def main():
# trainLabelFile = '/tmp2/yucwang/data/mongo/train.csv'
# trainPrefix = '/tmp2/yucwang/data/mongo/C1-P1_Train/'
# validLabelFile = '/tmp2/yucwang/data/mongo/dev.csv'
# validPrefix = '/tmp2/yucwang/data/mongo/C1-P1_Dev/'
#
# trainX, trainY = extractFeatures(trainLabelFile, trainPrefix)
# validX, validY = extractFeatures(validLabelFile, validPrefix)
#
# np.save('./train_x.npy', trainX)
# np.save('./train_y.npy', trainY)
# np.save('./val_x.npy', validX)
# np.save('./val_y.npy', validY)
trainX = np.load('./bin/exp2/train_x.npz.npy')
trainY = np.load('./bin/exp2/train_y.npz.npy')
validX = np.load('./bin/exp2/val_x.npz.npy')
validY = np.load('./bin/exp2/val_y.npz.npy')
model = SVM(penalty='l2', loss='squared_hinge', C=0.85, maxIter=2000)
print("SVM: Training get started.")
model.train(trainX, trainY)
print("SVM: Validation get started.")
acc, metrics = model.valid(validX, validY, classNum=3)
print(acc)
print(metrics)
def main(arguments):
# load the features of the dataset
features = datasets.load_breast_cancer().data
# standardize the features
features = StandardScaler().fit_transform(features)
# get the number of features
num_features = features.shape[1]
# load the corresponding labels for the features
labels = datasets.load_breast_cancer().target
# transform the labels to {-1, +1}
labels[labels == 0] = -1
# split the dataset to 70/30 partition: 70% train, 30% test
train_features, test_features, train_labels, test_labels = train_test_split(
features, labels, test_size=0.3, stratify=labels)
train_size = train_features.shape[0]
test_size = test_features.shape[0]
# slice the dataset as per the batch size
train_features = train_features[:train_size - (train_size % BATCH_SIZE)]
train_labels = train_labels[:train_size - (train_size % BATCH_SIZE)]
test_features = test_features[:test_size - (test_size % BATCH_SIZE)]
test_labels = test_labels[:test_size - (test_size % BATCH_SIZE)]
# instantiate the SVM class
model = SVM(
alpha=LEARNING_RATE,
batch_size=BATCH_SIZE,
svm_c=arguments.svm_c,
num_classes=NUM_CLASSES,
num_features=num_features,
)
# train the instantiated model
model.train(
epochs=arguments.num_epochs,
log_path=arguments.log_path,
train_data=[train_features, train_labels],
train_size=train_features.shape[0],
validation_data=[test_features, test_labels],
validation_size=test_features.shape[0],
result_path=arguments.result_path,
)
test_conf, test_accuracy = utils.plot_confusion_matrix(
phase="testing",
path=arguments.result_path,
class_names=["benign", "malignant"])
print("True negatives : {}".format(test_conf[0][0]))
print("False negatives : {}".format(test_conf[1][0]))
print("True positives : {}".format(test_conf[1][1]))
print("False positives : {}".format(test_conf[0][1]))
print("Testing accuracy : {}".format(test_accuracy))
def train_svm():
data_helper = DataHelper()
train_text, train_labels, ver_text, ver_labels, test_text, test_labels = data_helper.get_data_and_labels()
stopwords = data_helper.get_stopwords()
svm = SVM(train_text, train_labels, ver_text, ver_labels, test_text, test_labels, stopwords)
svm.train()
svm.verification()
print('ver_acc: {:.3}'.format(svm.ver_acc))
svm.test()
print('test_acc: {:.3}'.format(svm.test_acc))
def main(arguments):
# load the features of the dataset
features = datasets.load_breast_cancer().data
# standardize the features
features = StandardScaler().fit_transform(features)
# get the number of features
num_features = features.shape[1]
# load the corresponding labels for the features
labels = datasets.load_breast_cancer().target
# transform the labels to {-1, +1}
labels[labels == 0] = -1
# split the dataset to 70/30 partition: 70% train, 30% test
train_features, test_features, train_labels, test_labels = train_test_split(features, labels,
test_size=0.3, stratify=labels)
train_size = train_features.shape[0]
test_size = test_features.shape[0]
# slice the dataset as per the batch size
train_features = train_features[:train_size - (train_size % BATCH_SIZE)]
train_labels = train_labels[:train_size - (train_size % BATCH_SIZE)]
test_features = test_features[:test_size - (test_size % BATCH_SIZE)]
test_labels = test_labels[:test_size - (test_size % BATCH_SIZE)]
# instantiate the SVM class
model = SVM(alpha=LEARNING_RATE, batch_size=BATCH_SIZE, svm_c=arguments.svm_c, num_classes=NUM_CLASSES,
num_features=num_features)
# train the instantiated model
model.train(epochs=arguments.num_epochs, log_path=arguments.log_path, train_data=[train_features, train_labels],
train_size=train_features.shape[0], validation_data=[test_features, test_labels],
validation_size=test_features.shape[0], result_path=arguments.result_path)
test_conf, test_accuracy = utils.plot_confusion_matrix(phase='testing', path=arguments.result_path,
class_names=['benign', 'malignant'])
print('True negatives : {}'.format(test_conf[0][0]))
print('False negatives : {}'.format(test_conf[1][0]))
print('True positives : {}'.format(test_conf[1][1]))
print('False positives : {}'.format(test_conf[0][1]))
print('Testing accuracy : {}'.format(test_accuracy))
dp = DecayingPerceptron()
dp.train(learning_rates)
dp.report()
dp.evaluate()
ap = AveragedPerceptron()
ap.train(learning_rates)
ap.report()
ap.evaluate()
############################################
###### Part II ###########
############################################
svm = SVM(verbose=True)
svm.train(epochs=20)
hm.report(svm)
hm.evaluate(svm)
lr = LogisticRegression(verbose=True)
lr.train(epochs=20)
hm.report(lr)
hm.evaluate(lr)
nb = NaiveBayes()
nb.train(epochs=1)
hm.report(nb)
hm.evaluate(nb)
# Logistic regression using sklearn
import data as dt
