return math.sqrt(z)
def minmaxNormalize(dataSet):
# 数据映射到[0, 1]
dataSet = pd.DataFrame(dataSet)
minDf = dataSet.min()
maxDf = dataSet.max()
normalizedSet = (dataSet - minDf) / (maxDf - minDf)
return normalizedSet
def zscoreStanderize(dataSet):
# 用z-score方法进行数据标准化
dataSet = pd.DataFrame(dataSet)
meanDf = dataSet.mean()
stdDf = dataSet.std()
standerizedSet = (dataSet - meanDf) / stdDf
return standerizedSet
if __name__ == "__main__":
filePath = "F:/2020AI_SummerCamp/dataSet/"
# rawData = LoadFile.loadCSV(filePath + "Pima.csv")
rawData = LoadFile.loadCSV(filePath + "diabetesN.csv")
dataSet, labelSet = LoadFile.splitData(rawData)
# dataSet = solveMissingData(dataSet)
# dataSet = minmaxNormalize(dataSet)
dataSet = zscoreStanderize(dataSet)
print(dataSet)
sortResult = sorted(labelsCnt.items(),
key=operator.itemgetter(1),
reverse=True)
return sortResult[0][0]
# 根据列表生成式生成切分后的数据集
def splitToFeat(dataSet, labelSet, feat, val):
dataSet = np.array(dataSet)
labelSet = np.array(labelSet)
leftData = dataSet[np.nonzero(dataSet[:, feat] < val)[0]]
leftLabel = labelSet[np.nonzero(dataSet[:, feat] < val)[0]]
rightData = dataSet[np.nonzero(dataSet[:, feat] >= val)[0]]
rightLabel = labelSet[np.nonzero(dataSet[:, feat] >= val)[0]]
return leftData, leftLabel, rightData, rightLabel
if __name__ == '__main__':
# 读入文件
# 使用的是网上找到的一个数据集
filePath = "F:/2020AI_SummerCamp/dataSet/"
rawData = LoadFile.loadCSV(filePath + "cartDS.csv")
# 预处理
dataSet, labelSet = LoadFile.splitData(rawData)
tree = buildTree(dataSet, labelSet)
# 测试数据
testVec = np.array([7, 3.2, 4.7, 1.4])
print(classify(tree, testVec))