def generate_adoption_data(netdata,
interact_type,
split_timestamp,
min_interactions_per_user=1,
time_window=None,
time_scale=ord('o')):
print "ALERT: Generating adoption data chronologically"
core_nodes2 = netdata.get_nodes_list(should_have_interactions=True)
# caution: should do it for all users with interactions to be safe
interactions_stream, eligible_nodes = adopt_time.get_interactions_stream(
core_nodes2,
interact_type,
split_timestamp,
min_interactions_per_user,
after=True)
print "Number of interactions %d after time %d" % (
len(interactions_stream), split_timestamp)
counter = 0
kbest_lastm_heaps = {} # Heap storing last M interactions by neighbors
friends_lastm_heaps = {}
rnonfr_lastm_heaps = {}
# care only about friends of eligible_nodes
incoming_friends_dict = adopt_time.compute_incoming_friends(eligible_nodes)
# consider only k-nearest neighbors of eligible nodes
incoming_kbest_dict = adopt_time.compute_globalk_neighbors3(
netdata,
eligible_nodes,
interact_type,
k=10,
min_interactions_per_user=min_interactions_per_user)
# consider building lastm_heap only for an eligible nodes
friends_lastm_heaps = adopt_time.compute_initial_lastm_heaps(
eligible_nodes, incoming_friends_dict, interact_type, split_timestamp,
min_interactions_per_user, time_window)
kbest_lastm_heaps = adopt_time.compute_initial_lastm_heaps(
eligible_nodes, incoming_kbest_dict, interact_type, split_timestamp,
min_interactions_per_user, time_window)
items_pop = get_initial_items_pop(eligible_nodes, interact_type)
# we need friends_dict for only those that appear in the test set
# and more importantly, in the interaction stream (i.e. >=min_interactions_per_user),
# since that is what is compared in the suscept test.
outf = open("adoptions.dat", "w")
for node, item_id, timestamp, rating in interactions_stream:
fr_count, kbest_count, itempop = process_interaction(
node, item_id, timestamp, rating, friends_lastm_heaps,
kbest_lastm_heaps, rnonfr_lastm_heaps,
incoming_friends_dict[node.uid], incoming_kbest_dict[node.uid],
items_pop)
if node.has_friends():
outf.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\n".format(
node.uid, item_id, timestamp, rating, fr_count, kbest_count,
itempop))
outf.close()
def generate_adoption_data(netdata, interact_type, split_timestamp,
min_interactions_per_user=1, time_window=None, time_scale=ord('o')):
print "ALERT: Generating adoption data chronologically"
core_nodes2 = netdata.get_nodes_list(should_have_interactions=True)
# caution: should do it for all users with interactions to be safe
interactions_stream, eligible_nodes = adopt_time.get_interactions_stream(core_nodes2,
interact_type, split_timestamp, min_interactions_per_user, after=True)
print "Number of interactions %d after time %d" %(len(interactions_stream),
split_timestamp)
counter = 0
kbest_lastm_heaps = {} # Heap storing last M interactions by neighbors
friends_lastm_heaps = {}
rnonfr_lastm_heaps = {}
# care only about friends of eligible_nodes
incoming_friends_dict = adopt_time.compute_incoming_friends(eligible_nodes)
# consider only k-nearest neighbors of eligible nodes
incoming_kbest_dict = adopt_time.compute_globalk_neighbors3(netdata, eligible_nodes,
interact_type, k=10, min_interactions_per_user=min_interactions_per_user)
# consider building lastm_heap only for an eligible nodes
friends_lastm_heaps = adopt_time.compute_initial_lastm_heaps(eligible_nodes,
incoming_friends_dict, interact_type, split_timestamp, min_interactions_per_user,
time_window)
kbest_lastm_heaps = adopt_time.compute_initial_lastm_heaps(eligible_nodes,
incoming_kbest_dict, interact_type, split_timestamp, min_interactions_per_user,
time_window)
items_pop = get_initial_items_pop(eligible_nodes, interact_type)
# we need friends_dict for only those that appear in the test set
# and more importantly, in the interaction stream (i.e. >=min_interactions_per_user),
# since that is what is compared in the suscept test.
outf = open("adoptions.dat", "w")
for node, item_id, timestamp, rating in interactions_stream:
fr_count,kbest_count, itempop = process_interaction(node, item_id, timestamp, rating, friends_lastm_heaps,
kbest_lastm_heaps, rnonfr_lastm_heaps, incoming_friends_dict[node.uid],
incoming_kbest_dict[node.uid], items_pop)
if node.has_friends():
outf.write("{0}\t{1}\t{2}\t{3}\t{4}\t{5}\t{6}\n".format(node.uid, item_id, timestamp, rating, fr_count, kbest_count, itempop))
outf.close()
def generate_fake_preferences(
netdata,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=1,
time_window=None,
time_scale=ord("o"),
method="random",
):
global num_not_influence, num_not_homophily
global friends_share, nonfriends_share
num_not_homophily = 0
num_not_influence = 0
print "ALERT: Generating some fake data..."
"""
core_nodes = netdata.get_nodes_iterable(should_have_interactions=True,
should_have_friends=True)
# caution: should do it for all users with interactions to be safe
interactions_stream = get_interactions_stream(core_nodes, interact_type, split_timestamp, min_interactions_per_user)
"""
core_nodes2 = netdata.get_nodes_iterable(should_have_interactions=True)
# caution: should do it for all users with interactions to be safe
interactions_stream, eligible_nodes = adopt_time.get_interactions_stream(
core_nodes2, interact_type, split_timestamp, min_interactions_beforeaftersplit_per_user
)
print "Number of interactions to change", len(interactions_stream)
counter = 0
lastm_heaps = {}
if method == "homophily":
"""
globalk_neighbors_dict = compute_globalk_neighbors(netdata, all_future_nodes,
interact_type, k=10, min_interactions_per_user=min_interactions_per_user)
print "Generated k-best neighbors for all"
"""
globalk_incoming_dict = adopt_time.compute_globalk_neighbors3(
netdata,
eligible_nodes,
interact_type,
k=10,
min_interactions_per_user=min_interactions_beforeaftersplit_per_user,
)
lastm_heaps = adopt_time.compute_initial_lastm_heaps(
eligible_nodes,
globalk_incoming_dict,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user,
time_window,
)
"""
for node in netdata.get_nodes_iterable(should_have_interactions=True):
lastm_heaps[node.uid] = [(0,-1)]*time_window
heapq.heapify(lastm_heaps[node.uid])
"""
elif method == "random":
items_pop = get_items_dup_array(netdata, interact_type)
print "Generated items popularity dict"
elif method == "influence":
# we need friends_dict for only those that appear in the test set
# and more importantly, in the interaction stream (i.e. >=min_interactions_per_user),
# since that is what is compared in the suscept test.
incoming_friends_dict = adopt_time.compute_incoming_friends(eligible_nodes)
lastm_heaps = adopt_time.compute_initial_lastm_heaps(
eligible_nodes,
incoming_friends_dict,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user,
time_window,
)
"""
for node in netdata.get_nodes_iterable(should_have_interactions=True):
lastm_heaps[node.uid] = [(0,-1)]*time_window
heapq.heapify(lastm_heaps[node.uid])
"""
print len(lastm_heaps), "yoyo"
# print(incoming_friends_dict)
else:
print "Invalid fake prefs method"
sys.exit(1)
for node, item_id, timestamp, rating in interactions_stream:
if method == "random":
new_item_id = select_item_dueto_random(items_pop) # .randint(1, netdata.total_num_items)
elif method == "influence":
new_item_id = select_item_from_neighbors(
netdata, lastm_heaps, node, timestamp, time_window, incoming_friends_dict[node.uid]
)
elif method == "homophily":
new_item_id = select_item_from_neighbors(
netdata, lastm_heaps, node, timestamp, time_window, globalk_incoming_dict[node.uid]
)
else:
print "Invalid fake prefs method"
sys.exit(1)
# print node.uid, new_item_id, timestamp
ret = node.change_interacted_item(interact_type, item_id, new_item_id, timestamp)
if ret == -1:
print node.get_interactions(interact_type)
print "Cannot find in the above array", item_id
print "Big Error: Item_id not found in interactions list."
sys.exit(1)
counter += 1
if counter % 100000 == 0:
print "Done faked", counter
if method == "influence":
print "In influence: number of interactions that were not generated by influence:", num_not_influence
elif method == "homophily":
print "In homophily: friends share, and nonfriends share of fake data:", friends_share, nonfriends_share
print "In homophily: number of interactions that were not generated by influence:", num_not_homophily
print "Fake data generated"
def generate_fake_preferences(netdata, interact_type, split_timestamp,
min_interactions_beforeaftersplit_per_user=1, time_window=None, time_scale=ord('o'), method="random"):
global num_not_influence, num_not_homophily
global friends_share, nonfriends_share
num_not_homophily = 0
num_not_influence = 0
print "ALERT: Generating some fake data..."
"""
core_nodes = netdata.get_nodes_iterable(should_have_interactions=True,
should_have_friends=True)
# caution: should do it for all users with interactions to be safe
interactions_stream = get_interactions_stream(core_nodes, interact_type, split_timestamp, min_interactions_per_user)
"""
core_nodes2 = netdata.get_nodes_iterable(should_have_interactions=True)
# caution: should do it for all users with interactions to be safe
interactions_stream, eligible_nodes = adopt_time.get_interactions_stream(core_nodes2, interact_type, split_timestamp, min_interactions_beforeaftersplit_per_user)
print "Number of interactions to change", len(interactions_stream)
counter = 0
lastm_heaps = {}
if method=="homophily":
"""
globalk_neighbors_dict = compute_globalk_neighbors(netdata, all_future_nodes,
interact_type, k=10, min_interactions_per_user=min_interactions_per_user)
print "Generated k-best neighbors for all"
"""
globalk_incoming_dict = adopt_time.compute_globalk_neighbors3(netdata,eligible_nodes,
interact_type, k=10, min_interactions_per_user=min_interactions_beforeaftersplit_per_user)
lastm_heaps = adopt_time.compute_initial_lastm_heaps(eligible_nodes,
globalk_incoming_dict, interact_type, split_timestamp, min_interactions_beforeaftersplit_per_user,
time_window)
"""
for node in netdata.get_nodes_iterable(should_have_interactions=True):
lastm_heaps[node.uid] = [(0,-1)]*time_window
heapq.heapify(lastm_heaps[node.uid])
"""
elif method=="random":
items_pop = get_items_dup_array(netdata, interact_type)
print "Generated items popularity dict"
elif method=="influence":
# we need friends_dict for only those that appear in the test set
# and more importantly, in the interaction stream (i.e. >=min_interactions_per_user),
# since that is what is compared in the suscept test.
incoming_friends_dict = adopt_time.compute_incoming_friends(eligible_nodes)
lastm_heaps = adopt_time.compute_initial_lastm_heaps(eligible_nodes,
incoming_friends_dict, interact_type, split_timestamp, min_interactions_beforeaftersplit_per_user,
time_window)
"""
for node in netdata.get_nodes_iterable(should_have_interactions=True):
lastm_heaps[node.uid] = [(0,-1)]*time_window
heapq.heapify(lastm_heaps[node.uid])
"""
print len(lastm_heaps), "yoyo"
#print(incoming_friends_dict)
else:
print "Invalid fake prefs method"; sys.exit(1)
for node, item_id, timestamp, rating in interactions_stream:
if method == "random":
new_item_id = select_item_dueto_random(items_pop)#.randint(1, netdata.total_num_items)
elif method == "influence":
new_item_id = select_item_from_neighbors(netdata, lastm_heaps,
node, timestamp, time_window, incoming_friends_dict[node.uid])
elif method == "homophily":
new_item_id = select_item_from_neighbors(netdata, lastm_heaps,
node, timestamp, time_window, globalk_incoming_dict[node.uid])
else:
print "Invalid fake prefs method"; sys.exit(1)
#print node.uid, new_item_id, timestamp
ret = node.change_interacted_item(interact_type, item_id, new_item_id, timestamp)
if ret == -1:
print node.get_interactions(interact_type)
print "Cannot find in the above array", item_id
print "Big Error: Item_id not found in interactions list."; sys.exit(1)
counter += 1
if counter % 100000 == 0:
print "Done faked", counter
if method=="influence":
print "In influence: number of interactions that were not generated by influence:", num_not_influence
elif method=="homophily":
print "In homophily: friends share, and nonfriends share of fake data:", friends_share, nonfriends_share
print "In homophily: number of interactions that were not generated by influence:", num_not_homophily
print "Fake data generated"