def recommend_with_scores(self, test_device_events, tips):
last_session_events = _get_last_session(test_device_events)
event_to_score = {}
for (group_id, event_id) in self.event_types:
event_to_score[(group_id, event_id)] = 0
for (group_id2, event_id2) in last_session_events.keys():
if (group_id2, event_id2) in self.cp_matrix[(group_id,
event_id)].keys():
event_to_score[(group_id, event_id)] += self.cp_matrix[(
group_id, event_id)][(group_id2, event_id2)]
if (group_id2, event_id2) in self.dp_matrix.keys():
event_to_score[(group_id, event_id)] += self.dp_matrix[(
group_id2, event_id2)][(group_id, event_id)]
sorted_by_score_events = sorted(event_to_score.items(),
key=operator.itemgetter(1),
reverse=True)
tips_to_recommend = {}
for top_event in sorted_by_score_events:
event = top_event[0]
score = top_event[1]
if (event not in test_device_events.keys()) \
and _is_intersection(tips, event_to_tips(event[0], event[1])) > 0:
for tip in event_to_tips(event[0], event[1]):
if tip in tips:
tips_to_recommend[tip] = score
if self.is_logging:
logging.info("RecommenderCo+Dis:recommend: recommendation made.")
return tips_to_recommend
def _generate_recommendation_list(self, recommendations, test_device_events, tips):
recommendation_map = {}
for event, score in recommendations:
if event_to_tips(self.event_types[event][0], self.event_types[event][1]) and \
_is_intersection(tips, event_to_tips(self.event_types[event][0], self.event_types[event][1])) > 0 \
and self.event_types[event] not in test_device_events:
for tip in event_to_tips(self.event_types[event][0], self.event_types[event][1]):
if tip in tips:
recommendation_map[tip] = max(0, score)
return recommendation_map
def compute_map_k(user_to_done, user_to_recommendation, K):
user_cnt = 0
map_k = 0
for device_id in user_to_recommendation.keys():
user_cnt += 1
done_tips = user_to_done[device_id]
recommended_tips = user_to_recommendation[device_id]
ap_k = 0
for j in range(min(len(recommended_tips), K)):
if _is_intersection(done_tips, [recommended_tips[j]]):
p_k = 0
for k in range(j + 1):
if _is_intersection(done_tips, [recommended_tips[k]]):
p_k += 1
p_k = p_k * 1. / (j + 1)
ap_k += p_k
ap_k = ap_k * 1. / K
map_k += ap_k
map_k = map_k * 1. / user_cnt * 10
return map_k
def compute_accuracy_first(user_to_done, user_to_recommendation):
prec = 0
user_cnt = 0
for device_id in user_to_recommendation.keys():
user_cnt += 1
done_tips = user_to_done[device_id]
recommended_tips = user_to_recommendation[device_id]
if _is_intersection(done_tips, [recommended_tips[0]]):
prec += 1
prec = prec * 1. / user_cnt
return prec
def _get_not_done_events_with_probability(self, test_device_events, tips):
not_done_event_with_prob = []
all_not_done_top_sum = 0
for top_event in self.top_events:
event = top_event[0]
probability = top_event[1]
if (event not in test_device_events.keys()) \
and _is_intersection(tips, event_to_tips(event[0], event[1])) > 0:
not_done_event_with_prob.append(top_event)
all_not_done_top_sum += probability
return not_done_event_with_prob, all_not_done_top_sum
def compute_mrr_k(user_to_done, user_to_recommendation, K):
mrr_k = 0
user_cnt = 0
for device_id in user_to_recommendation.keys():
user_cnt += 1
done_tips = user_to_done[device_id]
recommended_tips = user_to_recommendation[device_id]
rr_k = 0
for j in range(min(len(recommended_tips), K)):
if _is_intersection(done_tips, [recommended_tips[j]]):
rr_k = 1. / (j + 1)
break
mrr_k += rr_k
mrr_k = mrr_k * 1. / user_cnt
return mrr_k
def compute_ndcg_k(user_to_done, user_to_recommendation, K):
ndcg_k = 0
user_cnt = 0
for device_id in user_to_recommendation.keys():
user_cnt += 1
done_tips = user_to_done[device_id]
recommended_tips = user_to_recommendation[device_id]
dcg_k = 0
idcg_k = 0
for j in range(min(len(recommended_tips), K)):
idcg_k += 1. / math.log2(j + 2)
if _is_intersection(done_tips, [recommended_tips[j]]):
dcg_k += 1. / math.log2(j + 2)
ndcg_k += dcg_k * 1. / idcg_k
ndcg_k = ndcg_k * 1. / user_cnt
return ndcg_k
def recommend_with_scores(self, test_device_events, tips):
if self.is_logging:
logging.info(
"RecommenderTopEvent:recommend: recommendation started.")
test_device_events = self._filter_old_test_device_events(
test_device_events)
tips_to_recommend = {}
for top_event in self.top_events:
event = top_event[0]
score = top_event[1]
if (event not in test_device_events.keys())\
and _is_intersection(tips, event_to_tips(event[0], event[1])) > 0:
for tip in event_to_tips(event[0], event[1]):
if tip in tips:
tips_to_recommend[tip] = score
if self.is_logging:
logging.info("RecommenderTopEvent:recommend: recommendation made.")
return tips_to_recommend