def run():
"""Main logic. Outputs data in format for further analysis."""
global _OUT_DIR
cache = Util.load_cache()
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
_OUT_DIR += 'switched/'
retweets = set()
if _EXCLUDE_RETWEETS:
retweets = ground_truths.find_retweets(months)
_OUT_DIR += 'no_retweets/'
Util.ensure_dir_exist(_OUT_DIR)
log('Output dir: %s' % _OUT_DIR)
for delta in _DELTAS:
for category in _CATEGORIES:
gt_rankings = ground_truths.get_gt_rankings(seeds, data_set, category,
exclude_tweets_within_delta=_EXCLUDE_TWEETS_WITHIN_DELTA,
retweets=retweets)
sort_users_by_tweet_count(months, seeds, cache, delta, category)
target_news = ground_truths.find_target_news(gt_rankings, _SIZE_TOP_NEWS)
find_hits_and_mises(months, target_news, seeds, cache,
delta, category)
# if _SWITCHED:
# gt_rankings = ground_truths.get_gt_rankings(seeds, DataSet.TESTING,
# category)
# sort_users_by_tweet_count(_TESTING_SET_MONTHS, seeds, cache,
# delta, category)
# target_news = ground_truths.find_target_news(gt_rankings, .02)
# find_hits_and_mises(_TESTING_SET_MONTHS, target_news, seeds, cache,
# delta, category)
# else:
# gt_rankings = ground_truths.get_gt_rankings(seeds, DataSet.TRAINING,
# category)
# sort_users_by_tweet_count(_TRAINING_SET_MONTHS, seeds, cache,
# delta, category)
# target_news = ground_truths.find_target_news(gt_rankings, .02)
# find_hits_and_mises(_TRAINING_SET_MONTHS, target_news, seeds, cache,
# delta, category)
log('Finished outputting data!')
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
def run():
"""Contains the main logic for this analysis."""
FileLog.set_log_dir()
seeds = Util.load_seeds()
for category in _CATEGORIES:
log('Preforming analysis for category: %s' % category)
size_top_news = _SIZE_TOP_NEWS
if category:
size_top_news = .10
data_set = DataSet.TESTING
retweets = set()
if _SWITCHED:
data_set = DataSet.TRAINING
if _EXCLUDE_RETWEETS:
retweets = ground_truths.find_retweets(_TESTING_SET_MONTHS)
log('Num retweets to exclude: %s' % len(retweets))
gt_rankings = ground_truths.get_gt_rankings(seeds, data_set, category,
exclude_tweets_within_delta=_EXCLUDE_TWEETS_WITHIN_DELTA,
retweets=retweets)
log('Num ground_truth_rankings: %s' % len(gt_rankings))
# Format for use later.
ground_truth_url_to_rank = {}
for rank, (url, count) in enumerate(gt_rankings):
ground_truth_url_to_rank[url] = rank
target_news = ground_truths.find_target_news(gt_rankings, size_top_news)
log('Size target_news: %s' % len(target_news))
for delta in _DELTAS:
run_params_str = 'd%s_t%s_e%s_%s' % (delta, int(size_top_news * 100),
int(_SIZE_EXPERTS * 100), category)
info_output_dir = '../graph/FolkWisdom/%s/info/' % run_params_str
Util.ensure_dir_exist(info_output_dir)
groups, d_num_followers = user_groups.get_all_user_groups(delta, category)
log('Num experts (precision): %s' % len(groups.precision))
log('Num experts (fscore): %s' % len(groups.fscore))
log('Num experts (ci): %s' % len(groups.ci))
log('Num Super Experts: %s' %len(groups.super_experts))
log('Num Social Bias Experts: %s' % len(groups.social_bias))
log('Finding rankings with an %s hour delta.' % delta)
ranks = rankings.get_rankings(delta, seeds, groups, category, d_num_followers)
# Output some interesting info to file
size_market_unfiltered = '0'
with open('../data/FolkWisdom/size_of_market_unfiltered.txt') as in_file:
size_market_unfiltered = in_file.readline().strip()
with open('%suser_demographics_%s.txt'
% (info_output_dir, run_params_str), 'w') as output_file:
output_file.write('Number of Newsaholics: %s\n' % len(groups.newsaholics))
output_file.write('Number of Active Users: %s\n' % len(groups.active_users))
output_file.write('Number of Common Users: %s\n' % len(groups.common_users))
output_file.write('\n');
output_file.write('Number of Precision Experts: %s\n' % len(groups.precision))
output_file.write('Number of F-Score Experts: %s\n' % len(groups.fscore))
output_file.write('Number of CI Experts: %s\n' % len(groups.ci))
output_file.write('Number of Social Bias Experts: %s\n' % len(groups.social_bias))
output_file.write('Total number of unique experts: %s\n' % len(groups.all_experts))
output_file.write('Number of Precision and F-Score Experts: %s\n'
% len(groups.precision.intersection(groups.fscore)))
output_file.write('Number of Precision and CI Experts: %s\n'
% len(groups.precision.intersection(groups.ci)))
output_file.write('Number of F-Score and CI Experts: %s\n'
% len(groups.fscore.intersection(groups.ci)))
output_file.write('Number of Super Experts: %s\n' % len(groups.super_experts))
output_file.write('\n');
output_file.write('Number of Users (Total): %s\n'
% (len(groups.newsaholics) + len(groups.active_users)
+ len(groups.common_users)))
output_file.write('Size of market (unfiltered): %s\n'
% size_market_unfiltered)
output_file.write('\n')
# output_file.write('Number of votes by Newsaholics: %s\n'
# % num_votes_newsaholics)
# output_file.write('Number of votes by Market: %s\n' % num_votes_market)
# output_file.write('Number of votes by Active Users: %s\n'
# % num_votes_active)
# 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 by Super Experts: %s\n'
# % num_votes_expert_s)
# output_file.write('Number of votes by Social Bias Experts: %s\n'
# % num_votes_expert_sb)
# output_file.write('\n')
# output_file.write('Total Number of votes cast: %s\n'
# % (num_votes_newsaholics + num_votes_active
# + num_votes_common))
# output_file.write('\n')
output_file.write('Total Number of Good News: %s\n' % len(target_news))
log('Ground Truth Top 50')
for i in range(min(len(gt_rankings), 50)):
url, count = gt_rankings[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Newsaholic Top 5')
for i in range(min(len(ranks.newsaholics), 5)):
url, count = ranks.newsaholics[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Active Top 5')
for i in range(min(len(ranks.active_users), 5)):
url, count = ranks.active_users[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Common Top 5')
for i in range(min(len(ranks.common_users), 5)):
url, count = ranks.common_users[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('nonexpert Top 5')
for i in range(min(len(ranks.non_experts), 5)):
url, count = ranks.non_experts[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (Precision) Top 5')
for i in range(min(len(ranks.precision), 5)):
url, count = ranks.precision[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (fscore) Top 5')
for i in range(min(len(ranks.fscore), 5)):
url, count = ranks.fscore[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Expert (ci) Top 5')
for i in range(min(len(ranks.ci), 5)):
url, count = ranks.ci[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Super Expert Top 5')
for i in range(min(len(ranks.super_experts), 5)):
url, count = ranks.super_experts[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
log('-----------------------------------')
log('Social Bias Expert Top 5')
for i in range(min(len(ranks.social_bias), 5)):
url, count = ranks.social_bias[i]
log('[%s] %s\t%s' %(i, url.strip(), count))
market_rank_to_url = {}
newsaholic_rank_to_url = {}
active_rank_to_url = {}
common_rank_to_url = {}
expert_p_rank_to_url = {}
expert_f_rank_to_url = {}
expert_c_rank_to_url = {}
expert_s_rank_to_url = {}
for rank, (url, count) in enumerate(ranks.newsaholics):
newsaholic_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.population):
market_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.active_users):
active_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.common_users):
common_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.precision):
expert_p_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.fscore):
expert_f_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.ci):
expert_c_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.super_experts):
expert_s_rank_to_url[rank] = url
population_url_to_rank = {}
market_url_to_rank = {}
precision_url_to_rank = {}
fscore_url_to_rank = {}
ci_url_to_rank = {}
ci_1_url_to_rank = {}
ci_2_url_to_rank = {}
ci_3_url_to_rank = {}
common_url_to_rank = {}
for rank, (url, count) in enumerate(ranks.population):
population_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.non_experts):
market_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.precision):
precision_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.fscore):
fscore_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci):
ci_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_1):
ci_1_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_2):
ci_2_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_3):
ci_3_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.common_users):
common_url_to_rank[url] = rank
precisions, recalls = precision_recall.get_precision_recalls(gt_rankings, ranks)
mixed_rankings = mixed_model.get_mixed_rankings(market_url_to_rank,
precisions.non_experts,
precision_url_to_rank,
precisions.precision,
fscore_url_to_rank,
precisions.fscore,
ci_url_to_rank,
precisions.ci,
ground_truth_url_to_rank)
mixed_inact_rankings = mixed_model.get_mixed_rankings(common_url_to_rank,
precisions.common_users,
precision_url_to_rank,
precisions.precision,
fscore_url_to_rank,
precisions.fscore,
ci_url_to_rank,
precisions.ci,
ground_truth_url_to_rank)
mixed_ci_rankings = mixed_model.get_mixed_rankings(market_url_to_rank,
precisions.non_experts,
ci_1_url_to_rank,
precisions.ci_1,
ci_2_url_to_rank,
precisions.ci_2,
ci_3_url_to_rank,
precisions.ci_3,
ground_truth_url_to_rank)
mixed_precisions, mixed_recalls = precision_recall.calc_precision_recall(gt_rankings,
mixed_rankings)
mixed_inact_precisions, mixed_inact_recalls = precision_recall.calc_precision_recall(gt_rankings,
mixed_inact_rankings)
mixed_ci_precisions, mixed_ci_recalls = precision_recall.calc_precision_recall(gt_rankings,
mixed_ci_rankings)
log('-----------------------------------')
log('Mixed (min) Top 5')
for i in range(min(len(mixed_rankings), 5)):
url, count = mixed_rankings[i]
log('[%s] %s\t%s' %(i + 1, url, count))
log('-----------------------------------')
with open('%sranking_comparisons_%s.tsv'
% (info_output_dir, run_params_str), 'w') as out_file:
for gt_rank, (gt_url, _) in enumerate(gt_rankings):
market_rank = 0
precision_rank = 0
ci_rank = 0
fscore_rank = 0
inactive_crowd_rank = 0
if gt_url in market_url_to_rank:
market_rank = market_url_to_rank[gt_url] + 1
if gt_url in precision_url_to_rank:
precision_rank = precision_url_to_rank[gt_url] + 1
if gt_url in ci_url_to_rank:
ci_rank = ci_url_to_rank[gt_url] + 1
if gt_url in fscore_url_to_rank:
fscore_rank = fscore_url_to_rank[gt_url] + 1
if gt_url in common_url_to_rank:
inactive_crowd_rank = common_url_to_rank[gt_url] + 1
line = '%s\t%s\t%s\t%s\t%s\t%s\t%s\n' % (gt_url, gt_rank + 1,
market_rank,
inactive_crowd_rank,
precision_rank, ci_rank,
fscore_rank)
out_file.write(line)
with open('%sground_truth_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for url, count in gt_rankings:
output_file.write('%s\t%s\n' % (url.strip(), count))
with open('%smarket_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.common_users):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%snewsaholic_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.newsaholics):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%sactive_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.active_users):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%scommon_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.common_users):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%snonexpert_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.non_experts):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%sexpert_p_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.precision):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%sexpert_f_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.fscore):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%sexpert_c_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.ci):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%sexpert_s_user_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.super_experts):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('%smixed_rankings_%s.tsv'
% (info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(mixed_rankings):
output_file.write('%s\t%s\t(%s,%s)\n'
% (url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open('../data/FolkWisdom/market_precisions_%s.txt'
% run_params_str, 'w') as out_file:
for precision in precisions.common_users:
out_file.write('%s\n' % precision)
with open('../data/FolkWisdom/nonexpert_precisions_%s.txt'
% run_params_str, 'w') as out_file:
for precision in precisions.non_experts:
out_file.write('%s\n' % precision)
with open('../data/FolkWisdom/expert_p_precisions_%s.txt'
% run_params_str, 'w') as out_file:
for precision in precisions.precision:
out_file.write('%s\n' % precision)
with open('../data/FolkWisdom/expert_f_precisions_%s.txt'
% run_params_str, 'w') as out_file:
for precision in precisions.fscore:
out_file.write('%s\n' % precision)
with open('../data/FolkWisdom/expert_c_precisions_%s.txt'
% run_params_str, 'w') as out_file:
for precision in precisions.ci:
out_file.write('%s\n' % precision)
log('Drawing summary precision-recall graphs...')
# draw_precision_recall_graph(market_precisions, market_recalls,
precision_recall.draw([precisions.newsaholics, precisions.active_users,
precisions.common_users, precisions.precision,
precisions.fscore, precisions.ci,
precisions.super_experts],
[recalls.newsaholics, recalls.active_users,
recalls.common_users, recalls.precision,
recalls.fscore, recalls.ci, recalls.super_experts],
['Newsaholics', 'Active', 'Common', 'Precision',
'F-score', 'CI', 'Super Experts'],
'precision_recall_all',
run_params_str)
# Draw via old method because it has fancy markings.
experts.draw_precision_recall_experts(precisions.non_experts, recalls.non_experts,
precisions.precision, recalls.precision,
precisions.fscore, recalls.fscore,
precisions.ci, recalls.ci,
run_params_str)
log('Drawing experts precision-recall graph...')
# precision_recall.draw_with_markers([precisions.population, precisions.non_experts, precisions.precision,
# precisions.fscore, precisions.ci],
# [recalls.population, recalls.non_experts, recalls.precision,
# recalls.fscore, recalls.ci],
# ['Population', 'Crowd', 'Precision', 'F-score', 'CI'],
# 'precision_recall_experts',
# 0, run_params_str)
log('Drawing mixed + inact graph...')
precision_recall.draw_with_markers([precisions.non_experts, precisions.common_users, mixed_inact_precisions],
[recalls.non_experts, recalls.common_users, mixed_inact_recalls],
['Crowd', 'Inactive Crowd', 'Mixed + Inactive'],
'precision_recall_mixed_and_inactive',
3, run_params_str, zoom=True)
log('Drawing ci breakdown by followers precisions-recall graph...')
precision_recall.draw([precisions.non_experts, precisions.ci,
precisions.ci_hi, precisions.ci_li],
[recalls.non_experts, recalls.ci,
recalls.ci_hi, recalls.ci_li],
['Crowd', 'CI', 'CI High', 'CI Low'],
'precision_recall_ci_followers_breakdown',
run_params_str)
log('Drawing social bias precision-recall graph...')
precision_recall.draw([precisions.non_experts, precisions.social_bias,
precisions.precision, precisions.fscore,
precisions.ci],
[recalls.non_experts, recalls.social_bias,
recalls.precision, recalls.fscore,
recalls.ci],
['Crowd', 'Influence Experts', 'Precision',
'F-score', 'CI'],
'precision_recall_social_bias',
run_params_str)
log('Drawing basic groups precision-recall graph...')
precision_recall.draw([precisions.newsaholics, precisions.active_users,
precisions.common_users],
[recalls.newsaholics, recalls.active_users,
recalls.common_users],
['Newsaholics', 'Active Users', 'Common Users'],
'precision_recall_basic_groups',
run_params_str)
log('Drawing crowd def precision-recall graph...')
precision_recall.draw([precisions.non_experts, precisions.common_users],
[recalls.non_experts, recalls.common_users],
['Crowd', 'Inactive Crowd'],
'precision_recall_crowd_def',
run_params_str, zoom=True)
log('Drawing non_expert_sampling precision-recall graph...')
precision_recall.draw_with_markers([precisions.non_experts, precisions.non_experts_sampled,
precisions.non_experts_10, precisions.non_experts_25,
precisions.non_experts_1, precisions.ci],
[recalls.non_experts, recalls.non_experts_sampled,
recalls.non_experts_10, recalls.non_experts_25,
recalls.non_experts_1, recalls.ci],
['Crowd', 'Crowd (33% sample)', 'Crowd (10% sample)',
'Crowd (5% sample)', 'Crowd (2% sample)', 'Experts (CI)'],
'precision_recall_non_expert_sampling',
3, run_params_str, ncol=2)
# TODO: Replace with new method.
log('Drawing mixed model precision-recall graph...')
mixed_model.draw_precision_recall_mixed(precisions.non_experts, recalls.non_experts,
mixed_precisions, mixed_recalls,
run_params_str, zoom=True)
log('Drawing mixed ci model precision-recall graph...')
precision_recall.draw([precisions.non_experts, mixed_ci_precisions],
[recalls.non_experts, mixed_ci_recalls],
['Crowd', 'Mixed'],
'precision_recall_mixed_ci',
run_params_str)
log('Drawing weighted followers precision-recall graph...')
precision_recall.draw([precisions.non_experts, precisions.weighted_followers, precisions.ci],
[recalls.non_experts, recalls.weighted_followers, recalls.ci],
['Crowd', 'Weighted Followers', 'CI'],
'precision_recall_weighted_followers',
run_params_str)
log('Drawing ci weighted graph...')
precision_recall.draw([precisions.population, precisions.ci, precisions.ci_weighted],
[recalls.population, recalls.ci, recalls.ci_weighted],
['Crowd', 'CI', 'CI (Weighted)'],
'precision_recall_ci_weighted',
run_params_str)
log('Drawing weighted graph...')
precision_recall.draw([precisions.population, precisions.weighted],
[recalls.population, recalls.weighted],
['Crowd', 'Crowd (Weighted)'],
'precision_recall_weighted',
run_params_str)
log('Drawing weighted both graph...')
precision_recall.draw([precisions.population, precisions.weighted, precisions.weighted_both],
[recalls.population, recalls.weighted, recalls.weighted_both],
['Crowd', 'Crowd (Weighted)', 'Crowd (Weighted Both)'],
'precision_recall_weighted_both',
run_params_str)
def run():
"""Contains the main logic for this analysis."""
FileLog.set_log_dir()
seeds = Util.load_seeds()
for category in _CATEGORIES:
log('Preforming analysis for category: %s' % category)
size_top_news = _SIZE_TOP_NEWS
if category:
size_top_news = .10
data_set = DataSet.TESTING
retweets = set()
if _SWITCHED:
data_set = DataSet.TRAINING
if _EXCLUDE_RETWEETS:
retweets = ground_truths.find_retweets(_TESTING_SET_MONTHS)
log('Num retweets to exclude: %s' % len(retweets))
gt_rankings = ground_truths.get_gt_rankings(
seeds,
data_set,
category,
exclude_tweets_within_delta=_EXCLUDE_TWEETS_WITHIN_DELTA,
retweets=retweets)
log('Num ground_truth_rankings: %s' % len(gt_rankings))
# Format for use later.
ground_truth_url_to_rank = {}
for rank, (url, count) in enumerate(gt_rankings):
ground_truth_url_to_rank[url] = rank
target_news = ground_truths.find_target_news(gt_rankings,
size_top_news)
log('Size target_news: %s' % len(target_news))
for delta in _DELTAS:
run_params_str = 'd%s_t%s_e%s_%s' % (delta, int(
size_top_news * 100), int(_SIZE_EXPERTS * 100), category)
info_output_dir = '../graph/FolkWisdom/%s/info/' % run_params_str
Util.ensure_dir_exist(info_output_dir)
groups, d_num_followers = user_groups.get_all_user_groups(
delta, category)
log('Num experts (precision): %s' % len(groups.precision))
log('Num experts (fscore): %s' % len(groups.fscore))
log('Num experts (ci): %s' % len(groups.ci))
log('Num Super Experts: %s' % len(groups.super_experts))
log('Num Social Bias Experts: %s' % len(groups.social_bias))
log('Finding rankings with an %s hour delta.' % delta)
ranks = rankings.get_rankings(delta, seeds, groups, category,
d_num_followers)
# Output some interesting info to file
size_market_unfiltered = '0'
with open('../data/FolkWisdom/size_of_market_unfiltered.txt'
) as in_file:
size_market_unfiltered = in_file.readline().strip()
with open(
'%suser_demographics_%s.txt' %
(info_output_dir, run_params_str), 'w') as output_file:
output_file.write('Number of Newsaholics: %s\n' %
len(groups.newsaholics))
output_file.write('Number of Active Users: %s\n' %
len(groups.active_users))
output_file.write('Number of Common Users: %s\n' %
len(groups.common_users))
output_file.write('\n')
output_file.write('Number of Precision Experts: %s\n' %
len(groups.precision))
output_file.write('Number of F-Score Experts: %s\n' %
len(groups.fscore))
output_file.write('Number of CI Experts: %s\n' %
len(groups.ci))
output_file.write('Number of Social Bias Experts: %s\n' %
len(groups.social_bias))
output_file.write('Total number of unique experts: %s\n' %
len(groups.all_experts))
output_file.write(
'Number of Precision and F-Score Experts: %s\n' %
len(groups.precision.intersection(groups.fscore)))
output_file.write(
'Number of Precision and CI Experts: %s\n' %
len(groups.precision.intersection(groups.ci)))
output_file.write('Number of F-Score and CI Experts: %s\n' %
len(groups.fscore.intersection(groups.ci)))
output_file.write('Number of Super Experts: %s\n' %
len(groups.super_experts))
output_file.write('\n')
output_file.write(
'Number of Users (Total): %s\n' %
(len(groups.newsaholics) + len(groups.active_users) +
len(groups.common_users)))
output_file.write('Size of market (unfiltered): %s\n' %
size_market_unfiltered)
output_file.write('\n')
# output_file.write('Number of votes by Newsaholics: %s\n'
# % num_votes_newsaholics)
# output_file.write('Number of votes by Market: %s\n' % num_votes_market)
# output_file.write('Number of votes by Active Users: %s\n'
# % num_votes_active)
# 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 by Super Experts: %s\n'
# % num_votes_expert_s)
# output_file.write('Number of votes by Social Bias Experts: %s\n'
# % num_votes_expert_sb)
# output_file.write('\n')
# output_file.write('Total Number of votes cast: %s\n'
# % (num_votes_newsaholics + num_votes_active
# + num_votes_common))
# output_file.write('\n')
output_file.write('Total Number of Good News: %s\n' %
len(target_news))
log('Ground Truth Top 50')
for i in range(min(len(gt_rankings), 50)):
url, count = gt_rankings[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Newsaholic Top 5')
for i in range(min(len(ranks.newsaholics), 5)):
url, count = ranks.newsaholics[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Active Top 5')
for i in range(min(len(ranks.active_users), 5)):
url, count = ranks.active_users[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Common Top 5')
for i in range(min(len(ranks.common_users), 5)):
url, count = ranks.common_users[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('nonexpert Top 5')
for i in range(min(len(ranks.non_experts), 5)):
url, count = ranks.non_experts[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Expert (Precision) Top 5')
for i in range(min(len(ranks.precision), 5)):
url, count = ranks.precision[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Expert (fscore) Top 5')
for i in range(min(len(ranks.fscore), 5)):
url, count = ranks.fscore[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Expert (ci) Top 5')
for i in range(min(len(ranks.ci), 5)):
url, count = ranks.ci[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Super Expert Top 5')
for i in range(min(len(ranks.super_experts), 5)):
url, count = ranks.super_experts[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
log('-----------------------------------')
log('Social Bias Expert Top 5')
for i in range(min(len(ranks.social_bias), 5)):
url, count = ranks.social_bias[i]
log('[%s] %s\t%s' % (i, url.strip(), count))
market_rank_to_url = {}
newsaholic_rank_to_url = {}
active_rank_to_url = {}
common_rank_to_url = {}
expert_p_rank_to_url = {}
expert_f_rank_to_url = {}
expert_c_rank_to_url = {}
expert_s_rank_to_url = {}
for rank, (url, count) in enumerate(ranks.newsaholics):
newsaholic_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.population):
market_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.active_users):
active_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.common_users):
common_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.precision):
expert_p_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.fscore):
expert_f_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.ci):
expert_c_rank_to_url[rank] = url
for rank, (url, count) in enumerate(ranks.super_experts):
expert_s_rank_to_url[rank] = url
population_url_to_rank = {}
market_url_to_rank = {}
precision_url_to_rank = {}
fscore_url_to_rank = {}
ci_url_to_rank = {}
ci_1_url_to_rank = {}
ci_2_url_to_rank = {}
ci_3_url_to_rank = {}
common_url_to_rank = {}
for rank, (url, count) in enumerate(ranks.population):
population_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.non_experts):
market_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.precision):
precision_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.fscore):
fscore_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci):
ci_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_1):
ci_1_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_2):
ci_2_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.ci_3):
ci_3_url_to_rank[url] = rank
for rank, (url, count) in enumerate(ranks.common_users):
common_url_to_rank[url] = rank
precisions, recalls = precision_recall.get_precision_recalls(
gt_rankings, ranks)
mixed_rankings = mixed_model.get_mixed_rankings(
market_url_to_rank, precisions.non_experts,
precision_url_to_rank, precisions.precision,
fscore_url_to_rank, precisions.fscore, ci_url_to_rank,
precisions.ci, ground_truth_url_to_rank)
mixed_inact_rankings = mixed_model.get_mixed_rankings(
common_url_to_rank, precisions.common_users,
precision_url_to_rank, precisions.precision,
fscore_url_to_rank, precisions.fscore, ci_url_to_rank,
precisions.ci, ground_truth_url_to_rank)
mixed_ci_rankings = mixed_model.get_mixed_rankings(
market_url_to_rank, precisions.non_experts, ci_1_url_to_rank,
precisions.ci_1, ci_2_url_to_rank, precisions.ci_2,
ci_3_url_to_rank, precisions.ci_3, ground_truth_url_to_rank)
mixed_precisions, mixed_recalls = precision_recall.calc_precision_recall(
gt_rankings, mixed_rankings)
mixed_inact_precisions, mixed_inact_recalls = precision_recall.calc_precision_recall(
gt_rankings, mixed_inact_rankings)
mixed_ci_precisions, mixed_ci_recalls = precision_recall.calc_precision_recall(
gt_rankings, mixed_ci_rankings)
log('-----------------------------------')
log('Mixed (min) Top 5')
for i in range(min(len(mixed_rankings), 5)):
url, count = mixed_rankings[i]
log('[%s] %s\t%s' % (i + 1, url, count))
log('-----------------------------------')
with open(
'%sranking_comparisons_%s.tsv' %
(info_output_dir, run_params_str), 'w') as out_file:
for gt_rank, (gt_url, _) in enumerate(gt_rankings):
market_rank = 0
precision_rank = 0
ci_rank = 0
fscore_rank = 0
inactive_crowd_rank = 0
if gt_url in market_url_to_rank:
market_rank = market_url_to_rank[gt_url] + 1
if gt_url in precision_url_to_rank:
precision_rank = precision_url_to_rank[gt_url] + 1
if gt_url in ci_url_to_rank:
ci_rank = ci_url_to_rank[gt_url] + 1
if gt_url in fscore_url_to_rank:
fscore_rank = fscore_url_to_rank[gt_url] + 1
if gt_url in common_url_to_rank:
inactive_crowd_rank = common_url_to_rank[gt_url] + 1
line = '%s\t%s\t%s\t%s\t%s\t%s\t%s\n' % (
gt_url, gt_rank + 1, market_rank, inactive_crowd_rank,
precision_rank, ci_rank, fscore_rank)
out_file.write(line)
with open(
'%sground_truth_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for url, count in gt_rankings:
output_file.write('%s\t%s\n' % (url.strip(), count))
with open(
'%smarket_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.common_users):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%snewsaholic_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.newsaholics):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%sactive_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.active_users):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%scommon_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.common_users):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%snonexpert_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.non_experts):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%sexpert_p_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.precision):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%sexpert_f_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.fscore):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%sexpert_c_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.ci):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%sexpert_s_user_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(ranks.super_experts):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'%smixed_rankings_%s.tsv' %
(info_output_dir, run_params_str), 'w') as output_file:
for rank, (url, count) in enumerate(mixed_rankings):
output_file.write('%s\t%s\t(%s,%s)\n' %
(url.strip(), count, rank,
ground_truth_url_to_rank[url]))
with open(
'../data/FolkWisdom/market_precisions_%s.txt' %
run_params_str, 'w') as out_file:
for precision in precisions.common_users:
out_file.write('%s\n' % precision)
with open(
'../data/FolkWisdom/nonexpert_precisions_%s.txt' %
run_params_str, 'w') as out_file:
for precision in precisions.non_experts:
out_file.write('%s\n' % precision)
with open(
'../data/FolkWisdom/expert_p_precisions_%s.txt' %
run_params_str, 'w') as out_file:
for precision in precisions.precision:
out_file.write('%s\n' % precision)
with open(
'../data/FolkWisdom/expert_f_precisions_%s.txt' %
run_params_str, 'w') as out_file:
for precision in precisions.fscore:
out_file.write('%s\n' % precision)
with open(
'../data/FolkWisdom/expert_c_precisions_%s.txt' %
run_params_str, 'w') as out_file:
for precision in precisions.ci:
out_file.write('%s\n' % precision)
log('Drawing summary precision-recall graphs...')
# draw_precision_recall_graph(market_precisions, market_recalls,
precision_recall.draw([
precisions.newsaholics, precisions.active_users,
precisions.common_users, precisions.precision,
precisions.fscore, precisions.ci, precisions.super_experts
], [
recalls.newsaholics, recalls.active_users,
recalls.common_users, recalls.precision, recalls.fscore,
recalls.ci, recalls.super_experts
], [
'Newsaholics', 'Active', 'Common', 'Precision', 'F-score',
'CI', 'Super Experts'
], 'precision_recall_all', run_params_str)
# Draw via old method because it has fancy markings.
experts.draw_precision_recall_experts(
precisions.non_experts, recalls.non_experts,
precisions.precision, recalls.precision, precisions.fscore,
recalls.fscore, precisions.ci, recalls.ci, run_params_str)
log('Drawing experts precision-recall graph...')
# precision_recall.draw_with_markers([precisions.population, precisions.non_experts, precisions.precision,
# precisions.fscore, precisions.ci],
# [recalls.population, recalls.non_experts, recalls.precision,
# recalls.fscore, recalls.ci],
# ['Population', 'Crowd', 'Precision', 'F-score', 'CI'],
# 'precision_recall_experts',
# 0, run_params_str)
log('Drawing mixed + inact graph...')
precision_recall.draw_with_markers(
[
precisions.non_experts, precisions.common_users,
mixed_inact_precisions
], [
recalls.non_experts, recalls.common_users,
mixed_inact_recalls
], ['Crowd', 'Inactive Crowd', 'Mixed + Inactive'],
'precision_recall_mixed_and_inactive',
3,
run_params_str,
zoom=True)
log('Drawing ci breakdown by followers precisions-recall graph...')
precision_recall.draw([
precisions.non_experts, precisions.ci, precisions.ci_hi,
precisions.ci_li
], [recalls.non_experts, recalls.ci, recalls.ci_hi, recalls.ci_li],
['Crowd', 'CI', 'CI High', 'CI Low'],
'precision_recall_ci_followers_breakdown',
run_params_str)
log('Drawing social bias precision-recall graph...')
precision_recall.draw([
precisions.non_experts, precisions.social_bias,
precisions.precision, precisions.fscore, precisions.ci
], [
recalls.non_experts, recalls.social_bias, recalls.precision,
recalls.fscore, recalls.ci
], ['Crowd', 'Influence Experts', 'Precision', 'F-score', 'CI'],
'precision_recall_social_bias',
run_params_str)
log('Drawing basic groups precision-recall graph...')
precision_recall.draw([
precisions.newsaholics, precisions.active_users,
precisions.common_users
], [
recalls.newsaholics, recalls.active_users, recalls.common_users
], ['Newsaholics', 'Active Users', 'Common Users'],
'precision_recall_basic_groups',
run_params_str)
log('Drawing crowd def precision-recall graph...')
precision_recall.draw(
[precisions.non_experts, precisions.common_users],
[recalls.non_experts, recalls.common_users],
['Crowd', 'Inactive Crowd'],
'precision_recall_crowd_def',
run_params_str,
zoom=True)
log('Drawing non_expert_sampling precision-recall graph...')
precision_recall.draw_with_markers(
[
precisions.non_experts, precisions.non_experts_sampled,
precisions.non_experts_10, precisions.non_experts_25,
precisions.non_experts_1, precisions.ci
], [
recalls.non_experts, recalls.non_experts_sampled,
recalls.non_experts_10, recalls.non_experts_25,
recalls.non_experts_1, recalls.ci
], [
'Crowd', 'Crowd (33% sample)', 'Crowd (10% sample)',
'Crowd (5% sample)', 'Crowd (2% sample)', 'Experts (CI)'
],
'precision_recall_non_expert_sampling',
3,
run_params_str,
ncol=2)
# TODO: Replace with new method.
log('Drawing mixed model precision-recall graph...')
mixed_model.draw_precision_recall_mixed(precisions.non_experts,
recalls.non_experts,
mixed_precisions,
mixed_recalls,
run_params_str,
zoom=True)
log('Drawing mixed ci model precision-recall graph...')
precision_recall.draw(
[precisions.non_experts, mixed_ci_precisions],
[recalls.non_experts, mixed_ci_recalls], ['Crowd', 'Mixed'],
'precision_recall_mixed_ci', run_params_str)
log('Drawing weighted followers precision-recall graph...')
precision_recall.draw([
precisions.non_experts, precisions.weighted_followers,
precisions.ci
], [recalls.non_experts, recalls.weighted_followers, recalls.ci],
['Crowd', 'Weighted Followers', 'CI'],
'precision_recall_weighted_followers',
run_params_str)
log('Drawing ci weighted graph...')
precision_recall.draw(
[precisions.population, precisions.ci, precisions.ci_weighted],
[recalls.population, recalls.ci, recalls.ci_weighted],
['Crowd', 'CI', 'CI (Weighted)'],
'precision_recall_ci_weighted', run_params_str)
log('Drawing weighted graph...')
precision_recall.draw([precisions.population, precisions.weighted],
[recalls.population, recalls.weighted],
['Crowd', 'Crowd (Weighted)'],
'precision_recall_weighted', run_params_str)
log('Drawing weighted both graph...')
precision_recall.draw(
[
precisions.population, precisions.weighted,
precisions.weighted_both
],
[recalls.population, recalls.weighted, recalls.weighted_both],
['Crowd', 'Crowd (Weighted)', 'Crowd (Weighted Both)'],
'precision_recall_weighted_both', run_params_str)