How to use the cornac.models.recommender.Recommender function in cornac

def fit(self, train_set, val_set=None):
        """Fit the model to observations.

        Parameters
        ----------
        train_set: :obj:`cornac.data.Dataset`, required
            User-Item preference data as well as additional modalities.

        val_set: :obj:`cornac.data.Dataset`, optional, default: None
            User-Item preference data for model selection purposes (e.g., early stopping).

        Returns
        -------
        self : object
        """
        Recommender.fit(self, train_set, val_set)

        from .skmeans import skmeans

        X = self.train_set.matrix
        X = sp.csr_matrix(X)

        # Skmeans requires rows of X to have a unit L2 norm. We therefore need to make a copy of X as we should not modify the latter.
        X1 = X.copy()
        X1 = X1.multiply(sp.csc_matrix(1. / (np.sqrt(X1.multiply(X1).sum(1).A1) + 1e-20)).T)

        if self.trainable:
            res = skmeans(X1, k=self.k, max_iter=self.max_iter, tol=self.tol, verbose=self.verbose,
                          init_par=self.init_par)
            self.centroids = res['centroids']
            self.final_par = res['partition']
        else:

def fit(self, train_set, val_set=None):
        """Fit the model to observations.

        Parameters
        ----------
        train_set: :obj:`cornac.data.Dataset`, required
            User-Item preference data as well as additional modalities.

        val_set: :obj:`cornac.data.Dataset`, optional, default: None
            User-Item preference data for model selection purposes (e.g., early stopping).

        Returns
        -------
        self : object
        """
        Recommender.fit(self, train_set)

        from cornac.models.pmf import pmf

        if self.trainable:
            # converting data to the triplet format (needed for cython function pmf)
            (uid, iid, rat) = train_set.uir_tuple
            rat = np.array(rat, dtype='float32')
            if self.variant == 'non_linear':  # need to map the ratings to [0,1]
                if [self.train_set.min_rating, self.train_set.max_rating] != [0, 1]:
                    rat = scale(rat, 0., 1., self.train_set.min_rating, self.train_set.max_rating)
            uid = np.array(uid, dtype='int32')
            iid = np.array(iid, dtype='int32')

            if self.verbose:
                print('Learning...')

def fit(self, train_set, val_set=None):
        """Fit the model to observations.

        Parameters
        ----------
        train_set: :obj:`cornac.data.Dataset`, required
            User-Item preference data as well as additional modalities.

        val_set: :obj:`cornac.data.Dataset`, optional, default: None
            User-Item preference data for model selection purposes (e.g., early stopping).

        Returns
        -------
        self : object
        """
        Recommender.fit(self, train_set, val_set)
        from ...utils.init_utils import normal

        self.n_item = self.train_set.num_items
        self.n_user = self.train_set.num_users

        self.alpha = self.init_params.get('alpha', train_set.global_mean)
        self.beta_u = self.init_params.get('beta_u', normal(self.n_user, std=0.01, random_state=self.seed))
        self.beta_i = self.init_params.get('beta_i', normal(self.n_item, std=0.01, random_state=self.seed))
        self.gamma_u = self.init_params.get('gamma_u', normal((self.n_user, self.k), std=0.01, random_state=self.seed))
        self.gamma_i = self.init_params.get('gamma_i', normal((self.n_item, self.k), std=0.01, random_state=self.seed))

        if self.trainable:
            self._fit_hft()

        return self

# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================

import numpy as np

from ..recommender import Recommender
from ...utils.common import sigmoid
from ...utils.common import scale
from ...exception import ScoreException


class PMF(Recommender):
    """Probabilistic Matrix Factorization.

    Parameters
    ----------
    k: int, optional, default: 5
        The dimension of the latent factors.

    max_iter: int, optional, default: 100
        Maximum number of iterations or the number of epochs for SGD.

    learning_rate: float, optional, default: 0.001
        The learning rate for SGD_RMSProp.
        
    gamma: float, optional, default: 0.9
        The weight for previous/current gradient in RMSProp.

# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================

import numpy as np

from ..recommender import Recommender
from ...utils.common import sigmoid
from ...utils.common import scale
from ...exception import ScoreException


class MCF(Recommender):
    """Matrix Co-Factorization.

    Parameters
    ----------
    k: int, optional, default: 5
        The dimension of the latent factors.

    max_iter: int, optional, default: 100
        Maximum number of iterations or the number of epochs for SGD.

    learning_rate: float, optional, default: 0.001
        The learning rate for SGD_RMSProp.

    gamma: float, optional, default: 0.9
        The weight for previous/current gradient in RMSProp.

#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================

import numpy as np

from ..recommender import Recommender
from ...exception import ScoreException


class VAECF(Recommender):
    """Variational Autoencoder for Collaborative Filtering.

    Parameters
    ----------
    k: int, optional, default: 10
        The dimension of the stochastic user factors ``z''.

    h: int, optional, default: 20
       The dimension of the deterministic hidden layer.

    n_epochs: int, optional, default: 100
        The number of epochs for SGD.

    batch_size: int, optional, default: 100
        The batch size.

def _validate_models(input_models):
        if not hasattr(input_models, "__len__"):
            raise ValueError('models have to be an array but {}'.format(type(input_models)))

        valid_models = []
        for model in input_models:
            if isinstance(model, Recommender):
                valid_models.append(model)
        return valid_models

def __init__(self, k=100, z_dims=[300], max_iter=300, batch_size=300, learning_rate=0.001, name="pcrl",
                 trainable=True,
                 verbose=False, w_determinist=True, init_params={'G_s': None, 'G_r': None, 'L_s': None, 'L_r': None}):

        Recommender.__init__(self, name=name, trainable=trainable, verbose=verbose)

        self.k = k
        self.z_dims = z_dims  # the dimension of the second hidden layer (we consider a 2-layers PCRL)
        self.max_iter = max_iter
        self.batch_size = batch_size
        self.learning_rate = learning_rate
        self.init_params = init_params
        self.w_determinist = w_determinist

#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================

import numpy as np

from ..recommender import Recommender
from ...exception import ScoreException


class HFT(Recommender):
    """Hidden Factors and Hidden Topics

    Parameters
    ----------
    name: string, default: 'HFT'
        The name of the recommender model.

    k: int, optional, default: 10
        The dimension of the latent factors.

    max_iter: int, optional, default: 50
        Maximum number of iterations for EM.

    grad_iter: int, optional, default: 50
        Maximum number of iterations for L-BFGS.