CategoryTagHeader.remove({"loanType":loanType})
for index in range(len(preCategoryHeader)):
CategoryTagHeader.insert_one(
{
"tagName": preCategoryHeader[index],
"updateTime": int(time.time()),
"version": version,
"loanType": loanType,
"index" : index
})
# Step12: get pre-processed numerical data
sortedMap, trans = bpModelDataPrcocessor.getAssociatedMapFromPCA((npNumericalHeader, npNumericalData))
kmLists = bpModelDataPrcocessor.getKMeansListByCalculation((npNumericalHeader, npNumericalData), (sortedMap, trans), path='./Figures/')
bpModelDataPrcocessor.saveKMeansListToFile('./KMeansModel/', npNumericalHeader)
preNumericalHeader, preNumericalData = bpModelDataPrcocessor.getPreProcessedFlattenNumericalData((npNumericalHeader, npNumericalData), dropTags=['livePlace', 'occupation', 'brandModel'])
with open('Data/PreProcessedFlattenNumericalData.csv', 'w') as f:
print >> f, ','.join(preNumericalHeader).encode('utf-8')
np.savetxt(f, preNumericalData, delimiter=',', fmt='%d') # please note the fmt arg
NumericalTagHeader = dataBase.NumericalTagHeader
NumericalTagHeader.remove({"loanType":loanType})
for index in range(len(preNumericalHeader)):
NumericalTagHeader.insert_one(
{
"tagName": preNumericalHeader[index],
"updateTime": int(time.time()),
"version": version,
"loanType": loanType,
