1)core dump in regex for big strings 2) Boolean Var bugs 3) adding support for other...

[satune.git] / src / analyzer / tunerloganalyzer.py

diff --git a/src/analyzer/tunerloganalyzer.py b/src/analyzer/tunerloganalyzer.py
index d4e52cc8127ac0bb5bab14325a9ff190af83223c..993e445b7dbe98b3ce64ff930695a04959e10721 100644 (file)
--- a/src/analyzer/tunerloganalyzer.py
+++ b/src/analyzer/tunerloganalyzer.py
@@ -2,20 +2,18 @@ import re
 import argparse
 import sys
 import os
-
+import plot as pl
 
 class AutoTunerArgParser:
        def __init__(self):
                self.parser = argparse.ArgumentParser(description='Parsing the output log of the CSolver auto tuner ...')
                self.parser.add_argument('--folder', '-f', metavar='bin', type=str, nargs=1,help='output log of running the autotuner ...')
-               self.parser.add_argument('--number', '-n', metavar='122', type=int, nargs=1,help='Number of runs ...')
                self.args = self.parser.parse_args()
 
        def getFolder(self):
                return self.args.folder[0]
 
-       def getRunNumber(self):
-               return self.args.number[0]
+PROBLEMS = []
 
 TUNABLEHEADER = ["DECOMPOSEORDER", "MUSTREACHGLOBAL", "MUSTREACHLOCAL", "MUSTREACHPRUNE", "OPTIMIZEORDERSTRUCTURE",
                 "ORDERINTEGERENCODING", "PREPROCESS", "NODEENCODING", "EDGEENCODING", "MUSTEDGEPRUNE", "ELEMENTOPT",
@@ -55,21 +53,26 @@ def printHeader(file):
        mystr=""
        for header in TUNABLEHEADER:
                 mystr+=str(header)+","
-       print >>file, mystr
+       file.write(mystr)
+       file.write("\n")
 
 def dump(file, row):
        global TUNABLEHEADER
        mystr=""
+       data = []
        for i in range(len(TUNABLEHEADER)):
                mystr += row[TUNABLEHEADER[i]]+ ","
-       print "mystr is:"+ mystr
-       print >>file, mystr
+               data.append(row[TUNABLEHEADER[i]])
+       print ("mystr is:"+ mystr)
+       file.write(mystr)
+       file.write("\n")
+       return data
 
 def loadTunerInfo(row, filename):
        with open(filename) as f:
                for line in f:
                        numbers = re.findall('\d+',line)
-                       numbers = map(int,numbers)
+                       numbers = list(map(int,numbers))
                        row[TUNABLEHEADER[numbers[3]]] = row[TUNABLEHEADER[numbers[3]]] + str(numbers[7])
 
 def loadSolverTime(row, filename):
@@ -89,8 +92,16 @@ def loadSolverTime(row, filename):
        row["EXECTIME"] = configs["EXECTIME"]
 
 def loadProblemName(row,filename):
+       global PROBLEMS
        with open(filename) as f:
-               row["PROBLEM"] = f.readline().replace("\n","")
+               problem = f.readline().replace("\n","")
+               probNumber = int(f.readline())
+               if probNumber >= len(PROBLEMS):
+                       PROBLEMS.insert(probNumber,problem)
+               elif PROBLEMS[probNumber] != problem:
+                       PROBLEMS[probNumber] = problem
+               row["PROBLEM"] = problem
+
 def loadTunerNumber(row, filename):
        with open(filename) as f:
                row["TUNERNUMBER"] = f.readline().replace("\n","")
@@ -99,7 +110,9 @@ def analyzeLogs(file):
        argprocess = AutoTunerArgParser()
        printHeader(file)
        rows = []
-       for i in range(argprocess.getRunNumber()):
+       data = []
+       i = 0
+       while True :
                row = {"DECOMPOSEORDER" : "",
                        "MUSTREACHGLOBAL" : "",
                        "MUSTREACHLOCAL" : "",
@@ -122,22 +135,30 @@ def analyzeLogs(file):
                        "EXECTIME": "",
                        "TUNERNUMBER":""
                }
-               loadTunerNumber(row, argprocess.getFolder() + "/tunernum" + str(i))
-               loadTunerInfo(row, argprocess.getFolder()+"/tuner"+str(i)+"used")
-               loadSolverTime(row, argprocess.getFolder()+"/log"+str(i))
-               loadProblemName(row, argprocess.getFolder()+"/problem"+str(i))
-               dump(file, row)
-               rows.append(row)
-       return rows
-
-def tunerNumberAnalysis(file, rows):
+               try:
+                       loadTunerNumber(row, argprocess.getFolder() + "/tunernum" + str(i))
+                       loadTunerInfo(row, argprocess.getFolder()+"/tuner"+str(i)+"used")
+                       loadSolverTime(row, argprocess.getFolder()+"/log"+str(i))
+                       loadProblemName(row, argprocess.getFolder()+"/problem"+str(i))
+                       data.append(dump(file, row))
+                       rows.append(row)
+               except IOError:
+                       break
+               i += 1
+       return rows, data
+
+def tunerCountAnalysis(file, rows):
        global TUNABLEHEADER
+       global PROBLEMS
        tunercount = {}
        tunernumber = {}
        for row in rows:
                mystr=""
                for i in range(18):
-                       mystr+=row[TUNABLEHEADER[i]]
+                       if not row[TUNABLEHEADER[i]]:
+                               mystr += "."
+                       else:
+                               mystr+=row[TUNABLEHEADER[i]]
                if mystr not in tunercount:
                        tunercount.update({mystr : 1})
                        tunernumber.update({mystr : str(row["TUNERNUMBER"])})
@@ -146,18 +167,38 @@ def tunerNumberAnalysis(file, rows):
                        tunernumber[mystr] += "-" + str(row["TUNERNUMBER"])
 
        problems = set(map(lambda x: x["PROBLEM"], rows))
-       print "Number of repititive tuners"
+       print ("Number of repititive tuners")
        for key in tunercount:
                if tunercount[key] > 1:
-                       print key + "(ids:" + tunernumber[key]  + ") = #" + str(tunercount[key])
+                       print( key + "(ids:" + tunernumber[key]  + ") = #" + str(tunercount[key]) )
+
+def combineRowForEachTuner(rows):
+       global PROBLEMS
+       newRows = []
+       combined = None
+       for row in rows:
+               if row["PROBLEM"] == PROBLEMS[0]:
+                       combined = row
+               for key in row:
+                       if row[key]:
+                               combined[key] = row[key]
+               if row["PROBLEM"] == PROBLEMS[len(PROBLEMS)-1]:
+                       newRows.append(combined)
+       return newRows
+
+def transformDataset(rows):
+       print(rows)
 
 
 def main():
+       global TUNABLEHEADER
        file = open("tuner.csv", "w")
-       rows = analyzeLogs(file)
-       tunerNumberAnalysis(file, rows)
+       rows, data = analyzeLogs(file)
+       tunerCountAnalysis(file, combineRowForEachTuner(rows) )
        file.close()
-       return
+       #transformDataset(data)
+       pl.plot(data, TUNABLEHEADER)
+
 
 if __name__ == "__main__":
        main()