def run_classifier(train_fv,
train_label,
val_fv,
val_label,
k,
C=1.0,
gamma='auto'):
estimator = SVC(kernel=k, C=C, gamma=gamma)
classifier = OneVsRestClassifier(estimator, n_jobs=-1)
classifier.fit(train_fv, train_label)
val_pd = classifier.predict(val_fv)
val_f1 = npmetrics.label_f1_macro(val_label, val_pd)
print("\n---val---", "k:", k, 'C:', C, 'gamma', gamma, 'f1:', val_f1)
npmetrics.print_metrics(val_label, val_pd)
return classifier, val_f1
def svm(fv='fv0'):
train_items, val_items, test_items = load_fv(fv)
print("train items", len(train_items))
print("val items", len(val_items))
print("test items", len(test_items))
train_gene, train_fv, train_label = zip(*train_items)
val_gene, val_fv, val_label = zip(*val_items)
test_gene, test_fv, test_label = zip(*test_items)
print("-------run svm for bov--------", fv)
scaler = StandardScaler()
scaler.fit(train_fv)
train_fv = np.stack(scaler.transform(train_fv))
val_fv = np.stack(scaler.transform(val_fv))
test_fv = np.stack(scaler.transform(test_fv))
train_label = np.stack(train_label)
val_label = np.stack(val_label)
test_label = np.stack(test_label)
kernels = ['linear', 'rbf', 'poly', 'sigmoid']
class_weights = ['balanced', None]
best_f1 = 0.0
best_classifier = None
best_k = None
best_b = None
for k in kernels:
for b in class_weights:
estimator = SVC(kernel=k, class_weight=b)
classifier = OneVsRestClassifier(estimator, n_jobs=-1)
classifier.fit(train_fv, train_label)
val_pd = classifier.predict(val_fv)
val_f1 = npmetrics.label_f1_macro(val_label, val_pd)
print("\n---svm for bov---", "k:", k, 'b:', b, 'f1:', val_f1)
npmetrics.print_metrics(val_label, val_pd)
if val_f1 > best_f1:
best_f1 = val_f1
best_classifier = classifier
best_k = k
best_b = b
test_pd = best_classifier.predict(test_fv)
print("\n---svm for bov test result---", "k:", best_k, "b:", best_b)
npmetrics.print_metrics(test_label, test_pd)