def load_file(self):
try:
vector_list = ld.LoadFile().read_file()
except Exception:
self.error_lab.config(text="Файл не загружен")
rw.ResultWindow(vector_list)
def getStandardedMatData(rawData):
# 将数据标准化后，再分割为数据集、标签集，然后将格式转换为矩阵
dataSet, labelSet = LoadFile.splitData(rawData)
dataSet = np.mat(dataSet)
labelSet = np.mat(labelSet).T
dataSet = standardize(dataSet)
return dataSet, labelSet
def kFoldCrossValidation(rawData, processFunc, k):
rawData = pd.DataFrame(rawData)
n = np.shape(rawData)[0]
step = n // k
bestModel = 0
leastErr = 0
for i in range(k):
if i == (k-1):
testData = rawData.iloc[step*i: n, :]
trainData = rawData.iloc[: step*i, :]
else:
testData = rawData.iloc[step*i: step*(i+1), :]
trainData = rawData.iloc[: step*i, :]
trainData = trainData.append(rawData.iloc[step*(i+1):])
testData, testLabel = LoadFile.splitData(testData)
trainData, trainLabel = LoadFile.splitData(trainData)
model = getModel(trainData, trainLabel)
err = testModel(model, testData, testLabel)
if err < leastErr:
leastErr = err
bestModel = model
return model
#HAItech,2018.02.14
from useful import *
from random import *
from LoadFile import *
from PrintFile import *
courses = LoadFile("/root/a/useful1.txt")
space_time = SpaceTime()
length = courses.__len__()
# length=3
mincredit = 9
bixiucredit = 3
sequence = range(1, length)
aimcredit = 16.5
weight = 1
POP = GeneratePopulation(courses, sequence, length)
lower = aimcredit * weight + mincredit + bixiucredit
record = [[] for score in range(int(aimcredit * (weight + 1) - lower) * 10)]
Maxscore = [-1] * 5000
Maxscore[-1] = 0
while Maxscore[-1] != Maxscore[-4999]:
POP, record = Fitness(POP, courses, aimcredit, weight, record, lower)
Maxscore.append(POP.maxscore)
POP = ReproduceOffspring(POP, sequence, length)
POP.generation = POP.generation + 1
c = PrintFile("/root/a/result.txt", record, courses)
import LoadFile
if __name__ == "__main__":
try:
shpfilePath = r"E:\data\moto_trackdata_4city_shp\755\000159_20171127_20171203.shp"
shapeFac = LoadFile.LoadTraceDataFromShapefileFactory(
args=(shpfilePath))
#trace data order by person,time,motiontype
OnetraceDF = shapeFac.getTraceData()
#trace segment stop cluster detection
except Exception, e:
print e.message
def testOne(self):
self.assertEqual(LoadFile.get_responses(),\
{'436': '436 <FAIL>##ROUTER=KIMENG##', \
'802': '802 <APP_ID=d26d9b499041e735d00c84676b58959a|SEC_CODES=|ROUND=2|ROUND-OPTION=3>##ROUTER=KIMENG,HTTPS=1,CLIENT_TYPE=ANDROID,VERSION=1.0.1,PLATFORM_MODE=development,TIME_OUT=25,MESSAGE_ID=428642b311979cfd9e40ebe8d19d8b07,PROTO_REV=2,ECHO=8f55f93d5f6b5f6f79a6b2abc6893565_0##'})
def setUp(self): LoadFile.load()
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))
import LoadFile
import GetLCS
import ListOperate
import time
start = time.clock()
symbol_list_readfile = LoadFile.loadfile()
symbol_list = LoadFile.loadfile()
symbol_list = list(set(symbol_list))
ExtractKeyWord = []
result_index = []
symbol_list_old = []
print(symbol_list)
matrix = [[999 for i in range(len(symbol_list))] for j in range(len(symbol_list))]
while len(symbol_list) != 1:#and ListOperate.GetMaxElement(matrix) > 0.1 and not ListOperate.CmpList(symbol_list,symbol_list_old):
for i in range(0, len(symbol_list)):
for j in range(0, len(symbol_list)):
if i == j:
matrix[i][j] = 0
else:
result = GetLCS.GetLCS2(symbol_list[i], symbol_list[j])
matrix[i][j] = len(result) / max(len(symbol_list[i]),len(symbol_list[j]))
print(matrix)
x, y = ListOperate.GetMaxElementIndex(matrix)
print("symbol_list is " + str(symbol_list))
print("x=" + str(x) + " y=" + str(y) + " symbol_list_lenth=" + str(len(symbol_list)))
result = GetLCS.GetLCSandIndex(symbol_list[x], symbol_list[y])
print(result)
np.diag((1-px).getA1()) * dataSet) / n + 0.001
weights = weights - Hessian.I * grad
return weights
def calcAccuracy(rawData, lrFunc, alpha=0.001, maxCycles=500):
# 计算回归的准确率
dataSet, labelSet = getStandardedMatData(rawData)
dataSize = np.shape(dataSet)[0]
weights = lrFunc(rawData, alpha, maxCycles)
px = sigmoid(dataSet * weights)
# 统计在训练集上，训练得到的回归函数有多少
trainErrCnt = 0
for i, pxi in enumerate(px):
if pxi < 0.5 and labelSet[i] == 1:
trainErrCnt += 1
elif pxi >= 0.5 and labelSet[i] == 0:
trainErrCnt += 1
trainAccuracy = 1 - trainErrCnt / dataSize
return trainAccuracy
if __name__ == "__main__":
filePath = "F:/2020AI_SummerCamp/dataSet/"
rawData = LoadFile.loadCSV(filePath + "diabetesN.csv")
# rawData = pd.read_table(filePath + 'testSet.txt', header=None)
print(calcAccuracy(rawData, newtonLogisticRegression))
