Skip to content

Commit

Permalink
new experiments
Browse files Browse the repository at this point in the history
  • Loading branch information
@kfoynt
kfoynt committed Sep 21, 2019
1 parent 051b97b commit 97b79bf
Showing 1 changed file with 111 additions and 111 deletions.
222 changes: 111 additions & 111 deletions ...stical_guarantees_paper_experiments/statistical_guarantees_paper_COLGATE88_experiments.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -59,154 +59,154 @@
print("Cluster: ", counter, " conductance: ", cond, "Size: ", len(cluster), " Volume: ", np.sum(g.d[cluster]))
all_clusters.append(cluster)

# ## Collect data for ACL (with rounding)
## Collect data for ACL (with rounding)

# nodes = {}
# external_best_cond_acl = {}
# external_best_pre_cond_acl = {}
# vol_best_cond_acl = {}
# vol_best_pre_acl = {}
# size_clust_best_cond_acl = {}
# size_clust_best_pre_acl = {}
# f1score_best_cond_acl = {}
# f1score_best_pre_acl = {}
# true_positives_best_cond_acl = {}
# true_positives_best_pre_acl = {}
# precision_best_cond_acl = {}
# precision_best_pre_acl = {}
# recall_best_cond_acl = {}
# recall_best_pre_acl = {}
# cuts_best_cond_acl = {}
# cuts_best_pre_acl = {}
# cuts_acl_ALL = {}
nodes = {}
external_best_cond_acl = {}
external_best_pre_cond_acl = {}
vol_best_cond_acl = {}
vol_best_pre_acl = {}
size_clust_best_cond_acl = {}
size_clust_best_pre_acl = {}
f1score_best_cond_acl = {}
f1score_best_pre_acl = {}
true_positives_best_cond_acl = {}
true_positives_best_pre_acl = {}
precision_best_cond_acl = {}
precision_best_pre_acl = {}
recall_best_cond_acl = {}
recall_best_pre_acl = {}
cuts_best_cond_acl = {}
cuts_best_pre_acl = {}
cuts_acl_ALL = {}

# ct_outer = 0
ct_outer = 0

# number_experiments = 0
number_experiments = 0

# for rr in all_clusters:
for rr in all_clusters:

# how_many = int(len(rr))
# print(how_many)
how_many = int(len(rr))
print(how_many)

# random.seed(4)
random.seed(4)

# nodes[ct_outer] = np.random.choice(rr, how_many, replace=False)
nodes[ct_outer] = np.random.choice(rr, how_many, replace=False)

# eigv, lambda_val = fiedler_local(g, rr)
# lambda_val = np.real(lambda_val)
eigv, lambda_val = fiedler_local(g, rr)
lambda_val = np.real(lambda_val)

# step = (2*lambda_val - lambda_val/2)/4
step = (2*lambda_val - lambda_val/2)/4

# a_list = np.arange(lambda_val/2,2*lambda_val,step)
a_list = np.arange(lambda_val/2,2*lambda_val,step)

# ct = 0
ct = 0

# start = time.time()
start = time.time()

# for node in nodes[ct_outer]:
# ref_node = [node]
for node in nodes[ct_outer]:
ref_node = [node]

# max_precision = -1
# min_conduct = 100
max_precision = -1
min_conduct = 100

# ct_inner = 0
# for a in a_list:
ct_inner = 0
for a in a_list:

# if ct_outer <= 1:
# rho = 0.15/np.sum(g.d[rr])
# else:
# rho = 0.2/np.sum(g.d[rr])
if ct_outer <= 1:
rho = 0.10/np.sum(g.d[rr])
else:
rho = 0.15/np.sum(g.d[rr])

# output_pr_clustering = approximate_PageRank(g,ref_node,method = "acl", rho=rho, alpha=a, cpp = True, normalize=True,normalized_objective=True)
# number_experiments += 1
output_pr_clustering = approximate_PageRank(g,ref_node,method = "acl", rho=rho, alpha=a, cpp = True, normalize=True,normalized_objective=True)
number_experiments += 1

# output_pr_sc = sweep_cut(g,output_pr_clustering,cpp=True)
output_pr_sc = sweep_cut(g,output_pr_clustering,cpp=True)

# S = output_pr_sc[0]
S = output_pr_sc[0]

# cuts_acl_ALL[ct_outer,node,ct_inner] = S
cuts_acl_ALL[ct_outer,node,ct_inner] = S

# size_clust_acl_ = len(S)
size_clust_acl_ = len(S)

# cond_val_l1pr = g.compute_conductance(S)
cond_val_l1pr = g.compute_conductance(S)

# vol_ = sum(g.d[S])
# true_positives_acl_ = set(rr).intersection(S)
# if len(true_positives_acl_) == 0:
# true_positives_acl_ = set(ref_node)
# vol_ = g.d[ref_node][0,0]
# precision = sum(g.d[np.array(list(true_positives_acl_))])/vol_
# recall = sum(g.d[np.array(list(true_positives_acl_))])/sum(g.d[rr])
# f1_score_ = 2*(precision*recall)/(precision + recall)
vol_ = sum(g.d[S])
true_positives_acl_ = set(rr).intersection(S)
if len(true_positives_acl_) == 0:
true_positives_acl_ = set(ref_node)
vol_ = g.d[ref_node][0,0]
precision = sum(g.d[np.array(list(true_positives_acl_))])/vol_
recall = sum(g.d[np.array(list(true_positives_acl_))])/sum(g.d[rr])
f1_score_ = 2*(precision*recall)/(precision + recall)

# if f1_score_ >= max_precision:
if f1_score_ >= max_precision:

# max_precision = f1_score_
max_precision = f1_score_

# external_best_pre_cond_acl[ct_outer,node] = cond_val_l1pr
# vol_best_pre_acl[ct_outer,node] = vol_
external_best_pre_cond_acl[ct_outer,node] = cond_val_l1pr
vol_best_pre_acl[ct_outer,node] = vol_

# size_clust_best_pre_acl[ct_outer,node] = size_clust_acl_
# true_positives_best_pre_acl[ct_outer,node] = true_positives_acl_
# precision_best_pre_acl[ct_outer,node] = precision
# recall_best_pre_acl[ct_outer,node] = recall
# f1score_best_pre_acl[ct_outer,node] = f1_score_
size_clust_best_pre_acl[ct_outer,node] = size_clust_acl_
true_positives_best_pre_acl[ct_outer,node] = true_positives_acl_
precision_best_pre_acl[ct_outer,node] = precision
recall_best_pre_acl[ct_outer,node] = recall
f1score_best_pre_acl[ct_outer,node] = f1_score_

# cuts_best_pre_acl[ct_outer,node] = S
cuts_best_pre_acl[ct_outer,node] = S

# if cond_val_l1pr <= min_conduct:
if cond_val_l1pr <= min_conduct:

# min_conduct = cond_val_l1pr
min_conduct = cond_val_l1pr

# external_best_cond_acl[ct_outer,node] = cond_val_l1pr
# vol_best_cond_acl[ct_outer,node] = vol_
external_best_cond_acl[ct_outer,node] = cond_val_l1pr
vol_best_cond_acl[ct_outer,node] = vol_

# size_clust_best_cond_acl[ct_outer,node] = size_clust_acl_
# true_positives_best_cond_acl[ct_outer,node] = true_positives_acl_
# precision_best_cond_acl[ct_outer,node] = precision
# recall_best_cond_acl[ct_outer,node] = recall
# f1score_best_cond_acl[ct_outer,node] = f1_score_
size_clust_best_cond_acl[ct_outer,node] = size_clust_acl_
true_positives_best_cond_acl[ct_outer,node] = true_positives_acl_
precision_best_cond_acl[ct_outer,node] = precision
recall_best_cond_acl[ct_outer,node] = recall
f1score_best_cond_acl[ct_outer,node] = f1_score_

# cuts_best_cond_acl[ct_outer,node] = S
cuts_best_cond_acl[ct_outer,node] = S

# print('outer:', ct_outer, 'number of node: ',node, ' completed: ', ct/how_many, ' degree: ', g.d[node])
# print('conductance: ', external_best_cond_acl[ct_outer,node], 'f1score: ', f1score_best_cond_acl[ct_outer,node], 'precision: ', precision_best_cond_acl[ct_outer,node], 'recall: ', recall_best_cond_acl[ct_outer,node])
# ct += 1
# end = time.time()
# print(" ")
# print("Outer: ", ct_outer," Elapsed time ACL with rounding: ", end - start)
# print("Outer: ", ct_outer," Number of experiments: ", number_experiments)
# print(" ")
# ct_outer += 1
print('outer:', ct_outer, 'number of node: ',node, ' completed: ', ct/how_many, ' degree: ', g.d[node])
print('conductance: ', external_best_cond_acl[ct_outer,node], 'f1score: ', f1score_best_cond_acl[ct_outer,node], 'precision: ', precision_best_cond_acl[ct_outer,node], 'recall: ', recall_best_cond_acl[ct_outer,node])
ct += 1
end = time.time()
print(" ")
print("Outer: ", ct_outer," Elapsed time ACL with rounding: ", end - start)
print("Outer: ", ct_outer," Number of experiments: ", number_experiments)
print(" ")
ct_outer += 1

# ## Performance of ACL (with rounding).
## Performance of ACL (with rounding).

# all_data = []
# xlabels_ = []
all_data = []
xlabels_ = []

# print('Results for ACL with rounding')
# sum_precision = 0
# sum_recall = 0
# sum_f1 = 0
# sum_conductance = 0
print('Results for ACL with rounding')
sum_precision = 0
sum_recall = 0
sum_f1 = 0
sum_conductance = 0

# info_ref_nodes = all_clusters
# l_info_ref_nodes = len(info_ref_nodes)
info_ref_nodes = all_clusters
l_info_ref_nodes = len(info_ref_nodes)

# for i in range(l_info_ref_nodes):
# temp_pre = []
# temp_rec = []
# temp_f1 = []
# temp_conductance = []
for i in range(l_info_ref_nodes):
temp_pre = []
temp_rec = []
temp_f1 = []
temp_conductance = []

# for j in all_clusters[i]:
# temp_pre.append(precision_best_cond_acl[i,j])
# temp_rec.append(recall_best_cond_acl[i,j])
# temp_f1.append(f1score_best_cond_acl[i,j])
# temp_conductance.append(external_best_cond_acl[i,j])
for j in all_clusters[i]:
temp_pre.append(precision_best_cond_acl[i,j])
temp_rec.append(recall_best_cond_acl[i,j])
temp_f1.append(f1score_best_cond_acl[i,j])
temp_conductance.append(external_best_cond_acl[i,j])

# print('Feature:', i,'Precision', stat_.mean(temp_pre), 'Recall', stat_.mean(temp_rec), 'F1', stat_.mean(temp_f1), 'Cond.', stat_.mean(temp_conductance))
print('Feature:', i,'Precision', stat_.mean(temp_pre), 'Recall', stat_.mean(temp_rec), 'F1', stat_.mean(temp_f1), 'Cond.', stat_.mean(temp_conductance))



Expand Down Expand Up @@ -617,9 +617,9 @@ def seed_grow_bfs_steps(g,seeds,steps,vol_target,target_cluster):
for a in a_list:

if ct_outer <= 1:
rho = 0.15/np.sum(g.d[rr])
rho = 0.10/np.sum(g.d[rr])
else:
rho = 0.2/np.sum(g.d[rr])
rho = 0.15/np.sum(g.d[rr])

output_pr_clustering = approximate_PageRank(g,ref_node,method = "acl", rho=rho, alpha=a, cpp = True, normalize=True,normalized_objective=True)
number_experiments += 1
Expand Down Expand Up @@ -783,9 +783,9 @@ def seed_grow_bfs_steps(g,seeds,steps,vol_target,target_cluster):
for a in a_list:

if ct_outer <= 1:
rho = 0.15/np.sum(g.d[rr])
rho = 0.10/np.sum(g.d[rr])
else:
rho = 0.2/np.sum(g.d[rr])
rho = 0.15/np.sum(g.d[rr])

output_pr_clustering = approximate_PageRank(g,ref_node,method = "l1reg-rand", epsilon=1.0e-2, rho=rho, alpha=a, cpp = True, normalize=True,normalized_objective=True,iterations=1000000)
number_experiments += 1
Expand Down

0 comments on commit 97b79bf

Please sign in to comment.