help="comma-separated item IDs for loved items")
parser.add_argument('--like',
type=csv,
help="comma-separated item IDs for liked items")
parser.add_argument('--neutral',
type=csv,
help="comma-separated item IDs for neutral items")
parser.add_argument('--dislike',
type=csv,
help="comma-separated item IDs for disliked items")
parser.add_argument('--hate',
type=csv,
help="comma-separated item IDs for hated items")
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
if args.love is not None:
for item in args.love:
tastes[item] = 1.0
if args.like is not None:
for item in args.like:
tastes[item] = 0.75
if args.neutral is not None:
for item in args.neutral:
tastes[item] = 0.5
if args.dislike is not None:
for item in args.dislike:
tastes[item] = 0.25
if args.hate is not None:
#!/usr/bin/python # -*- coding: utf8 -*- # # recommend.py # José Devezas ([email protected]) # 2013-06-28 import os import sys import argparse from jld import LatentFactorsModel if __name__ == "__main__": parser = argparse.ArgumentParser( description='Recommend new items to an existing user ordered by predicted rating.') parser.add_argument('user', help='user identification string, as defined in the training set') parser.add_argument('model_path', help='HDF5 file with the trained model containing the factorized matrices') args = parser.parse_args() model = LatentFactorsModel(args.model_path) rank = 1 for item_id, rating in model.recommend(args.user, limit=20): print "%d\t%.10f\t%s" % (rank, rating, item_id) rank += 1
from jld import LatentFactorsModel
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description='Predict a normalized rating for any unrated item of an existing user.')
parser.add_argument('user',
help='user identification string, as defined in the training set')
parser.add_argument('item',
help='item identification string, as defined in the training set')
parser.add_argument('model_path',
help='HDF5 file with the trained model containing the factorized matrices')
parser.add_argument('-f', '--force-predict', action='store_true',
help='returns the predicted value even when the original rating is available')
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
if not args.force_predict:
# If rating exists, return real rating instead of prediction.
rating = model.get_rating(args.user, args.item)
if rating is not None:
print("User %s rated item %s with %f." % (args.user, args.item, rating))
sys.exit(0)
predicted_rating = model.predict(args.user, args.item)
if predicted_rating is None:
print("Could not predict rating for user %s and item %s." % (args.user, args.item))
sys.exit(1)
print("Predicted rating for user %s and item %s is of %f." % (args.user, args.item, predicted_rating))
parser.add_argument('--precompute', action='store_true',
help="precompute and store prediction values in HDF5 (DEFAULT=False)")
args = parser.parse_args()
if not os.access(args.ratings_path, os.R_OK):
print("'%s' is not readable." % args.ratings_path)
sys.exit(0)
if os.path.exists(args.model_path):
ans = None
while ans != 'y' and ans != 'n':
ans = raw_input("===> HDF5 model already exists at %s. Overwrite? [yn] " % args.model_path)
if ans != 'y': sys.exit(0)
os.remove(args.model_path)
model = LatentFactorsModel(args.model_path)
if args.delimiter is not None:
model.set_training_csv_delimiter(args.delimiter)
if args.rank is not None:
model.set_training_rank(args.rank)
if args.size is not None:
model.set_training_sample_size(args.size)
model.train(args.ratings_path)
if args.precompute:
model.precompute_predictions()
"HDF5 file with the trained model containing the factorized matrices")
parser.add_argument(
'preferences_csv_path',
help=
"HDF5 file with the trained model containing the factorized matrices")
parser.add_argument(
'-c',
'--group-combine',
choices=['mean', 'usage-wmean'],
default='mean',
help=
'selects the method to combine the user profiles into a single group profile (DEFAULT: mean)'
)
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
with open(args.preferences_csv_path, 'rb') as f:
for user_id, item_id, normalized_rating in csv.reader(f):
if not user_id in tastes:
tastes[user_id] = {}
tastes[user_id][item_id] = float(normalized_rating)
group_combine = jld.group_mean
if args.group_combine == 'usage-wmean':
group_combine = jld.group_weighted_mean_by_user_activity
rank = 1
for item_id, rating in model.recommend_to_group_by_query(
tastes, group_combine=group_combine)[0:20]:
)
parser.add_argument(
"-m",
"--max-features",
type=int,
help="""the maximum number of features to use in cross-validation
(ignored if sampling size is not defined)""",
)
parser.add_argument("-o", "--output", type=str, help="output CSV filename, to store validation scores (MAE)")
args = parser.parse_args()
if not os.access(args.ratings_path, os.R_OK):
print("'%s' is not readable." % args.ratings_path)
sys.exit(0)
model = LatentFactorsModel()
if args.delimiter is not None:
model.set_training_csv_delimiter(args.delimiter)
if args.rank is not None:
model.set_training_rank(args.rank)
k = 10
if args.folds is not None:
k = args.folds
feature_sampling = None
if args.feature_sampling_interval is not None:
feature_sampling_interval = args.feature_sampling_interval
'item',
help='item identification string, as defined in the training set')
parser.add_argument(
'model_path',
help=
'HDF5 file with the trained model containing the factorized matrices')
parser.add_argument(
'-f',
'--force-predict',
action='store_true',
help=
'returns the predicted value even when the original rating is available'
)
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
if not args.force_predict:
# If rating exists, return real rating instead of prediction.
rating = model.get_rating(args.user, args.item)
if rating is not None:
print("User %s rated item %s with %f." %
(args.user, args.item, rating))
sys.exit(0)
predicted_rating = model.predict(args.user, args.item)
if predicted_rating is None:
print("Could not predict rating for user %s and item %s." %
(args.user, args.item))
sys.exit(1)
args = parser.parse_args()
if not os.access(args.ratings_path, os.R_OK):
print("'%s' is not readable." % args.ratings_path)
sys.exit(0)
if os.path.exists(args.model_path):
ans = None
while ans != 'y' and ans != 'n':
ans = raw_input(
"===> HDF5 model already exists at %s. Overwrite? [yn] " %
args.model_path)
if ans != 'y': sys.exit(0)
os.remove(args.model_path)
model = LatentFactorsModel(args.model_path)
if args.delimiter is not None:
model.set_training_csv_delimiter(args.delimiter)
if args.rank is not None:
model.set_training_rank(args.rank)
if args.size is not None:
model.set_training_sample_size(args.size)
model.train(args.ratings_path)
if args.precompute:
model.precompute_predictions()
import argparse
import jld
from jld import LatentFactorsModel
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Use group preferences to recommend new items.")
parser.add_argument('model_path',
help="HDF5 file with the trained model containing the factorized matrices")
parser.add_argument('preferences_csv_path',
help="HDF5 file with the trained model containing the factorized matrices")
parser.add_argument('-c', '--group-combine', choices=['mean', 'usage-wmean'], default='mean',
help='selects the method to combine the user profiles into a single group profile (DEFAULT: mean)')
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
with open(args.preferences_csv_path, 'rb') as f:
for user_id, item_id, normalized_rating in csv.reader(f):
if not user_id in tastes:
tastes[user_id] = {}
tastes[user_id][item_id] = float(normalized_rating)
group_combine = jld.group_mean
if args.group_combine == 'usage-wmean':
group_combine = jld.group_weighted_mean_by_user_activity
rank = 1
for item_id, rating in model.recommend_to_group_by_query(tastes, group_combine=group_combine)[0:20]:
print "%d\t%.10f\t%s" % (rank, rating, item_id)
help="comma-separated item IDs for loved items")
parser.add_argument('--like',
type=csv,
help="comma-separated item IDs for liked items")
parser.add_argument('--neutral',
type=csv,
help="comma-separated item IDs for neutral items")
parser.add_argument('--dislike',
type=csv,
help="comma-separated item IDs for disliked items")
parser.add_argument('--hate',
type=csv,
help="comma-separated item IDs for hated items")
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
if args.love is not None:
for item in args.love:
tastes[item] = 1.0
if args.like is not None:
for item in args.like:
tastes[item] = 0.75
if args.neutral is not None:
for item in args.neutral:
tastes[item] = 0.5
if args.dislike is not None:
for item in args.dislike:
tastes[item] = 0.25
if args.hate is not None:
# -*- coding: utf8 -*- # # recommend.py # José Devezas ([email protected]) # 2013-06-28 import os import sys import argparse from jld import LatentFactorsModel if __name__ == "__main__": parser = argparse.ArgumentParser( description= 'Recommend new items to an existing user ordered by predicted rating.') parser.add_argument( 'user', help='user identification string, as defined in the training set') parser.add_argument( 'model_path', help= 'HDF5 file with the trained model containing the factorized matrices') args = parser.parse_args() model = LatentFactorsModel(args.model_path) rank = 1 for item_id, rating in model.recommend(args.user, limit=20): print "%d\t%.10f\t%s" % (rank, rating, item_id) rank += 1
description="Discover nearest neighbor in trained model based on qualitative user input.")
parser.add_argument('model_path',
help="HDF5 file with the trained model containing the factorized matrices")
parser.add_argument('--love', type=csv,
help="comma-separated item IDs for loved items")
parser.add_argument('--like', type=csv,
help="comma-separated item IDs for liked items")
parser.add_argument('--neutral', type=csv,
help="comma-separated item IDs for neutral items")
parser.add_argument('--dislike', type=csv,
help="comma-separated item IDs for disliked items")
parser.add_argument('--hate', type=csv,
help="comma-separated item IDs for hated items")
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
if args.love is not None:
for item in args.love:
tastes[item] = 1.0
if args.like is not None:
for item in args.like:
tastes[item] = 0.75
if args.neutral is not None:
for item in args.neutral:
tastes[item] = 0.5
if args.dislike is not None:
for item in args.dislike:
tastes[item] = 0.25
if args.hate is not None:
description="Use qualitative users preferences to recommend new items.")
parser.add_argument('model_path',
help="HDF5 file with the trained model containing the factorized matrices")
parser.add_argument('--love', type=csv,
help="comma-separated item IDs for loved items")
parser.add_argument('--like', type=csv,
help="comma-separated item IDs for liked items")
parser.add_argument('--neutral', type=csv,
help="comma-separated item IDs for neutral items")
parser.add_argument('--dislike', type=csv,
help="comma-separated item IDs for disliked items")
parser.add_argument('--hate', type=csv,
help="comma-separated item IDs for hated items")
args = parser.parse_args()
model = LatentFactorsModel(args.model_path)
tastes = {}
if args.love is not None:
for item in args.love:
tastes[item] = 1.0
if args.like is not None:
for item in args.like:
tastes[item] = 0.75
if args.neutral is not None:
for item in args.neutral:
tastes[item] = 0.5
if args.dislike is not None:
for item in args.dislike:
tastes[item] = 0.25
if args.hate is not None:
'--max-features',
type=int,
help="""the maximum number of features to use in cross-validation
(ignored if sampling size is not defined)""")
parser.add_argument(
'-o',
'--output',
type=str,
help="output CSV filename, to store validation scores (MAE)")
args = parser.parse_args()
if not os.access(args.ratings_path, os.R_OK):
print("'%s' is not readable." % args.ratings_path)
sys.exit(0)
model = LatentFactorsModel()
if args.delimiter is not None:
model.set_training_csv_delimiter(args.delimiter)
if args.rank is not None:
model.set_training_rank(args.rank)
k = 10
if args.folds is not None:
k = args.folds
feature_sampling = None
if args.feature_sampling_interval is not None:
feature_sampling_interval = args.feature_sampling_interval
