def __init__(self, filename=None):
"""
:param filename: if provided, cache parameters trained
"""
self.filename = filename
self.rmat = None
self.users = None
self.items = None
self.log = LogUtil.getLogger(self.__class__.__name__)
super(Predictor, self).__init__()
def get_data(filename, columns, delimiter='::'):
"""
:param filename: path of data source
:param columns: column name for each column
:param delimiter: delimiter to split a line
:return: dataframe
"""
log = LogUtil.getLogger('get_data')
clock = Timer()
with open(os.path.join(filename), 'r') as infile:
data = infile.readlines()
df = pd.DataFrame([row.rstrip().split(delimiter) for row in data],
columns=columns)
e0 = clock.restart()
log.info("loading data from %s with columns %s takes %.3f secs ",
filename, columns, e0)
return df
def train_test_split(ratings, frac=0.1, group='user', seed=1):
"""
split data into train and test by frac
if group is provide, split date into train and test by frac in each group
"""
log = LogUtil.getLogger('train_test_split')
log.info("start splitting test and train data ...")
clock = Timer()
if group:
ratings_test = ratings.groupby(group).apply(
lambda x: x.sample(frac=frac, random_state=seed))
ratings_test.index = ratings_test.index.droplevel(group)
else:
ratings_test = ratings.sample(frac=frac, random_state=seed)
ratings_train = pd.merge(ratings,
ratings_test,
indicator=True,
how='outer').query('_merge=="left_only"').drop(
'_merge', axis=1)
e0 = clock.restart()
log.info("splitting test and train data takes %.3f secs", e0)
return ratings_train, ratings_test
from recsys.cf.funksvd import FunkSVD from recsys.utils.data import train_test_split, load_movielen_data from recsys.utils.debug import LogUtil LogUtil.configLog() model = FunkSVD(learning_rate=0.001, reg=0.005, n_epochs=100, n_factors=30) ratings, users, movies = load_movielen_data() training, testing = train_test_split(ratings) model.fit(training) model.eval(testing)
def __init__(self, **kwargs):
self.rmat = None
self.users = None
self.items = None
self.log = LogUtil.getLogger(self.__class__.__name__)
super(BaseSelector, self).__init__(**kwargs)