def __init__(self, users, eps, MinPts, reduce_dimensions=False):
if reduce_dimensions:
autoencoder = AutoEncoder(users)
users = autoencoder.reduce_dimensions(
) # num_dimensions should be bigger than 4. else it runs for 4.
self.userLength = users.shape[0]
self.eps = eps
self.MinPts = MinPts
self.DistanceMatrix = self.__calcDistanceMatrix(users)
def __init__(self, train, test, reduce_dimensions=False):
self.train_data = train
self.test_data = test
labels = self.extractLabels(self.train_data)
if reduce_dimensions:
train_autoencoder = AutoEncoder(self.train_data)
self.train_data = train_autoencoder.reduce_dimensions() # num_dimensions should be bigger than 4. else it runs for 4.
test_autoencoder = AutoEncoder(self.test_data)
self.test_data = test_autoencoder.reduce_dimensions()
self.train_data["label"] = labels
def __init__(self, train, test, reduce_dimensions=False):
self.train_data = train
self.test_data = test
self.train_data = self.train_data.sort_values(
by='popularity', ascending=False
) # test data is also sorted, so in this way i can find them and discriminate them
self.train_data = self.train_data[self.test_data.shape[
0]:] # keep for train only the data that isnt contained in test
self.train_data.reset_index(drop=True, inplace=True)
labels = self.extractLabels()
if reduce_dimensions:
train_autoencoder = AutoEncoder(self.train_data)
self.train_data = train_autoencoder.reduce_dimensions(
) # num_dimensions should be bigger than 4. else it runs for 4.
test_autoencoder = AutoEncoder(self.test_data)
self.test_data = test_autoencoder.reduce_dimensions()
self.train_data["label"] = labels