def traitementFichierTXT(indicatorSpi, unitEurostat, ageEurostat, sexEurostat,
nomFichierTXT):
dicIndicator = {}
dicNoCountry = {}
dicNation = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
minimumYearWithActualData = 999999
## added 20190326
iscedTOindicator = {
'ED0-2': 'edusl',
'ED3_4': 'edusup',
'ED5-8': 'edut',
'ED3-8': 'edust'
}
fichierTXT = open(nomFichierTXT, 'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iAge = dicEurostat['age']
iSex = dicEurostat['sex']
iIsced = dicEurostat['indic'] ## added 20190326
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
age = ligne[iAge].strip()
unit = ligne[iUnit].strip()
sex = ligne[iSex].strip()
indicator = iscedTOindicator[ligne[iIsced].strip()] ## added 20190326
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if sex == sexEurostat and age == ageEurostat and unit == unitEurostat and indicator == indicatorSpi: # added indicator check to if statement 20190326
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(
timeSerie, int(startYear), minimumYearWithActualData)
dicIndicator[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
spiLib.defnoCountry(dicNoCountry, fileLog)
dicIndicator = spiLib.reverseAndNormalizeDicNoIndicator(
dicIndicator, minimumYearWithActualData, int(endYear))
spiLibCreateTable.createTableCountryLevelEduTech(
dicIndicator, G_spiIndicator, minimumYearWithActualData, fileLog,
G_tableName)
def traitementFichierTXT(indicatorSpi, unitEurostat, flowEurostat, partnerEurostat, nomFichierTXT):
dicIndicator = {}
dicNoCountry = {}
dicNation = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
minimumYearWithActualData = 999999
fichierTXT = open(nomFichierTXT,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iFlow = dicEurostat['flow']
iPartner = dicEurostat['partner']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
flow = ligne[iFlow].strip()
unit = ligne[iUnit].strip()
partner = ligne[iPartner].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if flow == flowEurostat and partner == partnerEurostat and unit == unitEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(timeSerie,int(startYear),minimumYearWithActualData)
dicIndicator[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
spiLib.defnoCountry(dicNoCountry,fileLog)
dicIndicator = spiLib.reverseAndNormalizeDicNoIndicator(dicIndicator, minimumYearWithActualData, int(endYear))
spiLibCreateTable.createTableCountryLevelEduTech(dicIndicator,G_spiIndicator,minimumYearWithActualData,fileLog,G_tableName)
def traitementFichierTXT(indicatorInputEurostat, unitEurostat, nomFichierTXT):
startIndice = 0
dicIndicators = {}
dicNoCountry = {}
dicNation = {}
indicatorEurostat = indicatorInputEurostat
dicNation = DBAccess.lectureNationEurostat(dicNation)
#dicStartValue = dict(startIndice=1,startCountry='',startNace='',startIndicator='',startValeur=0)
minimumYearWithActualData = 999999
fichierTXT = open(nomFichierTXT,'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',') #RAPPEL strip enleve des extremites
indicator = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indicator in indicatorEurostat and unit == unitEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(timeSerie,int(startYear),minimumYearWithActualData)
dicIndicators = spiLib.defDicIndicators(country,indicator,vector,dicIndicators)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
spiLib.defnoCountry(dicNoCountry,fileLog)
dicIndicators = spiLib.reverseAndNormalizeDicIndicators(dicIndicators, minimumYearWithActualData, int(endYear))
spiLibCreateTable.createTableCountryLevelOpen(dicIndicators,minimumYearWithActualData,fileLog,G_tableName)
def traitementFichierTXT(indicatorSpi, categoryEurostat, ageEurostat,
iscoEurostat, unitEurostat, nomFichierTXT,
nomFichierTXT2, naceEurostat, itemEurostat,
unitEurostat2):
dicIndicator = {}
dicIndicator2 = {}
dicNoCountry = {}
dicNation = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
minimumYearWithActualData = 999999
fichierTXT = open(nomFichierTXT, 'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iCategory = dicEurostat['category']
iUnit = dicEurostat['unit']
iIsco = dicEurostat['isco']
iAge = dicEurostat['age']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
category = ligne[iCategory].strip()
isco = ligne[iIsco].strip()
age = ligne[iAge].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if unit == unitEurostat and age == ageEurostat and isco == iscoEurostat and category == categoryEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(
timeSerie, int(startYear), minimumYearWithActualData)
dicIndicator[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fichierTXT.close()
spiLib.defnoCountry(dicNoCountry, fileLog)
fichierTXT = open(nomFichierTXT2, 'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iNace = dicEurostat['nace']
iUnit = dicEurostat['unit']
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear2 = geotime[1].strip()
startYear2 = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
nace = ligne[iNace].strip()
unit = ligne[iUnit].strip()
indic = ligne[iIndic].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if unit == unitEurostat2 and indic == itemEurostat and nace == naceEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear2, endYear2)
dicIndicator2[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fichierTXT.close()
dicIndicator = spiLib.reverseAndNormalizeDic(dicIndicator,
minimumYearWithActualData,
int(endYear))
dicIndicator2 = spiLib.reverseAndNormalizeDic(dicIndicator2,
minimumYearWithActualData,
int(endYear))
spiLibCreateTable.createTableCountryLevelFdi(dicIndicator, dicIndicator2,
G_spiIndicator,
minimumYearWithActualData,
fileLog, G_tableName)
def traitementFichierTXT(indicatorInput, indicatorInputEurostat, nomenclature,
compteEurostat):
startIndice = 0
dicIndicator = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicNation = {}
indicatorSpi = indicatorInput
indicatorEurostat = indicatorInputEurostat
Unit = G_Unit
dicNace = spiLib.defSelectdicNace(nomenclature, compteEurostat)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,
startCountry='',
startNace='',
startIndicator='',
startValeur=0,
startYear=1900)
minStartYear = 99999
maxEndYear = -1
fichiersTXT.sort()
fichiersTXT.reverse()
for txt in fichiersTXT:
fichierTXT = open(txt, 'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iSize = dicEurostat['size']
iSector = dicEurostat['sector']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n') #RAPPEL strip enleve des extremites
ligne = ligne.split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
# la colonne sector existait pour le nama_nace64_e.tsv
# il a disparu dans le esa2010 mais on garde le test
if iSector == -1:
sector = 'S1'
else:
sector = ligne[iSector].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indicator == indicatorEurostat and (unit == Unit) and (
sector == 'S1') and dicNace.has_key(nace):
dicNaceCheck[
nace] = nace #on remplit le dic pour faire un check si autant de nace que dans la table SPI
vector = spiLib.defVectorYears(
timeSerie, startYear,
endYear) #traitement de la serie Eurostat
dicStartValue = spiLib.defDicStartValue(
timeSerie, country, nace, indicator, dicStartValue,
endYear)
dicIndicator = spiLib.defDicIndicator(
country, nace, vector, dicIndicator)
minStartYear, maxEndYear = spiLib.defMinMaxYear(
startYear, minStartYear, endYear, maxEndYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
#retour avec l'annee de la 1er valeur existante dans les vecteurs
#different de la 1er annee ou vecteur le plus long car la valeur peut etre ':'
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+\
' valeur '+str(dicStartValue['startValeur'])+' startYear '+str(dicStartValue['startYear'])+'\n')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
#test des annee de debut, soit par valeur reelle ou par vecteur la valeur peut etre ':'
if minStartYear != dicStartValue['startYear']:
fileLog.write('annee min. pour les vecteurs =' + str(minStartYear) +
' annee min. avec une valeur =' +
str(dicStartValue['startYear']) + '\n')
minStartYear = dicStartValue['startYear']
#traitement indicator
dicIndicator = spiLib.reverseAndNormalizeDicIndicator(
dicIndicator, minStartYear, maxEndYear)
spiLibCreateTable.createTable(nomenclature, dicIndicator, fileLog,
minStartYear, dicNace, indicatorSpi,
compteEurostat, G_tableName, G_FileExt)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear, fileLog,
indicatorSpi, compteEurostat, G_tableName)
def traitementFichierTXT(tableName, spiIndicator, indicEurostat, postEurostat, unitEurostat, partnerEurostat, gdpIndicEurostat, nomFichierTXT, nomFichierTXTGdp, nomFichierTXT2, partnerEurostat2, itemEurostat, gdpUnit):
dicIndicator = {}
dicIndicator2 = {}
dicGdp = {}
dicNoCountry = {}
dicNation = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
minimumYearWithActualData = 999999
fichierTXT = open(nomFichierTXT,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iIndic = dicEurostat['indic']
iPostTime = dicEurostat['post']
iPartner = dicEurostat['partner']
iGeo = dicEurostat['geotime']
posttime = lstrec[iPostTime].split('\t')
endYear = int(posttime[1].strip())
startYear = int(posttime[-1].strip())
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
indic = ligne[iIndic].strip()
geo = ligne[iGeo].strip()
partner = ligne[iPartner].strip()
postTime = ligne[iPostTime].split('\t')
post = postTime[0].strip()
try:
country = dicNation[geo]
timeSerie = postTime[1:]
if partner == partnerEurostat and post == postEurostat and indic == indicEurostat :
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(timeSerie,int(startYear),minimumYearWithActualData)
dicIndicator[country] = vector
except:
dicNoCountry[geo] = geo
fichierTXT.close()
dicIndicator = spiLib.reverseAndNormalizeDic(dicIndicator, minimumYearWithActualData, endYear)
fileEndYear = endYear
fichierTXT = open(nomFichierTXT2,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iIndic = dicEurostat['indic']
iPartnerTime = dicEurostat['partner']
iGeo = dicEurostat['geotime']
iItem = dicEurostat['item']
geotime = lstrec[iGeo].split('\t')
endYear2 = int(geotime[1].strip())
startYear2 = int(geotime[-1].strip())
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
indic = ligne[iIndic].strip()
item = ligne[iItem].strip()
partner = ligne[iPartnerTime].strip()
geotime = ligne[iGeo].split('\t')
geo = geotime[0].strip()
try:
country = dicNation[geo]
timeSerie = geotime[1:]
if partner == partnerEurostat2 and indic == indicEurostat and item == itemEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear2, endYear2)
dicIndicator2[country] = vector
except:
dicNoCountry[geo] = geo
fichierTXT.close()
dicIndicator2 = spiLib.reverseAndNormalizeDic(dicIndicator2, startYear2, endYear2)
finalEndYear = endYear2
for country in dicIndicator :
if country not in dicIndicator2 :
dicIndicator2[country] = []
for i in range(startYear2-1, endYear2) :
dicIndicator2[country].append(':')
for country in dicIndicator2 :
if country not in dicIndicator :
dicIndicator[country] = []
for i in range(minimumYearWithActualData-1, endYear) :
dicIndicator[country].append(':')
yearGap = startYear2 - endYear - 1
if yearGap == 0 :
for country in dicIndicator :
dicIndicator[country].extend(dicIndicator2[country])
elif yearGap > 0 :
fillingVector = []
for i in range(0, yearGap) :
fillingVector.append(':')
for country in dicIndicator :
dicIndicator[country].extend(fillingVector)
dicIndicator[country].extend(dicIndicator2[country])
elif yearGap < 0 :
for country in dicIndicator :
del dicIndicator[country][yearGap:]
for country in dicIndicator :
dicIndicator[country].extend(dicIndicator2[country])
fichierTXT = open(nomFichierTXTGdp,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
iUnit = dicEurostat['unit']
geotime = lstrec[iGeoTime].split('\t')
endYear = int(geotime[1].strip())
startYear = int(geotime[-1].strip())
for ligneTXT in fichierTXT :
ligne = ligneTXT.strip('\n').split(',')
indic = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEurostat = geoTime[0].strip()
try:
country = dicNation[geoEurostat]
timeSerie = geoTime[1:]
if indic == gdpIndicEurostat and unit == gdpUnit:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
dicGdp[country] = vector
except:
dicNoCountry[geoEurostat] = geoEurostat
fichierTXT.close()
dicGdp = spiLib.reverseAndNormalizeDic(dicGdp, minimumYearWithActualData, finalEndYear)
spiLib.defnoCountry(dicNoCountry,fileLog)
spiLibCreateTable.createTableCountryLevelFdi(dicIndicator,dicGdp,spiIndicator,minimumYearWithActualData,fileLog,tableName)
def traitementFichierTXT(indicatorEurostatDenominator, unitDenominator,
unitNumerator, nomenclature, filesDenominator,
fileNumerator, indicatorSpi, fileLog, tableName):
dicIndicatorNumerator = {}
dicIndicatorDenominator = {}
dicNoCountry = {}
dicNation = {}
dicNaceCheck = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicNace = spiLib.defSelectdicNace(nomenclature, 'nama')
minimumYearWithActualData = 999999
maxEndYear = -1
filesDenominator.sort()
filesDenominator.reverse()
file = open(fileNumerator, 'r')
line1st = file.readline()
list1st = line1st.split(',')
dicEurostat = spiLib.defDicEurostat(list1st)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iGeoTime = dicEurostat['geotime']
geotime = list1st[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#This code is added to create special aggregates asked on 30-09-2016
if (indicatorSpi == 'patintens'
or indicatorSpi == 'patintrd') and nomenclature == 'nace2':
dicNace['C10'] = 'C'
dicNace['C11'] = 'C'
dicNace['C12'] = 'C'
dicNace['C13'] = 'C'
dicNace['C14'] = 'C'
dicNace['C15'] = 'C'
dicNace['C31'] = 'C'
dicNace['C32'] = 'C'
#________________________________________________________________________
for line in file:
lineList = line.strip('\n').split(',')
nace = lineList[iNace].strip()
unit = lineList[iUnit].strip()
geoTime = lineList[iGeoTime].split('\t')
geo = geoTime[0].strip()
try:
dicNaceCheck[nace] = nace
country = dicNation[geo]
timeSerie = geoTime[1:]
if dicNace.has_key(nace) and unit == unitNumerator:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(
timeSerie, int(startYear), minimumYearWithActualData)
dicIndicatorNumerator = spiLib.defDicIndicator(
country, nace, vector, dicIndicatorNumerator)
if int(endYear) > maxEndYear:
maxEndYear = int(endYear)
except:
dicNoCountry[geo] = geo
file.close()
dicIndicatorNumerator = spiLib.reverseAndNormalizeDic(
dicIndicatorNumerator, minimumYearWithActualData, maxEndYear)
#This code is added to create special aggregates asked on 30-09-2016
if (indicatorSpi == 'patintens'
or indicatorSpi == 'patintrd') and nomenclature == 'nace2':
for country in dicIndicatorNumerator:
try:
C10 = dicIndicatorNumerator[country]['C10']
C11 = dicIndicatorNumerator[country]['C11']
C12 = dicIndicatorNumerator[country]['C12']
except:
C10 = []
C11 = []
C12 = []
try:
C13 = dicIndicatorNumerator[country]['C13']
C14 = dicIndicatorNumerator[country]['C14']
C15 = dicIndicatorNumerator[country]['C15']
except:
C13 = []
C14 = []
C15 = []
try:
C31 = dicIndicatorNumerator[country]['C31']
C32 = dicIndicatorNumerator[country]['C32']
except:
C31 = []
C32 = []
res = []
for i in range(0, len(C10)):
if C10[i] == ':' or C11[i] == ':' or C12[i] == ':':
res.append(':')
else:
res.append(
str(float(C10[i]) + float(C11[i]) + float(C12[i])))
if len(res) > 0:
dicIndicatorNumerator[country]['C10-C12'] = res
res = []
for i in range(0, len(C13)):
if C13[i] == ':' or C14[i] == ':' or C15[i] == ':':
res.append(':')
else:
res.append(
str(float(C13[i]) + float(C14[i]) + float(C15[i])))
if len(res) > 0:
dicIndicatorNumerator[country]['C13-C15'] = res
res = []
for i in range(0, len(C31)):
if C31[i] == ':' or C32[i] == ':':
res.append(':')
else:
res.append(str(float(C31[i]) + float(C32[i])))
if len(res) > 0:
dicIndicatorNumerator[country]['C31_C32'] = res
#__________________________________________________________________________
dicIndicatorNumerator = spiLibTotal.calcNaceAggregates(
dicIndicatorNumerator, nomenclature, 'nama')
for txt in filesDenominator:
file = open(txt, 'r')
line1st = file.readline()
list1st = line1st.split(',')
dicEurostat = spiLib.defDicEurostat(list1st)
iUnit = dicEurostat['unit']
try:
iIndic = dicEurostat['indic']
except:
pass
iNace = dicEurostat['nace']
iGeoTime = dicEurostat['geotime']
geotime = list1st[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for line in file:
lineList = line.strip('\n').split(',')
nace = lineList[iNace].strip()
if iIndic != -1:
indicator = lineList[iIndic].strip()
else:
indicator = 'noindicator'
unit = lineList[iUnit].strip()
geoTime = lineList[iGeoTime].split('\t')
geo = geoTime[0].strip()
try:
dicNaceCheck[nace] = nace
country = dicNation[geo]
timeSerie = geoTime[1:]
if indicator != 'noindicator':
if indicator == indicatorEurostatDenominator and dicNace.has_key(
nace) and unit == unitDenominator:
vector = spiLib.defVectorYears(timeSerie, startYear,
endYear)
dicIndicatorDenominator = spiLib.defDicIndicator(
country, nace, vector, dicIndicatorDenominator)
else:
if dicNace.has_key(nace) and unit == unitDenominator:
vector = spiLib.defVectorYears(timeSerie, startYear,
endYear)
dicIndicatorDenominator = spiLib.defDicIndicator(
country, nace, vector, dicIndicatorDenominator)
except:
dicNoCountry[geo] = geo
file.close()
dicIndicatorDenominator = spiLib.reverseAndNormalizeDic(
dicIndicatorDenominator, minimumYearWithActualData, maxEndYear)
dicIndicatorDenominator = spiLibTotal.calcNaceAggregates(
dicIndicatorDenominator, nomenclature, 'nama')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
spiLibCreateTable.createTableNacePercentage(
nomenclature, dicIndicatorNumerator, dicIndicatorDenominator,
indicatorSpi, minimumYearWithActualData, fileLog, tableName)
def traitementFichierTXT(indicatorInputEurostat, unitEurostat, nomenclature, sbsFile = ''):
startIndice = 0
dicIndicator = {}
dicIndicatorTotal = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicNation = {}
indicatorEurostat = indicatorInputEurostat
dicNace = spiLib.defSelectdicNaceSkillTech(nomenclature)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,startCountry='',startNace='',startIndicator='',startValeur=0)
minStartYear = 99999
maxEndYear = -1
for txt in fichiersTXT:
fichierTXT = open(txt,'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#nace_r1,indic_sb,size_emp,geo\time
#E,V11110,TOTAL,ES 9037 6410 3544 3311 3336 3084
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',') #RAPPEL strip enleve des extremites
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indicator == indicatorEurostat and dicNace.has_key(nace) and unit == unitEurostat:
dicNaceCheck[nace] = nace
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
dicStartValue = spiLib.defDicStartValue(timeSerie,country,nace,indicator,dicStartValue, endYear)
dicIndicator = spiLib.defDicIndicator(country,nace,vector,dicIndicator)
if int(endYear) > maxEndYear :
maxEndYear = int(endYear)
if int(startYear) < minStartYear :
minStartYear = int(startYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fichierTXT.close()
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+' valeur '+str(dicStartValue['startValeur'])+'\n')
spiLib.defnoCountry(dicNoCountry,fileLog)
spiLib.defDicNaceCheck(dicNaceCheck,dicNace,fileLog)
dicIndicator = spiLib.reverseAndNormalizeDic(dicIndicator, minStartYear, maxEndYear)
if nomenclature == 'nace2' :
dicSbs = {}
fichierTXT = open(sbsFile,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for ligneTXT in fichierTXT :
ligne = ligneTXT.strip('\n').split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indicator == 'V12150' and nace in ('N80', 'N81', 'N82') :
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
dicSbs = spiLib.defDicIndicator(country,nace,vector,dicSbs)
except:
continue
fichierTXT.close()
dicSbs = spiLib.reverseAndNormalizeDic(dicSbs, minStartYear, maxEndYear)
dicSbs = spiLibTotal.createSkillTechNace2SbsTotal(dicSbs)
dicRatio = spiLibTotal.createSkillTechNace2Ratio(dicSbs)
del dicSbs
dicIndicator = spiLibTotal.addSkillTechNace2RemainingCodes(dicIndicator, dicRatio)
spiLibCreateTable.createTableSkillTech(nomenclature,dicIndicator,minStartYear,fileLog,G_tableName)
def traitementFichierTXT(indicatorSpi, indicatorEurostat, nomFichierTXT, nomFichierTXT2, indicatorEurostat2, eurostatUnit):
dicIndicator = {}
dicIndicator2 = {}
dicNoCountry = {}
dicNation = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
minimumYearWithActualData = 999999
fichierTXT = open(nomFichierTXT,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = int(geotime[1].strip())
startYear = int(geotime[-1].strip())
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
indic = ligne[iIndic].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indic == indicatorEurostat :
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(timeSerie,int(startYear),minimumYearWithActualData)
dicIndicator[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fichierTXT.close()
dicIndicator = spiLib.reverseAndNormalizeDicNoIndicator(dicIndicator, minimumYearWithActualData, int(endYear))
fichierTXT = open(nomFichierTXT2,'r')
rec1er = fichierTXT.readline()
lstrec = rec1er.split(',')
dicEurostat = spiLib.defDicEurostat(lstrec)
iIndic = dicEurostat['indic']
iUnit = dicEurostat['unit']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear2 = int(geotime[1].strip())
startYear2 = int(geotime[-1].strip())
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n').split(',')
indic = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if indic == indicatorEurostat2 and unit == eurostatUnit :
vector = spiLib.defVectorYears(timeSerie, startYear2, endYear2)
dicIndicator2[country] = vector
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fichierTXT.close()
dicIndicator2 = spiLib.reverseAndNormalizeDicNoIndicator(dicIndicator2, int(startYear2), int(endYear2))
for country in dicIndicator :
if country not in dicIndicator2 :
dicIndicator2[country] = []
for i in range(startYear2-1, endYear2) :
dicIndicator2[country].append(':')
for country in dicIndicator2 :
if country not in dicIndicator :
dicIndicator[country] = []
for i in range(minimumYearWithActualData-1, endYear) :
dicIndicator[country].append(':')
yearGap = startYear2 - endYear - 1
if yearGap == 0 :
for country in dicIndicator :
dicIndicator[country].extend(dicIndicator2[country])
elif yearGap > 0 :
fillingVector = []
for i in range(0, yearGap) :
fillingVector.append(':')
for country in dicIndicator :
dicIndicator[country].extend(fillingVector)
dicIndicator[country].extend(dicIndicator2[country])
elif yearGap < 0 :
for country in dicIndicator :
del dicIndicator[country][yearGap:]
for country in dicIndicator :
dicIndicator[country].extend(dicIndicator2[country])
spiLib.defnoCountry(dicNoCountry,fileLog)
spiLibCreateTable.createTableCountryLevelEduTech(dicIndicator,G_spiIndicator,minimumYearWithActualData,fileLog,G_tableName)
def traitementFichierTXT(indicatorEurostatDenominator, indicatorEurostatNumerator, unitDenominator, unitNumerator, nomenclature, filesDenominator, filesNumerator, baseYear, indicatorSpi, fileLog, tableName):
dicIndicatorNumerator = {}
dicIndicatorDenominator = {}
dicNoCountry = {}
dicNation = {}
dicNaceCheck = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicNace = spiLib.defSelectdicNace(nomenclature, 'nama')
minimumYearWithActualData = 999999
maxEndYear = -1
filesNumerator.sort()
filesNumerator.reverse()
filesDenominator.sort()
filesDenominator.reverse()
for txt in filesNumerator :
file = open(txt, 'r')
line1st = file.readline()
list1st = line1st.split(',')
dicEurostat = spiLib.defDicEurostat(list1st)
iUnit = dicEurostat['unit']
iIndic = dicEurostat['indic']
iNace = dicEurostat['nace']
iGeoTime = dicEurostat['geotime']
geotime = list1st[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for line in file :
lineList = line.strip('\n').split(',')
nace = lineList[iNace].strip()
indicator = lineList[iIndic].strip()
unit = lineList[iUnit].strip()
geoTime = lineList[iGeoTime].split('\t')
geo = geoTime[0].strip()
try :
dicNaceCheck[nace] = nace
country = dicNation[geo]
timeSerie = geoTime[1:]
if indicator == indicatorEurostatNumerator and dicNace.has_key(nace) and unit == unitNumerator:
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(timeSerie,int(startYear),minimumYearWithActualData)
dicIndicatorNumerator = spiLib.defDicIndicator(country,nace,vector,dicIndicatorNumerator)
if int(endYear) > maxEndYear :
maxEndYear = int(endYear)
except :
dicNoCountry[geo] = geo
file.close()
dicIndicatorNumerator = spiLib.reverseAndNormalizeDic(dicIndicatorNumerator, minimumYearWithActualData, maxEndYear)
dicIndicatorNumerator = spiLibTotal.calcNaceAggregates(dicIndicatorNumerator, nomenclature, 'nama')
for txt in filesDenominator :
file = open(txt, 'r')
line1st = file.readline()
list1st = line1st.split(',')
dicEurostat = spiLib.defDicEurostat(list1st)
iUnit = dicEurostat['unit']
iIndic = dicEurostat['indic']
iNace = dicEurostat['nace']
iGeoTime = dicEurostat['geotime']
iSector = dicEurostat['sector']
geotime = list1st[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for line in file :
lineList = line.strip('\n').split(',')
nace = lineList[iNace].strip()
indicator = lineList[iIndic].strip()
unit = lineList[iUnit].strip()
geoTime = lineList[iGeoTime].split('\t')
if iSector == -1 :
sector = 'S1'
else :
sector = lineList[iSector].strip()
geo = geoTime[0].strip()
try :
dicNaceCheck[nace] = nace
country = dicNation[geo]
timeSerie = geoTime[1:]
if indicator == indicatorEurostatDenominator and dicNace.has_key(nace) and unit == unitDenominator and sector == 'S1' :
vector = spiLib.defVectorYears(timeSerie, startYear, endYear)
dicIndicatorDenominator = spiLib.defDicIndicator(country,nace,vector,dicIndicatorDenominator)
except :
dicNoCountry[geo] = geo
file.close()
dicIndicatorDenominator = spiLib.reverseAndNormalizeDic(dicIndicatorDenominator, minimumYearWithActualData, maxEndYear)
dicIndicatorDenominator = spiLibTotal.calcNaceAggregates(dicIndicatorDenominator, nomenclature, 'nama')
#The following lines are added on demand of B2 team to calculate aggregates that cannot be extracted from the nama_nace10_e file
if nomenclature == 'nace2' and indicatorEurostatDenominator == 'EMP':
dicIndicatorDenominator = spiLibTotal.calcNace2EmpAggr(dicIndicatorDenominator)
##############################################################################################################################
spiLib.defnoCountry(dicNoCountry,fileLog)
spiLib.defDicNaceCheck(dicNaceCheck,dicNace,fileLog)
spiLibCreateTable.createTableDomesticIndex(nomenclature,dicIndicatorNumerator, dicIndicatorDenominator, indicatorSpi, minimumYearWithActualData, baseYear,fileLog, tableName)
def traitementFichierTXT(indicatorInput, indicatorInputEurostat, nomenclature,
compteEurostat):
startIndice = 0
dicIndicator = {}
dicIndicatorTotal = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicAgregatNace = {}
dicNation = {}
indicatorSpi = indicatorInput
indicatorSpiTotal = G_IndicatorSPI_T
indicatorEurostat = indicatorInputEurostat
dicNace = spiLib.defSelectdicNace(nomenclature, compteEurostat)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,
startCountry='',
startNace='',
startIndicator='',
startValeur=0,
startYear=1900)
minStartYear = 99999
maxEndYear = -1
for txt in fichiersTXT:
fichierTXT = open(txt, 'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iSize = dicEurostat['size']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#nace_r1,indic_sb,size_emp,geo\time
#E,V11110,TOTAL,ES 9037 6410 3544 3311 3336 3084
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n') #RAPPEL strip enleve des extremites
ligne = ligne.split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
if (indicator == indicatorEurostat ) and\
((nomenclature == 'nace1' and dicNace.has_key(nace)) or \
(nomenclature == 'nace2' and len(nace) < 4)):
dicNaceCheck[
nace] = nace #on remplit le dic pour faire un check si autant de nace que dans la table SPI
vector = spiLib.defVectorYears(
timeSerie, startYear,
endYear) #traitement de la serie Eurostat
dicStartValue = spiLib.defDicStartValue(
timeSerie, country, nace, indicator, dicStartValue,
endYear)
dicIndicator = spiLib.defDicIndicator(
country, nace, vector, dicIndicator)
minStartYear, maxEndYear = spiLib.defMinMaxYear(
startYear, minStartYear, endYear, maxEndYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+\
' valeur '+str(dicStartValue['startValeur'])+' startYear '+str(dicStartValue['startYear'])+'\n')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
minStartYear = dicStartValue['startYear']
dicIndicator = spiLib.reverseAndNormalizeDicIndicator(
dicIndicator, minStartYear, maxEndYear)
#creation indicateur SPI par ex vabus avec en retour le dic des agregats
dicAgregatNace = spiLibCreateTable.createTable(nomenclature, dicIndicator,
fileLog, minStartYear,
dicNace, indicatorSpi,
compteEurostat, G_tableName)
if indicatorSpiTotal != 'noTotal':
#creation indicateur total SPI par ex vabussh
spiLibCreateTable.createTableTotal(nomenclature, dicAgregatNace,
dicIndicator, minStartYear, fileLog,
dicNace, indicatorSpiTotal,
compteEurostat, G_tableName)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear,
fileLog, indicatorSpiTotal,
compteEurostat, G_tableName)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear, fileLog,
indicatorSpi, compteEurostat, G_tableName)
def traitementFichierTXT(indicatorInput, indicatorInputEurostat, nomenclature,
compteEurostat):
startIndice = 0
dicIndicator = {}
dicIndicatorTotal = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicNation = {}
dicSize = {}
indicatorSpi = indicatorInput
indicatorEurostat = indicatorInputEurostat
dicNace = spiLib.defSelectdicNace(nomenclature, compteEurostat)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,
startCountry='',
startNace='',
startIndicator='',
startValeur=0,
startYear=1900)
minStartYear = 99999
maxEndYear = -1
for txt in fichiersTXT:
fichierTXT = open(txt, 'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iSize = dicEurostat['size']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#nace_r1,indic_sb,size_emp,geo\time
#E,V11110,TOTAL,ES 9037 6410 3544 3311 3336 3084
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n') #RAPPEL strip enleve des extremites
ligne = ligne.split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
size = ligne[iSize].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
#print indicator,indicatorEurostat,indicatorInput,size,nomenclature,nace
if (indicator == indicatorEurostat and (G_LstSize.count(size))) and\
((nomenclature == 'nace1' and dicNace.has_key(nace)) or \
(nomenclature == 'nace2' and len(nace) < 4)):
dicSize[size] = size #pour connaitre les size de eurostat
try: #on cherche l'indicateur SPI correspondant
indicator_size = indicatorSpi + '_' + G_DicSize[size]
except:
fileLog.write('pas de size ' + size +
' indicateur : ' + indicator +
' country : ' + country + '\n')
continue #on passe on record suivant
dicNaceCheck[
nace] = nace #on remplit le dic pour faire un check si autant de nace que dans la table SPI
vector = spiLib.defVectorYears(timeSerie, startYear,
endYear)
dicStartValue = spiLib.defDicStartValue(
timeSerie, country, nace, indicator, dicStartValue,
endYear)
dicIndicator = spiLib.defDicIndicatorSize(
country, nace, vector, indicator_size, dicIndicator)
minStartYear, maxEndYear = spiLib.defMinMaxYear(
startYear, minStartYear, endYear, maxEndYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+\
' valeur '+str(dicStartValue['startValeur'])+' startYear '+str(dicStartValue['startYear'])+'\n')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
keySize = dicSize.keys()
keySize.sort()
for s in keySize:
fileLog.write(' List Size in Eurostat Input : ' + s + '\n')
minStartYear = dicStartValue['startYear']
dicIndicator = spiLib.reverseAndNormalizeDicIndicatorSize(
dicIndicator, minStartYear, maxEndYear)
spiLibCreateTable.createTableSize(nomenclature, dicIndicator, fileLog,
minStartYear, dicNace, indicatorSpi,
compteEurostat, G_tableName)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear, fileLog,
indicatorSpi, compteEurostat, G_tableName,
G_DicSize)
def traitementFichierTXT(indicatorInput, indicatorInputEurostat, nomenclature,
compteEurostat):
startIndice = 0
dicIndicator = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicNation = {}
indicatorSpi = indicatorInput
indicatorEurostat = indicatorInputEurostat
Unit = G_Unit
dicNace = spiLib.defSelectdicNace(nomenclature, compteEurostat)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,
startCountry='',
startNace='',
startIndicator='',
startValeur=0,
startYear=1900)
minStartYear = 99999
maxEndYear = -1
fichiersTXT.sort()
fichiersTXT.reverse()
for txt in fichiersTXT:
fichierTXT = open(txt, 'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#recherche de la position de chaque variable dans input eurostat
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iSector = dicEurostat['sector']
iSize = dicEurostat['size']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#nace 1 : unit,sector,nace_r1,indic_na,geo\time
#nace 2 : unit,nace_r2,indic_na,sector,geo\time
#MIO_EUR,A,B1G,AT : : : 3781.7 4375.5 4322.6 3827.4 3542.7 3921.8 3763.1
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n') #RAPPEL strip enleve des extremites
ligne = ligne.split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
unit = ligne[iUnit].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
if iSector == -1:
sector = 'S1'
else:
sector = ligne[iSector].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
#indicateur pour savoir si on doit selectionner les indicateurs
#dans la liste definie dans la table oracle ou uniquement sur la longueur (4)
#la regle est si nace1 alors on prend la liste
#si nace2 et nama on prend la liste sur sbs on teste sur la longueur max 4
if indicator == indicatorEurostat and (unit == Unit) and (
sector == 'S1') and dicNace.has_key(nace):
dicNaceCheck[
nace] = nace #on remplit le dic pour faire un check si autant de nace que dans la table SPI
vector = spiLib.defVectorYears(
timeSerie, startYear,
endYear) #traitement de la serie Eurostat
dicStartValue = spiLib.defDicStartValue(
timeSerie, country, nace, indicator, dicStartValue,
endYear)
dicIndicator = spiLib.defDicIndicator(
country, nace, vector, dicIndicator)
minStartYear, maxEndYear = spiLib.defMinMaxYear(
startYear, minStartYear, endYear, maxEndYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+\
' valeur '+str(dicStartValue['startValeur'])+' startYear '+str(dicStartValue['startYear'])+'\n')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
minStartYear = dicStartValue['startYear']
dicIndicator = spiLib.reverseAndNormalizeDicIndicator(
dicIndicator, minStartYear, maxEndYear)
spiLibCreateTable.createTableGrowth(nomenclature, dicIndicator, fileLog,
minStartYear, dicNace, indicatorSpi,
compteEurostat, G_tableName, G_Growth,
G_FileExt)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear, fileLog,
indicatorSpi, compteEurostat, G_tableName)
def traitementFichierTXT(indicatorInput, nomenclature, compteEurostat):
startIndice = 0
dicIndicator = {}
dicIndicatorTotal = {}
dicNoCountry = {}
dicNaceCheck = {}
dicNace = {}
dicNation = {}
dicIndicatorDomain = {}
dicIndicatorDomain = FileAccess.lectureIndicator(dicIndicatorDomain,
'competition', dirUse)
indicatorSpi = dicIndicatorDomain[indicatorInput]
dicNace = spiLib.defSelectdicNace(nomenclature, compteEurostat)
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicStartValue = dict(startIndice=1,
startCountry='',
startNace='',
startIndicator='',
startValeur=0,
startYear=1900)
minStartYear = 99999
maxEndYear = -1
for txt in fichiersTXT:
fichierTXT = open(txt, 'r')
rec1er = fichierTXT.readline() #1er rec avec les meta
lstrec = rec1er.split(',')
#on selectionne les colonne de l'input d'Eurostat
dicEurostat = spiLib.defDicEurostat(lstrec)
iUnit = dicEurostat['unit']
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iSize = dicEurostat['size']
iGeoTime = dicEurostat['geotime']
geotime = lstrec[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
#nace_r1,indic_sb,size_emp,geo\time
#E,V11110,TOTAL,ES 9037 6410 3544 3311 3336 3084
for ligneTXT in fichierTXT:
ligne = ligneTXT.strip('\n') #RAPPEL strip enleve des extremites
ligne = ligne.split(',')
nace = ligne[iNace].strip()
indicator = ligne[iIndic].strip()
sizeEurostat = ligne[iSize].strip()
#la colonne size n'existe pas pour le NACE2 pour les sbs_na *on rempli donc la condition a chaque fois
if nomenclature == 'nace2' and compteEurostat == 'sbs':
sizeEurostat = 'TOTAL'
else:
sizeEurostat = ligne[iSize].strip()
geoTime = ligne[iGeoTime].split('\t')
geoEuroStat = geoTime[0].strip()
try:
country = dicNation[geoEuroStat]
timeSerie = geoTime[1:]
#indicateur pour savoir si on doit selectionner les indicateurs
#dans la liste definie dans la table oracle ou uniquement sur la longueur (4)
#la regle est si nace1 alors on prend la liste
#si bd on prend tout
#if indicator == indicatorInput and sizeEurostat == G_Size and dicNace.has_key(nace):
if indicator == indicatorInput and sizeEurostat == G_Size:
dicNaceCheck[
nace] = nace #on remplit le dic pour faire un check si autant de nace que dans la table SPI
vector = spiLib.defVectorYears(timeSerie, startYear,
endYear)
dicStartValue = spiLib.defDicStartValue(
timeSerie, country, nace, indicator, dicStartValue,
endYear)
dicIndicator = spiLib.defDicIndicator(
country, nace, vector, dicIndicator)
minStartYear, maxEndYear = spiLib.defMinMaxYear(
startYear, minStartYear, endYear, maxEndYear)
except:
dicNoCountry[geoEuroStat] = geoEuroStat
fileLog.write('highIndice '+str(dicStartValue['startIndice'])+' highCountry '+dicStartValue['startCountry']+\
' Indicator '+dicStartValue['startIndicator']+' Nace '+dicStartValue['startNace']+\
' valeur '+str(dicStartValue['startValeur'])+' startYear '+str(dicStartValue['startYear'])+'\n')
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
minStartYear = dicStartValue['startYear']
#traitement indicator
dicIndicator = spiLib.reverseAndNormalizeDicIndicator(
dicIndicator, minStartYear, maxEndYear)
spiLibCreateTable.createTable(nomenclature, dicIndicator, fileLog,
minStartYear, dicNace, indicatorSpi,
compteEurostat, G_tableName)
spiLibCreateTable.createTableNE(nomenclature, dicNation, endYear, fileLog,
indicatorSpi, compteEurostat, G_tableName)
def traitementFichierTXT(nomenclature, indicNumerator, indicDenominator,
filePaths):
dicNumerator = {}
dicDenominator = {}
dicNace = spiLib.defSelectdicNace(nomenclature, 'sbs')
dicNation = DBAccess.lectureNationEurostat({})
maxEndYear = -1
minStartYear = 9999
for filePath in filePaths:
with open(filePath, 'r') as file:
csvFile = csv.reader(file, delimiter='\t')
firstLine = csvFile.next()
metaLabel = firstLine[0].split(',')
dicEurostat = spiLib.defDicEurostat(metaLabel)
iNace = dicEurostat['nace']
iIndic = dicEurostat['indic']
iGeoTime = dicEurostat['geotime']
iSize = dicEurostat['size']
endYear = firstLine[1].strip()
startYear = firstLine[-1].strip()
if int(endYear) > maxEndYear:
maxEndYear = int(endYear)
if int(startYear) < minStartYear:
minStartYear = int(startYear)
for line in csvFile:
meta = line[0].split(',')
code = meta[iNace]
country = meta[iGeoTime]
indic = meta[iIndic]
if nomenclature == 'nace2':
size = 'TOTAL'
else:
size = meta[iSize]
if code in dicNace and country in dicNation and size == 'TOTAL':
if indic == indicNumerator or indic == indicDenominator:
vector = []
vector.append(endYear)
vector.extend([
re.sub('[" ",a-z]', '', element)
for element in line[1:]
])
vector.append(startYear)
if indic == indicNumerator:
dicNumerator = spiLib.defDicIndicator(
country, code, vector, dicNumerator)
else:
dicDenominator = spiLib.defDicIndicator(
country, code, vector, dicDenominator)
dicNumerator = spiLib.reverseAndNormalizeDic(dicNumerator, minStartYear,
maxEndYear)
dicDenominator = spiLib.reverseAndNormalizeDic(dicDenominator,
minStartYear, maxEndYear)
dicNumerator = spiLibTotal.calcNaceAggregates(dicNumerator, nomenclature,
'sbs')
dicDenominator = spiLibTotal.calcNaceAggregates(dicDenominator,
nomenclature, 'sbs')
spiLibCreateTable.createTableOverOtherShare(dicNumerator, dicDenominator,
minStartYear, 'surpl',
nomenclature, 'competition')
def traitementFichierTXT(indicatorEurostat, unitEurostat, nomenclature, cpa,
files, fileLog, tableName):
infoX = DBAccess.lectureCpaNaceIndicatorData('x', cpa, 'external')
infoM = DBAccess.lectureCpaNaceIndicatorData('m', cpa, 'external')
refDicX = infoX[0]
startYearX = infoX[1]
refDicM = infoM[0]
startYearM = infoM[1]
refDicGO = {}
dicNoCountry = {}
dicNation = {}
dicNaceCheck = {}
dicNation = DBAccess.lectureNationEurostat(dicNation)
dicNace = spiLib.defSelectdicNace(nomenclature, 'nama')
minimumYearWithActualData = 999999
maxEndYear = -1
files.sort()
files.reverse()
for txt in files:
file = open(txt, 'r')
line1st = file.readline()
list1st = line1st.split(',')
dicEurostat = spiLib.defDicEurostat(list1st)
iUnit = dicEurostat['unit']
iIndic = dicEurostat['indic']
iNace = dicEurostat['nace']
iGeoTime = dicEurostat['geotime']
geotime = list1st[iGeoTime].split('\t')
endYear = geotime[1].strip()
startYear = geotime[-1].strip()
for line in file:
lineList = line.strip('\n').split(',')
nace = lineList[iNace].strip()
indicator = lineList[iIndic].strip()
unit = lineList[iUnit].strip()
geoTime = lineList[iGeoTime].split('\t')
geo = geoTime[0].strip()
try:
dicNaceCheck[nace] = nace
country = dicNation[geo]
timeSerie = geoTime[1:]
if indicator == indicatorEurostat and dicNace.has_key(
nace) and unit == unitEurostat:
vector = spiLib.defVectorYears(timeSerie, startYear,
endYear)
minimumYearWithActualData = spiLib.findMinimumYearWithActualData(
timeSerie, int(startYear), minimumYearWithActualData)
refDicGO = spiLib.defDicIndicator(country, nace, vector,
refDicGO)
if int(endYear) > maxEndYear:
maxEndYear = int(endYear)
except:
dicNoCountry[geo] = geo
refDicGO = spiLib.reverseAndNormalizeDic(refDicGO, startYearX, maxEndYear)
refDicGO = spiLibTotal.calcNaceAggregates(refDicGO, nomenclature, 'nama')
refDicX = spiLib.normalizeDicSize(refDicX, startYearX, startYearX,
maxEndYear)
refDicM = spiLib.normalizeDicSize(refDicM, startYearM, startYearX,
maxEndYear)
spiLib.defnoCountry(dicNoCountry, fileLog)
spiLib.defDicNaceCheck(dicNaceCheck, dicNace, fileLog)
spiLibCreateTable.createTableCompetitionImportpen(nomenclature, refDicGO,
refDicX, refDicM,
startYearX, fileLog,
tableName)