def printinfo():
fnamelist = ["../10"+str(v)+".csv" for v in xrange(22,23)]
cnt = 0
found = 0
wholeresult = {}
# writefile = open("../cleandata","w")
missloc = {}
for fname in fnamelist:
filereader = FileReader(fname)
alarmcode = filereader.getattridx("ALARMCODE")
attridx = filereader.getattridx("SUMMARY")
locidx= filereader.getattridx("LOCATION")
timeidx = filereader.getattridx("ALARMHAPPENTIME")
cntidx = 0
while True:
tmptran = filereader.readtransection()
cntidx += 1
# print cntidx
if tmptran is None:
filereader.close()
break
summary = tmptran[attridx]
location = tmptran[locidx]
if location.startswith("SU6095-SU2551"):
print "SUMMARY:"
print summary
print "--------------"
print "LOCATION"
print location
def loadloc(self):
filereader = FileReader("../NE_INFO.csv")
neididx = filereader.getattridx("NE_ID")
noidx = filereader.getattridx("NE_NO")
nameidx = filereader.getattridx("NE_NAME")
ididx = filereader.getattridx("ID_IN_NM")
self.m_locdata = []
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
innminfo = tmptran[ididx]
siteididx = innminfo.find("BtsSiteMgr=BCF-")
if siteididx == -1:
siteididx = innminfo.find("BtsSiteMgr=")
if siteididx == -1:
innm = "-1"
else:
innm = innminfo[siteididx + len("BtsSiteMgr="):]
else:
# innm = innminfo[siteididx+len("BtsSiteMgr=BCF-"):]
innm = "-1"
self.m_locdata.append(
NE(tmptran[noidx], tmptran[nameidx], tmptran[ididx],
tmptran[neididx]))
def loadtopo(self):
self.m_directtopo = {}
self.m_fatherdata = {}
self.m_topodict = {}
filereader = FileReader("../NE_TOPO_INFO.csv")
neidx = filereader.getattridx("NE_ID")
parentidx = filereader.getattridx("PARENT_NE_ID")
empty = 0
nonempty = 0
halfempty = 0
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
neid = tmptran[neidx]
parentneid = tmptran[parentidx]
childne = self.getnebysiteid(neid)
parentne = self.getnebysiteid(parentneid)
if childne is None and parentne is None:
empty += 1
continue
elif childne is None or parentne is None:
halfempty += 1
if parentne is None:
childnename = childne.m_name
parentnename = parentneid
if childnename not in self.m_fatherdata:
self.m_fatherdata[childnename] = []
self.m_fatherdata[childnename].append(parentnename)
continue
else:
nonempty += 1
childnename = childne.m_name
parentnename = parentne.m_name
if childnename not in self.m_fatherdata:
self.m_fatherdata[childnename] = []
self.m_fatherdata[childnename].append(parentnename)
if childnename not in self.m_topodict:
self.m_topodict[childnename] = []
if parentnename not in self.m_topodict:
self.m_topodict[parentnename] = []
if parentnename not in self.m_directtopo:
self.m_directtopo[parentnename] = []
self.m_topodict[childnename].append(parentnename)
self.m_topodict[parentnename].append(childnename)
self.m_directtopo[parentnename].append(childnename)
print "empty:", empty
print "halfempty:", halfempty
print "nonempty:", nonempty
def tongjilocation():
filereader = FileReader("../1022.csv")
attridx = filereader.getattridx("LOCATION")
trandata = {}
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
loc = tmptran[attridx]
try:
locinfo = loc.split(";")[1].split("/")
targetloc = locinfo[0]
if targetloc not in trandata:
trandata[targetloc] = 0
trandata[targetloc] += 1
except:
print loc
# raw_input()
valuelist = trandata.values()
valuelist.sort()
c = Counter(valuelist)
keylist = c.keys()
keylist.sort()
for key in keylist:
print key,"\t:\t",c[key]
raw_input()
raw_input()
itemslist = trandata.items()
itemslist.sort(key=lambda v:v[1],reverse=True)
for key,value in itemslist:
print key
print value
raw_input()
def tongjidistype(fname, attrname):
filereader = FileReader(fname)
attridx = filereader.getattridx(attrname)
trandata = {}
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
summary = tmptran[attridx]
if summary not in trandata:
trandata[summary] = 0
trandata[summary] += 1
valuelist = trandata.values()
valuelist.sort()
c = Counter(valuelist)
keylist = c.keys()
keylist.sort()
for key in keylist:
print key, "\t:\t", c[key]
itemslist = trandata.items()
itemslist.sort(key=lambda v: v[1], reverse=True)
# for key,value in itemslist:
# print key
# print value
# raw_input()
# print valuelist
# raw_input()
print "========================================================"
import pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(trandata)
print "length:", len(trandata)
def printidentifier():
filereader = FileReader("../1022.csv")
identifieridx = filereader.getattridx("NEIDENTIFIER")
while True:
tmptran = filereader.readtransection()
identifier = tmptran[identifieridx]
if tmptran is None:
filereader.close()
break
print identifier
raw_input()
def testwrongfile():
filereader = FileReader("../wrongdocfile")
alarmcodeidx = filereader.getattridx("ALARMCODE")
attridx = filereader.getattridx("SUMMARY")
locidx = filereader.getattridx("LOCATION")
timeidx = filereader.getattridx("ALARMHAPPENTIME")
print "idxdata:", timeidx, alarmcodeidx, locidx, attridx
print filereader.m_header
print filereader.m_headerlen
while True:
tmptran = filereader.readtransection()
if tmptran is None:
filereader.close()
break
summary = tmptran[attridx]
location = tmptran[locidx]
alarmcode = tmptran[alarmcodeidx]
timestr = tmptran[timeidx]
print tmptran
raw_input()
def tongjinetype():
filereader = FileReader("../NE_INFO.csv")
attridx = filereader.getattridx("NE_CAT_ID")
trandata = {}
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
summary = tmptran[attridx]
if summary not in trandata:
trandata[summary] = 0
trandata[summary] += 1
import pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(trandata)
def calneidlen():
filereader = FileReader("../NE_INFO.csv")
attridx = filereader.getattridx("NE_NO")
lendict = {}
idx = 0
while True:
tmptran = filereader.readtransection()
if tmptran is None:
break
neid = tmptran[attridx]
neidlen = len(neid)
if neidlen not in lendict:
lendict[neidlen] = 0
lendict[neidlen] += 1
idx += 1
print neid
if idx % 100 == 0:
raw_input()
import pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(lendict)
def testfound(self):
# fnamelist = ["../wrongdocfile",]
# fnamelist = ["../10"+str(v)+".csv" for v in xrange(22,23)]
# fnamelist = ["../1125.csv",]
fnamelist = ["../10"+str(v)+".csv" for v in xrange(22,32)] + \
["../110"+str(v)+".csv" for v in xrange(01,10)] + \
["../11"+str(v)+".csv" for v in xrange(10,31)] + \
["../120"+str(v)+".csv" for v in xrange(01,10)] + \
["../12"+str(v)+".csv" for v in xrange(10,23)]
cnt = 0
found = 0
wholeresult = {}
writeflag = True
if writeflag:
writefile = open("../cleandata", "w")
wrongdocflag = False
if wrongdocflag:
wrongdocfile = open("../wrongdocfile", "w")
wrongdocfile.write(",".join([
'"ALARMHAPPENTIME"', '"ALARMCODE"', '"LOCATION"', '"SUMMARY"'
]) + "\n")
missloc = {}
print "||||||||||||||||"
fnamecnt = open("fnamecnt", "w")
for fname in fnamelist:
print fname
filereader = FileReader(fname)
alarmcodeidx = filereader.getattridx("ALARMCODE")
attridx = filereader.getattridx("SUMMARY")
locidx = filereader.getattridx("LOCATION")
timeidx = filereader.getattridx("ALARMHAPPENTIME")
identifieridx = filereader.getattridx("NEIDENTIFIER")
cntidx = 0
while True:
tmptran = filereader.readtransection()
cntidx += 1
# print cntidx
if tmptran is None:
filereader.close()
break
summary = tmptran[attridx]
location = tmptran[locidx]
alarmcode = tmptran[alarmcodeidx]
identifier = tmptran[identifieridx]
warn = Warning(summary, location)
if warn.m_type == NOTP4:
continue
ftword = warn.getfirstword()
if ftword not in wholeresult:
wholeresult[ftword] = {"cnt": 0, "good": 0}
wholeresult[ftword]["cnt"] += 1
cnt += 1
loc = self.m_topo.getnebyidentifier(identifier)
if loc is None:
loc = warn.fetchloc(self.m_topo)
if loc is None:
locstr = warn.fetchlocstr()
if warn.m_type != NOTP5 and warn.m_type != TP9:
if locstr not in missloc:
missloc[locstr] = 0
print "==============================================="
print warn.m_summary
print "----------------------------------"
print warn.m_location
print "----------------------------------"
print identifier
print "locstr:", warn.m_type, locstr
missloc[locstr] += 1
if wrongdocflag:
wrongdocfile.write(",".join(['\"'+v+'\"' for v in \
[tmptran[timeidx],tmptran[alarmcodeidx],tmptran[locidx],tmptran[attridx],]])+"\r\n")
continue
wholeresult[ftword]["good"] += 1
found += 1
summary = summary.replace("\n", "_")
if writeflag:
writefile.write(alarmcode + "\t" + loc.m_name + "\t" +
summary + "\t" + tmptran[timeidx] + "\n")
print fname, "\t", cntidx
fnamecnt.write(fname + "\t" + str(cntidx) + "\n")
fnamecnt.close()
if writeflag:
writefile.close()
if wrongdocflag:
wrongdocfile.close()
print "result:"
print "cnt:", cnt
print "found:", found
print "pcg:", found * 1.0 / cnt
for v in wholeresult.keys():
if wholeresult[v]["good"] == wholeresult[v]["cnt"]:
del wholeresult[v]
else:
wholeresult[v]["pcg"] = wholeresult[v][
"good"] * 1.0 / wholeresult[v]["cnt"]
import pprint
pprint.pprint(wholeresult)
print "-----------------------"
pprint.pprint(missloc)
print "missloclen:", len(missloc)
json.dump(wholeresult, open("tmpwholeresult", "w"))
json.dump(missloc, open("missloc", "w"))
