update to new bench onset

update to new bench onset

diff --git a/python/test/bench/onset/bench-onset b/python/test/bench/onset/bench-onset
index d8ede4e8107c72c0c28ffa7b15451388ad0c7d06..9b3ee4363d0789fb8b3785a6d09dad10312163d7 100755 (executable)
--- a/python/test/bench/onset/bench-onset
+++ b/python/test/bench/onset/bench-onset
@@ -3,60 +3,150 @@
 from aubio.bench.node import *
 from aubio.tasks import *
 
+
+
+
+def mmean(l):
+       return sum(l)/float(len(l))
+
+def stdev(l):
+       smean = 0
+       lmean = mmean(l)
+       for i in l:
+               smean += (i-lmean)**2
+       smean *= 1. / len(l)
+       return smean**.5
+
 class benchonset(bench):
+
+       valuenames = ['orig','missed','Tm','expc','bad','Td']
+       valuelists = ['l','labs']
+       printnames = [ 'mode', 'thres', 'dist', 'prec', 'recl', 'Ttrue', 'Tfp',  'Tfn',  'Tm',   'Td',
+               'aTtrue', 'aTfp', 'aTfn', 'aTm',  'aTd',  'mean', 'smean',  'amean', 'samean']
+
+       formats = {'mode': "%12s" , 
+       'thres': "%5.4s",
+       'dist':  "%5.4s",
+       'prec':  "%5.4s",
+       'recl':  "%5.4s",
+                 
+       'Ttrue': "%5.4s", 
+       'Tfp':   "%5.4s",
+       'Tfn':   "%5.4s",
+       'Tm':    "%5.4s",
+       'Td':    "%5.4s",
+                 
+       'aTtrue':"%5.4s", 
+       'aTfp':  "%5.4s",
+       'aTfn':  "%5.4s",
+       'aTm':   "%5.4s",
+       'aTd':   "%5.4s",
+                 
+       'mean':  "%5.40s", 
+       'smean': "%5.40s",
+       'amean':  "%5.40s", 
+       'samean': "%5.40s"}
        
-       def dir_eval(self):
-               self.P = 100*float(self.expc-self.missed-self.merged)/(self.expc-self.missed-self.merged + self.bad+self.doubled)
-               self.R = 100*float(self.expc-self.missed-self.merged)/(self.expc-self.missed-self.merged + self.missed+self.merged)
-               if self.R < 0: self.R = 0
-               self.F = 2* self.P*self.R / (self.P+self.R)
-
-               self.values = [self.params.onsetmode, 
-               "%2.3f" % self.params.threshold,
-               self.orig,
-               self.expc,
-               self.missed,
-               self.merged,
-               self.bad,
-               self.doubled,
-               (self.orig-self.missed-self.merged),
-               "%2.3f" % (100*float(self.orig-self.missed-self.merged)/(self.orig)),
-               "%2.3f" % (100*float(self.bad+self.doubled)/(self.orig)), 
-               "%2.3f" % (100*float(self.orig-self.missed)/(self.orig)), 
-               "%2.3f" % (100*float(self.bad)/(self.orig)),
-               "%2.3f" % self.P,
-               "%2.3f" % self.R,
-               "%2.3f" % self.F  ]
+       def file_gettruth(self,input):
+               from os.path import isfile
+               ftrulist = []
+               # search for match as filetask.input,".txt" 
+               ftru = '.'.join(input.split('.')[:-1])
+               ftru = '.'.join((ftru,'txt'))
+               if isfile(ftru):
+                       ftrulist.append(ftru)
+               else:
+                       # search for matches for filetask.input in the list of results
+                       for i in range(len(self.reslist)):
+                               check = '.'.join(self.reslist[i].split('.')[:-1])
+                               check = '_'.join(check.split('_')[:-1])
+                               if check == '.'.join(input.split('.')[:-1]):
+                                       ftrulist.append(self.reslist[i])
+               return ftrulist
 
        def file_exec(self,input,output):
                filetask = self.task(input,params=self.params)
                computed_data = filetask.compute_all()
-               results = filetask.eval(computed_data)
-               self.orig    += filetask.orig
-               self.missed  += filetask.missed
-               self.merged  += filetask.merged
-               self.expc    += filetask.expc
-               self.bad     += filetask.bad
-               self.doubled += filetask.doubled
+               ftrulist = self.file_gettruth(filetask.input)
+               for i in ftrulist:
+                       #print i
+                       filetask.eval(computed_data,i,mode='rocloc',vmode='')
+                       for i in self.valuenames:
+                               self.v[i] += filetask.v[i]
+                       for i in filetask.v['l']:
+                               self.v['l'].append(i)
+                       for i in filetask.v['labs']:
+                               self.v['labs'].append(i)
+       
+       def dir_exec(self):
+               """ run file_exec on every input file """
+               self.l , self.labs = [], [] 
+               self.v = {}
+               for i in self.valuenames:
+                       self.v[i] = 0. 
+               for i in self.valuelists:
+                       self.v[i] = [] 
+               self.v['thres'] = self.params.threshold 
+               act_on_files(self.file_exec,self.sndlist,self.reslist, \
+                       suffix='',filter=sndfile_filter)
 
+       def dir_eval(self):
+               totaltrue = self.v['expc']-self.v['bad']-self.v['Td']
+               totalfp = self.v['bad']+self.v['Td']
+                totalfn = self.v['missed']+self.v['Tm']
+               self.P = 100*float(totaltrue)/max(totaltrue + totalfp,1)
+               self.R = 100*float(totaltrue)/max(totaltrue + totalfn,1)
+               if self.R < 0: self.R = 0
+               self.F = 2.* self.P*self.R / max(float(self.P+self.R),1)
+               
+               N = float(len(self.reslist))
+
+               self.v['mode']      = self.params.onsetmode
+               self.v['thres']     = "%2.3f" % self.params.threshold
+               self.v['dist']      = "%2.3f" % self.F
+               self.v['prec']      = "%2.3f" % self.P
+               self.v['recl']      = "%2.3f" % self.R
+               self.v['Ttrue']     = totaltrue
+               self.v['Tfp']       = totalfp
+               self.v['Tfn']       = totalfn
+               self.v['aTtrue']    = totaltrue/N
+               self.v['aTfp']      = totalfp/N
+               self.v['aTfn']      = totalfn/N
+               self.v['aTm']       = self.v['Tm']/N
+               self.v['aTd']       = self.v['Td']/N
+               self.v['mean']      = mmean(self.v['l'])
+               self.v['smean']     = stdev(self.v['l'])
+               self.v['amean']     = mmean(self.v['labs'])
+               self.v['samean']    = stdev(self.v['labs'])
 
        def run_bench(self,modes=['dual'],thresholds=[0.5]):
                self.modes = modes
                self.thresholds = thresholds
 
-               self.pretty_print(self.titles)
+               self.pretty_titles()
                for mode in self.modes:
                        self.params.onsetmode = mode
                        for threshold in self.thresholds:
                                self.params.threshold = threshold
                                self.dir_exec()
                                self.dir_eval()
-                               self.pretty_print(self.values)
+                               self.pretty_print()
+                               #print self.v
+
+       def pretty_print(self,sep='|'):
+               for i in self.printnames:
+                       print self.formats[i] % self.v[i], sep,
+               print
+
+       def pretty_titles(self,sep='|'):
+               for i in self.printnames:
+                       print self.formats[i] % i, sep,
+               print
 
        def auto_learn(self,modes=['dual'],thresholds=[0.1,1.5]):
                """ simple dichotomia like algorithm to optimise threshold """
                self.modes = modes
-               self.pretty_print(self.titles)
+               self.pretty_titles()
                for mode in self.modes:
                        steps = 10 
                        lesst = thresholds[0] 
@@ -66,20 +156,20 @@ class benchonset(bench):
                        self.params.threshold = topt 
                        self.dir_exec()
                        self.dir_eval()
-                       self.pretty_print(self.values)
+                       self.pretty_print()
                        topF = self.F 
 
                        self.params.threshold = lesst 
                        self.dir_exec()
                        self.dir_eval()
-                       self.pretty_print(self.values)
+                       self.pretty_print()
                        lessF = self.F 
 
                        for i in range(steps):
                                self.params.threshold = ( lesst + topt ) * .5 
                                self.dir_exec()
                                self.dir_eval()
-                               self.pretty_print(self.values)
+                               self.pretty_print()
                                if self.F == 100.0 or self.F == topF: 
                                        print "assuming we converged, stopping" 
                                        break
@@ -97,46 +187,51 @@ class benchonset(bench):
                                if topt == lesst:
                                        lesst /= 2.
 
-       def auto_learn2(self,modes=['dual'],thresholds=[0.1,1.0]):
+       def auto_learn2(self,modes=['dual'],thresholds=[0.00001,1.0]):
                """ simple dichotomia like algorithm to optimise threshold """
                self.modes = modes
-               self.pretty_print(self.titles)
+               self.pretty_titles([])
                for mode in self.modes:
                        steps = 10 
-                       step = thresholds[1]
-                       curt = thresholds[0] 
+                       step = 0.4
                        self.params.onsetmode = mode
-
-                       self.params.threshold = curt 
-                       self.dir_exec()
-                       self.dir_eval()
-                       self.pretty_print(self.values)
-                       curexp = self.expc
+                       self.params.threshold = thresholds[0] 
+                       cur = 0
 
                        for i in range(steps):
-                               if curexp < self.orig:
-                                       #print "we found at most less onsets than annotated"
-                                       self.params.threshold -= step 
-                                       step /= 2
-                               elif curexp > self.orig:
-                                       #print "we found more onsets than annotated"
-                                       self.params.threshold += step 
-                                       step /= 2
                                self.dir_exec()
                                self.dir_eval()
-                               curexp = self.expc
-                               self.pretty_print(self.values)
-                               if self.orig == 100.0 or self.orig == self.expc: 
-                                       print "assuming we converged, stopping" 
+                               self.pretty_print()
+                               new = self.P
+                               if self.R == 0.0:
+                                       #print "Found maximum, highering"
+                                       step /= 2.
+                                       self.params.threshold -= step 
+                               elif new == 100.0:
+                                       #print "Found maximum, highering"
+                                       step *= .99
+                                       self.params.threshold += step 
+                               elif cur > new:
+                                       #print "lower"
+                                       step /= 2.
+                                       self.params.threshold -= step 
+                               elif cur < new:
+                                       #print "higher"
+                                       step *= .99
+                                       self.params.threshold += step 
+                               else:
+                                       print "Assuming we converged"
                                        break
+                               cur = new
+
 
 if __name__ == "__main__":
        import sys
        if len(sys.argv) > 1: datapath = sys.argv[1]
        else: print "ERR: a path is required"; sys.exit(1)
        modes = ['complex', 'energy', 'phase', 'specdiff', 'kl', 'mkl', 'dual']
-       #modes = [ 'complex' ]
-       thresholds = [ 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5]
+       #modes = [ 'phase' ]
+       thresholds = [ 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0, 1.1, 1.2]
        #thresholds = [1.5]
 
        #datapath = "%s%s" % (DATADIR,'/onset/DB/*/')
@@ -145,16 +240,11 @@ if __name__ == "__main__":
        benchonset = benchonset(datapath,respath,checkres=True,checkanno=True)
        benchonset.params = taskparams()
        benchonset.task = taskonset
+       benchonset.valuesdict = {}
 
-       benchonset.titles = [ 'mode', 'thres', 'orig', 'expc', 'missd', 'mergd',
-       'bad', 'doubl', 'corrt', 'GD', 'FP', 'GD-merged', 'FP-pruned',
-       'prec', 'recl', 'dist' ]
-       benchonset.formats = ["%12s" , "| %6s", "| %6s", "| %6s", "| %6s", "| %6s", 
-       "| %6s", "| %6s", "| %6s", "| %8s", "| %8s", "| %8s", "| %8s",
-       "| %6s", "| %6s", "| %6s"] 
 
        try:
-               benchonset.auto_learn2(modes=modes)
-               #benchonset.run_bench(modes=modes)
+               #benchonset.auto_learn2(modes=modes)
+               benchonset.run_bench(modes=modes,thresholds=thresholds)
        except KeyboardInterrupt:
                sys.exit(1)