def flixster_obfuscated(classifier):
import FlixsterData as FD
X1, T, _ = FD.load_flixster_data_subset()
X2, _, _ = FD.load_flixster_data_subset_masked(
file_index=15) # max_user=max_user, max_item=max_item)
# X2 = X1
print(X1.shape, X2.shape)
# X1, T = Utils.balance_data(X1, T)
# X2, T2 = Utils.balance_data(X2, T)
# X1 = Utils.normalize(X1)
# X2 = Utils.normalize(X2)
X_train, T_train = X1[0:int(0.8 * len(X1))], T[0:int(0.8 * len(X1))]
X_test, T_test = X2[int(0.8 * len(X2)):], T[int(0.8 * len(X2)):]
print(list(X1[0, :]))
print(list(X2[0, :]))
# print(X)
print("before", X_train.shape)
# X = Utils.remove_significant_features(X, T)
# X_train, _ = Utils.random_forest_selection(X_train, T_train)
# X = feature_selection(X, T, Utils.select_male_female_different)
print(X_train.shape)
from sklearn.linear_model import LogisticRegression
random_state = np.random.RandomState(0)
model = LogisticRegression(penalty='l2', random_state=random_state)
Utils.ROC_cv_obf(X1, X2, T, model)
model = LogisticRegression(penalty='l2', random_state=random_state)
def load_real_fake_data_flixster(file_index=-1):
import FlixsterData as FD
real, _, valid_movies = FD.load_flixster_data_subset(small=True)
real = real[0:int(real.shape[0] / 2), :]
fake = FD.load_flixster_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