def glassCeil(DATAPATH2,
binss,
edgelist,
gc_File,
organic,
type2=False,
ccdfflag=False):
gender, race = read_instagram_genrace(DATAPATH2 + 'london.genrace')
if not organic:
for i in range(5):
print "Iteration ", i
DATAPATH = DATAPATH2 + str(i) + "/"
nxgraph = nx.read_edgelist(DATAPATH + edgelist,
nodetype=int) #, delimiter=',',
get_degree_dist(DATAPATH, nxgraph, binss, gender, gc_File, type2,
ccdfflag)
if organic:
nxgraph = read_nxgraph(DATAPATH2 + edgelist) # , delimiter=',',
get_degree_dist(DATAPATH2, nxgraph, binss, gender, gc_File, type2,
ccdfflag)
def glassCeil_race(DATAPATH2, binss, edgelist, gc_File, organic):
genderdict, racedict = read_instagram_genrace(DATAPATH2 + 'london.genrace')
if not organic:
for it in range(5):
print "Iteration ", it
DATAPATH = DATAPATH2 + str(it) + "/"
nxgraph = nx.read_edgelist(DATAPATH + edgelist,
nodetype=int) # , delimiter=',',
get_degree_dist_race(DATAPATH2, nxgraph, binss, racedict, gc_File)
elif organic:
nxgraph = read_nxgraph(DATAPATH2 + edgelist)
print DATAPATH2 + edgelist
print "nxgraph.number_of_edges", nxgraph.number_of_edges()
get_degree_dist_race(DATAPATH2, nxgraph, binss, racedict, gc_File)
import sys
sys.path.append("../../src/")
from graph_utils import read_instagram_genrace
from dataset_utils import make_5_recofiles #, make_5_trainfilesmake_5_testfiles,
from bias_metrics import sort_Reco, write_topRecos, count_race_groups # , getROCs_race, grow, glassCeil, get_degree_dist # , get_bias_genrace,get_degree_dist, get_accuracies, get_Equality_opportunity, get_Disparate_impact
DATAPATH = "../../data/la/"
gender, race = read_instagram_genrace(DATAPATH + 'la.genrace')
#make_5_trainfiles(gender, DATAPATH)
##### Branch 1 ##########
#make_5_recofiles(gender, DATAPATH,embfile='known_80_80_20_128.emb', pickfile_frn="known_80_top100.pick", pickfile_str="known_80_rand.pick", testfile_suffix= "hada_100_test.csv")
make_5_recofiles(gender,
DATAPATH,
embfile='known_80_raceeq_80_20_128.emb',
pickfile_frn="known_80_raceeq_top100.pick",
pickfile_str="known_80_rand.pick",
testfile_suffix="hada_100_test_raceeq.csv")
#sort_Reco(DATAPATH, testfile= "hada_100_test.csv", reco_file= "recommendations_1.csv")
sort_Reco(DATAPATH,
testfile="hada_100_test_raceeq.csv",
reco_file="recommendations_raceeq.csv")
#write_topRecos(DATAPATH, growtharr=[0.20], testfile="hada_100_test_2.csv", reco_file= "recommendations.csv", toprecofile="_topRecos.edgelist")
write_topRecos(DATAPATH,
growtharr=[0.20],
testfile="hada_100_test_raceeq.csv",
def get_bias_genrace(DATAPATH, recofile, k_arr):
df = pd.read_csv(DATAPATH + recofile)
gender, race = read_instagram_genrace(DATAPATH + "london.genrace")
grouped = df.groupby(['u'])
arr = []
count_df_arr = []
for u, group in grouped:
in_arr = [u, gender[u], race[u]]
for k in k_arr:
if gender[u] == -1 and race[u] == -1:
in_arr.extend([-1, -1, -1, -1, -1, -1])
arr.append(in_arr)
continue
gen_K, race_K = 0, 0
same_gen_ctr, fem_ctr, same_race_ctr, race_ctr_0, race_ctr_1, race_ctr_2 = 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
for u2 in group.v:
if gender[u2] != -1:
gen_K += 1
if (gen_K == k):
break
if (gender[u] == gender[u2]):
same_gen_ctr += 1
if (gender[u2] == 1): #if female friend
fem_ctr += 1
if race[u2] != -1:
race_K += 1
if (race_K == k):
break
if (race[u] == race[u2]):
same_race_ctr += 1
if (race[u2] == 0):
race_ctr_0 += 1
if (race[u2] == 1):
race_ctr_1 += 1
if (race[u2] == 2):
race_ctr_2 += 1
if gen_K == 0 or gender[u] == -1:
same_gen_ctr, fem_ctr = -1, -1
else:
same_gen_ctr /= gen_K
fem_ctr /= gen_K
if race_K == 0 or race[u] == -1:
same_race_ctr, race_ctr_0, race_ctr_1, race_ctr_2 = -1, -1, -1, -1
else:
same_race_ctr /= race_K
race_ctr_0 /= race_K
race_ctr_1 /= race_K
race_ctr_2 /= race_K
in_arr.extend([
same_gen_ctr, fem_ctr, same_race_ctr, race_ctr_0, race_ctr_1,
race_ctr_2
])
count_df_arr.append([u, k, gen_K, race_K])
arr.append(in_arr)
bias_df = pd.DataFrame(
data=arr,
columns=[
'u', 'gender[u]', 'race[u]', 'sup_same_gen_bias100',
'sup_fem_gen_bias100', 'sup_same_race_bias100',
'sup_0_race_bias100', 'sup_1_race_bias100', 'sup_2_race_bias100',
'sup_same_gen_bias50', 'sup_fem_gen_bias50',
'sup_same_race_bias50', 'sup_0_race_bias50', 'sup_1_race_bias50',
'sup_2_race_bias50', 'sup_same_gen_bias10', 'sup_fem_gen_bias10',
'sup_same_race_bias10', 'sup_0_race_bias10', 'sup_1_race_bias10',
'sup_2_race_bias10'
])
bias_df.to_csv(DATAPATH + "sup_bias_250.csv")
count_df = pd.DataFrame(data=count_df_arr,
columns=['u', 'top_k', 'gen_K', 'race_K'])
count_df.to_csv(DATAPATH + "size_non-neg_users_250.csv")
def get_bias_json(DATAPATH, k_arr):
for filename in ["top100cos.json", "top100euc.json"]:
arr = read_json(DATAPATH + filename)
gender, race = read_instagram_genrace(DATAPATH + "london.genrace")
outer_arr = []
count_df_arr = []
for u in range(len(arr)):
in_arr = [u, gender[u], race[u]]
for k in k_arr:
gen_K, race_K = 0, 0
same_gen_ctr, fem_ctr, same_race_ctr, race_ctr_0, race_ctr_1, race_ctr_2 = 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
for u2, prob in arr[u]:
if gender[u2] != -1:
gen_K += 1
if (gen_K == k):
break
if (gender[u] == gender[u2]):
same_gen_ctr += 1
if (gender[u2] == 1): # if female friend
fem_ctr += 1
if race[u2] != -1:
race_K += 1
if (race_K == k):
break
if (race[u] == race[u2]):
same_race_ctr += 1
if (race[u2] == 0):
race_ctr_0 += 1
if (race[u2] == 1):
race_ctr_1 += 1
if (race[u2] == 2):
race_ctr_2 += 1
same_gen_ctr /= gen_K
fem_ctr /= gen_K
same_race_ctr /= race_K
race_ctr_0 /= race_K
race_ctr_1 /= race_K
race_ctr_2 /= race_K
in_arr.extend([
same_gen_ctr, fem_ctr, same_race_ctr, race_ctr_0,
race_ctr_1, race_ctr_2
])
count_df_arr.append([u, k, gen_K, race_K])
outer_arr.append(in_arr)
bias_df = pd.DataFrame(
data=arr,
columns=[
'u', 'gender[u]', 'race[u]', 'sup_same_gen_bias100',
'sup_fem_gen_bias100', 'sup_same_race_bias100',
'sup_0_race_bias100', 'sup_1_race_bias100',
'sup_2_race_bias100', 'sup_same_gen_bias50',
'sup_fem_gen_bias50', 'sup_same_race_bias50',
'sup_0_race_bias50', 'sup_1_race_bias50', 'sup_2_race_bias50',
'sup_same_gen_bias10', 'sup_fem_gen_bias10',
'sup_same_race_bias10', 'sup_0_race_bias10',
'sup_1_race_bias10', 'sup_2_race_bias10'
])
bias_df.to_csv(DATAPATH + "unsup_bias.csv")
count_df = pd.DataFrame(data=count_df_arr,
columns=['u', 'top_k', 'gen_K', 'race_K'])
count_df.to_csv(DATAPATH + "size_non-neg_users.csv")