def calc_weighted_top_list_method1(self,
site_id,
similarity_type,
items_list,
extra_excludes_list=[]):
if len(items_list) > 15:
recent_history = items_list[:15]
else:
recent_history = items_list
excludes_set = set(items_list + extra_excludes_list)
# calculate weighted top list from recent browsing history
rec_map = {}
for row in self.getSimilaritiesForItems(site_id, similarity_type,
recent_history):
recommended_items = row["mostSimilarItems"]
for rec_item, score in recommended_items:
if rec_item not in excludes_set:
rec_map.setdefault(rec_item, [0, 0])
rec_map[rec_item][0] += float(score)
rec_map[rec_item][1] += 1
rec_tuples = []
for key in rec_map.keys():
score_total, count = rec_map[key][0], rec_map[key][1]
rec_tuples.append((key, score_total / count))
rec_tuples.sort(lambda a, b: sign(b[1] - a[1]))
topn = [rec_tuple for rec_tuple in rec_tuples]
return topn
def calc_weighted_top_list_method1(self, site_id, similarity_type,
items_list, extra_excludes_list=[]):
if len(items_list) > 15:
recent_history = items_list[:15]
else:
recent_history = items_list
excludes_set = set(items_list + extra_excludes_list)
# calculate weighted top list from recent browsing history
rec_map = {}
for row in self.getSimilaritiesForItems(site_id, similarity_type, recent_history):
recommended_items = row["mostSimilarItems"]
for rec_item, score in recommended_items:
if rec_item not in excludes_set:
rec_map.setdefault(rec_item, [0, 0])
rec_map[rec_item][0] += float(score)
rec_map[rec_item][1] += 1
rec_tuples = []
for key in rec_map.keys():
score_total, count = rec_map[key][0], rec_map[key][1]
rec_tuples.append((key, score_total / count))
rec_tuples.sort(lambda a, b: sign(b[1] - a[1]))
topn = [rec_tuple for rec_tuple in rec_tuples]
return topn
def updateRecord(connection, site_id, item_view_times_map, last_item_id1,
last_rows):
last_rows.sort(lambda a, b: sign(b[1] - a[1]))
item1_total_views = item_view_times_map[last_item_id1]
content_dict = {
"item_id": last_item_id1,
"total_views": item1_total_views,
"viewedUltimatelyBuys": []
}
for row in last_rows:
item_id2, count = row
content_dict["viewedUltimatelyBuys"].append({
"item_id":
item_id2,
"count":
count,
"percentage":
count / item1_total_views
})
c_viewed_ultimately_buys = getSiteDBCollection(connection, site_id,
"viewed_ultimately_buys")
c_viewed_ultimately_buys.update({"item_id": last_item_id1},
content_dict,
upsert=True)
def updateRecord(connection, site_id, item_view_times_map, last_item_id1, last_rows):
last_rows.sort(lambda a, b: sign(b[1] - a[1]))
item1_total_views = item_view_times_map[last_item_id1]
content_dict = {"item_id": last_item_id1,
"total_views": item1_total_views, "viewedUltimatelyBuys": []}
for row in last_rows:
item_id2, count = row
content_dict["viewedUltimatelyBuys"].append(
{"item_id": item_id2,
"count": count,
"percentage": count / item1_total_views})
c_viewed_ultimately_buys = getSiteDBCollection(
connection, site_id, "viewed_ultimately_buys")
c_viewed_ultimately_buys.update(
{"item_id": last_item_id1}, content_dict, upsert=True)
def calc_weighted_top_list_method1(self,
site_id,
similarity_type,
items_list,
extra_excludes_list=[]):
# the new items added to the items_list, are appended to the end of the list
# here we have to get the latest 15 items, so we get the last 15 items
# from the items_list
if len(items_list) > 15:
recent_history = items_list[-15:]
else:
recent_history = items_list
# some calc are item-order releated, so we have to get the items reversed
recent_history = recent_history[::-1]
weights = settings.SIMILARITY_WEIGHT.get(similarity_type, [])
wei_cnt = len(weights)
his_cnt = len(recent_history)
if his_cnt <= wei_cnt:
weight_dict = dict(zip(recent_history, weights[0:his_cnt]))
else:
weight_dict = dict(zip(recent_history[0:wei_cnt], weights))
excludes_set = set(items_list + extra_excludes_list)
# calculate weighted top list from recent browsing history
rec_map = {}
for row in self.getSimilaritiesForItems(site_id, similarity_type,
recent_history):
recommended_items = row["mostSimilarItems"]
for rec_item, score in recommended_items:
if rec_item not in excludes_set:
rec_map.setdefault(rec_item, [0, 0])
rec_map[rec_item][0] += (
float(score) * weight_dict.get(row['item_id'], 1))
rec_map[rec_item][1] += 1
rec_tuples = []
for key in rec_map.keys():
score_total, count = rec_map[key][0], rec_map[key][1]
rec_tuples.append((key, score_total / count))
rec_tuples.sort(lambda a, b: sign(b[1] - a[1]))
topn = [rec_tuple for rec_tuple in rec_tuples]
return topn
def calc_weighted_top_list_method1(self, site_id, similarity_type,
items_list, extra_excludes_list=[]):
# the new items added to the items_list, are appended to the end of the list
# here we have to get the latest 15 items, so we get the last 15 items
# from the items_list
if len(items_list) > 15:
recent_history = items_list[-15:]
else:
recent_history = items_list
# some calc are item-order releated, so we have to get the items reversed
recent_history = recent_history[::-1]
weights = settings.SIMILARITY_WEIGHT.get(similarity_type, [])
wei_cnt = len(weights)
his_cnt = len(recent_history)
if his_cnt <= wei_cnt:
weight_dict = dict(zip(recent_history, weights[0:his_cnt]))
else:
weight_dict = dict(zip(recent_history[0:wei_cnt], weights))
excludes_set = set(items_list + extra_excludes_list)
# calculate weighted top list from recent browsing history
rec_map = {}
for row in self.getSimilaritiesForItems(site_id, similarity_type, recent_history):
recommended_items = row["mostSimilarItems"]
for rec_item, score in recommended_items:
if rec_item not in excludes_set:
rec_map.setdefault(rec_item, [0, 0])
rec_map[rec_item][0] += (float(score) * weight_dict.get(row['item_id'], 1))
rec_map[rec_item][1] += 1
rec_tuples = []
for key in rec_map.keys():
score_total, count = rec_map[key][0], rec_map[key][1]
rec_tuples.append((key, score_total / count))
rec_tuples.sort(lambda a, b: sign(b[1] - a[1]))
topn = [rec_tuple for rec_tuple in rec_tuples]
return topn
