def test_repeating_spliced_data(self):
"""
Test repeating data on the same model by splitting a dataFrame
"""
splitter = RandomSplitter()
for i in range(10):
training, testing = splitter.split(self.df, 0.20)
self.popularity.fit(training)
for _, row in testing.iterrows():
score = self.popularity.getScore(row["user"], row["item"])
assert isinstance(score, float), "The result of the score is not a float"
def test_bpr(self):
"""
Test the bpr okapi algorithm
"""
splitter = RandomSplitter()
training, testing = splitter.split(self.df, 0.20)
bpr = BPR()
bpr.fit(training)
self.bpr.fit(training)
for _, row in testing.iterrows():
okapi_score = self.bpr.getScore(row["user"], row["item"])
python_score = bpr.getScore(row["user"], row["item"])
assert (
okapi_score == python_score
), "Okapi bpr(%f) don't give the same score as his python implementation(%f)" % (okapi_score, python_score)
def test_popularity(self):
"""
Test the popularity okapi algorithm
"""
splitter = RandomSplitter()
training, testing = splitter.split(self.df, 0.20)
pop = Popularity(normalize=False)
pop.fit(training)
self.popularity.fit(training)
for _, row in testing.iterrows():
assert row["user"] in training["user"]
python_score = pop.getScore(row["user"], row["item"])
okapi_score = self.popularity.getScore(row["user"], row["item"])
assert okapi_score == python_score, \
"Okapi popularity(%f) don't give the same score as his python implementation(%f)" % (okapi_score,
python_score)
def test_popularity(self):
"""
Test the popularity okapi algorithm
"""
splitter = RandomSplitter()
training, testing = splitter.split(self.df, 0.20)
pop = Popularity(normalize=False)
pop.fit(training)
self.popularity.fit(training)
for _, row in testing.iterrows():
assert row["user"] in training["user"]
python_score = pop.getScore(row["user"], row["item"])
okapi_score = self.popularity.getScore(row["user"], row["item"])
assert okapi_score == python_score, \
"Okapi popularity(%f) don't give the same score as his python implementation(%f)" % (okapi_score,
python_score)
class split(object):
holdout = HoldoutSplitter()
holdoutByRandomSlow = RandomHoldoutSplitter()
holdoutByUser = HoldoutSplitterByUser()
holdoutByRandom = RandomSplitter()
