def test_user_user_strengths_incremental_with_new_impressions_identified_users(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
"""
test_descriptions = [("u_esp_4", "p_nonsense_1", "p_empty_with_missing_category", "p_filter_2", "buy")]
for idx, (user, product1, product2, product3, activity_type) in enumerate(test_descriptions):
# Saves a couple of impressions for the chosen user
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 6:00:00") + dt.timedelta(seconds=(2 * idx + 1)))
self.db_proxy.increment_impression_summary(user_id=user, product_id=product1,
date=date, anonymous=False)
self.db_proxy.increment_impression_summary(user_id=user, product_id=product2,
date=date, anonymous=False)
ut.generate_templates(self.session_context)
# it is important to regenerate from scratch (with all new impressions)
# Saves one activity for that same user
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 6:00:00") + dt.timedelta(seconds=(2 * idx + 2)))
activity = {"external_user_id": user,
"external_product_id": product3,
"activity": activity_type,
"created_at": date}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(
target_users=[user] if self.session_context.impressions_enabled else None)
def test_user_user_strengths_incremental_with_new_impressions_two_new_products(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
This test saves two new, identical products, with impressions for only one user.
After activities of a like-minded user have been saved involving those products,
checks whether all strengths were correctly updated.
"""
# Saves two new, identical products. Initially, no users will have impressions on them.
id_twin_product_1 = "p_tec_TWIN_1"
id_twin_product_2 = "p_tec_TWIN_2"
date = self.session_context.get_present_date() - dt.timedelta(days=2)
twin_product_1 = {"external_id": id_twin_product_1,
"language": "english",
"date": date,
"resources": {"title": "Whatever Gets You Through The Night"},
"full_content": """Begin. Technology. Technology. This is all we got. End.""",
"category": "Nonsense"}
twin_product_2 = {"external_id": id_twin_product_2,
"language": "english",
"date": date,
"resources": {"title": "Whatever Gets You Through The Night"},
"full_content": """Begin. Technology. Technology. This is all we got. End.""",
"category": "Nonsense"}
self.db_proxy.insert_product(twin_product_1)
self.db_proxy.insert_product(twin_product_2)
user1 = "u_eco_1"
user2 = "u_eco_2"
activity_type = self.session_context.activities_by_rating[5][0]
# Saves an impression on just one of the new products
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 9:00:00"))
self.db_proxy.increment_impression_summary(user_id=user1, product_id=id_twin_product_1,
date=date, anonymous=False)
# Saves a couple of activities for another user using the new products
activity = {"external_user_id": user2,
"external_product_id": id_twin_product_1,
"activity": activity_type,
"created_at": self.session_context.get_present_date()}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(target_users=[user2]
if self.session_context.impressions_enabled else None)
activity = {"external_user_id": user2,
"external_product_id": id_twin_product_2,
"activity": activity_type,
"created_at": self.session_context.get_present_date()}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(
target_users=[user2] if self.session_context.impressions_enabled else None)
def test_user_user_strengths_incremental_new_product_5_to_3_to_5star(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
This test saves a 3-star activity with a 5-star product that had never been consumed,
then another activity with the same product (this time a 5-star activity),
checking whether all strengths were correctly updated.
"""
user = "******"
product = "p_mus_1"
activity_type = self.session_context.activities_by_rating[3][0]
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 9:00:00"))
activity = {"external_user_id": user,
"external_product_id": product,
"activity": activity_type,
"created_at": date}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(
target_users=[user] if self.session_context.impressions_enabled else None)
activity_type = self.session_context.activities_by_rating[5][0]
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 9:01:00"))
activity = {"external_user_id": user,
"external_product_id": product,
"activity": activity_type,
"created_at": date}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(target_users=[user]
if self.session_context.impressions_enabled else None)
def test_user_user_strengths_incremental_random(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
This test saves several random activities in a row,
checking whether all strengths were correctly updated.
"""
if not tests.INCLUDE_RANDOM_TESTS:
return
all_users = [u for u in self.db_proxy.fetch_all_user_ids()]
all_products = [p for p in self.db_proxy.fetch_all_product_ids()]
for i in range(100):
user = random.choice(all_users)
product = random.choice(all_products)
activity_type = random.choice(self.session_context.supported_activities)
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 6:00:00")) + dt.timedelta(seconds=2 * i)
activity = {"external_user_id": user,
"external_product_id": product,
"activity": activity_type,
"created_at": date}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(
target_users=[user] if self.session_context.impressions_enabled else None)
def test_user_user_strengths_incremental_with_new_impressions_random(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
This test saves several random activities in a row,
checking whether all strengths were correctly updated.
"""
if not tests.INCLUDE_RANDOM_TESTS:
return
all_users = [u for u in self.db_proxy.fetch_all_user_ids()]
all_products = [p for p in self.db_proxy.fetch_all_product_ids()]
for i in range(100):
user = random.choice(all_users)
is_anonymous = config.is_anonymous(user)
print("user: %s" % user)
# Saves a couple of impressions for the chosen user
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 6:00:00")) + dt.timedelta(seconds=2 * i)
product1 = random.choice(all_products)
product2 = random.choice(all_products)
self.db_proxy.increment_impression_summary(user_id=user, product_id=product1,
date=date, anonymous=is_anonymous)
self.db_proxy.increment_impression_summary(user_id=user, product_id=product2,
date=date, anonymous=is_anonymous)
print("impressions --> %s, %s" % (product1, product2))
ut.generate_templates(self.session_context)
# it is important to regenerate from scratch (with all new impressions)
# Saves one activity for that same user
product3 = random.choice(all_products)
activity_type = random.choice(self.session_context.supported_activities)
date = pytz.utc.localize(dateutil.parser.parse("1988-11-06 6:00:00")) + dt.timedelta(seconds=2 * i + 1)
activity = {"external_user_id": user,
"external_product_id": product3,
"activity": activity_type,
"created_at": date}
print("activity --> " + str(activity))
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(
target_users=[user] if self.session_context.impressions_enabled else None)
def test_user_user_strengths_incremental_new_product_5star(self):
""" Tests whether the user x user strengths generated on a step-by-step basis
match exactly those created from scratch.
This test saves a new activity with a 5-star product that had never been consumed by
the target user and checks whether whether all strengths were correctly updated.
"""
user = "******"
product = "p_mus_1"
activity_type = self.session_context.activities_by_rating[5][0]
activity = {"external_user_id": user,
"external_product_id": product,
"activity": activity_type,
"created_at": self.session_context.get_present_date()}
ut.update_templates(self.session_context, activity)
tasks.update_summaries(self.session_context, activity)
self.compare_incremental_vs_from_scratch(target_users=[user]
if self.session_context.impressions_enabled else None)
def update_collaborative_filtering_strengths(session_context, activity):
""" Updates user-user strengths and product-product strengths in conformity to the informed activity.
:param session_context: The session context.
:param activity: The activity which triggered the updates.
"""
user = activity["external_user_id"]
is_anonymous = config.is_anonymous(user)
if is_anonymous:
return # we do NOT want anonymous users to influence collaborative filtering strengths!
product = activity["external_product_id"]
act_type = activity["activity"]
log.info("Processing strengths [user=%s, product=%s, type=%s]..." % (user, product, act_type))
start = time()
u_p_activity_summary = _get_current_user_product_summary(session_context, user, product, anonymous=False)
first_impression_date = None
if session_context.impressions_enabled:
product_user_impressions_summary = session_context.data_proxy.fetch_impressions_summary(
product_ids=[product],
user_ids=[user],
group_by_product=True,
anonymous=False).get(product, {}).get(user, (0, None))
first_impression_date = product_user_impressions_summary[1]
log.info("Updating user-user strengths affected by user/product pair ({0}, {1})...".format(user, product))
ut.update_templates(session_context, activity, u_p_activity_summary, first_impression_date,
should_lookup_activities_summary=False, should_lookup_first_impression=False)
log.info("Updating product-product strengths affected by user/product pair ({0}, {1})...".format(user, product))
pt.update_templates(session_context, activity, u_p_activity_summary, first_impression_date,
should_lookup_activities_summary=False, should_lookup_first_impression=False)
log.info("---Done processing strengths [user=%s, product=%s, type=%s] (took %.6f seconds)"
% (user, product, act_type, time() - start))
