class NBClassify(object):
  def __init__(self, fillNa = 1):
    self.fillNa = 1
    pass
  def train(self, trainSet):
    # 計(jì)算每種類別的概率
    # 保存所有tag的所有種類，及它們出現(xiàn)的頻次
    dictTag = {}
    for subTuple in trainSet:
      dictTag[str(subTuple[1])] = 1 if str(subTuple[1]) not in dictTag.keys() else dictTag[str(subTuple[1])] + 1
    # 保存每個(gè)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
    ##############################################################################
    # 計(jì)算特征的條件概率
    # 保存特征屬性基本信息{特征1:{值1:出現(xiàn)5次, 值2:出現(xiàn)1次}, 特征2:{值1:出現(xiàn)1次, 值2:出現(xiàn)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 = {
      # '職業(yè)': {'農(nóng)夫': 1, '教師': 2, '建筑工人': 2, '護(hù)士': 1},
      # '癥狀': {'打噴嚏': 3, '頭痛': 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 ': {'癥狀': {'打噴嚏': None, '頭痛': None}, '職業(yè)': {'護(hù)士': None, '農(nóng)夫': None, '建筑工人': None, '教師': None}},
    #  '腦震蕩': {'癥狀': {'打噴嚏': None, '頭痛': None}, '職業(yè)': {'護(hù)士': None, '農(nóng)夫': None, '建筑工人': None, '教師': None}},
    #  '過敏 ': {'癥狀': {'打噴嚏': None, '頭痛': None}, '職業(yè)': {'護(hù)士': None, '農(nóng)夫': None, '建筑工人': None, '教師': 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)
    # 將馴良樣本中沒有的項(xiàng)目，由None改為一個(gè)非常小的數(shù)值，表示其概率極小而并非是零
    for tag, featuresDict in dictFeatures.items():
      for featureName, fetureValueDict in featuresDict.items():
        for featureKey, featureValues in fetureValueDict.items():
          if featureValues == None:
            fetureValueDict[featureKey] = 1
    # 由特征頻率計(jì)算特征的條件概率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 = {}
    # 計(jì)算每個(gè)tag的條件概率
    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
    # 對(duì)比每個(gè)tag的條件概率的大小
    resultList = sorted(resultDict.items(), key=lambda x:x[1], reverse=True)
    return resultList[0][0]
if __name__ == '__main__':
  trainSet = [
    ({"癥狀":"打噴嚏", "職業(yè)":"護(hù)士"}, "感冒 "),
    ({"癥狀":"打噴嚏", "職業(yè)":"農(nóng)夫"}, "過敏 "),
    ({"癥狀":"頭痛", "職業(yè)":"建筑工人"}, "腦震蕩"),
    ({"癥狀":"頭痛", "職業(yè)":"建筑工人"}, "感冒 "),
    ({"癥狀":"打噴嚏", "職業(yè)":"教師"}, "感冒 "),
    ({"癥狀":"頭痛", "職業(yè)":"教師"}, "腦震蕩"),
  ]
  monitor = NBClassify()
  # trainSet is something like that [(featureDict, tag), ]
  monitor.train(trainSet)
  # 打噴嚏的建筑工人
  # 請(qǐng)問他患上感冒的概率有多大？
  result = monitor.classify({"癥狀":"打噴嚏", "職業(yè)":"建筑工人"})
  print(result)