士': None, '农夫': None, '建筑工人': None, '教师': None}}
# }
# initialise dictFeatures
for subTuple in trainSet:
for key, value in subTuple[0].items():
dictFeatures[subTuple[1]][key][value] = 1 if dictFeatures[subTuple[1]][key][value] == None else dictFeatures[subTuple[1]][key][value] + 1
# print(dictFeatures)
# 将驯良样本中没有的项目，由None改为一个非常小的数值，表示其概率极小而并非是零
for tag, featuresDict in dictFeatures.items():
for featureName, fetureValueDict in featuresDict.items():
for featureKey, featureValues in fetureValueDict.items():
if featureValues == None:
fetureValueDict[featureKey] = 1
# 由特征频率计算特征的条件概率P(feature|tag)
for tag, featuresDict in dictFeatures.items():
for featureName, fetureValueDict in featuresDict.items():
totalCount = sum([x for x in fetureValueDict.values() if x != None])
for featureKey, featureValues in fetureValueDict.items():
fetureValueDict[featureKey] = featureValues/totalCount if featureValues != None else None
self.featuresProbablity = dictFeatures
##############################################################################
def classify(self, featureDict):
resultDict = {}
# 计算每个tag的条件概率
for key, value in self.tagProbablity.items():
iNumList = []
for f, v in featureDict.items():
if self.featuresProbablity[key][f][v]:
iNumList.append(self.featuresProbablity[key][f][v])
conditionPr = 1
for iNum in iNumList:
conditionPr *= iNum
resultDict[key] = value * conditionPr
# 对比每个tag的条件概率的大小
resultList = sorted(resultDict.items(), key=lambda x:x[1], reverse=True)
return resultList[0][0]
if __name__ == '__main__':
trainSet = [
({"症状":"打喷嚏", "职业":"护士"}, "感冒 "),
({"症状":"打喷嚏", "职业":"农夫"}, "过敏 "),
({"症状":"头痛", "职业":"建筑工人"}, "脑震荡"),
({"症状":"头痛", "职业":"建筑工人"}, "感冒 "),
({"症状":"打喷嚏", "职业":"教师"}, "感冒 "),
({"症状":"头痛", "职业":"教师"}, "脑震荡"),
]
monitor = NBClassify()
# trainSet is something like that [(featureDict, tag), ]
monitor.train(trainSet)
# 打喷嚏的建筑工人
# 请问他患上感冒的概率有多大？
result = monitor.classify({"症状":"打喷嚏", "职业":"建筑工人"})
print(result)
另：关于朴素贝叶斯算法详细说明还可参看本站前面一篇/post/129903.htm。
更多关于Python相关内容感兴趣的读者可查看本站专题：《Python数据结构与算法教程》、《Python加密解密算法与技巧总结》、《Python编码操作技巧总结》、《Python函数使用技巧总结》、《Python字符串操作技巧汇总》及《Python入门与进阶经典教程》
希望本文所述对大家Python程序设计有所帮助。
