def run():
"""Contains the main logic for this analysis."""
global _SIZE_TOP_NEWS
FileLog.set_log_dir()
seeds = Util.load_seeds()
for category in _CATEGORIES:
log('Preforming analysis for category: %s' % category)
if category:
_SIZE_TOP_NEWS = .10
else:
_SIZE_TOP_NEWS = .02
gt_rankings = ground_truths.get_gt_rankings(seeds, DataSet.TESTING,
category)
log('Num ground_truth_rankings: %s' % len(gt_rankings))
target_news = ground_truths.find_target_news(gt_rankings, _SIZE_TOP_NEWS)
log('Size target_news: %s' % len(target_news))
# for delta in _DELTAS:
for delta in [4]:
run_params_str = 'd%s_t%s_e%s_%s' % (delta, int(_SIZE_TOP_NEWS * 100),
int(_SIZE_EXPERTS * 100), category)
output_dir = '../graph/CrowdWisdomDef/%s/' % run_params_str
Util.ensure_dir_exist(output_dir)
info_output_dir = '../graph/CrowdWisdomDef/%s/info/' % run_params_str
Util.ensure_dir_exist(info_output_dir)
output_dir = '../graph/CrowdWisdomDef/%s/' % run_params_str
Util.ensure_dir_exist(output_dir)
(num_users, newsaholics,
active_users, common_users) = basic_groups.group_users(delta, category)
log('Num newsaholics: %s' % len(newsaholics))
log('Num active: %s' % len(active_users))
log('Num common: %s' % len(common_users))
common_user_buckets = common_user_groups.group_users(common_users, _NUM_GROUPS)
for i, common_user_bucket in enumerate(common_user_buckets):
print 'Number users in common user bucket %s: %s' % (i, len(common_user_bucket))
experts_precision = experts.select_experts_precision(
newsaholics.union(active_users), num_users, delta, _SIZE_EXPERTS,
category)
experts_fscore = experts.select_experts_fscore(len(target_news),
num_users,
delta, _SIZE_EXPERTS,
category)
experts_ci = experts.select_experts_ci(num_users, delta, _SIZE_EXPERTS,
category)
super_experts = experts.select_super_experts(experts_precision,
experts_fscore,
experts_ci)
log('Num experts (precision): %s' % len(experts_precision))
log('Num experts (fscore): %s' % len(experts_fscore))
log('Num experts (ci): %s' % len(experts_ci))
log('Finding rankings with an %s hour delta.' % delta)
(market_rankings, newsaholic_rankings,
active_rankings,
common_rankings) = basic_groups.get_rankings(delta, seeds, newsaholics,
active_users, category)
(expert_precision_rankings, expert_fscore_rankings,
expert_ci_rankings,
expert_s_rankings) = experts.get_rankings(delta, seeds,
experts_precision,
experts_fscore,
experts_ci,
super_experts,
category)
common_groups_rankings = common_user_groups.get_rankings(delta, seeds,
common_user_buckets,
category)
num_votes_common = 0
for url, count in common_rankings:
num_votes_common += count
log('Num common_rankings: %s' % len(common_rankings))
log('Num common votes: %s' % num_votes_common)
num_votes_expert_precision = 0
for url, count in expert_precision_rankings:
num_votes_expert_precision += count
log('Num expert_precision rankings: %s' % len(expert_precision_rankings))
log('Num expert_precision votes: %s' % num_votes_expert_precision)
num_votes_expert_fscore = 0
for url, count in expert_fscore_rankings:
num_votes_expert_fscore += count
log('Num expert_fscore rankings: %s' % len(expert_fscore_rankings))
log('Num expert_fscore votes: %s' % num_votes_expert_fscore)
num_votes_expert_ci = 0
for url, count in expert_ci_rankings:
num_votes_expert_ci += count
log('Num expert_ci rankings: %s' % len(expert_ci_rankings))
log('Num expert_ci votes: %s' % num_votes_expert_ci)
num_votes_buckets = []
for i, common_group_rankings in enumerate(common_groups_rankings):
num_votes = 0
for url, count in common_group_rankings:
num_votes += count
num_votes_buckets.append(num_votes)
log('Num common rankings (%s buckets): %s' % (i, len(common_group_rankings)))
log('Num expert_ci votes (%s buckets): %s' % (i, num_votes))
with open('%suser_demographics_%s.txt'
% (info_output_dir, run_params_str), 'w') as output_file:
output_file.write('Number of Common Users: %s\n' % len(common_users))
output_file.write('\n');
output_file.write('Number of Precision Experts: %s\n' % len(experts_precision))
output_file.write('Number of F-Score Experts: %s\n' % len(experts_fscore))
output_file.write('Number of CI Experts: %s\n' % len(experts_ci))
output_file.write('Number users per common user bucket: %s\n' %len(common_user_buckets[0]))
output_file.write('Number of Precision and F-Score Experts: %s\n'
% len(experts_precision.intersection(experts_fscore)))
output_file.write('Number of Precision and CI Experts: %s\n'
% len(experts_precision.intersection(experts_ci)))
output_file.write('Number of F-Score and CI Experts: %s\n'
% len(experts_fscore.intersection(experts_ci)))
output_file.write('\n');
output_file.write('Number of Users (Total): %s\n'
% (len(newsaholics) + len(active_users)
+ len(common_users)))
output_file.write('\n')
output_file.write('Number of votes by Common Users: %s\n'
% num_votes_common)
output_file.write('\n');
output_file.write('Number of votes by Expert (Precision) Users: %s\n'
% num_votes_expert_precision)
output_file.write('Number of votes by Expert (fscore) Users: %s\n'
% num_votes_expert_fscore)
output_file.write('Number of votes by Expert (ci) Users: %s\n'
% num_votes_expert_ci)
output_file.write('Number of votes per bucket: %s\n' % num_votes_buckets)
output_file.write('\n')
output_file.write('Total Number of Good News: %s\n' % len(target_news))
log('Ground Truth Top 5')
for i in range(min(len(gt_rankings), 5)):
url, count = gt_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Common Top 5')
for i in range(min(len(common_rankings), 5)):
url, count = common_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (Precision) Top 5')
for i in range(min(len(expert_precision_rankings), 5)):
url, count = expert_precision_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (fscore) Top 5')
for i in range(min(len(expert_fscore_rankings), 5)):
url, count = expert_fscore_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (ci) Top 5')
for i in range(min(len(expert_ci_rankings), 5)):
url, count = expert_ci_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
common_precisions, common_recalls = calc_precision_recall(gt_rankings,
common_rankings)
(expert_p_precisions,
expert_p_recalls) = calc_precision_recall(gt_rankings,
expert_precision_rankings)
(expert_f_precisions,
expert_f_recalls) = calc_precision_recall(gt_rankings,
expert_fscore_rankings)
(expert_c_precisions,
expert_c_recalls) = calc_precision_recall(gt_rankings,
expert_ci_rankings)
common_group_ps = []
common_group_rs = []
for common_group_ranking in common_groups_rankings:
common_group_p, common_group_r = calc_precision_recall(gt_rankings,
common_group_ranking)
common_group_ps.append(common_group_p)
common_group_rs.append(common_group_r)
log('Drawing common group model precision-recall graph...')
common_user_groups.draw_precision_recall(common_group_ps, common_group_rs,
expert_p_precisions, expert_p_recalls,
expert_f_precisions, expert_f_recalls,
expert_c_precisions, expert_c_recalls,
run_params_str)
log('Drawing common group model precision graph...')
common_user_groups.draw_precision(common_group_ps, expert_p_precisions,
expert_f_precisions, expert_c_precisions,
run_params_str)
def get_all_user_groups(delta=4, category=None):
seeds = Util.load_seeds()
# Set up params appropriately.
data_set = DataSet.TRAINING
months = _TRAINING_SET_MONTHS
if _SWITCHED:
data_set = DataSet.TESTING
months = _TESTING_SET_MONTHS
retweets = set()
if _EXCLUDE_RETWEETS:
retweets = ground_truths.find_retweets(months)
gt_rankings = ground_truths.get_gt_rankings(seeds, data_set, category,
exclude_tweets_within_delta=_EXCLUDE_TWEETS_WITHIN_DELTA,
retweets=retweets)
target_news = ground_truths.find_target_news(gt_rankings, _SIZE_TOP_NEWS)
groups = UserGroups()
(num_users, groups.newsaholics,
groups.active_users,
groups.common_users) = basic_groups.group_users(delta, category)
groups.population = groups.newsaholics.union(groups.active_users).union(groups.common_users)
num_users_eg, groups.even_groups = even_groups.group_users(delta,
_NUM_GROUPS,
_SIZE_OF_GROUP_IN_PERCENT,
category)
groups.precision = experts.select_experts_precision(
groups.newsaholics.union(groups.active_users), num_users, delta,
_SIZE_EXPERTS, category)
groups.fscore = experts.select_experts_fscore(len(target_news),
num_users,
delta, _SIZE_EXPERTS,
category)
groups.ci = experts.select_experts_ci(num_users, delta, _SIZE_EXPERTS,
category)
groups.super_experts = experts.select_super_experts(groups.precision,
groups.fscore,
groups.ci)
groups.ci_hi, groups.ci_li = experts.split_ci_experts_by_followers(groups.ci)
groups.ci_1 = set()
groups.ci_2 = set()
groups.ci_3 = set()
counter = 0
for ci_expert in groups.ci:
if counter % 3 == 0:
groups.ci_1.add(ci_expert)
elif counter % 3 == 1:
groups.ci_2.add(ci_expert)
elif counter % 3 == 2:
groups.ci_3.add(ci_expert)
counter += 1
groups.social_bias, d_num_followers = experts.select_experts_social_bias(num_users,
_SIZE_EXPERTS)
groups.all_experts = experts.select_all_experts(groups.precision,
groups.fscore,
groups.ci)
groups.non_experts = groups.population.difference(groups.all_experts)
sample_size = int(len(groups.non_experts) * _NON_EXPERTS_SAMPLE_SIZE)
sample_size_25 = int(len(groups.non_experts) * 0.05)
sample_size_10 = int(len(groups.non_experts) * 0.10)
sample_size_1 = int(len(groups.non_experts) * 0.02)
groups.non_experts_sampled = set(random.sample(groups.non_experts, sample_size))
groups.non_experts_25 = set(random.sample(groups.non_experts, sample_size_25))
groups.non_experts_10 = set(random.sample(groups.non_experts, sample_size_10))
groups.non_experts_1 = set(random.sample(groups.non_experts, sample_size_1))
return groups, d_num_followers
