def main():
# args from Simple Queries paper
DIM = 30
WORDGRAMS = 2
MINCOUNT = 8
MINN = 3
MAXN = 3
BUCKET = 1000000
# adjust these
EPOCH = 5
LR = 0.15 # 0.15 good for ~5000
KERN = 'lin' # lin or rbf or poly
NUM_RUNS = 1 # number of test runs
SUBSET_VAL = 300 # number of subset instances for self reported dataset
LIN_C = 0.90 # hyperparameter for linear kernel
run = 0
print("starting dictionary creation.............................")
dictionary = Dictionary(WORDGRAMS, MINCOUNT, BUCKET, SUBSET_VAL, run)
X_train, X_test, y_train, y_test = dictionary.get_train_and_test()
print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
n_train = dictionary.get_n_train_instances()
n_test = dictionary.get_n_manual_instances()
X_train = dictionary.get_trainset()
X_test = dictionary.get_manual_testset()
print()
print("starting optimization")
#coef = kernel_mean_matching(X_train, X_test, n_train, n_test, kern='lin', B=10)
coef = kernel_mean_matching(X_test, X_train[0], LIN_C, kern='lin', B=10)
print(coef)
###################################################################
WORDGRAMS = 3
MINCOUNT = 2
BUCKET = 1000000
print("starting dictionary creation.............................")
dictionary = Dictionary(WORDGRAMS, MINCOUNT, BUCKET)
X_train, X_test, y_train, y_test = dictionary.get_train_and_test()
print(X_train.shape, X_test.shape, y_train.shape, y_test.shape)
n_train = dictionary.get_n_train_instances()
n_test = dictionary.get_n_manual_instances()
X_train = dictionary.get_trainset()
X_test = dictionary.get_manual_testset()
B = n_train
#sigma = np.std(X_train) # compute standard deviation ????
sigma = 0.25
b = (0.0, B)
bounds = (b, b, b, b, b)
beta0 = np.zeros((n_train))
print("creating gram matrix")
K = create_K()
k = create_k()
print(K.shape, k.shape)
print("dont creating gram matrix")