def Classify(clf, featuresAll, bestParam):
if clf == 'svm':
model = aT.trainSVM(featuresAll, bestParam)
elif clf == 'svm_rbf':
model = aT.trainSVM_RBF(featuresAll, bestParam)
elif clf == 'extratrees':
model = aT.trainExtraTrees(featuresAll, bestParam)
elif clf == 'randomforest':
model = aT.trainRandomForest(featuresAll, bestParam)
elif clf == 'knn':
model = aT.trainKNN(featuresAll, bestParam)
elif clf == 'gradientboosting':
model = aT.trainGradientBoosting(featuresAll, bestParam)
return model
def getTrainClassifier(f_train,classifier_name,param):
if classifier_name == AudioClassifierManager.__svmModelName:
classifier = aT.trainSVM(f_train, param)
elif classifier_name == AudioClassifierManager.__svmRbfModelName:
classifier = aT.trainSVM_RBF(f_train, param)
elif classifier_name == AudioClassifierManager.__knnModelName:
classifier = aT.trainKNN(f_train, param)
elif classifier_name == AudioClassifierManager.__randomforestModelName:
classifier = aT.trainRandomForest(f_train, param)
elif classifier_name == AudioClassifierManager.__gradientboostingModelName:
classifier = aT.trainGradientBoosting(f_train, param)
elif classifier_name == AudioClassifierManager.__extratreesModelName:
classifier = aT.trainExtraTrees(f_train, param)
else:
classifier = None
return classifier
def evaluateclassifier(features, class_names, n_exp, classifier_name, Params, parameterMode, perTrain=0.90):
'''
ARGUMENTS:
features: a list ([numOfClasses x 1]) whose elements containt numpy matrices of features.
each matrix features[i] of class i is [n_samples x numOfDimensions]
class_names: list of class names (strings)
n_exp: number of cross-validation experiments
classifier_name: svm or knn or randomforest
Params: list of classifier parameters (for parameter tuning during cross-validation)
parameterMode: 0: choose parameters that lead to maximum overall classification ACCURACY
1: choose parameters that lead to maximum overall f1 MEASURE
RETURNS:
bestParam: the value of the input parameter that optimizes the selected performance measure
'''
# feature normalization:
(features_norm, MEAN, STD) = normalizeFeatures(features)
#features_norm = features;
n_classes = len(features)
ac_all = []
f1_all = []
precision_classes_all = []
recall_classes_all = []
f1_classes_all = []
cms_all = []
# compute total number of samples:
n_samples_total = 0
for f in features:
n_samples_total += f.shape[0]
if n_samples_total > 1000 and n_exp > 50:
n_exp = 50
print("Number of training experiments changed to 50 due to high number of samples")
if n_samples_total > 2000 and n_exp > 10:
n_exp = 10
print("Number of training experiments changed to 10 due to high number of samples")
for Ci, C in enumerate(Params):
# for each param value
cm = numpy.zeros((n_classes, n_classes))
for e in range(n_exp):
# for each cross-validation iteration:
print("Param = {0:.5f} - classifier Evaluation "
"Experiment {1:d} of {2:d}".format(C, e+1, n_exp))
# split features:
f_train, f_test = randSplitFeatures(features_norm, perTrain)
# train multi-class svms:
if classifier_name == "svm":
classifier = trainSVM(f_train, C)
elif classifier_name == "svm_rbf":
classifier = trainSVM_RBF(f_train, C)
elif classifier_name == "knn":
classifier = trainKNN(f_train, C)
elif classifier_name == "randomforest":
classifier = trainRandomForest(f_train, C)
elif classifier_name == "gradientboosting":
classifier = trainGradientBoosting(f_train, C)
elif classifier_name == "extratrees":
classifier = trainExtraTrees(f_train, C)
elif classifier_name == "logisticregression":
classifier = trainLogisticRegression(f_train, C)
cmt = numpy.zeros((n_classes, n_classes))
for c1 in range(n_classes):
n_test_samples = len(f_test[c1])
res = numpy.zeros((n_test_samples, 1))
for ss in range(n_test_samples):
[res[ss], _] = classifierWrapperHead(classifier,
classifier_name,
f_test[c1][ss])
for c2 in range(n_classes):
cmt[c1][c2] = float(len(numpy.nonzero(res == c2)[0]))
cm = cm + cmt
cm = cm + 0.0000000010
rec = numpy.zeros((cm.shape[0], ))
pre = numpy.zeros((cm.shape[0], ))
for ci in range(cm.shape[0]):
rec[ci] = cm[ci, ci] / numpy.sum(cm[ci, :])
pre[ci] = cm[ci, ci] / numpy.sum(cm[:, ci])
precision_classes_all.append(pre)
recall_classes_all.append(rec)
f1 = 2 * rec * pre / (rec + pre)
f1_classes_all.append(f1)
ac_all.append(numpy.sum(numpy.diagonal(cm)) / numpy.sum(cm))
cms_all.append(cm)
f1_all.append(numpy.mean(f1))
print("\t\t", end="")
for i, c in enumerate(class_names):
if i == len(class_names)-1:
print("{0:s}\t\t".format(c), end="")
else:
print("{0:s}\t\t\t".format(c), end="")
print("OVERALL")
print("\tC", end="")
for c in class_names:
print("\tPRE\tREC\tf1", end="")
print("\t{0:s}\t{1:s}".format("ACC", "f1"))
best_ac_ind = numpy.argmax(ac_all)
best_f1_ind = numpy.argmax(f1_all)
for i in range(len(precision_classes_all)):
print("\t{0:.3f}".format(Params[i]), end="")
for c in range(len(precision_classes_all[i])):
print("\t{0:.1f}\t{1:.1f}\t{2:.1f}".format(100.0 * precision_classes_all[i][c],
100.0 * recall_classes_all[i][c],
100.0 * f1_classes_all[i][c]), end="")
print("\t{0:.1f}\t{1:.1f}".format(100.0 * ac_all[i], 100.0 * f1_all[i]), end="")
if i == best_f1_ind:
print("\t best f1", end="")
if i == best_ac_ind:
print("\t best Acc", end="")
print("")
if parameterMode == 0: # keep parameters that maximize overall classification accuracy:
print("Confusion Matrix:")
printConfusionMatrix(cms_all[best_ac_ind], class_names)
return Params[best_ac_ind]
elif parameterMode == 1: # keep parameters that maximize overall f1 measure:
print("Confusion Matrix:")
printConfusionMatrix(cms_all[best_f1_ind], class_names)
return Params[best_f1_ind]