def main(): print 'logistic_regression2_pca' train_x,train_y,kaggle_test = getNumpy() # train_x = train_x[:100] # train_y = train_y[:100] # kaggle_test = kaggle_test[:100] logistic_regression2_pca(train_x, train_y, kaggle_test)
def main(): train_x,train_y,kaggle_test = getNumpy() print 'svm_3_pca' # train_x = train_x[:100] # train_y = train_y[:100] # kaggle_test = kaggle_test[:100] svm_3_pca(train_x, train_y, kaggle_test)
def main(): train_x,train_y,test_x = getNumpy() # train_x = train_x[:10] # train_y = train_y[:10] # test_x = test_x[:10] X_train, X_valid, Y_train, Y_valid = train_test_split(train_x, train_y,test_size=0.2,random_state=0) print 'logistic_regression' logistic_regression(X_train,X_valid,Y_train,Y_valid,train_x,train_y,test_x)
cost_batch, output_train = train(X_batch, y_batch)
costs += [cost_batch]
preds = np.argmax(output_train, axis=-1)
correct += np.sum(y_batch == preds)
return np.mean(costs), correct / float(num_samples)
def eval_epoch(X, y):
output_eval, transform_eval = eval(X)
preds = np.argmax(output_eval, axis=-1)
acc = np.mean(preds == y)
return acc, transform_eval
from load_numpy import getNumpy
X,Y,testx = getNumpy()
X_train, X_test, Y_train, Y_test = train_test_split(X, Y,test_size=0.2,random_state=0)
valid_accs, train_accs, test_accs = [], [], []
try:
for n in range(NUM_EPOCHS):
train_cost, train_acc = train_epoch(X_train, Y_train)
# valid_acc, valid_trainsform = eval_epoch(data['X_valid'], data['y_valid'])
test_acc, test_transform = eval_epoch(X_test, Y_test)
# valid_accs += [valid_acc]
test_accs += [test_acc]
train_accs += [train_acc]
if (n+1) % 20 == 0:
new_lr = sh_lr.get_value() * 0.7
print "New LR:", new_lr
sh_lr.set_value(lasagne.utils.floatX(new_lr))
from load_numpy import getNumpy from test_classifier import svm1 from preprocesses import pca from rbm import rbm from sklearn.cross_validation import train_test_split train_x,train_y,test_x = getNumpy() train_x_transform = pca(train_x,100) X_train, X_valid, Y_train, Y_valid = train_test_split(train_x_transform, train_y,test_size=0.2,random_state=0) # svm1(train_x_transform,train_y) rbm(train_x,train_y)
