def evaluate_cf_recommender():
min_number_of_ratings = 5
min_overlap = 5
min_sim = 0.1
k = 10
min_rank = 5
timestr = time.strftime("%Y%m%d-%H%M%S")
file_name = '{}-cf.csv'.format(timestr)
with open(file_name, 'a', 1) as logfile:
logfile.write(
"ar, map, mae, min_overlap, min_sim, K, min_num_of_ratings, min_rank\n"
)
for k in np.arange(0, 20, 2):
min_rank = min_number_of_ratings / 2
recommender = NeighborhoodBasedRecs()
er = EvaluationRunner(
0, ItemSimilarityMatrixBuilder(min_overlap, min_sim=min_sim),
recommender, k)
result = er.calculate(min_number_of_ratings,
min_rank,
number_test_users=-1)
map = result['map']
mae = result['mae']
ar = result['ar']
logfile.write("{}, {}, {}, {}, {}, {}, {}, {}\n".format(
ar, map, mae, min_overlap, min_sim, k, min_number_of_ratings,
min_rank))
logfile.flush()
def train(self, ratings=None, train_feature_recs=False):
if train_feature_recs:
ItemSimilarityMatrixBuilder().build(ratings)
LdaModel.build()
regr = linear_model.LinearRegression(fit_intercept=True,
n_jobs=-1,
normalize=True)
regr.fit(self.train_data[['cb1', 'cb2', 'cf1', 'cf2']],
self.train_data['rating'])
self.logger.info(regr.coef_)
result = {
'cb1': regr.coef_[0],
'cb2': regr.coef_[1],
'cf1': regr.coef_[2],
'cf2': regr.coef_[3],
'intercept': regr.intercept_
}
self.logger.debug(result)
self.logger.debug(self.train_data.iloc[100])
ensure_dir(self.save_path)
with open(self.save_path + 'fwls_parameters.data', 'wb') as ub_file:
pickle.dump(result, ub_file)
return result
def test_split_data(self):
ratings = pd.DataFrame(
[
[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
],
columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
er = EvaluationRunner(5, ItemSimilarityMatrixBuilder(1, min_sim=0.0),
NeighborhoodBasedRecs())
test, train = er.split_data(2, ratings, [1, 2], [3])
self.assertTrue(test is not None)
self.assertTrue(test.shape[0], 4)
self.assertEqual(train.shape[0], 16)
def test_simple_similarity(self):
builder = ItemSimilarityMatrixBuilder(0)
no_items = len(set(self.ratings['movie_id']))
cor = builder.build(ratings=self.ratings, save=False)
self.assertIsNotNone(cor)
self.assertEqual(
cor.shape[0], no_items,
"Expected correlations matrix to have a row for each item")
self.assertEqual(
cor.shape[1], no_items,
"Expected correlations matrix to have a column for each item")
self.assertEqual(
cor[WONDER_WOMAN][AVENGERS], -1,
"Expected Wolverine and Star Wars to have similarity 0.5")
self.assertEqual(
cor[AVENGERS][AVENGERS], 1,
"Expected items to be similar to themselves similarity 1")
self.assertEqual(
cor[STAR_WARS][STAR_WARS], 1,
"Expected items to be similar to themselves similarity 1")
self.assertEqual(
cor[WONDER_WOMAN][WONDER_WOMAN], 1,
"Expected items to be similar to themselves similarity 1")
self.assertEqual(
cor[WOLVERINE][WOLVERINE], 1,
"Expected items to be similar to themselves similarity 1")
def test_overlap(self):
builder = ItemSimilarityMatrixBuilder(1, -1)
cor, movies = builder.build(ratings=self.ratings, save=False)
self.assertIsNotNone(cor)
self.assertEqual(cor.count_nonzero(), 9)
def test_min_ratings(self):
builder = ItemSimilarityMatrixBuilder(2)
cor, movies = builder.build(ratings=self.ratings, save=False)
df = pd.DataFrame(cor.toarray(), columns=movies.values(), index=movies.values())
self.assertEqual(cor.shape[0], 4, "Expected correlations matrix to have a row for each item")
self.assertEqual(cor.shape[1], 4, "Expected correlations matrix to have a column for each item")
self.assertAlmostEqual(df[WONDER_WOMAN][AVENGERS], 0.71066905451870177)
self.assertAlmostEqual(df[AVENGERS][AVENGERS], 1)
def test_save_similarities(self):
builder = ItemSimilarityMatrixBuilder(0)
cor = builder.build(ratings=self.ratings)
self.assertIsNotNone(cor)
similarities = Similarity.objects.all()
av_log = similarities[0]
self.assertEqual(Similarity.objects.count(), 4)
self.assertEqual(av_log.source, AVENGERS)
self.assertEqual(av_log.target, WOLVERINE)
self.assertEqual(av_log.similarity, 0.5)
def test_save_similarities(self):
builder = ItemSimilarityMatrixBuilder(0, 0.1)
cor = builder.build(ratings=self.ratings)
self.assertIsNotNone(cor)
similarities = Similarity.objects.all()
av_log = similarities[0]
self.assertEqual(Similarity.objects.count(), 2)
self.assertEqual(av_log.source, WONDER_WOMAN)
self.assertEqual(av_log.target, AVENGERS)
self.assertAlmostEqual(float(av_log.similarity), 0.71066905451870177)
def test_simple_similarity(self):
builder = ItemSimilarityMatrixBuilder(0)
no_items = len(set(self.ratings['movie_id']))
cor, movies = builder.build(ratings=self.ratings, save=False)
df = pd.DataFrame(cor.toarray(), columns=movies.values(), index=movies.values())
self.assertIsNotNone(df)
self.assertEqual(df.shape[0], no_items, "Expected correlations matrix to have a row for each item")
self.assertEqual(df.shape[1], no_items, "Expected correlations matrix to have a column for each item")
self.assertAlmostEqual(df[WONDER_WOMAN][AVENGERS], 0.71066905451870177)
self.assertAlmostEqual(df[AVENGERS][AVENGERS], 1)
self.assertAlmostEqual(df[STAR_WARS][STAR_WARS], 1)
self.assertAlmostEqual(df[WONDER_WOMAN][WONDER_WOMAN], 1.0)
self.assertAlmostEqual(df[WOLVERINE][WOLVERINE], 1)
def test_min_ratings(self):
builder = ItemSimilarityMatrixBuilder(2)
cor = builder.build(ratings=self.ratings, save=False)
self.assertIsNotNone(cor)
self.assertEqual(
cor.shape[0], 2,
"Expected correlations matrix to have a row for each item")
self.assertEqual(
cor.shape[1], 2,
"Expected correlations matrix to have a column for each item")
self.assertEqual(
cor[WONDER_WOMAN][AVENGERS], -1,
"Expected Wolverine and Star Wars to have similarity 0.5")
self.assertEqual(
cor[AVENGERS][AVENGERS], 1,
"Expected items to be similar to themselves similarity 1")
def evaluate_cf_recommender():
min_number_of_ratings = 20
min_overlap = 5
min_sim = 0.1
K = 20
min_rank = 5
timestr = time.strftime("%Y%m%d-%H%M%S")
file_name = '{}-min_overlap_item_similarity.csv'.format(timestr)
with open(file_name, 'a', 1) as logfile:
logfile.write(
"rak, pak, mae, min_overlap, min_sim, K, min_num_of_ratings, min_rank, user_coverage, "
"movie_coverage\n")
builder = ItemSimilarityMatrixBuilder(min_overlap, min_sim=min_sim)
for min_overlap in np.arange(0, 20, 2):
min_rank = min_number_of_ratings / 2
recommender = NeighborhoodBasedRecs()
er = EvaluationRunner(0, builder, recommender, K)
# Run the baseline recommender:
# er = EvaluationRunner(3, None, PopularityBasedRecs(), K)
result = er.calculate(min_number_of_ratings,
min_rank,
number_test_users=-1)
user_coverage, movie_coverage = RecommenderCoverage(
recommender).calculate_coverage()
pak = result['pak']
mae = result['mae']
rak = result['rak']
logfile.write("{}, {}, {}, {}, {}, {}, {}, {}, {}, {}\n".format(
rak, pak, mae, min_overlap, min_sim, K, min_number_of_ratings,
min_rank, user_coverage, movie_coverage))
logfile.flush()
if __name__ == '__main__':
min_number_of_ratings = 30
min_overlap = 25
min_sim = 0
K = 25 #redo
min_rank = 5
timestr = time.strftime("%Y%m%d-%H%M%S")
file_name = '{}-min_number_of_ratings_training.csv'.format(timestr)
with open(file_name, 'a', 1) as logfile:
logfile.write(
"pak, mae, min_overlap, min_sim, K, min_num_of_ratings, min_rank\n"
)
for min_number_of_ratings in np.arange(5, 30, 10):
min_rank = min_number_of_ratings / 2
min_overlap = min_number_of_ratings - min_rank
er = EvaluationRunner(
3, ItemSimilarityMatrixBuilder(min_overlap, min_sim=min_sim),
NeighborhoodBasedRecs(), K)
result = er.calculate(min_number_of_ratings,
min_rank,
number_test_users=1000)
pak = result['pak']
mae = result['mae']
logfile.write("{}, {}, {}, {}, {}, {}, {} \n".format(
pak, mae, min_overlap, min_sim, K, min_number_of_ratings,
min_rank, datetime.now()))
len(self.all_users)))
for user in self.all_users:
user_id = str(user['user_id'])
recset = self.cf.recommend_items(user_id)
if recset:
self.users_with_recs.append(user)
for rec in recset:
self.items_in_rec[rec[0]] += 1
print('found recs for {}'.format(user_id))
print('writing cf coverage to file.')
json.dump(self.items_in_rec, open('cf_coverage.json', 'w'))
no_movies = Movie.objects.all().count()
no_movies_in_rec = len(self.items_in_rec.items())
print("{} {} {}".format(no_movies, no_movies_in_rec,
float(no_movies / no_movies_in_rec)))
return no_movies_in_rec / no_movies
if __name__ == '__main__':
# print("Calculating coverage...")
# CFCoverage().calculate_coverage()
print("Calculating Precision at K")
pak = PrecissionAtK(5, NeighborhoodBasedRecs(),
ItemSimilarityMatrixBuilder())
pak.calculate_old()
def test(self):
er = EvaluationRunner(5, ItemSimilarityMatrixBuilder(1, min_sim=0.0), NeighborhoodBasedRecs())
STAR_WARS = 'star wars'
WONDER_WOMAN = 'wonder woman'
AVENGERS = 'avengers'
WOLVERINE = 'logan'
PIRATES_OF = 'pirates of the caribbien'
HARRY = 'harry potter I'
CAPTAIN_AMERICA = 'captain america'
ALIEN = 'alien'
DR_STRANGELOVE = 'doctor strangelove'
JACQUES = 'jacques'
ratings = pd.DataFrame(
[[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
[4, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[4, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[4, AVENGERS, 9, '2015-10-12 23:20:27+00:00'],
[4, PIRATES_OF, 5, '2013-10-12 23:20:27+00:00'],
[4, HARRY, 6, '2014-10-12 23:20:27+00:00'],
[4, ALIEN, 8, '2015-10-12 23:20:27+00:00'],
[4, DR_STRANGELOVE, 9, '2015-10-12 23:20:27+00:00'],
[5, STAR_WARS, 6, '2013-10-12 23:20:27+00:00'],
[5, AVENGERS, 6, '2014-10-12 23:20:27+00:00'],
[5, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[5, PIRATES_OF, 2, '2016-10-12 23:20:27+00:00'],
[5, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[5, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[5, ALIEN, 4, '2016-10-12 23:20:27+00:00'],
[5, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[5, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[6, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[6, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[6, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[6, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[6, PIRATES_OF, 6, '2016-10-12 23:20:27+00:00'],
[6, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[6, JACQUES, 8, '2016-10-12 23:20:27+00:00'],
[7, AVENGERS, 10, '2014-10-12 23:20:27+00:00'],
[7, PIRATES_OF, 3, '2016-10-12 23:20:27+00:00'],
[7, HARRY, 1, '2016-10-12 23:20:27+00:00'],
[7, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[7, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[8, STAR_WARS, 9, '2013-10-12 23:20:27+00:00'],
[8, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[8, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[8, WOLVERINE, 7, '2015-10-12 23:20:27+00:00'],
[8, PIRATES_OF, 8, '2016-10-12 23:20:27+00:00'],
[8, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[8, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[8, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[8, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[9, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[9, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[9, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[9, PIRATES_OF, 7, '2016-10-12 23:20:27+00:00'],
[9, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[9, CAPTAIN_AMERICA, 10, '2016-10-12 23:20:27+00:00'],
[9, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[9, JACQUES, 7, '2016-10-12 23:20:27+00:00'],
[10, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[10, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[10, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[10, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
], columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
result = er.calculate_using_ratings(ratings, min_number_of_ratings=4, min_rank=5)
#figure out what to do with result ;)
print(result)
def test(self):
er = EvaluationRunner(5, ItemSimilarityMatrixBuilder(1, min_sim=0.0),
NeighborhoodBasedRecs())
ratings = pd.DataFrame(
[
[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
[4, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[4, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[4, AVENGERS, 9, '2015-10-12 23:20:27+00:00'],
[4, PIRATES_OF, 5, '2013-10-12 23:20:27+00:00'],
[4, HARRY, 6, '2014-10-12 23:20:27+00:00'],
[4, ALIEN, 8, '2015-10-12 23:20:27+00:00'],
[4, DR_STRANGELOVE, 9, '2015-10-12 23:20:27+00:00'],
[5, STAR_WARS, 6, '2013-10-12 23:20:27+00:00'],
[5, AVENGERS, 6, '2014-10-12 23:20:27+00:00'],
[5, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[5, PIRATES_OF, 2, '2016-10-12 23:20:27+00:00'],
[5, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[5, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[5, ALIEN, 4, '2016-10-12 23:20:27+00:00'],
[5, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[5, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[6, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[6, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[6, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[6, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[6, PIRATES_OF, 6, '2016-10-12 23:20:27+00:00'],
[6, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[6, JACQUES, 8, '2016-10-12 23:20:27+00:00'],
[7, AVENGERS, 10, '2014-10-12 23:20:27+00:00'],
[7, PIRATES_OF, 3, '2016-10-12 23:20:27+00:00'],
[7, HARRY, 1, '2016-10-12 23:20:27+00:00'],
[7, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[7, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[8, STAR_WARS, 9, '2013-10-12 23:20:27+00:00'],
[8, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[8, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[8, WOLVERINE, 7, '2015-10-12 23:20:27+00:00'],
[8, PIRATES_OF, 8, '2016-10-12 23:20:27+00:00'],
[8, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[8, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[8, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[8, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[9, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[9, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[9, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[9, PIRATES_OF, 7, '2016-10-12 23:20:27+00:00'],
[9, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[9, CAPTAIN_AMERICA, 10, '2016-10-12 23:20:27+00:00'],
[9, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[9, JACQUES, 7, '2016-10-12 23:20:27+00:00'],
[10, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[10, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[10, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[10, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
],
columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
result = er.calculate_using_ratings(ratings,
min_number_of_ratings=4,
min_rank=5)
#figure out what to do with result ;)
self.assertLess(result['mae'], decimal.Decimal(1.7))
self.assertLess(result['pak'], decimal.Decimal(0.7))
self.assertLess(result['rak'], decimal.Decimal(0.7))
print(result)
def setUp(self):
self.ratings = pd.DataFrame(
[
[1, STAR_WARS, 9, '2013-10-12 23:21:27+00:00'],
[1, WONDER_WOMAN, 10, '2014-10-12 23:22:27+00:00'],
[1, AVENGERS, 10, '2015-11-12 23:20:27+00:00'],
[1, WOLVERINE, 8, '2015-08-12 23:20:27+00:00'],
[1, PIRATES_OF, 10, '2015-10-12 22:20:27+00:00'],
[1, HARRY, 10, '2015-10-12 23:21:27+00:00'],
[1, CAPTAIN_AMERICA, 10, '2014-10-12 23:20:27+00:00'],
[1, ALIEN, 6, '2015-10-12 23:22:27+00:00'],
[1, JACQUES, 6, '2015-10-12 11:20:27+00:00'],
[2, STAR_WARS, 10, '2013-10-12 23:20:27+00:00'],
[2, WONDER_WOMAN, 10, '2014-10-12 23:20:27+00:00'],
[2, AVENGERS, 9, '2016-10-12 23:20:27+00:00'],
[2, PIRATES_OF, 6, '2010-10-12 23:20:27+00:00'],
[2, CAPTAIN_AMERICA, 10, '2005-10-12 23:20:27+00:00'],
[2, DR_STRANGELOVE, 10, '2015-01-12 23:20:27+00:00'],
[3, STAR_WARS, 9, '2013-10-12 20:20:27+00:00'],
[3, AVENGERS, 10, '2015-10-12 10:20:27+00:00'],
[3, PIRATES_OF, 9, '2013-03-12 23:20:27+00:00'],
[3, HARRY, 8, '2016-10-13 23:20:27+00:00'],
[3, DR_STRANGELOVE, 10, '2016-09-12 23:20:27+00:00'],
[4, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[4, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[4, AVENGERS, 9, '2015-10-12 23:20:27+00:00'],
[4, PIRATES_OF, 5, '2013-10-12 23:20:27+00:00'],
[4, HARRY, 6, '2014-10-12 23:20:27+00:00'],
[4, ALIEN, 8, '2015-10-12 23:20:27+00:00'],
[4, DR_STRANGELOVE, 9, '2015-10-12 23:20:27+00:00'],
[5, STAR_WARS, 6, '2013-10-12 23:20:27+00:00'],
[5, AVENGERS, 6, '2014-10-12 23:20:27+00:00'],
[5, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[5, PIRATES_OF, 2, '2016-10-12 23:20:27+00:00'],
[5, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[5, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[5, ALIEN, 4, '2016-10-12 23:20:27+00:00'],
[5, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[5, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[6, STAR_WARS, 8, '2013-10-12 23:20:27+00:00'],
[6, WONDER_WOMAN, 8, '2014-10-12 23:20:27+00:00'],
[6, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[6, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[6, PIRATES_OF, 6, '2016-10-12 23:20:27+00:00'],
[6, HARRY, 10, '2016-10-12 23:20:27+00:00'],
[6, JACQUES, 8, '2016-10-12 23:20:27+00:00'],
[7, AVENGERS, 10, '2014-10-12 23:20:27+00:00'],
[7, PIRATES_OF, 3, '2016-10-12 23:20:27+00:00'],
[7, HARRY, 1, '2016-10-12 23:20:27+00:00'],
[7, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[7, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[8, STAR_WARS, 9, '2013-10-12 23:20:27+00:00'],
[8, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[8, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[8, WOLVERINE, 7, '2015-10-12 23:20:27+00:00'],
[8, PIRATES_OF, 8, '2016-10-12 23:20:27+00:00'],
[8, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[8, ALIEN, 8, '2016-10-12 23:20:27+00:00'],
[8, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
[8, JACQUES, 10, '2016-10-12 23:20:27+00:00'],
[9, WONDER_WOMAN, 7, '2014-10-12 23:20:27+00:00'],
[9, AVENGERS, 8, '2014-10-12 23:20:27+00:00'],
[9, WOLVERINE, 8, '2015-10-12 23:20:27+00:00'],
[9, PIRATES_OF, 7, '2016-10-12 23:20:27+00:00'],
[9, HARRY, 8, '2016-10-12 23:20:27+00:00'],
[9, CAPTAIN_AMERICA, 10, '2016-10-12 23:20:27+00:00'],
[9, DR_STRANGELOVE, 10, '2016-10-12 23:20:27+00:00'],
[9, JACQUES, 7, '2016-10-12 23:20:27+00:00'],
[10, AVENGERS, 7, '2014-10-12 23:20:27+00:00'],
[10, ALIEN, 10, '2016-10-12 23:20:27+00:00'],
[10, CAPTAIN_AMERICA, 6, '2016-10-12 23:20:27+00:00'],
[10, DR_STRANGELOVE, 8, '2016-10-12 23:20:27+00:00'],
],
columns=['user_id', 'movie_id', 'rating', 'rating_timestamp'])
ItemSimilarityMatrixBuilder(0, min_sim=0).build(self.ratings,
save=True)
) as rank
from analytics_rating as rating1
where rank < 3"""
columns = ['user_id', 'movie_id', 'rating', 'type']
rating_data = data_helper.get_data_frame(sql, columns)
print('found {} ratings'.format(rating_data.count()))
return rating_data
if __name__ == '__main__':
TEST = False
if TEST:
er = EvaluationRunner(5, ItemSimilarityMatrixBuilder(2),
NeighborhoodBasedRecs())
ratings = pd.DataFrame(
[
[1, '11', 5, '2013-10-12 23:20:27+00:00'],
[1, '12', 3, '2014-10-12 23:20:27+00:00'],
[1, '14', 2, '2015-10-12 23:20:27+00:00'],
[2, '11', 4, '2013-10-12 23:20:27+00:00'],
[2, '12', 3, '2014-10-12 23:20:27+00:00'],
[2, '13', 4, '2015-10-12 23:20:27+00:00'],
[3, '11', 5, '2013-10-12 23:20:27+00:00'],
[3, '12', 2, '2014-10-12 23:20:27+00:00'],
[3, '13', 5, '2015-10-12 23:20:27+00:00'],
[3, '14', 2, '2016-10-12 23:20:27+00:00'],
[4, '11', 3, '2013-10-12 23:20:27+00:00'],
[4, '12', 5, '2014-10-12 23:20:27+00:00'],