categoryHeader, npCategoryData = util.deleteColumnWithConstantValue((categoryHeader, npCategoryData))
numericalHeader, npNumericalData = util.deleteColumnWithConstantValue((numericalHeader, npNumericalData))
np.savetxt('./Data/reducedCategoryData.csv',npCategoryData,header=','.join(categoryHeader).encode('utf-8'),delimiter=',', fmt='%d',comments='')
np.savetxt('./Data/reducedNumericalData.csv',npNumericalData,header=','.join(numericalHeader).encode('utf-8'),delimiter=',', fmt='%.4f',comments='')
# z-score format
zscoreNumericalData = preprocessing.scale(npNumericalData)
np.savetxt('./Data/zscoreNumericalData.csv',zscoreNumericalData,header=','.join(numericalHeader).encode('utf-8'),delimiter=',', fmt='%.4f',comments='')
# bitformat for categoryData
preCategoryHeader, preCategoryData = bpModelDataPrcocessor.getPreProcessedFlattenCategoryData((categoryHeader, npCategoryData), mongoDataProcessor.getCategoryInfo())
np.savetxt('./Data/preCategoryData.csv',preCategoryData,header=','.join(preCategoryHeader).encode('utf-8'),delimiter=',', fmt='%d',comments='')
# PCA+KMeans for numericalData
PCAResultMap, transResultMap = bpModelDataPrcocessor.getAssociatedMapFromPCA((numericalHeader, zscoreNumericalData))
kmLists = bpModelDataPrcocessor.getKMeansListByCalculation((numericalHeader, zscoreNumericalData), (PCAResultMap, transResultMap), path='./Figures/')
bpModelDataPrcocessor.saveKMeansListToFile('./KMeansModel/', numericalHeader)
preNumericalHeader, preNumericalData = bpModelDataPrcocessor.getPreProcessedFlattenNumericalData((numericalHeader, zscoreNumericalData), dropTags=[])
np.savetxt('./Data/preNumericalData.csv',preNumericalData,header=','.join(preNumericalHeader).encode('utf-8'),delimiter=',', fmt='%d',comments='')
# ANN
bPModelTrainer = BPModelTrainer(
flattenCategoryHeader=preCategoryHeader,
flattenCategoryData=preCategoryData,
flattenNumericalHeader=preNumericalHeader,
flattenNumericalData=preNumericalData,
flattenTargetHeader=targetHeader,
flattenTargetData=targetData
)
# transport targetData to discrete value
bPModelTrainer.targetTransform()
CategoryTagHeader = dataBase.CategoryTagHeader
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,
# bitformat for categoryData
preCategoryHeader, preCategoryData = bpModelDataPrcocessor.getPreProcessedFlattenCategoryData(
(categoryHeader, npCategoryData), mongoDataProcessor.getCategoryInfo())
np.savetxt('./Data/preCategoryData.csv',
preCategoryData,
header=','.join(preCategoryHeader).encode('utf-8'),
delimiter=',',
fmt='%d',
comments='')
# PCA+KMeans for numericalData
PCAResultMap, transResultMap = bpModelDataPrcocessor.getAssociatedMapFromPCA(
(numericalHeader, zscoreNumericalData))
kmLists = bpModelDataPrcocessor.getKMeansListByCalculation(
(numericalHeader, zscoreNumericalData), (PCAResultMap, transResultMap),
path='./Figures/')
bpModelDataPrcocessor.saveKMeansListToFile('./KMeansModel/', numericalHeader)
preNumericalHeader, preNumericalData = bpModelDataPrcocessor.getPreProcessedFlattenNumericalData(
(numericalHeader, zscoreNumericalData), dropTags=[])
np.savetxt('./Data/preNumericalData.csv',
preNumericalData,
header=','.join(preNumericalHeader).encode('utf-8'),
delimiter=',',
fmt='%d',
comments='')
# ANN
bPModelTrainer = BPModelTrainer(flattenCategoryHeader=preCategoryHeader,
flattenCategoryData=preCategoryData,
flattenNumericalHeader=preNumericalHeader,