def early_movement():
"""
Q1: how early a spammer would begin to act
:return: None
"""
pid_rid_time_list = load_pid_rid_time_list()
rid_label = load_rid_label()
rid_orders_pos = {}
rid_orders_neg = {}
for i in range(len(pid_rid_time_list.keys())):
pid = pid_rid_time_list.keys()[i]
rid_time_list = pid_rid_time_list[pid]
for j in range(len(rid_time_list)):
rid = rid_time_list[j][0]
if rid_label.get(rid) == 1:
rid_orders_pos.setdefault(rid, [])
rid_orders_pos[rid].append(j)
elif rid_label.get(rid) == 0:
rid_orders_neg.setdefault(rid, [])
rid_orders_neg[rid].append(j)
ave_order_pos = []
ave_order_neg = []
for rid, orders in rid_orders_pos.items():
ave_order_pos.append(np.mean(orders))
for rid, orders in rid_orders_neg.items():
ave_order_neg.append(np.mean(orders))
plt.hist([ave_order_pos, ave_order_neg],
bins=100, normed=True, cumulative=True,
histtype='step', label=['pos', 'neg'], color=['red', 'blue'])
plt.legend()
plt.show()
def stat_pid_rid_time():
"""
Statistics for pid_rid_time structure
:rtype : None
:return: None
"""
rid_pid_set = load_rid_pid_set()
rid_label = load_rid_label()
pid_rid_time_list = load_pid_rid_time_list()
spammed_pid = set()
rids = set()
for pid, rid_time_list in pid_rid_time_list.items():
for rid, ts in rid_time_list:
rids.add(rid)
if rid_label.get(rid) == 1:
spammed_pid.add(pid)
rid_num_review_dist = [len(rid_pid_set[rid]) for rid in list(rids)]
singletons = [num for num in rid_num_review_dist if num == 1]
print 'The total number of products:', len(pid_rid_time_list.keys())
print 'The number of spammed products:', len(spammed_pid)
print 'The total number of users:', len(rids)
print 'The number of singleton:', len(singletons)
plt.hist(rid_num_review_dist, bins=100, range=(0, 50), normed=True, cumulative=True, histtype='step')
plt.show()
def select_spammed_product_for_early_detection():
"""
Select suitable products for early detection experiments
Condition: the product has been reviewed by at least 3 spammers (1515)
:return:
"""
rid_label = load_rid_label()
pid_rid_time_list = load_pid_rid_time_list()
selected_product = set()
for pid, rid_time_list in pid_rid_time_list.items():
num_spammer = 0
for rid, ts in rid_time_list:
if rid_label.get(rid) == 1:
num_spammer += 1
if num_spammer >= 3:
selected_product.add(pid)
print pid + '\t' + str(len(rid_time_list)) + '\t' + str(num_spammer)
print len(selected_product)
__author__ = 'xuch0007'
from dataset.amazon_cn.utility import load_pid_rid_time_list
####################################################################################
# This module is to evaluate the utility of a feature in terms of timeliness
####################################################################################
def product_timeline(pid, pid_rid_time_list):
"""
For a product, inspect how early can we decide whether it has been involved in opinion spam.
Example: B004VDBR04, B0046HAHBU, B0046HAHA6, B003R50Q9K, B0046HAH9W, B001MYL1GK, B001MYL1GA, B001MYL1FQ
:param pid: product id
:return:
"""
rid_time_list = pid_rid_time_list[pid]
print rid_time_list[:10]
if __name__ == '__main__':
pid_rid_time_list = load_pid_rid_time_list()
product_timeline('B004VDBR04', pid_rid_time_list)
