def test_explain(self):
counts = csr_matrix(
[
[1, 1, 0, 1, 0, 0],
[0, 1, 1, 1, 0, 0],
[1, 4, 1, 0, 7, 0],
[1, 1, 0, 0, 0, 0],
[9, 0, 4, 1, 0, 1],
[0, 1, 0, 0, 0, 1],
[0, 0, 2, 0, 1, 1],
],
dtype=np.float64,
)
user_items = counts * 2
item_users = user_items.T
model = AlternatingLeastSquares(
factors=4,
regularization=20,
use_native=False,
use_cg=False,
use_gpu=False,
iterations=100,
random_state=23,
)
model.fit(user_items, show_progress=False)
userid = 0
# Assert recommendation is the the same if we recompute user vectors
recs = model.recommend(userid, item_users, N=10)
recalculated_recs = model.recommend(userid, item_users, N=10, recalculate_user=True)
for (item1, score1), (item2, score2) in zip(recs, recalculated_recs):
self.assertEqual(item1, item2)
self.assertAlmostEqual(score1, score2, 4)
# Assert explanation makes sense
top_rec, score = recalculated_recs[0]
score_explained, contributions, W = model.explain(userid, item_users, itemid=top_rec)
scores = [s for _, s in contributions]
items = [i for i, _ in contributions]
self.assertAlmostEqual(score, score_explained, 4)
self.assertAlmostEqual(score, sum(scores), 4)
self.assertEqual(scores, sorted(scores, reverse=True), "Scores not in order")
self.assertEqual([0, 2, 3, 4], sorted(items), "Items not seen by user")
# Assert explanation with precomputed user weights is correct
top_score_explained, top_contributions, W = model.explain(
userid, item_users, itemid=top_rec, user_weights=W, N=2
)
top_scores = [s for _, s in top_contributions]
top_items = [i for i, _ in top_contributions]
self.assertEqual(2, len(top_contributions))
self.assertAlmostEqual(score, top_score_explained, 4)
self.assertEqual(scores[:2], top_scores)
self.assertEqual(items[:2], top_items)
def test_explain(self):
counts = csr_matrix([[1, 1, 0, 1, 0, 0],
[0, 1, 1, 1, 0, 0],
[1, 4, 1, 0, 7, 0],
[1, 1, 0, 0, 0, 0],
[9, 0, 4, 1, 0, 1],
[0, 1, 0, 0, 0, 1],
[0, 0, 2, 0, 1, 1]], dtype=np.float64)
user_items = counts * 2
item_users = user_items.T
model = AlternatingLeastSquares(factors=4,
regularization=20,
use_native=False,
use_cg=False,
iterations=100)
np.random.seed(23)
model.fit(user_items, show_progress=False)
userid = 0
# Assert recommendation is the the same if we recompute user vectors
recs = model.recommend(userid, item_users, N=10)
recalculated_recs = model.recommend(userid, item_users, N=10, recalculate_user=True)
for (item1, score1), (item2, score2) in zip(recs, recalculated_recs):
self.assertEqual(item1, item2)
self.assertAlmostEqual(score1, score2, 4)
# Assert explanation makes sense
top_rec, score = recalculated_recs[0]
score_explained, contributions, W = model.explain(userid, item_users, itemid=top_rec)
scores = [s for _, s in contributions]
items = [i for i, _ in contributions]
self.assertAlmostEqual(score, score_explained, 4)
self.assertAlmostEqual(score, sum(scores), 4)
self.assertEqual(scores, sorted(scores, reverse=True), "Scores not in order")
self.assertEqual([0, 2, 3, 4], sorted(items), "Items not seen by user")
# Assert explanation with precomputed user weights is correct
top_score_explained, top_contributions, W = model.explain(
userid, item_users, itemid=top_rec, user_weights=W, N=2)
top_scores = [s for _, s in top_contributions]
top_items = [i for i, _ in top_contributions]
self.assertEqual(2, len(top_contributions))
self.assertAlmostEqual(score, top_score_explained, 4)
self.assertEqual(scores[:2], top_scores)
self.assertEqual(items[:2], top_items)
class Recommender:
def __init__(self, factors=50):
self.model = AlternatingLeastSquares(factors=factors,
regularization=0.01,
dtype=np.float64,
iterations=50)
def train(self, data):
userids = data.userid.astype("category")
itemids = data.itemid.astype("category")
matrix = coo_matrix((data.confidence.astype('float64'),
(itemids.cat.codes.copy(),
userids.cat.codes.copy())))
self.model.fit(matrix)
self.t_matrix = matrix.T.tocsr()
self.userid_to_code = dict([(category, code)
for code, category in enumerate(userids.cat.categories)])
self.itemid_to_code = dict([(category, code)
for code, category in enumerate(itemids.cat.categories)])
self.usercode_to_id = dict([(code, category)
for code, category in enumerate(userids.cat.categories)])
self.itemcode_to_id = dict([(code, category)
for code, category in enumerate(itemids.cat.categories)])
def similar_items(self, itemid, N=10):
item_code = self.itemid_to_code[itemid]
similar_codes = self.model.similar_items(item_code, N)
similar_ids = [(self.itemcode_to_id[code], s)
for code, s in similar_codes]
return pd.DataFrame(similar_ids, columns=["itemid", "similarity"])
def recommendations(self, userid, N=10):
user_code = self.userid_to_code[userid]
user_item_codes = self.model.recommend(user_code, self.t_matrix, N)
user_item_ids = [(self.itemcode_to_id[code], c)
for code, c in user_item_codes]
return pd.DataFrame(user_item_ids, columns=["itemid", "confidence"])
def explain(self, userid, itemid):
user_code = self.userid_to_code[userid]
item_code = self.itemid_to_code[itemid]
return self.model.explain(user_code, self.t_matrix, item_code)
def confidence(self, userid, itemid):
item_code = self.itemid_to_code[itemid]
user_code = self.userid_to_code[userid]
item_factor = self.model.item_factors[item_code]
user_factor = self.model.user_factors[user_code]
return item_factor.dot(user_factor)
def user_factors(self):
factors = pd.DataFrame(self.model.user_factors).add_prefix("f")
ids = factors.index.map(lambda code: self.usercode_to_id[code])
factors.insert(0, "userid", ids)
return factors
def item_factors(self):
factors = pd.DataFrame(self.model.item_factors).add_prefix("f")
ids = factors.index.map(lambda code: self.itemcode_to_id[code])
factors.insert(0, "itemid", ids)
return factors
def items_recommendations(self, itemids, N=10):
user_code = 0
item_codes = [self.itemid_to_code[id] for id in itemids]
data = [1 for _ in item_codes]
rows = [0 for _ in item_codes]
shape = (1, self.model.item_factors.shape[0])
user_items = coo_matrix(
(data, (rows, item_codes)), shape=shape).tocsr()
user_item_codes = self.model.recommend(
user_code, user_items, N, recalculate_user=True)
user_item_ids = [(self.itemcode_to_id[code], c)
for code, c in user_item_codes]
return pd.DataFrame(user_item_ids, columns=["itemid", "confidence"])