def load_real_fake_data_ML_1m(file_index=24):
data = []
real = MD.load_user_item_matrix_1m()
#real = MD.load_user_item_matrix_100k()
#real = load_user_item_matrix_1m_masked(file_index=17)
real = real[0:int(real.shape[0] / 2), :]
#fake = load_user_item_matrix_100k()
#fake = simulate_data(real.shape)
fake = load_user_item_matrix_1m_masked(file_index=file_index)
#fake = MD.load_user_item_matrix_100k_masked(file_index=1)
fake = fake[int(fake.shape[0] / 2):, :]
#fake = real
#fake = np.random.randint(5, size=real.shape)
#print(fake)
data = np.zeros(shape=(real.shape[0] + fake.shape[0], real[0].shape[0]))
labels = np.zeros(shape=(real.shape[0] + fake.shape[0], ))
for user_index, user in enumerate(real):
data[user_index, :] = user
labels[user_index] = 1
for user_index, user in enumerate(fake):
data[len(real) + user_index, :] = user
labels[len(real) + user_index] = 0
from Utils import shuffle_two_arrays
data, labels = shuffle_two_arrays(data, labels)
return data, labels
def load_real_fake_data_ML_100k():
from MovieLensData import load_user_item_matrix_100k, load_user_item_matrix_100k_masked
data = []
real = load_user_item_matrix_100k()
#fake = load_user_item_matrix_100k()
#fake = simulate_data(real.shape)
fake = load_user_item_matrix_100k_masked(file_index=1)
#fake = np.random.randint(5, size=real.shape)
print(fake)
data = np.zeros(shape=(len(real) + len(fake), len(real[0])))
labels = np.zeros(shape=(len(real) + len(fake), ))
for user_index, user in enumerate(real):
data[user_index, :] = user
labels[user_index] = 1
for user_index, user in enumerate(fake):
data[len(real) + user_index, :] = user
labels[len(real) + user_index] = 0
from Utils import shuffle_two_arrays
data, labels = shuffle_two_arrays(data, labels)
return data, labels
def load_real_fake_data_libimseti(file_index=-1):
import LibimSeTiData as LD
real, _, valid_movies = LD.load_libimseti_data_subset(small=True)
real = real[0:int(real.shape[0] / 2), :]
fake = LD.load_libimseti_data_subset_masked(file_index=file_index,
small=True,
valid_movies=valid_movies)[0]
fake = fake[int(fake.shape[0] / 2):, :]
data = np.zeros(shape=(real.shape[0] + fake.shape[0], real[0].shape[0]))
labels = np.zeros(shape=(real.shape[0] + fake.shape[0], ))
for user_index, user in enumerate(real):
data[user_index, :] = user
labels[user_index] = 1
for user_index, user in enumerate(fake):
data[len(real) + user_index, :] = user
labels[len(real) + user_index] = 0
from Utils import shuffle_two_arrays
data, labels = shuffle_two_arrays(data, labels)
return data, labels