How to use the cornac.models function in cornac

# 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.
# ============================================================================
"""Example for Variational Autoencoder for Collaborative Filtering for Implicit Feedback Datasets (Citeulike)"""

import cornac
from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit

data = citeulike.load_feedback()

ratio_split = RatioSplit(data=data, test_size=0.2, exclude_unknowns=True,
                         verbose=True, seed=123, rating_threshold=0.5)

vaecf = cornac.models.VAECF(k=10, h=20, n_epochs=100, batch_size=100, learning_rate=0.001, beta=1.0, seed=123)

rec_20 = cornac.metrics.Recall(k=20)
ndcg_20 = cornac.metrics.NDCG(k=20)
auc = cornac.metrics.AUC()

cornac.Experiment(eval_method=ratio_split,
                  models=[vaecf],
                  metrics=[rec_20, ndcg_20, auc],
                  user_based=True).run()

import cornac
from cornac.datasets import amazon_toy
from cornac.data import SentimentModality
from cornac.eval_methods import RatioSplit

rating = amazon_toy.load_feedback()
sentiment = amazon_toy.load_sentiment()
md = SentimentModality(data=sentiment)

split_data = RatioSplit(data=rating,
                        test_size=0.15,
                        exclude_unknowns=True, verbose=True,
                        sentiment=md, seed=123)

efm = cornac.models.EFM(num_explicit_factors=40, num_latent_factors=60, num_most_cared_aspects=15,
                        rating_scale=5.0, alpha=0.85,
                        lambda_x=1, lambda_y=1, lambda_u=0.01, lambda_h=0.01, lambda_v=0.01,
                        max_iter=100, num_threads=1,
                        trainable=True, verbose=True, seed=123)

rmse = cornac.metrics.RMSE()
ndcg_50 = cornac.metrics.NDCG(k=50)
auc = cornac.metrics.AUC()

exp = cornac.Experiment(eval_method=split_data,
                        models=[efm],
                        metrics=[rmse, ndcg_50, auc])
exp.run()

# limitations under the License.
# ============================================================================


import cornac
from cornac.eval_methods import RatioSplit
from cornac.datasets import amazon_clothing
from cornac.data import Reader

ratio_split = RatioSplit(data=amazon_clothing.load_feedback(reader=Reader(bin_threshold=1.0)),
                         test_size=0.2, rating_threshold=1.0, seed=123,
                         exclude_unknowns=True, verbose=True)

gmf = cornac.models.GMF(num_factors=8, num_epochs=10, learner='adam',
                        batch_size=256, lr=0.001, num_neg=50, seed=123)
mlp = cornac.models.MLP(layers=[64, 32, 16, 8], act_fn='tanh', learner='adam',
                        num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123)
neumf1 = cornac.models.NeuMF(num_factors=8, layers=[64, 32, 16, 8], act_fn='tanh', learner='adam',
                             num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123)
neumf2 = cornac.models.NeuMF(name='NeuMF_pretrained', learner='adam',
                             num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123,
                             num_factors=gmf.num_factors, layers=mlp.layers, act_fn=mlp.act_fn).pretrain(gmf, mlp)

ndcg_50 = cornac.metrics.NDCG(k=50)
rec_50 = cornac.metrics.Recall(k=50)

cornac.Experiment(eval_method=ratio_split,
                  models=[gmf, mlp, neumf1, neumf2],
                  metrics=[ndcg_50, rec_50]).run()

# 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 cornac as cn

ml_100k = cn.datasets.movielens.load_feedback()
ratio_split = cn.eval_methods.RatioSplit(data=ml_100k, test_size=0.2,
                                         rating_threshold=4.0, verbose=True)

bo = cn.models.BaselineOnly(max_iter=30, learning_rate=0.01, lambda_reg=0.02, verbose=True)
svd = cn.models.SVD(k=10, max_iter=30, learning_rate=0.01, lambda_reg=0.02, verbose=True)

mae = cn.metrics.MAE()
rmse = cn.metrics.RMSE()

cn.Experiment(eval_method=ratio_split,
              models=[bo, svd],
              metrics=[mae, rmse]).run()

# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""Example for Matrix Factorization with biases"""

import cornac
from cornac.datasets import movielens
from cornac.eval_methods import RatioSplit

ratio_split = RatioSplit(data=movielens.load_feedback(variant='1M'),
                         test_size=0.2,
                         exclude_unknowns=False,
                         verbose=True)

global_avg = cornac.models.GlobalAvg()
mf = cornac.models.MF(k=10, max_iter=25, learning_rate=0.01, lambda_reg=0.02,
                      use_bias=True, early_stop=True, verbose=True)

mae = cornac.metrics.MAE()
rmse = cornac.metrics.RMSE()

exp = cornac.Experiment(eval_method=ratio_split,
                        models=[global_avg, mf],
                        metrics=[mae, rmse],
                        user_based=True)
exp.run()

# ============================================================================
"""Example for Collaborative Filtering for Implicit Feedback Datasets (Citeulike)"""

import cornac
from cornac.data import Reader
from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit

_, item_ids = citeulike.load_text()

data = citeulike.load_feedback(reader=Reader(item_set=item_ids))

ratio_split = RatioSplit(data=data, test_size=0.2, exclude_unknowns=True,
                         verbose=True, seed=123, rating_threshold=0.5)

cf = cornac.models.WMF(k=50, max_iter=50, learning_rate=0.001, lambda_u=0.01, lambda_v=0.01, verbose=True, seed=123)

rec_300 = cornac.metrics.Recall(k=300)

cornac.Experiment(eval_method=ratio_split,
                  models=[cf],
                  metrics=[rec_300],
                  user_based=True).run()

# 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 cornac
from cornac.eval_methods import RatioSplit
from cornac.datasets import amazon_clothing
from cornac.data import Reader

ratio_split = RatioSplit(data=amazon_clothing.load_feedback(reader=Reader(bin_threshold=1.0)),
                         test_size=0.2, rating_threshold=1.0, seed=123,
                         exclude_unknowns=True, verbose=True)

gmf = cornac.models.GMF(num_factors=8, num_epochs=10, learner='adam',
                        batch_size=256, lr=0.001, num_neg=50, seed=123)
mlp = cornac.models.MLP(layers=[64, 32, 16, 8], act_fn='tanh', learner='adam',
                        num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123)
neumf1 = cornac.models.NeuMF(num_factors=8, layers=[64, 32, 16, 8], act_fn='tanh', learner='adam',
                             num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123)
neumf2 = cornac.models.NeuMF(name='NeuMF_pretrained', learner='adam',
                             num_epochs=10, batch_size=256, lr=0.001, num_neg=50, seed=123,
                             num_factors=gmf.num_factors, layers=mlp.layers, act_fn=mlp.act_fn).pretrain(gmf, mlp)

ndcg_50 = cornac.metrics.NDCG(k=50)
rec_50 = cornac.metrics.Recall(k=50)

cornac.Experiment(eval_method=ratio_split,
                  models=[gmf, mlp, neumf1, neumf2],
                  metrics=[ndcg_50, rec_50]).run()

#
# 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 cornac as cn

ml_100k = cn.datasets.movielens.load_feedback()
ratio_split = cn.eval_methods.RatioSplit(data=ml_100k, test_size=0.2,
                                         rating_threshold=4.0, verbose=True)

bo = cn.models.BaselineOnly(max_iter=30, learning_rate=0.01, lambda_reg=0.02, verbose=True)
svd = cn.models.SVD(k=10, max_iter=30, learning_rate=0.01, lambda_reg=0.02, verbose=True)

mae = cn.metrics.MAE()
rmse = cn.metrics.RMSE()

cn.Experiment(eval_method=ratio_split,
              models=[bo, svd],
              metrics=[mae, rmse]).run()

from cornac.datasets import citeulike
from cornac.eval_methods import RatioSplit
from cornac.data import TextModality
from cornac.data.text import BaseTokenizer

docs, item_ids = citeulike.load_text()
data = citeulike.load_feedback(reader=Reader(item_set=item_ids))

# build text modality
item_text_modality = TextModality(corpus=docs, ids=item_ids,
                                tokenizer=BaseTokenizer(stop_words='english'),
                                max_vocab=8000, max_doc_freq=0.5)

ratio_split = RatioSplit(data=data, test_size=0.2, exclude_unknowns=True,
                         item_text=item_text_modality, verbose=True, seed=123, rating_threshold=0.5)
cdl = cornac.models.CDL(k=50, autoencoder_structure=[200], max_iter=30,
                        lambda_u=0.1, lambda_v=1, lambda_w=0.1, lambda_n=1000)
rec_300 = cornac.metrics.Recall(k=300)

exp = cornac.Experiment(eval_method=ratio_split,
                        models=[cdl],
                        metrics=[rec_300])
exp.run()

from cornac.eval_methods import RatioSplit
from cornac.data import TextModality
from cornac.data.text import BaseTokenizer

docs, item_ids = citeulike.load_text()
data = citeulike.load_feedback(reader=Reader(item_set=item_ids))

# build text modality
item_text_modality = TextModality(corpus=docs, ids=item_ids,
                                tokenizer=BaseTokenizer(sep=' ', stop_words='english'),
                                max_vocab=8000, max_doc_freq=0.5)

ratio_split = RatioSplit(data=data, test_size=0.2, exclude_unknowns=True,
                         item_text=item_text_modality, verbose=True, seed=123, rating_threshold=0.5)

ctr = cornac.models.CTR(k=50, max_iter=50, lambda_v=1)

rec_300 = cornac.metrics.Recall(k=300)

exp = cornac.Experiment(eval_method=ratio_split,
                        models=[ctr],
                        metrics=[rec_300])
exp.run()