def log(message):
"""Helper method to modularize the format of log messages.
Keyword Arguments:
message -- A string to log.
"""
FileLog.log(_LOG_FILE, message)
def log(message): """Helper method to modularize the format of log messages. Keyword Arguments: message -- A string to log. """ FileLog.log(_LOG_FILE, message)
def __init__(self, input_filter_words, verbose_log=False):
#Setup log
FileLog.set_log_dir()
self.log_filename = "StreamFileSaverWrapper.log"
self.verbose_log = verbose_log #suppress all debug log
#Setup filenames (for storing tsv)
self.data_path = "../data/tsv/"
if self.data_path [-1] != os.sep: #make sure we have a path separtor charcter
self.data_path += os.sep
if not os.path.exists(self.data_path): #make sure path exist
self.log("Creating dir: " + self.data_path)
os.makedirs(self.data_path )
#self.check_all_old_processes_are_dead = False #Set to true to check "old processes" status
self.filter_words = input_filter_words
self.today_str = StreamFileSaverWrapper.static_get_date_string() #'2011_03_09'
### Setup Worker Processes ###
#For storing the obsolete worker processes
self.obsolete_process_dict = None
#Create a dictionary that holds all the worker processes.
self.current_process_dict = self.build_new_worker_process_dict()
#start all worker processes
self.start_all_worker(self.current_process_dict)
def run():
"""Contains the main logic for this analysis."""
FileLog.set_log_dir()
seeds = load_seeds()
counts = find_total_tweet_count(seeds)
calc_90_percent_count(counts)
time_of_90s = find_90_times(counts)
truths = get_gt_rankings(seeds)
top_news = get_top_news(truths, _SIZE_TOP_NEWS)
aggregates, aggregates_top = aggr_by_hour(time_of_90s, top_news)
draw_graph(aggregates, aggregates_top)
def run(): """Contains the main logic for this analysis.""" FileLog.set_log_dir() seeds = load_seeds() counts = find_total_tweet_count(seeds) calc_90_percent_count(counts) time_of_90s = find_90_times(counts) truths = get_gt_rankings(seeds) top_news = get_top_news(truths, _SIZE_TOP_NEWS) aggregates, aggregates_top = aggr_by_hour(time_of_90s, top_news) draw_graph(aggregates, aggregates_top)
def static_status_to_tweet_tsv(status, filter_words):
"""Extract data related to Tweets Table, and return a tab splitted string.
Returns:
line -- a tab splitted string
None -- some exception happens
"""
retweeted = False
origin_user_id = ''
origin_tweet_id = ''
source = ''
source_url = ''
retweet_count = 0
#if it is a retweet, update the retweet infomation
if hasattr(status,'retweeted_status'):
origin_user_id = str(status.retweeted_status.user.id)
origin_tweet_id = str(status.retweeted_status.id)
retweeted = True
if hasattr(status, 'source'):
source = status.source
if hasattr(status, 'source_url'):
source_url = status.source_url
if str(status.retweet_count) == '100+':
status.retweet_count = 101
try:
line = ("\t".join([
str(status.id_str), #tweet_id
str(status.user.id), #user_id
StreamFileSaverWrapper.ensure_escape_for_mysql(status.text.encode('utf8')), #content
str(status.created_at), #created_at
str(retweeted), #retweeted
str(int(status.retweet_count)), #retweeted_count
str(origin_user_id), #origin_user_id
str(origin_tweet_id), #origin_tweet_id
str(source.encode('utf8')), # source
str(source_url), #source_url
str(filter_words), #filter
datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') #insert_timestamp
# leave it blank: HASH
]))
return line + "\n"
except Exception as e:
FileLog.log("FileSaver.log", "FileSaver(pid:{0}): "
.format(str(os.getpid())) + str(e),
exception_tb=sys.exc_traceback)
return None
def __init__(self, keywords, username, password):
self.pid = str(os.getpid())
### Log ###
self.log_file = "StreamingCrawler.log"
FileLog.set_log_dir() #check the log dir, and create it if necessary
### Run ###
self.key = keywords #keyword for filtering
self.listener = CrawlerListener(keywords)
self.log("(" + self.pid + ") " +
"Start monitoring streaming... keywords: " + str(keywords))
auth = BasicAuthHandler(username, password)
self.stream = Stream(auth, self.listener, timeout=None, retry_count = sys.maxint); #retry_time = 10.0
def run():
"""Contains the main logic for this analysis."""
FileLog.set_log_dir()
num_tweets_in_log = []
count_tweets_bin_log = []
with open(_DATA_DIR + 'popularity.graph.data.100bins') as in_file:
for line in in_file.readlines():
tokens = line.split('\t')
num_tweets_log = float(tokens[1])
count_tweets_in_bin = float(tokens[4]) * 100.0
num_tweets_in_log.append(num_tweets_log)
count_tweets_bin_log.append(count_tweets_in_bin)
log('x: %s' % num_tweets_in_log)
log('y: %s' % count_tweets_bin_log)
draw_graph(num_tweets_in_log, count_tweets_bin_log)
def run():
"""Contains the main logic for this analysis."""
FileLog.set_log_dir()
num_tweets_in_log = []
count_tweets_bin_log = []
with open(_DATA_DIR + 'popularity.graph.data.100bins') as in_file:
for line in in_file.readlines():
tokens = line.split('\t')
num_tweets_log = float(tokens[1])
count_tweets_in_bin = float(tokens[4]) * 100.0
num_tweets_in_log.append(num_tweets_log)
count_tweets_bin_log.append(count_tweets_in_bin)
log('x: %s' % num_tweets_in_log)
log('y: %s' % count_tweets_bin_log)
draw_graph(num_tweets_in_log, count_tweets_bin_log)
def __init__(self, filter ):
self.running = True #Set to FALSE will stop a listener
self.on_data_running = False # this value is true if we are processing data
self.pid = str(os.getpid())
self.log_file = "StreamingCrawler.log"
#database module
if gSave_to_DB:
#self.dbconn = DBConnection.DBConnection(log=self.log)
self.log("not support: storing to DB")
#FileSaver
self.fileconn = StreamFileSaverWrapper.StreamFileSaverWrapper(filter[0]) # ['http nyti ms']
StreamListener.__init__(self)
self.filter = filter
now_str = datetime.datetime.now().strftime('%m%d%Y_%H%M%S')
self.log_file = "CrawlerListener." + now_str + "." + "pid_{0}".format(self.pid) + ".log"
FileLog.set_log_dir() #check the log dir, and create it if necessary
def run():
"""Main logic for this analysis."""
FileLog.set_log_dir()
Util.ensure_dir_exist(_OUTPUT_DIR)
if _REGENERATE_DATA:
deltas = find_deltas()
cache = Util.load_cache()
seeds = Util.load_seeds()
# Find top news
param_str = '_t%s' % (int(_SIZE_TOP_NEWS * 100))
gts = ground_truths.get_gt_rankings(seeds, DataSet.ALL)
top_news = ground_truths.find_target_news(gts, _SIZE_TOP_NEWS)
# Do analysis for all delta, including sys.max to do analysis with no delta.
for delta in [sys.maxint] + _DELTAS:
param_str = _get_param_str(delta)
(all_counts, original_counts,
retweet_counts, top_counts) = find_device_counts(delta, deltas, top_news,
cache)
(sorted_all_counts, sorted_original_counts,
sorted_retweet_counts, sorted_top_counts) = sort_data(all_counts,
original_counts,
retweet_counts,
top_counts)
output_data(sorted_all_counts, sorted_original_counts,
sorted_retweet_counts, sorted_top_counts, param_str)
if _REDRAW_GRAPH:
for delta in [sys.maxint] + _DELTAS:
param_str = _get_param_str(delta)
(top, original_dict, retweet_dict) = load_data(param_str)
log('Drawing graph for delta %s...' % delta)
draw_graph(top, original_dict, retweet_dict, param_str)
log('Analysis complete.')
def static_status_to_user_tsv(status_user):
#insert a new user
location = ""
utc_offset = ""
time_zone = ""
if hasattr(status_user, 'time_zone'):
if status_user.time_zone != None:
time_zone = status_user.time_zone
if hasattr(status_user, 'utc_offset'):
if status_user.utc_offset != None:
utc_offset = status_user.utc_offset
if hasattr(status_user, 'location'):
if status_user.location != None:
location = status_user.location.encode('utf8')
try:
line = "\t".join([
str(status_user.id_str), #user_id
StreamFileSaverWrapper.ensure_escape_for_mysql(str(status_user.screen_name)), #screen_id
str(status_user.statuses_count), #tweets_count
str(status_user.created_at), #created_at
str(status_user.followers_count), #followers_count
str(status_user.friends_count), #friends_count
StreamFileSaverWrapper.ensure_escape_for_mysql(str(location)), #location
str(status_user.listed_count), #listed_count
str(time_zone), #time_zone
str(utc_offset) #utc_offset
]
)
return line + "\n"
except Exception as e:
FileLog.log("FileSaver.log", "FileSaver(pid:{0}): "
.format(str(os.getpid())) + str(e),
exception_tb=sys.exc_traceback)
return None
def run():
"""Main logic for this analysis."""
FileLog.set_log_dir()
Util.ensure_dir_exist(_OUTPUT_DIR)
if _REGENERATE_DATA:
deltas = find_deltas()
cache = Util.load_cache()
seeds = Util.load_seeds()
# Find top news
param_str = '_t%s' % (int(_SIZE_TOP_NEWS * 100))
gts = ground_truths.get_gt_rankings(seeds, DataSet.ALL)
top_news = ground_truths.find_target_news(gts, _SIZE_TOP_NEWS)
# Do analysis for all delta, including sys.max to do analysis with no delta.
for delta in [sys.maxint] + _DELTAS:
param_str = _get_param_str(delta)
(all_counts, original_counts, retweet_counts,
top_counts) = find_device_counts(delta, deltas, top_news, cache)
(sorted_all_counts, sorted_original_counts, sorted_retweet_counts,
sorted_top_counts) = sort_data(all_counts, original_counts,
retweet_counts, top_counts)
output_data(sorted_all_counts, sorted_original_counts,
sorted_retweet_counts, sorted_top_counts, param_str)
if _REDRAW_GRAPH:
for delta in [sys.maxint] + _DELTAS:
param_str = _get_param_str(delta)
(top, original_dict, retweet_dict) = load_data(param_str)
log('Drawing graph for delta %s...' % delta)
draw_graph(top, original_dict, retweet_dict, param_str)
log('Analysis complete.')
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 log(self, message, tb=None):
"""Log error message and its traceback(optional)"""
FileLog.log(self.log_filename, "StreamFileSaverWrapper: " + str(message), exception_tb=tb)
def run():
FileLog.set_log_dir()
output_dir = '../data/TimeConstraint/'
Util.ensure_dir_exist(output_dir)
seeds = Util.load_seeds()
for category in _CATEGORIES:
run_params_str = '%s' % (category)
log('Preforming analysis: Cateogry = %s' % run_params_str)
# Find counts.
(num_0_1, num_0_1_common, num_0_1_experts_p, num_0_1_experts_f, num_0_1_experts_ci, num_0_1_experts_all,
num_1_4, num_1_4_common, num_1_4_experts_p, num_1_4_experts_f, num_1_4_experts_ci, num_1_4_experts_all,
num_4_8, num_4_8_common, num_4_8_experts_p, num_4_8_experts_f, num_4_8_experts_ci, num_4_8_experts_all,
num_cu_1_1, num_cu_1_2, num_cu_1_3,
num_cu_4_1, num_cu_4_2, num_cu_4_3,
num_cu_8_1, num_cu_8_2, num_cu_8_3,
num_after_8, num_total) = find_counts(seeds, category)
# Calculate non-common users.
num_0_1_noncommon = num_0_1 - num_0_1_common
num_1_4_noncommon = num_1_4 - num_1_4_common
num_4_8_noncommon = num_4_8 - num_4_8_common
with open('%s%s.txt' % (output_dir, run_params_str), 'w') as out_file:
out_file.write('Common Users\n')
out_file.write('------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_common, (100 * (float(num_0_1_common) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_common, (100 * (float(num_1_4_common) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_common, (100 * (float(num_4_8_common) / num_total))))
out_file.write('\nCommon Users (Breakdown, Delta 1)\n')
out_file.write('------------\n')
out_file.write('Common Users 1: %s (%s percent of total)\n'
% (num_cu_1_1, (100 * (float(num_cu_1_1) / num_total))))
out_file.write('Common Users 2: %s (%s percent of total)\n'
% (num_cu_1_2, (100 * (float(num_cu_1_2) / num_total))))
out_file.write('Common Users 3: %s (%s percent of total)\n'
% (num_cu_1_3, (100 * (float(num_cu_1_1) / num_total))))
out_file.write('\nCommon Users (Breakdown, Delta 4)\n')
out_file.write('\nCommon Users (Breakdown, Delta 4)\n')
out_file.write('------------\n')
out_file.write('Common Users 1: %s (%s percent of total)\n'
% (num_cu_4_1, (100 * (float(num_cu_4_1) / num_total))))
out_file.write('Common Users 2: %s (%s percent of total)\n'
% (num_cu_4_2, (100 * (float(num_cu_4_2) / num_total))))
out_file.write('Common Users 3: %s (%s percent of total)\n'
% (num_cu_4_3, (100 * (float(num_cu_4_3) / num_total))))
out_file.write('\nCommon Users (Breakdown, Delta 8)\n')
out_file.write('------------\n')
out_file.write('Common Users 1: %s (%s percent of total)\n'
% (num_cu_8_1, (100 * (float(num_cu_8_1) / num_total))))
out_file.write('Common Users 2: %s (%s percent of total)\n'
% (num_cu_8_2, (100 * (float(num_cu_8_2) / num_total))))
out_file.write('Common Users 3: %s (%s percent of total)\n'
% (num_cu_8_3, (100 * (float(num_cu_8_3) / num_total))))
out_file.write('\nNon-Common Users\n')
out_file.write('----------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_noncommon, (100 * (float(num_0_1_noncommon) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_noncommon, (100 * (float(num_1_4_noncommon) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_noncommon, (100 * (float(num_4_8_noncommon) / num_total))))
out_file.write('\nExpert Precision Users\n')
out_file.write('----------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_experts_p, (100 * (float(num_0_1_experts_p) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_experts_p, (100 * (float(num_1_4_experts_p) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_experts_p, (100 * (float(num_4_8_experts_p) / num_total))))
out_file.write('\nExpert Fscore Users\n')
out_file.write('----------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_experts_f, (100 * (float(num_0_1_experts_f) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_experts_f, (100 * (float(num_1_4_experts_f) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_experts_f, (100 * (float(num_4_8_experts_f) / num_total))))
out_file.write('\nExpert CI Users\n')
out_file.write('----------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_experts_ci, (100 * (float(num_0_1_experts_ci) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_experts_ci, (100 * (float(num_1_4_experts_ci) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_experts_ci, (100 * (float(num_4_8_experts_ci) / num_total))))
out_file.write('\nExpert All Users\n')
out_file.write('----------------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1_experts_all, (100 * (float(num_0_1_experts_all) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4_experts_all, (100 * (float(num_1_4_experts_all) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8_experts_all, (100 * (float(num_4_8_experts_all) / num_total))))
out_file.write('\nAll Users\n')
out_file.write('---------\n')
out_file.write('0 - 1 hours: %s (%s percent of total)\n'
% (num_0_1, (100 * (float(num_0_1) / num_total))))
out_file.write('1 - 4 hours: %s (%s percent of total)\n'
% (num_1_4, (100 * (float(num_1_4) / num_total))))
out_file.write('4 - 8 hours: %s (%s percent of total)\n'
% (num_4_8, (100 * (float(num_4_8) / num_total))))
out_file.write('8 - + hours: %s (%s percent of total)\n'
% (num_after_8, (100 * (float(num_after_8) / num_total))))
out_file.write('\ntotal: %s' % num_total);
def log(self, msg, tb=None):
FileLog.log(self.log_file, msg, exception_tb=tb)
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 log(self, msg, tb=None, screen_only=False):
if screen_only: #do not save to log file, only print it to screen
FileLog.log(None, "StreamingCrawler:" + msg, exception_tb=tb)
else:
FileLog.log(self.log_file, "StreamingCrawler:" + msg, exception_tb=tb)
def log(self, msg, tb=None): #for future debug, not called in this class yet
FileLog.log(self.log_file, "(pid:{0})".format(self.pid) + str(msg), exception_tb=tb)
def log(self, msg, tb=None): #for debug purpose
FileLog.log(self.log_file, str(msg), exception_tb=tb)
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)
