merge some benchonset code into node

merge some benchonset code into node

diff --git a/python/aubio/bench/node.py b/python/aubio/bench/node.py
index 9ab753bab7713ca2a517afd87dcbcf32620dad65..22e231a64734b7377fd684446b29984ab6d6a3c9 100644 (file)
--- a/python/aubio/bench/node.py
+++ b/python/aubio/bench/node.py
@@ -143,20 +143,62 @@ class bench:
                print "Creating results directory"
                act_on_results(mkdir,self.datadir,self.resdir,filter='d')
 
-       def pretty_print(self,values,sep='|'):
-               for i in range(len(values)):
-                       print self.formats[i] % values[i], sep,
+       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 dir_exec(self):
                """ run file_exec on every input file """
-               pass
+               self.l , self.labs = [], [] 
+               self.v = {}
+               for i in self.valuenames:
+                       self.v[i] = [] 
+               for i in self.valuelists:
+                       self.v[i] = [] 
+               act_on_files(self.file_exec,self.sndlist,self.reslist, \
+                       suffix='',filter=sndfile_filter)
 
        def dir_eval(self):
                pass
 
-       def file_exec(self):
-               pass
+       def file_gettruth(self,input):
+               """ get ground truth filenames """
+               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):
+               """ create filetask, extract data, evaluate """
+               filetask = self.task(input,params=self.params)
+               computed_data = filetask.compute_all()
+               ftrulist = self.file_gettruth(filetask.input)
+               for i in ftrulist:
+                       filetask.eval(computed_data,i,mode='rocloc',vmode='')
+                       """ append filetask.v to self.v """
+                       for i in self.valuenames:
+                               self.v[i].append(filetask.v[i])
+                       for j in self.valuelists:
+                               if filetask.v[j]:
+                                       for i in range(len(filetask.v[j])):
+                                               self.v[j].append(filetask.v[j][i])
        
        def file_eval(self):
                pass

diff --git a/python/test/bench/onset/bench-onset b/python/test/bench/onset/bench-onset
index 9b3ee4363d0789fb8b3785a6d09dad10312163d7..a3b1b7cddd29db55794e85218ae05271bf2ade16 100755 (executable)
--- a/python/test/bench/onset/bench-onset
+++ b/python/test/bench/onset/bench-onset
@@ -19,89 +19,38 @@ def stdev(l):
 
 class benchonset(bench):
 
+       """ list of values to store per file """
        valuenames = ['orig','missed','Tm','expc','bad','Td']
+       """ list of lists to store per file """
        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 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()
-               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)
+       """ list of values to print per dir """
+       printnames = [ 'mode', 'thres', 'dist', 'prec', 'recl', 
+               'Ttrue', 'Tfp',  'Tfn',  'Tm',   'Td',
+               'aTtrue', 'aTfp', 'aTfn', 'aTm',  'aTd',  
+               'mean', 'smean',  'amean', 'samean']
+
+       """ per dir """
+       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):
-               totaltrue = self.v['expc']-self.v['bad']-self.v['Td']
-               totalfp = self.v['bad']+self.v['Td']
-                totalfn = self.v['missed']+self.v['Tm']
+               """ evaluate statistical data over the directory """
+               totaltrue = sum(self.v['expc'])-sum(self.v['bad'])-sum(self.v['Td'])
+               totalfp = sum(self.v['bad'])+sum(self.v['Td'])
+                totalfn = sum(self.v['missed'])+sum(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']     = self.params.threshold 
                self.v['thres']     = "%2.3f" % self.params.threshold
                self.v['dist']      = "%2.3f" % self.F
                self.v['prec']      = "%2.3f" % self.P
@@ -112,8 +61,8 @@ class benchonset(bench):
                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['aTm']       = sum(self.v['Tm'])/N
+               self.v['aTd']       = sum(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'])
@@ -122,7 +71,6 @@ class benchonset(bench):
        def run_bench(self,modes=['dual'],thresholds=[0.5]):
                self.modes = modes
                self.thresholds = thresholds
-
                self.pretty_titles()
                for mode in self.modes:
                        self.params.onsetmode = mode
@@ -133,22 +81,12 @@ class benchonset(bench):
                                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_titles()
                for mode in self.modes:
-                       steps = 10 
+                       steps = 11 
                        lesst = thresholds[0] 
                        topt = thresholds[1]
                        self.params.onsetmode = mode
@@ -230,7 +168,7 @@ if __name__ == "__main__":
        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 = [ 'phase' ]
+       #modes = [ 'mkl' ]
        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]
 
@@ -242,7 +180,6 @@ if __name__ == "__main__":
        benchonset.task = taskonset
        benchonset.valuesdict = {}
 
-
        try:
                #benchonset.auto_learn2(modes=modes)
                benchonset.run_bench(modes=modes,thresholds=thresholds)