def influence(la):
split_timestamp = int(time.mktime(datetime.datetime.strptime("2013/01/01", "%Y/%m/%d").timetuple()))
time_diff = 86400
influence_tuples = la.estimate_influencer_effect(1, split_timestamp, time_diff,
control_divider=0.1,
selection_method="random",
klim=5)
mean_fr_influence = utils.mean_sd([v[5] for v in influence_tuples])
mean_nonfr_influence = utils.mean_sd([v[6] for v in influence_tuples])
print mean_fr_influence, mean_nonfr_influence
def locality(la):
items_cov_list, items_popularity, cov_ratio_list, degree_distr = la.compare_items_edge_coverage(1, minimum_interactions=1)
print utils.mean_sd(items_cov_list)
print utils.mean_sd(items_popularity)
plotter.plotHist(sorted([val for val in cov_ratio_list]), "Ratio of Common Likes with friends to total popularity", "Frequency (Number of items)", logyscale=True, bins=20)
#####plotter.plotHist(sorted([val for val in cov_ratio_list]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#plotter.plotHist(sorted(items_popularity), "Item", "total popularity")
plotter.plotCumulativePopularity(items_popularity, labelx="Item percentile", labely="Cum. percent of number of likes")
f_out = open('plots/data/influenced_loves_ratio.tsv', 'w')
for i in range(len(items_cov_list)):
f_out.write(str(items_cov_list[i])+' '+str(items_popularity[i])+' '+str(cov_ratio_list[i])+'\n')
f_out.close()
def influence(la):
split_timestamp = int(
time.mktime(
datetime.datetime.strptime("2013/01/01", "%Y/%m/%d").timetuple()))
time_diff = 86400
influence_tuples = la.estimate_influencer_effect(1,
split_timestamp,
time_diff,
control_divider=0.1,
selection_method="random",
klim=5)
mean_fr_influence = utils.mean_sd([v[5] for v in influence_tuples])
mean_nonfr_influence = utils.mean_sd([v[6] for v in influence_tuples])
print mean_fr_influence, mean_nonfr_influence
def locality(la):
items_cov_list, items_popularity, cov_ratio_list, degree_distr = la.compare_items_edge_coverage(
1, minimum_interactions=1)
print utils.mean_sd(items_cov_list)
print utils.mean_sd(items_popularity)
plotter.plotHist(sorted([val for val in cov_ratio_list]),
"Ratio of Common Likes with friends to total popularity",
"Frequency (Number of items)",
logyscale=True,
bins=20)
#####plotter.plotHist(sorted([val for val in cov_ratio_list]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#plotter.plotHist(sorted(items_popularity), "Item", "total popularity")
plotter.plotCumulativePopularity(items_popularity,
labelx="Item percentile",
labely="Cum. percent of number of likes")
f_out = open('plots/data/influenced_loves_ratio.tsv', 'w')
for i in range(len(items_cov_list)):
f_out.write(
str(items_cov_list[i]) + ' ' + str(items_popularity[i]) + ' ' +
str(cov_ratio_list[i]) + '\n')
f_out.close()
def test_influence(la, interact_type, time_diff, time_scale, split_timestamp, control_divider,
min_interactions_beforeaftersplit_per_user, max_tries, max_node_computes, num_threads,
max_interact_ratio_error,max_sim_ratio_error,
min_friends_match_ratio, klim, nonfr_match,
method, allow_duplicates):
#time_diff = 90000 #86400
influence_tuples = la.estimate_influencer_effect_parallel(interact_type, split_timestamp,
time_diff, time_scale,
control_divider=control_divider,
min_interactions_beforeaftersplit_per_user=min_interactions_beforeaftersplit_per_user,
selection_method="random",
klim=klim, max_tries=max_tries,
max_node_computes=max_node_computes,
num_threads=num_threads,
max_interact_ratio_error=max_interact_ratio_error,
max_sim_ratio_error=max_sim_ratio_error,
min_friends_match_ratio=min_friends_match_ratio,
nonfr_match = nonfr_match,
method=method,
allow_duplicates=allow_duplicates)
node_test_set_sizes = [v[0] for v in influence_tuples]
fr_inf_vals = [v[5] for v in influence_tuples]
nonfr_inf_vals = [v[6] for v in influence_tuples]
diff_inf_vals = [v[5]-v[6] for v in influence_tuples]
# Considering only positive values
diff_inf_vals_positiveonly = [v[5]-v[6] if v[5]-v[6] > 0 else 0 for v in influence_tuples]
mean_fr_influence = utils.mean_sd(fr_inf_vals)
mean_nonfr_influence = utils.mean_sd(nonfr_inf_vals)
mean_diff_influence = utils.mean_sd(diff_inf_vals)
mean_diff_influence_positiveonly = utils.mean_sd(diff_inf_vals_positiveonly)
fr_sim_vals = [v[3] for v in influence_tuples]
nonfr_sim_vals = [v[4] for v in influence_tuples]
diff_sim_vals = [v[3]-v[4] for v in influence_tuples]
mean_fr_sim = utils.mean_sd(fr_sim_vals)
mean_nonfr_sim = utils.mean_sd(nonfr_sim_vals)
mean_diff_sim = utils.mean_sd(diff_sim_vals)
print "\nTest Results"
print "Mean FrSim={0}, Mean NonFrSim={1}, MeanDiff={2}".format(mean_fr_sim, mean_nonfr_sim, mean_diff_sim)
print "MeanFrInf={0}, Mean NonFrInf={1}".format(mean_fr_influence, mean_nonfr_influence)
print "MeanDiff={0}, MeanDiffPositiveOnly={1}".format(mean_diff_influence, mean_diff_influence_positiveonly)
print len(fr_inf_vals), len(nonfr_inf_vals)
return node_test_set_sizes, fr_sim_vals, nonfr_sim_vals, fr_inf_vals, nonfr_inf_vals
def show_basic_stats(self):
num_interactdata_users = sum([1 for _ in self.netdata.get_nodes_iterable(should_have_interactions=True)])
print "Number of Users with interaction data", num_interactdata_users
num_frienddata_users = sum([1 for _ in self.netdata.get_nodes_iterable(should_have_friends=True)])
print "Number of Users with friendship data", num_frienddata_users
num_overall_users = self.netdata.get_total_num_nodes()
print "Number of overall users", num_overall_users
fr_arr = [v.get_num_friends() for v in self.netdata.get_nodes_iterable(should_have_friends=True)]
print "Mean, SD of number of friends per user", mean_sd(fr_arr)
print "Number of users with zero friends", sum([1 for v in fr_arr if v == 0])
num_items_all = self.netdata.get_total_num_items()
print "Total number of items", num_items_all
print "Types of interactions with items", self.netdata.interaction_types
items_by_interaction = []
for interact_type in self.netdata.interaction_types:
items_by_interaction.append(set())
for v in self.netdata.get_nodes_iterable(should_have_interactions=True):
for interact_type in self.netdata.interaction_types:
items_by_interaction[interact_type] |= set(v.get_items_interacted_with(interact_type))
for i in range(len(items_by_interaction)):
print( "--Total number of items with interaction %s: %d" %(i, len(items_by_interaction[i])) )
sum_each_interaction_dict = self.get_sum_interactions_by_type()
for interact_type, total_interacts in sum_each_interaction_dict.iteritems():
#print(interact_type)
print( "--Total, Mean, of %d-type interactions per user = (%d, %f"
%(interact_type, total_interacts, total_interacts/float(num_interactdata_users)))
print( "--Total, Mean, of %d-type interactions per item = (%d, %f)"
%(interact_type, total_interacts, total_interacts/float(num_items_all)) )
for interact_type in self.netdata.interaction_types:
user_interacts = [ v.get_num_interactions(interact_type) for v in self.netdata.get_nodes_iterable(should_have_interactions=True)]
print("--Min, Max %d-type interacts per user= %d, %d" %(interact_type, min(user_interacts), max(user_interacts)))
print "Min., Max. timestamp of interactions", self.get_min_max_interact_times()
return
def run_computation(data, computation_cmd, outf, interact_type, create_fake_prefs,
allow_duplicates, split_date_str, dataset_domain, dataset_path,
min_interacts_beforeaftersplit_per_user,
max_interact_ratio_error, max_sim_ratio_error, min_friends_match_ratio,
traindata_fraction, M):
net_analyzer = BasicNetworkAnalyzer(data)
interaction_types = data.interact_types_dict
filename_prefix = computation_cmd if computation_cmd is not None else ""
if computation_cmd=="basic_stats" or computation_cmd is None:
net_analyzer.show_basic_stats()
## use below if you want to write a new dataset (e.g. after filtering)
data.store_ego_dataset("/home/amit/datasets/social_activity_data/lastfm_filtered_listen/", write_maps=False)
#data.compute_allpairs_sim(interact_type, data_type=ord("a"))
elif computation_cmd=="random_similarity":
for type_name, type_index in interaction_types.iteritems():
circlesims, globalsims = net_analyzer.compare_circle_global_similarity(type_index, num_random_trials=5, cutoff_rating=cutoff_rating)
#plotter.plotLinesYY(circlesims, globalsims, "Friends", "Global")
outf.write("User_id\tcircle_sim\tnonfriend_sim\n")
outf.write(type_name + '\n')
for ind in range(len(circlesims)):
outf.write("%s\t%f\t%f\n" %(circlesims[ind][0], circlesims[ind][1], globalsims[ind][1]))
print "\n", type_name, ":"
print "Circle Average", sum([v2 for v1,v2 in circlesims])/float(len(circlesims))
print "Global Average", sum([v2 for v1,v2 in globalsims])/float(len(globalsims))
elif computation_cmd=="knn_similarity":
#Compute K-nearest similarity
KLIMITS = [10]
outf.write("User_id\tk\tcircle_sim\tnonfriend_sim\n")
for type_name, type_index in interaction_types.iteritems():
for curr_lim in KLIMITS:
plot_circle, plot_external = net_analyzer.compare_circle_global_knnsimilarity(type_index, klim=curr_lim, cutoff_rating=cutoff_rating)
compare_sims(plot_circle, plot_external)
outf.write(type_name+'\n')
for ind in range(len(plot_circle)):
outf.write("%s\t%d\t%f\t%f\n" %(plot_circle[ind][0], curr_lim, plot_circle[ind][1], plot_external[ind][1]))
#plotter.plotLinesYY(plot_circle, plot_external, "Friends", "Global")
print type_name, "K", curr_lim
print "Circle Average", utils.mean_sd([v2 for v1,v2 in plot_circle]), len(plot_circle)
print "Global Average", utils.mean_sd([v2 for v1,v2 in plot_external]), len(plot_external)
elif computation_cmd=="knn_recommender":
#Compute K-nearest recommender
KLIMITS = [10]
rec_analyzer = RecommenderAnalyzer(data, max_recs_shown=10, traintest_split=0.7, cutoff_rating=cutoff_rating)
outf.write("User_id\tk\trun_index\tcircle_ndcg\tnonfriend_ndcg\n")
for type_name, type_index in interaction_types.iteritems():
for curr_lim in KLIMITS:
local_avg=[]
global_avg=[]
Ntotal = 10
for i in range(Ntotal): # randomize because of training-test split.
plot_circle, plot_external = rec_analyzer.compare_knearest_recommenders(type_index, klim=curr_lim, num_processes=2)
compare_sims(plot_circle, plot_external)
outf.write(type_name + "\n")
for ind in range(len(plot_circle)):
outf.write("%s\t%d\t%d\t%f\t%f\n" %(plot_circle[ind][0], curr_lim, i, plot_circle[ind][1], plot_external[ind][1]))
print "\n", type_name, "K", curr_lim
#print plot_circle, plot_external
curr_avg_local = utils.mean_sd([v2 for v1,v2 in plot_circle])
curr_avg_global = utils.mean_sd([v2 for v1,v2 in plot_external])
print "Circle Average", curr_avg_local
print "Global Average", curr_avg_global
local_avg.append(curr_avg_local[0])
global_avg.append(curr_avg_global[0])
#plotLinesYY(plot_circle, plot_external, "Friends", "Global")
print "Local", sum(local_avg)/float(Ntotal)
print "Global", sum(global_avg)/float(Ntotal)
elif computation_cmd == "circle_coverage":
lim_friends = [(5,10), (10,20), (20,50), (50,100)]
for fr_limit in lim_friends:
locality_analyzer = LocalityAnalyzer(data)
coverage_list = locality_analyzer.compare_circle_item_coverages(0, fr_limit[0], fr_limit[1])
plotter.plotLineY(sorted(coverage_list), "User", "Fraction of Items Covered with %d-%d friends" % (fr_limit[0], fr_limit[1]))
print utils.mean_sd(coverage_list)
elif computation_cmd == "items_edge_coverage":
locality_analyzer = LocalityAnalyzer(data)
items_cov_list, items_popularity, cov_ratio_list = locality_analyzer.compare_items_edge_coverage(1, minimum_interactions=1)
print utils.mean_sd(items_cov_list)
print utils.mean_sd(items_popularity)
#plotter.plotHist(sorted([val for val in cov_ratio_list if val<=1]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#####plotter.plotHist(sorted([val for val in cov_ratio_list]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#plotter.plotHist(sorted(items_popularity), "Item", "total popularity")
plotter.plotCumulativePopularity(items_popularity, labelx="Item percentile", labely="Cum. percent of number of likes")
elif computation_cmd == "network_draw":
net_visualizor = NetworkVisualizor(data)
net_visualizor.draw_network()
elif computation_cmd == "network_item_adopt":
net_visualizor = NetworkVisualizor(data)
pprint(net_visualizor.plot_item_adoption(1669118))
elif computation_cmd == "node_details":
for node_id in open('user_ids'):
if node_id.strip('\n') != "User_id":
net_analyzer.get_node_details(int(node_id.strip('\n')))
elif computation_cmd=="store_dataset":
user_interacts = net_analyzer.get_user_interacts(1, cutoff_rating)
f = open(outf_path+ 'user_interacts_'+dataset_domain+'.tsv', 'w')
f.write("user_id\titem_id\ttimestamp\n")
for user_id, item_id, timestamp in user_interacts:
f.write("%s\t%s\t%s\n" %(user_id, item_id, timestamp))
f.close()
item_pop = net_analyzer.get_items_popularity(1, cutoff_rating)
f = open(outf_path+'items_'+dataset_domain+'.tsv','w')
f.write("item_id\tpopularity\n")
for item_id, pop in item_pop.iteritems():
f.write("%s\t%s\n" %(item_id, pop))
f.close()
user_friends = net_analyzer.get_user_friends()
f = open('user_friends_'+dataset_domain+'.tsv','w')
f.write("user_id\tfriend_id\n")
for user_id, friend_id in user_friends:
f.write("%s\t%s\n" %(user_id, friend_id))
f.close()
print "Successfully stored tsv dataset"
elif computation_cmd=="compare_interact_types":
num_interacts_dict = net_analyzer.compare_interaction_types()
interact_types = num_interacts_dict.keys()
plotter.plotLinesYY(num_interacts_dict[interact_types[0]],
num_interacts_dict[interact_types[1]],
interact_types[0], interact_types[1],
display=True, logyscale=True)
plotter.plotLinesYY(num_interacts_dict[interact_types[1]],
num_interacts_dict[interact_types[2]],
interact_types[1], interact_types[2],
display=True, logyscale=True)
plotter.plotLinesYY(num_interacts_dict[interact_types[0]],
num_interacts_dict[interact_types[2]],
interact_types[0], interact_types[2],
display=True, logyscale=True)
elif computation_cmd=="influence_test":
# ta = TemporalAnalyzer(data)
#interact_type = data.interact_types_dict["listen"
# time_scale can be 'w':wallclock_time or 'o':ordinal_time
split_date_str = "2008/01/01"
t_window = -1
t_scale = ord('w')
max_tries_val = 10000
max_node_computes_val = 100
max_interact_ratio_error = 0.1
klim_val=5
split_timestamp = int(time.mktime(datetime.datetime.strptime(split_date_str, "%Y/%m/%d").timetuple()))
# crate trainig test sets that will be used by fake geernation
data.create_training_test_bytime(interact_type, split_timestamp)
if create_fake_prefs is not None:
print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
fake_data.generate_fake_preferences(data,interact_type, split_timestamp,
min_interactions_beforeaftersplit_per_user=min_interacts_beforeaftersplit_per_user,
time_window=t_window, time_scale=t_scale, method=create_fake_prefs)
#fake_data.generate_random_preferences(data, interact_type, split_timestamp)
print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
# Need to generate again because fake data changes test data
data.create_training_test_bytime(interact_type, split_timestamp)
la = LocalityAnalyzer(data)
inf_tuple = compute.test_influence(la, interact_type=interact_type,
time_diff=t_window, time_scale=ord('w'), split_timestamp=split_timestamp,
#time_diff=100000, split_date_str="1970/06/23",
control_divider=0.01,
min_interactions_beforeaftersplit_per_user = min_interacts_beforeaftersplit_per_user,
max_tries = max_tries_val, max_node_computes=max_node_computes_val, num_processes=4,
max_interact_ratio_error=max_interact_ratio_error,
klim=klim_val,
method="influence")
print "t-test results", ttest_rel(inf_tuple[2], inf_tuple[3])
num_vals = len(inf_tuple[0])
f = open("influence_test", "w")
for i in range(num_vals):
f.write("%f\t%f\t%f\t%f\n" % (inf_tuple[0][i], inf_tuple[1][i],
inf_tuple[2][i], inf_tuple[3][i]))
f.close()
elif computation_cmd=="suscept_test":
use_artists = "songs" if "songs" in dataset_path else "artists"
interact_type_str = "listen" if interact_type==0 else "love"
#M = [50]#,20]#,30,40,50]
t_scale = ord('o') # ordinal scale, this is the default used in paper.
NUM_NODES_TO_COMPUTE = 4000000 # maximum number nodes to compute?
num_threads=4 # the number of threads to spawn
max_tries_val = None#30000 # should we stop after max_tries?
max_node_computes_val = NUM_NODES_TO_COMPUTE/num_threads # number of nodes to compute at each node
#max_interact_ratio_error =0.2 # these are errors (defaults are 0.1,0.1)
#max_sim_ratio_error = 0.2
#min_friends_match_ratio = 0.5 # important to be 1 for simulation--because e.g. in influence, we use a person's all friends to compute his next like
klim_val = None # not used for influence test
nonfr_match = "random" #random, serial, kbest. Default is random.
num_loop = 1 # number of times we calculate this. For averaging results over multiple runs.
f = open("suscept_test_results/"+dataset_domain + dataset_path.split("/")[-2] + interact_type_str+ strftime("%Y-%m-%d_%H:%M:%S")+'.dat', 'w')
f.write("# use_artists=%r\tallow_duplicates=%r\tmax_node_computes_val=%d\tcreate_fake_prefs=%r\tnum_loop=%d\n" % (
use_artists, allow_duplicates, max_node_computes_val,
create_fake_prefs, num_loop))
f.write("# split_train_test_date=%s\ttime_scale=%d\tmin_interactions_beforeaftersplit_per_user=%d\tnum_threads=%d\n" % (
split_date_str, t_scale, min_interacts_beforeaftersplit_per_user, num_threads))
f.write("# max_interact_ratio_error=%f\tmax_sim_ratio_error=%f\tmin_friends_match_ratio=%f\n" %(
max_interact_ratio_error, max_sim_ratio_error, min_friends_match_ratio
))
for t_window in M:
for h in range(num_loop):
f.write("\n\n################### ALERTINFO: STARTING ITERATION %d with M=%d\n" %( h, t_window))
if split_date_str=="test": split_timestamp = 2000
else:
split_timestamp = int(time.mktime(datetime.datetime.strptime(split_date_str, "%Y/%m/%d").timetuple()))
#split_timestamp=25000000
if create_fake_prefs is not None:
data.create_training_test_bytime(interact_type, split_timestamp)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
fake_data.generate_fake_preferences(data,interact_type, split_timestamp,
min_interactions_beforeaftersplit_per_user = min_interacts_beforeaftersplit_per_user,
time_window=t_window, time_scale=t_scale, method=create_fake_prefs)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
# Need to generate again because fake data changes test data
data.create_training_test_bytime(interact_type, split_timestamp, min_interactions_beforeaftersplit_per_user=min_interacts_beforeaftersplit_per_user)
la = LocalityAnalyzer(data)
inf_tuple = compute.test_influence(la, interact_type=interact_type,
time_diff=t_window, time_scale=t_scale, split_timestamp=split_timestamp,
#time_diff=100000, split_date_str="1970/06/23",
control_divider=0.01, # not used anymore
min_interactions_beforeaftersplit_per_user = min_interacts_beforeaftersplit_per_user,
max_tries = max_tries_val, max_node_computes=max_node_computes_val, num_threads=num_threads,
max_interact_ratio_error = max_interact_ratio_error,
max_sim_ratio_error = max_sim_ratio_error,
min_friends_match_ratio=min_friends_match_ratio,
klim = klim_val,
nonfr_match=nonfr_match,
method="suscept",
allow_duplicates=allow_duplicates)
print "t-test results", ttest_rel(inf_tuple[2], inf_tuple[3])
num_vals = len(inf_tuple[0])
f.write("TestSetSize\tFrSimilarity\tNonFrSimilarity\tFrOverlap\tNonFrOverlap\tRandom_run_no\tM\n")
for i in range(num_vals):
f.write("%d\t%f\t%f\t%f\t%f\t%d\t%d\n" % (inf_tuple[0][i], inf_tuple[1][i],
inf_tuple[2][i], inf_tuple[3][i], inf_tuple[4][i], h, t_window))
f.close()
elif computation_cmd=="gen_adopt_data":
t_window = 100
t_scale = ord('o')
if split_date_str=="test": split_timestamp = 2000
else:
split_timestamp = int(time.mktime(datetime.datetime.strptime(split_date_str, "%Y/%m/%d").timetuple()))
if create_fake_prefs is not None:
data.create_training_test_bytime(interact_type, split_timestamp)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
fake_data.generate_fake_preferences(data,interact_type, split_timestamp,
min_interactions_beforeaftersplit_per_user = min_interacts_beforeaftersplit_per_user,
time_window=t_window, time_scale=t_scale, method=create_fake_prefs)
data.create_training_test_bytime(interact_type, split_timestamp)
gen_adopt.generate_adoption_data(data, interact_type, split_timestamp,
min_interactions_beforeaftersplit_per_user=min_interacts_beforeaftersplit_per_user, time_window=t_window,
time_scale=t_scale)
elif computation_cmd=="compute_split_date":
ret_timestamp = compute.compute_cutoff_date(data, interact_type, traindata_fraction)
print ret_timestamp
print datetime.datetime.fromtimestamp(ret_timestamp*86400).strftime("%Y-%m-%d")
"""
def run_computation(data, computation_cmd, outf, interact_type,
create_fake_prefs, allow_duplicates, split_date_str,
dataset_domain, dataset_path,
min_interacts_beforeaftersplit_per_user,
max_interact_ratio_error, max_sim_ratio_error,
min_friends_match_ratio, traindata_fraction, M):
net_analyzer = BasicNetworkAnalyzer(data)
interaction_types = data.interact_types_dict
filename_prefix = computation_cmd if computation_cmd is not None else ""
if computation_cmd == "basic_stats" or computation_cmd is None:
net_analyzer.show_basic_stats()
## use below if you want to write a new dataset (e.g. after filtering)
data.store_ego_dataset(
"/home/amit/datasets/social_activity_data/lastfm_filtered_listen/",
write_maps=False)
#data.compute_allpairs_sim(interact_type, data_type=ord("a"))
elif computation_cmd == "random_similarity":
for type_name, type_index in interaction_types.iteritems():
circlesims, globalsims = net_analyzer.compare_circle_global_similarity(
type_index, num_random_trials=5, cutoff_rating=cutoff_rating)
#plotter.plotLinesYY(circlesims, globalsims, "Friends", "Global")
outf.write("User_id\tcircle_sim\tnonfriend_sim\n")
outf.write(type_name + '\n')
for ind in range(len(circlesims)):
outf.write("%s\t%f\t%f\n" %
(circlesims[ind][0], circlesims[ind][1],
globalsims[ind][1]))
print "\n", type_name, ":"
print "Circle Average", sum([v2 for v1, v2 in circlesims]) / float(
len(circlesims))
print "Global Average", sum([v2 for v1, v2 in globalsims]) / float(
len(globalsims))
elif computation_cmd == "knn_similarity":
#Compute K-nearest similarity
KLIMITS = [10]
outf.write("User_id\tk\tcircle_sim\tnonfriend_sim\n")
for type_name, type_index in interaction_types.iteritems():
for curr_lim in KLIMITS:
plot_circle, plot_external = net_analyzer.compare_circle_global_knnsimilarity(
type_index, klim=curr_lim, cutoff_rating=cutoff_rating)
compare_sims(plot_circle, plot_external)
outf.write(type_name + '\n')
for ind in range(len(plot_circle)):
outf.write("%s\t%d\t%f\t%f\n" %
(plot_circle[ind][0], curr_lim,
plot_circle[ind][1], plot_external[ind][1]))
#plotter.plotLinesYY(plot_circle, plot_external, "Friends", "Global")
print type_name, "K", curr_lim
print "Circle Average", utils.mean_sd(
[v2 for v1, v2 in plot_circle]), len(plot_circle)
print "Global Average", utils.mean_sd(
[v2 for v1, v2 in plot_external]), len(plot_external)
elif computation_cmd == "knn_recommender":
#Compute K-nearest recommender
KLIMITS = [10]
rec_analyzer = RecommenderAnalyzer(data,
max_recs_shown=10,
traintest_split=0.7,
cutoff_rating=cutoff_rating)
outf.write("User_id\tk\trun_index\tcircle_ndcg\tnonfriend_ndcg\n")
for type_name, type_index in interaction_types.iteritems():
for curr_lim in KLIMITS:
local_avg = []
global_avg = []
Ntotal = 10
for i in range(
Ntotal): # randomize because of training-test split.
plot_circle, plot_external = rec_analyzer.compare_knearest_recommenders(
type_index, klim=curr_lim, num_processes=2)
compare_sims(plot_circle, plot_external)
outf.write(type_name + "\n")
for ind in range(len(plot_circle)):
outf.write(
"%s\t%d\t%d\t%f\t%f\n" %
(plot_circle[ind][0], curr_lim, i,
plot_circle[ind][1], plot_external[ind][1]))
print "\n", type_name, "K", curr_lim
#print plot_circle, plot_external
curr_avg_local = utils.mean_sd(
[v2 for v1, v2 in plot_circle])
curr_avg_global = utils.mean_sd(
[v2 for v1, v2 in plot_external])
print "Circle Average", curr_avg_local
print "Global Average", curr_avg_global
local_avg.append(curr_avg_local[0])
global_avg.append(curr_avg_global[0])
#plotLinesYY(plot_circle, plot_external, "Friends", "Global")
print "Local", sum(local_avg) / float(Ntotal)
print "Global", sum(global_avg) / float(Ntotal)
elif computation_cmd == "circle_coverage":
lim_friends = [(5, 10), (10, 20), (20, 50), (50, 100)]
for fr_limit in lim_friends:
locality_analyzer = LocalityAnalyzer(data)
coverage_list = locality_analyzer.compare_circle_item_coverages(
0, fr_limit[0], fr_limit[1])
plotter.plotLineY(
sorted(coverage_list), "User",
"Fraction of Items Covered with %d-%d friends" %
(fr_limit[0], fr_limit[1]))
print utils.mean_sd(coverage_list)
elif computation_cmd == "items_edge_coverage":
locality_analyzer = LocalityAnalyzer(data)
items_cov_list, items_popularity, cov_ratio_list = locality_analyzer.compare_items_edge_coverage(
1, minimum_interactions=1)
print utils.mean_sd(items_cov_list)
print utils.mean_sd(items_popularity)
#plotter.plotHist(sorted([val for val in cov_ratio_list if val<=1]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#####plotter.plotHist(sorted([val for val in cov_ratio_list]), "Ratio of Edge coverage to total popularity", "Frequency", logyscale=True)
#plotter.plotHist(sorted(items_popularity), "Item", "total popularity")
plotter.plotCumulativePopularity(
items_popularity,
labelx="Item percentile",
labely="Cum. percent of number of likes")
elif computation_cmd == "network_draw":
net_visualizor = NetworkVisualizor(data)
net_visualizor.draw_network()
elif computation_cmd == "network_item_adopt":
net_visualizor = NetworkVisualizor(data)
pprint(net_visualizor.plot_item_adoption(1669118))
elif computation_cmd == "node_details":
for node_id in open('user_ids'):
if node_id.strip('\n') != "User_id":
net_analyzer.get_node_details(int(node_id.strip('\n')))
elif computation_cmd == "store_dataset":
user_interacts = net_analyzer.get_user_interacts(1, cutoff_rating)
f = open(outf_path + 'user_interacts_' + dataset_domain + '.tsv', 'w')
f.write("user_id\titem_id\ttimestamp\n")
for user_id, item_id, timestamp in user_interacts:
f.write("%s\t%s\t%s\n" % (user_id, item_id, timestamp))
f.close()
item_pop = net_analyzer.get_items_popularity(1, cutoff_rating)
f = open(outf_path + 'items_' + dataset_domain + '.tsv', 'w')
f.write("item_id\tpopularity\n")
for item_id, pop in item_pop.iteritems():
f.write("%s\t%s\n" % (item_id, pop))
f.close()
user_friends = net_analyzer.get_user_friends()
f = open('user_friends_' + dataset_domain + '.tsv', 'w')
f.write("user_id\tfriend_id\n")
for user_id, friend_id in user_friends:
f.write("%s\t%s\n" % (user_id, friend_id))
f.close()
print "Successfully stored tsv dataset"
elif computation_cmd == "compare_interact_types":
num_interacts_dict = net_analyzer.compare_interaction_types()
interact_types = num_interacts_dict.keys()
plotter.plotLinesYY(num_interacts_dict[interact_types[0]],
num_interacts_dict[interact_types[1]],
interact_types[0],
interact_types[1],
display=True,
logyscale=True)
plotter.plotLinesYY(num_interacts_dict[interact_types[1]],
num_interacts_dict[interact_types[2]],
interact_types[1],
interact_types[2],
display=True,
logyscale=True)
plotter.plotLinesYY(num_interacts_dict[interact_types[0]],
num_interacts_dict[interact_types[2]],
interact_types[0],
interact_types[2],
display=True,
logyscale=True)
elif computation_cmd == "influence_test":
# ta = TemporalAnalyzer(data)
#interact_type = data.interact_types_dict["listen"
# time_scale can be 'w':wallclock_time or 'o':ordinal_time
split_date_str = "2008/01/01"
t_window = -1
t_scale = ord('w')
max_tries_val = 10000
max_node_computes_val = 100
max_interact_ratio_error = 0.1
klim_val = 5
split_timestamp = int(
time.mktime(
datetime.datetime.strptime(split_date_str,
"%Y/%m/%d").timetuple()))
# crate trainig test sets that will be used by fake geernation
data.create_training_test_bytime(interact_type, split_timestamp)
if create_fake_prefs is not None:
print data.get_nodes_list()[1].get_interactions(interact_type,
cutoff_rating=-1)
fake_data.generate_fake_preferences(
data,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
time_window=t_window,
time_scale=t_scale,
method=create_fake_prefs)
#fake_data.generate_random_preferences(data, interact_type, split_timestamp)
print data.get_nodes_list()[1].get_interactions(interact_type,
cutoff_rating=-1)
# Need to generate again because fake data changes test data
data.create_training_test_bytime(interact_type, split_timestamp)
la = LocalityAnalyzer(data)
inf_tuple = compute.test_influence(
la,
interact_type=interact_type,
time_diff=t_window,
time_scale=ord('w'),
split_timestamp=split_timestamp,
#time_diff=100000, split_date_str="1970/06/23",
control_divider=0.01,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
max_tries=max_tries_val,
max_node_computes=max_node_computes_val,
num_processes=4,
max_interact_ratio_error=max_interact_ratio_error,
klim=klim_val,
method="influence")
print "t-test results", ttest_rel(inf_tuple[2], inf_tuple[3])
num_vals = len(inf_tuple[0])
f = open("influence_test", "w")
for i in range(num_vals):
f.write("%f\t%f\t%f\t%f\n" % (inf_tuple[0][i], inf_tuple[1][i],
inf_tuple[2][i], inf_tuple[3][i]))
f.close()
elif computation_cmd == "suscept_test":
use_artists = "songs" if "songs" in dataset_path else "artists"
interact_type_str = "listen" if interact_type == 0 else "love"
#M = [50]#,20]#,30,40,50]
t_scale = ord('o') # ordinal scale, this is the default used in paper.
NUM_NODES_TO_COMPUTE = 4000000 # maximum number nodes to compute?
num_threads = 4 # the number of threads to spawn
max_tries_val = None #30000 # should we stop after max_tries?
max_node_computes_val = NUM_NODES_TO_COMPUTE / num_threads # number of nodes to compute at each node
#max_interact_ratio_error =0.2 # these are errors (defaults are 0.1,0.1)
#max_sim_ratio_error = 0.2
#min_friends_match_ratio = 0.5 # important to be 1 for simulation--because e.g. in influence, we use a person's all friends to compute his next like
klim_val = None # not used for influence test
nonfr_match = "random" #random, serial, kbest. Default is random.
num_loop = 1 # number of times we calculate this. For averaging results over multiple runs.
f = open(
"suscept_test_results/" + dataset_domain +
dataset_path.split("/")[-2] + interact_type_str +
strftime("%Y-%m-%d_%H:%M:%S") + '.dat', 'w')
f.write(
"# use_artists=%r\tallow_duplicates=%r\tmax_node_computes_val=%d\tcreate_fake_prefs=%r\tnum_loop=%d\n"
% (use_artists, allow_duplicates, max_node_computes_val,
create_fake_prefs, num_loop))
f.write(
"# split_train_test_date=%s\ttime_scale=%d\tmin_interactions_beforeaftersplit_per_user=%d\tnum_threads=%d\n"
% (split_date_str, t_scale,
min_interacts_beforeaftersplit_per_user, num_threads))
f.write(
"# max_interact_ratio_error=%f\tmax_sim_ratio_error=%f\tmin_friends_match_ratio=%f\n"
% (max_interact_ratio_error, max_sim_ratio_error,
min_friends_match_ratio))
for t_window in M:
for h in range(num_loop):
f.write(
"\n\n################### ALERTINFO: STARTING ITERATION %d with M=%d\n"
% (h, t_window))
if split_date_str == "test": split_timestamp = 2000
else:
split_timestamp = int(
time.mktime(
datetime.datetime.strptime(
split_date_str, "%Y/%m/%d").timetuple()))
#split_timestamp=25000000
if create_fake_prefs is not None:
data.create_training_test_bytime(interact_type,
split_timestamp)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
fake_data.generate_fake_preferences(
data,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
time_window=t_window,
time_scale=t_scale,
method=create_fake_prefs)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
# Need to generate again because fake data changes test data
data.create_training_test_bytime(
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user)
la = LocalityAnalyzer(data)
inf_tuple = compute.test_influence(
la,
interact_type=interact_type,
time_diff=t_window,
time_scale=t_scale,
split_timestamp=split_timestamp,
#time_diff=100000, split_date_str="1970/06/23",
control_divider=0.01, # not used anymore
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
max_tries=max_tries_val,
max_node_computes=max_node_computes_val,
num_threads=num_threads,
max_interact_ratio_error=max_interact_ratio_error,
max_sim_ratio_error=max_sim_ratio_error,
min_friends_match_ratio=min_friends_match_ratio,
klim=klim_val,
nonfr_match=nonfr_match,
method="suscept",
allow_duplicates=allow_duplicates)
print "t-test results", ttest_rel(inf_tuple[2], inf_tuple[3])
num_vals = len(inf_tuple[0])
f.write(
"TestSetSize\tFrSimilarity\tNonFrSimilarity\tFrOverlap\tNonFrOverlap\tRandom_run_no\tM\n"
)
for i in range(num_vals):
f.write("%d\t%f\t%f\t%f\t%f\t%d\t%d\n" %
(inf_tuple[0][i], inf_tuple[1][i], inf_tuple[2][i],
inf_tuple[3][i], inf_tuple[4][i], h, t_window))
f.close()
elif computation_cmd == "gen_adopt_data":
t_window = 100
t_scale = ord('o')
if split_date_str == "test": split_timestamp = 2000
else:
split_timestamp = int(
time.mktime(
datetime.datetime.strptime(split_date_str,
"%Y/%m/%d").timetuple()))
if create_fake_prefs is not None:
data.create_training_test_bytime(interact_type, split_timestamp)
#print data.get_nodes_list()[1].get_interactions(interact_type, cutoff_rating=-1)
fake_data.generate_fake_preferences(
data,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
time_window=t_window,
time_scale=t_scale,
method=create_fake_prefs)
data.create_training_test_bytime(interact_type, split_timestamp)
gen_adopt.generate_adoption_data(
data,
interact_type,
split_timestamp,
min_interactions_beforeaftersplit_per_user=
min_interacts_beforeaftersplit_per_user,
time_window=t_window,
time_scale=t_scale)
elif computation_cmd == "compute_split_date":
ret_timestamp = compute.compute_cutoff_date(data, interact_type,
traindata_fraction)
print ret_timestamp
print datetime.datetime.fromtimestamp(ret_timestamp *
86400).strftime("%Y-%m-%d")
"""