def getNewsSummariesForUser(user_id, page_num):
page_num = int(page_num)
begin_index = (page_num - 1) * NEWS_LIST_BATCH_SIZE
end_index = page_num * NEWS_LIST_BATCH_SIZE
# The final list of news to be returned.
if redis_client.get(user_id) is not None:
# deserialized redis data
news_digests = pickle.loads(redis_client.get(user_id))
# If begin_index is out of range, this will return empty list;
# If end_index is out of range (begin_index is within the range), this
# will return all remaining news ids.
sliced_news_digests = news_digests[begin_index:end_index]
print(sliced_news_digests)
db = mongodb_client.get_db()
sliced_news = list(db[NEWS_TABLE_NAME].find(
{'digest': {
'$in': sliced_news_digests
}}))
else:
db = mongodb_client.get_db()
# -1 means latest one
# news for specific user
total_news = list(db[NEWS_TABLE_NAME].find().sort([
('publishedAt', -1)
]).limit(NEWS_LIMIT))
total_news_digests = [x['digest'] for x in total_news]
# redis doesn't take json object
# pickle used to serialized object/json/dict
redis_client.set(user_id, pickle.dumps(total_news_digests))
redis_client.expire(user_id, USER_NEWS_TIME_OUT_IN_SECONDS)
sliced_news = total_news[begin_index:end_index]
# Get preference for the user
# preference = news_recommendation_service_client.getPreferenceForUser(user_id)
# topPreference = None
#
# if preference is not None and len(preference) > 0:
# topPreference = preference[0]
#
# for news in sliced_news:
# # Remove text field to save bandwidth.
# del news['text']
# if news['class'] == topPreference:
# news['reason'] = 'Recommend'
# if news['publishedAt'].date() == datetime.today().date():
# news['time'] = 'today'
return json.loads(dumps(sliced_news))
def test_basic():
db = client.get_db('test')
db.demo.drop()
assert db.test.estimated_document_count() == 0
db.demo.insert_one({'test': 123})
assert db.demo.estimated_document_count() == 1
db.demo.drop()
assert db.demo.estimated_document_count() == 0
print('test passed')
def handle_message(msg):
if msg is None or not isinstance(msg, dict):
return
if ('userId' not in msg
or 'newsId' not in msg
or 'timestamp' not in msg):
return
userId = msg['userId']
newsId = msg['newsId']
print('newsid', newsId)
# Update user's preference
db = mongodb_client.get_db()
model = db[PREFERENCE_MODEL_TABLE_NAME].find_one({'userId': userId})
# If model not exists, create a new one
if model is None:
print('Creating preference model for new user: %s' % userId)
new_model = {'userId': userId}
# preference map for each topic
preference = {}
for i in news_classes.classes:
preference[i] = float(INITIAL_P)
new_model['preference'] = preference
model = new_model
print('Updating preference model for new user: %s' % userId)
# Update model using time decaying method
news = db[NEWS_TABLE_NAME].find_one({'digest': newsId})
print(news)
if (news is None
or 'class' not in news
or news['class'] not in news_classes.classes):
# print(news is None)
# print('class' not in news)
# print(news['class'] not in news_classes.classes)
# print('Skipping processing...')
return
click_class = news['class']
# Update the clicked topic
old_p = model['preference'][click_class]
model['preference'][click_class] = float((1 - ALPHA) * old_p + ALPHA)
# Update not clicked classes.
for i, prob in model['preference'].items():
if not i == click_class:
model['preference'][i] = float((1 - ALPHA) * model['preference'][i])
print("model", model)
db[PREFERENCE_MODEL_TABLE_NAME].replace_one({'userId': userId}, model, upsert=True)
def logNewsClickForUser(user_id, news_id):
# Send log task to machine learning service for prediction
message = {
'userId': user_id,
'newsId': news_id,
'timestamp': datetime.utcnow()
}
db = mongodb_client.get_db()
db[CLICK_LOGS_TABLE_NAME].insert(message)
message = {
'userId': user_id,
'newsId': news_id,
'timestamp': str(datetime.utcnow())
}
cloudAMQP_client.send_message(message)
def handle_message(msg):
if msg is None or not isinstance(msg, dict):
return
task = msg
text = task['text']
if text is None:
return
# get all recent news based on publishedAt
published_at = parser.parse(task['publishedAt'])
published_at_day_begin = datetime.datetime(published_at.year, published_at.month, published_at.day, 0, 0, 0, 0)
published_at_day_end = published_at_day_begin + datetime.timedelta(days=1)
db = mongodb_client.get_db()
recent_news_list = list(
db[NEWS_TABLE_NAME].find({'publishedAt': {'$gte': published_at_day_begin, '$lt': published_at_day_end}}))
if recent_news_list is not None and len(recent_news_list) > 0:
documents = [news['text'] for news in recent_news_list]
documents.insert(0, text)
# Calculate similarity matrix
tfidf = TfidfVectorizer().fit_transform(documents)
pairwise_sim = tfidf * tfidf.T
print(pairwise_sim)
rows, _ = pairwise_sim.shape
for row in range(1, rows):
if pairwise_sim[row, 0] > SAME_NEWS_SIMILARITY_THRESHOLD:
# Duplicated news. Ignore.
print("Duplicated news. Ignore.")
return
task['publishedAt'] = parser.parse(task['publishedAt'])
# Classify news
# title = task['title']
# if title is not None:
# topic = news_topic_modeling_service_client.classify(title)
# task['class'] = topic
# if exist, just replace, if not, same as insert
db[NEWS_TABLE_NAME].replace_one({'digest': task['digest']}, task, upsert=True)
def test_logNewsClickForUser_basic():
db = mongodb_client.get_db()
# clean the db, make sure the later test operation is test itself
db[operations.CLICK_LOGS_TABLE_NAME].delete_many({"userId": "test"})
operations.logNewsClickForUser('test', 'test_news')
record = list(db[operations.CLICK_LOGS_TABLE_NAME].find().sort([
('timestamp', -1)
]).limit(1))[0]
assert record is not None
assert record['userId'] == 'test'
assert record['newsId'] == 'test_news'
assert record['timestamp'] is not None
db[operations.CLICK_LOGS_TABLE_NAME].delete_many({"userId": "test"})
# Verify the message has been sent to queue
msg = cloudAMQP_client.get_message()
assert msg is not None
assert msg['userId'] == 'test'
assert msg['newsId'] == 'test_news'
assert msg['timestamp'] is not None
DEDUPE_NEWS_TASK_QUEUE_URL = cc.CLOUDAMQP_URL
DEDUPE_NEWS_TASK_QUEUE_NAME = "news-manager-dedupe-task"
SLEEP_TIME_IN_SECONDS = 1
SAME_NEWS_SIMILARITY_THRESHOLD = 0.9
logger_format = '%(asctime)s - %(message)s'
logging.basicConfig(format=logger_format)
logger = logging.getLogger('news_deduper')
logger.setLevel(logging.DEBUG)
NEWS_TABLE_NAME = "news_col"
cloudAMQP_client = CloudAMQPClient(DEDUPE_NEWS_TASK_QUEUE_URL,
DEDUPE_NEWS_TASK_QUEUE_NAME)
db = mongodb_client.get_db("demo_news")
# col=db.get_collection("news_col")
cloudAMQP_client = CloudAMQPClient(DEDUPE_NEWS_TASK_QUEUE_URL,
DEDUPE_NEWS_TASK_QUEUE_NAME)
news = cloudAMQP_client.getMessage()
def handle_message(news):
text = news['text']
description = news['description']
if description is None:
description = news['title']
news['publishedAt'] = parser.parse(
news['publishedAt']
