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)
