classifiers = [
("KNN", None, KNeighborsClassifier(2)),
("Linear SVM", None, SVC(kernel="linear")),
("RBF SVM", None, SVC(gamma=2, C=1)),
("DT", None, DecisionTreeClassifier(min_samples_split=1024, max_depth=20)),
("RF", None,
RandomForestClassifier(n_estimators=10,
min_samples_split=1024,
max_depth=20)),
("AB", None, AdaBoostClassifier(random_state=13370)),
#("GP ARD", ["MFCC"], gp.GaussianProcessClassifier(kernel=ard_kernel(sigma=1.2, length_scale=np.array([1]*1)))),
("GP-DP", ["MFCC", "All", "CIFE", "CFS"],
gp.GaussianProcessClassifier(kernel=gp.kernels.DotProduct()))
# output the confidence level and the predictive variance for the dot product (the only one that we keep in the end)
# GP beats SVM in our experiment (qualitative advantages)
# only keep RBF, dot product and matern on the chart
# add a paragraph 'Processed Data'
#1) generate the dataset with 526 features
#2) the predictive variance and predictive mean (best and worst) of some vectors from the dot product.
]
#classify(X_train[:,bitVec], X_dev[:,bitVec])
models_f1, models_performances = getClassifieresPerformances(
classifiers, models_f1, models_performances)
#models_f1, models_performances = getClassifieresPerformancesByDefinedX(classifiers, 'predict', models_f1, models_performances, newTrainX, y_bin_train, newDevX)
models_f1, models_performances = addRelatedWork(models_f1, models_performances)
models_f1 = sorted(models_f1, key=lambda l: l[1])
models_performances = sorted(models_performances, key=lambda l: l[1])
plot_f1(models_f1)
printPerformances(models_performances)
def showPerformance(models_f1, models_performances): plot_f1(models_f1) printPerformances(models_performances)