class TestReader(unittest.TestCase):
def setUp(self):
self.data_file = './tests/data.txt'
self.reader = Reader()
def test_raise(self):
try:
self.reader.read(self.data_file, fmt='bla bla')
except ValueError:
assert True
def test_read_ui(self):
triplets = self.reader.read(self.data_file, fmt='UI')
self.assertEqual(len(triplets), 30)
self.assertEqual(triplets[0][1], '93')
self.assertEqual(triplets[1][2], 1.0)
triplets = self.reader.read(self.data_file, fmt='UI', id_inline=True)
self.assertEqual(len(triplets), 40)
def test_read_uir(self):
triplet_data = self.reader.read(self.data_file)
self.assertEqual(len(triplet_data), 10)
self.assertEqual(triplet_data[4][2], 3)
self.assertEqual(triplet_data[6][1], '478')
self.assertEqual(triplet_data[8][0], '543')
def test_filter(self):
reader = Reader(bin_threshold=4.0)
self.assertEqual(len(reader.read(self.data_file)), 8)
reader = Reader(min_user_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(min_item_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(user_set=['76'], item_set=['93'])
self.assertEqual(len(reader.read(self.data_file)), 1)
reader = Reader(user_set=['76', '768'])
self.assertEqual(len(reader.read(self.data_file)), 2)
reader = Reader(item_set=['93', '257', '795'])
self.assertEqual(len(reader.read(self.data_file)), 3)
def test_read_text(self):
self.assertEqual(len(read_text(self.data_file, sep=None)), 10)
self.assertEqual(read_text(self.data_file, sep='\t')[1][0], '76')
def load_feedback(variant="closed_loop", reader=None):
"""Load the user-item ratings of one of the Yahoo Music datasets
Parameters
----------
variant: str, optional, default: 'closed_loop'
Specifies which Yahoo Music dataset to load, one of ['closed_loop', 'open_loop'].
reader: `obj:cornac.data.Reader`, optional, default: None
Reader object used to read the data.
Returns
-------
data: array-like
Data in the form of a list of tuples depending on the given data format.
"""
yah = YAHOO_DATASETS.get(variant.upper(), None)
if yah is None:
raise ValueError("variant must be one of {}.".format(
YAHOO_DATASETS.keys()))
fpath = cache(url=yah.url, unzip=yah.unzip, relative_path=yah.path)
reader = Reader() if reader is None else reader
return reader.read(fpath, 'UIR', sep=yah.sep, skip_lines=yah.skip)
def read_data(path):
fmt = validate_format("UIR", ["UIR", "UIRT"]) # HARDCODE UIR
reader = None
reader = Reader() if reader is None else reader
data = reader.read(path)
return data
def test_filter(self):
reader = Reader(bin_threshold=4.0)
self.assertEqual(len(reader.read(self.data_file)), 8)
reader = Reader(min_user_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(min_item_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(user_set=['76'], item_set=['93'])
self.assertEqual(len(reader.read(self.data_file)), 1)
reader = Reader(user_set=['76', '768'])
self.assertEqual(len(reader.read(self.data_file)), 2)
reader = Reader(item_set=['93', '257', '795'])
self.assertEqual(len(reader.read(self.data_file)), 3)
def test_filter(self):
reader = Reader(bin_threshold=4.0)
data = reader.read(self.data_file)
self.assertEqual(len(data), 8)
self.assertListEqual([x[2] for x in data], [1] * len(data))
reader = Reader(min_user_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(min_item_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(user_set=['76'], item_set=['93'])
self.assertEqual(len(reader.read(self.data_file)), 1)
reader = Reader(user_set=['76', '768'])
self.assertEqual(len(reader.read(self.data_file)), 2)
reader = Reader(item_set=['93', '257', '795'])
self.assertEqual(len(reader.read(self.data_file)), 3)
class TestReader(unittest.TestCase):
def setUp(self):
self.data_file = './tests/data.txt'
self.reader = Reader()
def test_raise(self):
try:
self.reader.read(self.data_file, fmt='bla bla')
except ValueError:
assert True
def test_read_ui(self):
triplets = self.reader.read(self.data_file, fmt='UI')
self.assertEqual(len(triplets), 30)
self.assertEqual(triplets[0][1], '93')
self.assertEqual(triplets[1][2], 1.0)
triplets = self.reader.read(self.data_file, fmt='UI', id_inline=True)
self.assertEqual(len(triplets), 40)
def test_read_uir(self):
triplet_data = self.reader.read(self.data_file)
self.assertEqual(len(triplet_data), 10)
self.assertEqual(triplet_data[4][2], 3)
self.assertEqual(triplet_data[6][1], '478')
self.assertEqual(triplet_data[8][0], '543')
def test_read_uirt(self):
data = self.reader.read(self.data_file, fmt='UIRT')
self.assertEqual(len(data), 10)
self.assertEqual(data[4][3], 891656347)
self.assertEqual(data[4][2], 3)
self.assertEqual(data[4][1], '705')
self.assertEqual(data[4][0], '329')
self.assertEqual(data[9][3], 879451804)
def test_read_tup(self):
tup_data = self.reader.read(self.data_file, fmt='UITup')
self.assertEqual(len(tup_data), 10)
self.assertEqual(tup_data[4][2], [('3', ), ('891656347', )])
self.assertEqual(tup_data[6][1], '478')
self.assertEqual(tup_data[8][0], '543')
def test_read_review(self):
review_data = self.reader.read('./tests/review.txt', fmt='UIReview')
self.assertEqual(len(review_data), 5)
self.assertEqual(review_data[0][2], 'Sample text 1')
self.assertEqual(review_data[1][1], '257')
self.assertEqual(review_data[4][0], '329')
def test_filter(self):
reader = Reader(bin_threshold=4.0)
data = reader.read(self.data_file)
self.assertEqual(len(data), 8)
self.assertListEqual([x[2] for x in data], [1] * len(data))
reader = Reader(min_user_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(min_item_freq=2)
self.assertEqual(len(reader.read(self.data_file)), 0)
reader = Reader(user_set=['76'], item_set=['93'])
self.assertEqual(len(reader.read(self.data_file)), 1)
reader = Reader(user_set=['76', '768'])
self.assertEqual(len(reader.read(self.data_file)), 2)
reader = Reader(item_set=['93', '257', '795'])
self.assertEqual(len(reader.read(self.data_file)), 3)
def test_read_text(self):
self.assertEqual(len(read_text(self.data_file, sep=None)), 10)
self.assertEqual(read_text(self.data_file, sep='\t')[1][0], '76')
print("# bpr samples:", args.bpr_samples)
print("# element samples:", args.element_samples)
print("lambda reg =", args.lambda_reg)
print("lambda bpr =", args.lambda_bpr)
print("learning rate =", args.learning_rate)
print("Seed value =", args.seed)
print("VERBOSE =", args.verbose)
return args
args = parse_arguments()
os.makedirs(args.out, exist_ok=True)
reader = Reader()
train_data = reader.read(os.path.join(args.indir, "train.txt"), sep=",")
test_data = reader.read(os.path.join(args.indir, "test.txt"), sep=",")
sentiment = reader.read(os.path.join(args.indir, "sentiment.txt"),
fmt="UITup",
sep=",",
tup_sep=":")
md = SentimentModality(data=sentiment)
eval_method = BaseMethod.from_splits(
train_data=train_data,
test_data=test_data,
sentiment=md,
exclude_unknowns=True,
verbose=args.verbose,
)
mter = cornac.models.MTER(
# -*- coding: utf-8 -*-
"""
Example to train and evaluate a model with given data
@author: Quoc-Tuan Truong <*****@*****.**>
"""
from cornac.data import Reader
from cornac.eval_methods import BaseMethod
from cornac.models import MF
from cornac.metrics import MAE, RMSE
from cornac.utils import cache
# Download MovieLens 100K provided training and test splits
reader = Reader()
train_data = reader.read(
cache(url='http://files.grouplens.org/datasets/movielens/ml-100k/u1.base'))
test_data = reader.read(
cache(url='http://files.grouplens.org/datasets/movielens/ml-100k/u1.test'))
eval_method = BaseMethod.from_splits(train_data=train_data,
test_data=test_data,
exclude_unknowns=False,
verbose=True)
mf = MF(k=10,
max_iter=25,
learning_rate=0.01,
lambda_reg=0.02,
use_bias=True,
early_stop=True,
verbose=True)
from cornac.data import Reader, GraphModality
from cornac.datasets import epinions
from cornac.eval_methods import RatioSplit
import numpy as np
dataset = "yelp_ON"
if dataset == "ciao":
data_path = "/cluster/home/it_stu110/proj/Rec_baseline/data_process/ciao/ciao_simple.txt"
trust_path = "/cluster/home/it_stu110/proj/Rec_baseline/data_process/ciao/ciao_trust.txt"
elif dataset == "yelp_ON":
data_path = "/cluster/home/it_stu110/proj/Rec_baseline/data_process/yelp/yelp_ON_simple.txt"
trust_path = '/cluster/home/it_stu110/proj/Rec_baseline/data_process/yelp/yelp_ON_trust.txt'
# SBPR integrates user social network into Bayesian Personalized Ranking.
# The necessary data can be loaded as follows
reader = Reader()
trust = reader.read(trust_path, sep=' ')
feedback = reader.read(data_path, sep=' ')
# Instantiate a GraphModality, it makes it convenient to work with graph (network) auxiliary information
# For more details, please refer to the tutorial on how to work with auxiliary data
user_graph_modality = GraphModality(data=trust)
# Define an evaluation method to split feedback into train and test sets
ratio_split = RatioSplit(
data=feedback,
test_size=0.1,
rating_threshold=0.5,
exclude_unknowns=True,
verbose=True,
user_graph=user_graph_modality,
)
