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_score_against_testfm(self):
"""
[recommendation.models.TensorCoFi] Test popularity scores with test.fm benchmark
"""
evaluator = Evaluator()
training, testing = testfm.split.holdoutByRandom(self.df, 0.9)
items = training.item.unique()
tc = Popularity(len(items))
ptc = TFMPopularity()
tc.fit(training)
ptc.fit(training)
tc_score = evaluator.evaluate_model(tc, testing, all_items=items)[0]
ptc_score = evaluator.evaluate_model(ptc, testing, all_items=items)[0]
assert abs(tc_score-ptc_score) < .1, \
"Popularity score is not close enough to testfm benchmark (%.3f != %.3f)" % (tc_score, ptc_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)
# specific environments. #
# Thank you. #
#########################################
# Tell me what models we want to evaluate
models = [
RandomModel(),
PopularityOkapi(hadoop_source="/data/b.ajf/hadoop1_env.sh",
host="igraph-01",
okapi_jar_dir="okapi/jar/",
#host='54.72.18.118', user='******',
#okapi_jar_dir='/Users/linas/devel/okapi/target/',
#okapi_jar_base_name='okapi-0.3.2-SNAPSHOT-jar-with-dependencies.jar',
#public_key_path='/Users/linas/.ssh/hack-okapi.pem'
),
Popularity(normalize=False),
BPROkapi(hadoop_source="/data/b.ajf/hadoop1_env.sh",
host="igraph-01",
okapi_jar_dir="okapi/jar/",
#host='54.72.18.118', user='******',
#okapi_jar_dir='/Users/linas/devel/okapi/target/',
# #okapi_jar_base_name='okapi-0.3.2-SNAPSHOT-jar-with-dependencies.jar',
#public_key_path='/Users/linas/.ssh/hack-okapi.pem'
)
]
# Setup the environment
evaluator = Evaluator()
for m in models:
m.fit(df)
