pull request to update tutorial

Analysis.py

@@ -1,75 +1,48 @@
 # Analysis
 import numpy as np
+import matplotlib as mpl
+mpl.use('pdf')
+import matplotlib.pyplot as plt
+from sklearn.metrics import roc_curve, auc    
 
-def ClassificationAnalysis(MyModel,Test_X,Test_Y,BatchSize, SignalClassIndex=5):
-    import matplotlib as mpl
-    mpl.use('pdf')
-    import matplotlib.pyplot as plt
+mpColors = ['red', 'darkorange', 'lawngreen', 'green', 'lightseagreen', 'cyan', 'royalblue', 'blue', 'blueviolet', 'magenta', 'hotpink']
 
-    from sklearn.metrics import roc_curve, auc    
+def ClassificationAnalysis (MyModel, Test_X, Test_Y, BatchSize, SignalClassIndex=5):
+    result = MyModel.Model.predict (Test_X, batch_size=BatchSize)
 
-    print "Prediction Analysis."
-    result = MyModel.Model.predict(Test_X, batch_size=BatchSize)
-
-    fpr, tpr, _ = roc_curve(Test_Y[:,SignalClassIndex], 
-                            result[:,SignalClassIndex])
-    roc_auc = auc(fpr, tpr)    
-
-    lw=2
-
-    plt.plot(fpr,tpr,color='darkorange',
-             lw=lw, label='ROC curve (area = %0.2f)' % roc_auc)
-
-    print "ROC AUC: ",roc_auc
-
-    plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
-    plt.xlim([0.0, 1.0])
-    plt.ylim([0.0, 1.05])
-
-    plt.xlabel('False Positive Rate')
-    plt.ylabel('True Positive Rate')
-
-    plt.legend(loc="lower right")
+    fpr, tpr, _ = roc_curve (Test_Y[:,SignalClassIndex], 
+                             result[:,SignalClassIndex])
+    roc_auc = auc (fpr, tpr)
 
-    plt.savefig(MyModel.OutDir+"/ROC.pdf")
-
-
-mpColors=["blue","green","red","cyan","magenta","yellow","black","white"]
+    lw=2
 
-def MultiClassificationAnalysis(MyModel,Test_X,Test_Y,BatchSize):
-    import matplotlib as mpl
-    mpl.use('pdf')
-    import matplotlib.pyplot as plt
+    plt.plot (fpr,tpr,color=mpColors[SignalClassIndex],
+              lw=lw, label='ROC curve (area = %0.2f)' % roc_auc)
 
-    from sklearn.metrics import roc_curve, auc    
+    print 'ROC', SignalClassIndex, 'AUC:', roc_auc
+    pass
 
-    print "Prediction Analysis."
-    result = MyModel.Model.predict(Test_X, batch_size=BatchSize)
-
-    NClasses=Test_Y.shape[1]
 
-    for ClassIndex in xrange(0,NClasses):
-        fpr, tpr, _ = roc_curve(Test_Y[:,ClassIndex], 
-                                result[:,ClassIndex])
-        roc_auc = auc(fpr, tpr)    
+def MultiClassificationAnalysis (MyModel, Test_X, Test_Y, BatchSize):
+    print 'Prediction Analysis.'
+    result = MyModel.Model.predict (Test_X, batch_size=BatchSize)
 
-        lw=2
+    NClasses = Test_Y.shape[1]
 
-        plt.plot(fpr,tpr,color=mpColors[ClassIndex],
-                 lw=lw, label='ROC curve (area = %0.2f)' % roc_auc)
+    for ClassIndex in xrange(NClasses):
+        ClassificationAnalysis (MyModel, Test_X, Test_Y, BatchSize, ClassIndex)
+        pass
 
-        print "ROC ",ClassIndex," AUC: ",roc_auc
+    lw=2
 
-        plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
-        plt.xlim([0.0, 1.0])
-        plt.ylim([0.0, 1.05])
+    plt.plot ([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
+    plt.xlim ([0.0, 1.0])
+    plt.ylim ([0.0, 1.05])
 
-        plt.xlabel('False Positive Rate')
-        plt.ylabel('True Positive Rate')
+    plt.xlabel ('False Positive Rate')
+    plt.ylabel ('True Positive Rate')
 
-        plt.legend(loc="lower right")
+    plt.legend (loc='lower right')
 
-
-    plt.savefig(MyModel.OutDir+"/ROC.pdf")
-
+    plt.savefig (MyModel.OutDir + '/ROC.pdf')
     return result

Arguments.py

@@ -1,49 +1,47 @@
+import argparse
+
 # Configuration of this job
 parser = argparse.ArgumentParser()
-parser.add_argument('-C', '--config',default="EventClassificationDNN/ScanConfig.py")
-parser.add_argument('-I', '--inputdata',default="/data/afarbin/crogan/h5/mP1000_mC200_mX100.h5")
-parser.add_argument('-L', '--LoadModel',default=False)
-parser.add_argument('--gpu', dest='gpuid', default="")
-parser.add_argument('--cpu', action="store_true")
-parser.add_argument('--NoTrain', action="store_true")
-parser.add_argument('-s',"--hyperparamset", default="0")
-parser.add_argument('-v',"--varset", default="0")
-parser.add_argument('--NoResults', action="store_false")
+parser.add_argument ('-C', '--config', default='EventClassificationDNN/ScanConfig.py')
+parser.add_argument ('-I', '--inputdata', default='/data/afarbin/crogan/h5/mP1000_mC200_mX100.h5')
+parser.add_argument ('-L', '--LoadModel', default=False)
+parser.add_argument ('--gpu', dest='gpuid', default='')
+parser.add_argument ('--cpu', action='store_true')
+parser.add_argument ('--NoTrain', action='store_true')
+parser.add_argument ('-s', '--hyperparamset', type=int, default=0)
+parser.add_argument ('-v', '--varset', type=int, default=0)
+parser.add_argument ('--NoResults', action='store_false')
 
 args = parser.parse_args()
 
-UseGPU=not args.cpu
-gpuid=args.gpuid
-if args.hyperparamset:
-    HyperParamSet = int(args.hyperparamset)
-
-if args.varset:
-    VarSet = int(args.varset)
-
-    print "Using VarSet: ",VarSet
+UseGPU = not args.cpu
+gpuid = args.gpuid
+HyperParamSet = args.hyperparamset
 
-ConfigFile=args.config
-InputData=args.inputdata
+VarSet = args.varset
+print 'Using VarSet:', VarSet
 
-LoadModel=args.LoadModel
+ConfigFile = args.config
+InputData = args.inputdata
+LoadModel = args.LoadModel
 
 # Configuration from PBS:
-if "PBS_ARRAYID" in os.environ:
-    HyperParamSet = int(os.environ["PBS_ARRAYID"])
+if 'PBS_ARRAYID' in os.environ: HyperParamSet = int(os.environ['PBS_ARRAYID'])
 
-if "PBS_QUEUE" in os.environ:
-    if "cpu" in os.environ["PBS_QUEUE"]:
-        UseGPU=False
-    if "gpu" in os.environ["PBS_QUEUE"]:
-        UseGPU=True
-        gpuid=int(os.environ["PBS_QUEUE"][3:4])
+if 'PBS_QUEUE' in os.environ:
+    if 'cpu' in os.environ['PBS_QUEUE']: UseGPU = False
+    if 'gpu' in os.environ['PBS_QUEUE']:
+        UseGPU = True
+        gpuid = int(os.environ['PBS_QUEUE'][3:4])
+        pass
+    pass
 
 if UseGPU:
-    print "Using GPU",gpuid
-    os.environ['THEANO_FLAGS'] = "mode=FAST_RUN,device=gpu%s,floatX=float32,force_device=True" % (gpuid)
-else:
-    print "Using CPU."
+    print 'Using GPU', gpuid
+    os.environ['THEANO_FLAGS'] = 'mode=FAST_RUN,device=gpu%s,floatX=float32,force_device=True' % (gpuid)
+    pass
+else: print 'Using CPU.'
 
-Train= not args.NoTrain
+Train = not args.NoTrain
 
-WriteResults=  args.NoResults
+WriteResults = args.NoResults

CSVWriter.py

@@ -1,27 +1,20 @@
-import numpy as np
-
-def CSVWriter(filename,X,Y,R):
-
-    names=X.dtype.names
-
-    colnames=""
+#!/usr/bin/env python
 
-    for n in names:
-        colnames+=n+"/f:"
+import numpy as np
 
-#    colnames+="TrueClass/f:"
-    for i in xrange(0,Y.shape[1]):
-        colnames+="true_"+str(i)+"/f:"
+def CSVWriter (filename, X, Y, R, arrType):
+    names = X.dtype.names
+    colnames = []
 
-    for i in xrange(0,R.shape[1]):
-        colnames+="predict_"+str(i)+"/f:"
+    for n in names: colnames.append(n)
+    for i in xrange(0, Y.shape[1]): colnames.append('true_' + str(i))
+    for i in xrange(0, R.shape[1]): colnames.append('predict_' + str(i))
 
     f = open(filename, 'w')
-    f.write(colnames[:-1]+"\n")
-
-    X0=X.view(np.float32).reshape(X.shape + (-1,))
+    f.write(','.join(colnames) + '\n')
 
-    YI=np.nonzero(Y)[1]
-    out=np.concatenate((X0,Y,R),axis=1)
+    X0 = X.view(arrType).reshape(X.shape + (-1,))
+    out = np.concatenate((X0,Y,R), axis=1)
 
-    np.savetxt(f,out,delimiter=',')
+    np.savetxt(f, out, delimiter=',')
+    pass

Classification.py

@@ -70,4 +70,4 @@ def Build(self):
         self.Model=model
 
     def Compile(self, Loss="categorical_crossentropy", Optimizer="rmsprop"):
-        self.Model.compile(loss=loss, optimizer=optimizer,metrics=["accuracy"])
+        self.Model.compile(loss=Loss, optimizer=Optimizer,metrics=["accuracy"])