-o output destination directory [default: output]
-n N number of recommendations for a unique user [default: 100]
-m MODULE import algorithms from MODULE [default: lkdemo.algorithms]
ALGO name of algorithm to load
"""
from docopt import docopt
from pathlib import Path
from lenskit.algorithms import Recommender, Predictor
from lenskit import batch, util
from lkdemo import log
import importlib
import pandas as pd
_log = log.script(__file__)
args = docopt(__doc__)
mod_name = args.get('-m')
input = args.get('--splits')
output = args.get('-o')
n_recs = int(args.get('-n'))
model = args.get('ALGO')
_log.info(f'importing from module {mod_name}')
algorithms = importlib.import_module(mod_name)
algo = getattr(algorithms, model)
path = Path(input)
path.name)
train = datasets.ds_diff(ds_def.ratings, test)
train.reset_index(drop=True, inplace=True)
else:
_log.error('could not find training data for %s', file.name)
continue
_log.info('[%s] Fitting the model', timer)
# We train isolated to manage resource use
model = batch.train_isolated(algo, train)
try:
_log.info('[%s] generating recommendations for unique users',
timer)
users = test.user.unique()
recs = batch.recommend(model, users, n_recs)
_log.info('[%s] writing recommendations to %s', timer, dest)
recs.to_csv(dest / f'recs-{suffix}', index=False)
if isinstance(algo, Predictor) and not args['--no-predict']:
_log.info('[%s] generating predictions for user-item', timer)
preds = batch.predict(model, test)
preds.to_csv(dest / f'pred-{suffix}', index=False)
finally:
model.close()
if __name__ == '__main__':
args = docopt(__doc__)
_log = log.script(__file__, log_file=args['--log-file'])
main(args)