def generate_output(folder_name):
measure1 = {}
tty_names = load.loadLocNames()
visitation_sum = ''
visitation_avg = ''
each_gang = ''
series_rival = []
series_nonrival = []
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'visit_sets.json', 'rb') as fp1:
measure1 = anyjson.deserialize(fp1.read())
for gang_id in measure1:
if not (len(measure1[gang_id]['rival']) == 0 and len(measure1[gang_id]['nonrival']) == 0):
visitation_sum += tty_names[int(gang_id)] + ',' + str(sum(measure1[gang_id]['rival'])) + ', ' + str(sum(measure1[gang_id]['nonrival'])) + '\n'
visitation_avg += tty_names[int(gang_id)] + ',' + str(0 if len(measure1[gang_id]['rival']) == 0 else round(sum(measure1[gang_id]['rival'])/float(len(measure1[gang_id]['rival'])), 5)) + ', ' + str(0 if len(measure1[gang_id]['nonrival']) == 0 else round(sum(measure1[gang_id]['nonrival'])/float(len(measure1[gang_id]['nonrival'])), 5) ) + '\n'
each_gang += "name = '" + tty_names[int(gang_id)] + "'\n"
each_gang += 'rival = ' + arr_to_str(measure1[gang_id]['rival']) + '\n'
each_gang += 'nonrival = ' + arr_to_str(measure1[gang_id]['nonrival']) + '\n\n'
series_rival += measure1[gang_id]['rival']
series_nonrival += measure1[gang_id]['nonrival']
visit_series = 'rival = ' + arr_to_str(series_rival) + '\n' + 'nonrival = ' + arr_to_str(series_nonrival)
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'visitation_sum' + '.csv', 'wb') as fp:
fp.write(visitation_sum)
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'visitation_avg' + '.csv', 'wb') as fp:
fp.write(visitation_avg)
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'each_gang' + '.txt', 'wb') as fp:
fp.write(each_gang)
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'visit_series' + '.txt', 'wb') as fp:
fp.write(visit_series)
def generate_charts(folder_name):
measure1 = {}
tty_names = load.loadLocNames()
names = []
sum_rival = []
sum_nonrival = []
avg_rival = []
avg_nonrival = []
with open('data/' + my.DATA_FOLDER + 'metrics/' + folder_name + '/' + 'visit_sets.json', 'rb') as fp1:
measure1 = anyjson.deserialize(fp1.read())
for gang_id in measure1:
if not (len(measure1[gang_id]['rival']) == 0 and len(measure1[gang_id]['nonrival']) == 0):
names.append(str(tty_names[int(gang_id)].replace('_', ' ')))
sum_rival.append(round(sum(measure1[gang_id]['rival']), 5))
sum_nonrival.append(round(sum(measure1[gang_id]['nonrival']),5))
avg_rival.append(0 if len(measure1[gang_id]['rival']) == 0 else round(sum(measure1[gang_id]['rival'])/float(len(measure1[gang_id]['rival'])), 5))
avg_nonrival.append(0 if len(measure1[gang_id]['nonrival']) == 0 else round(sum(measure1[gang_id]['nonrival'])/float(len(measure1[gang_id]['nonrival'])), 5))
'''print names
print sum_rival
print sum_nonrival
print avg_rival
print avg_nonrival'''
plot_visits_chart(names, sum_rival, sum_nonrival, folder_name, 'visits_sum.png')
plot_visits_chart(names, avg_rival, avg_nonrival, folder_name, 'visits_avg.png')
def see_rivalry_mat(): # See Rivalry matrix tty_names = load.loadLocNames() x = ['GANG NAME', '#'] x.extend(range(23,55)) print '%20s - %2s: %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s' % tuple(x) for gang_id in range(23,55): x = [tty_names[gang_id], gang_id] y = ['X' if rival_id in my.HBK_GANG_AND_RIVAL_IDS[gang_id] else '.' for rival_id in range(23,55)] x.extend(y) print '%20s - %2s: %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s %3s' % tuple(x)
def see_visit_mat(): # See Visit matrix tty_polys, hbk_poly = load.loadLocPoly() hbk_all_tweets = load.loadAllTweets() hbk_user_home_loc = load.loadAllHomeLoc(hbk_poly) hbk_users_in_gang_t = load.loadUsersInGangTty(tty_polys, hbk_user_home_loc) tty_names = load.loadLocNames() visit_mat = calc.calcVisitationMat(hbk_all_tweets, tty_polys, hbk_users_in_gang_t) x = ['GANG NAME', '#'] x.extend(range(23,55)) print '%20s - %2s: %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s' % tuple(x) for gang_id in visit_mat: x = [tty_names[gang_id], gang_id] y = dict([(to_id, visit_mat[gang_id][to_id]) if gang_id != to_id else (to_id, 0) for to_id in visit_mat[gang_id]]) y = dict([(to_id, y[to_id]) if y[to_id] != 0 else (to_id, '.') for to_id in y]) y = [str(y[to_id])+'r' if to_id in my.HBK_GANG_AND_RIVAL_IDS[gang_id] and y[to_id] !='.' else y[to_id] for to_id in y] x.extend(y) print '%20s - %2s: %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s %4s' % tuple(x)
def see_gang_tweet_counts():
# See each gang's tweet count
tty_polys, hbk_poly = load.loadLocPoly()
tty_names = load.loadLocNames()
hbk_all_tweets = load.loadAllTweets()
hbk_user_home_loc = load.loadAllHomeLoc(hbk_poly)
hbk_users_in_gang_t = load.loadUsersInGangTty(tty_polys, hbk_user_home_loc)
# read each gang's tweet count
hbk_tweets_by_gang = {}
print 'Finding tweet count by each gang...'
for gang_id in hbk_users_in_gang_t:
hbk_tweets_by_gang[gang_id] = len(prep.keepUserIds(hbk_all_tweets, hbk_users_in_gang_t[gang_id]))
print 'Each gang\'s tweet count: %s' % hbk_tweets_by_gang
print '%2s %15s %5s %5s %8s %6s' % ('ID', 'NAME', '#TWs', '#USERs', '#RIVALs', 'TW/USR')
for gang_id in hbk_tweets_by_gang:
if hbk_tweets_by_gang[gang_id] != 0:
print '%2s %15s %5s %5s %8s %6s' % (gang_id, tty_names[gang_id], hbk_tweets_by_gang[gang_id], len(hbk_users_in_gang_t[gang_id]), len(my.HBK_GANG_AND_RIVAL_IDS[gang_id]), int(hbk_tweets_by_gang[gang_id]/float(len(hbk_users_in_gang_t[gang_id]))))
print 'Total number of users: %s' % sum([len(hbk_users_in_gang_t[gang_id]) for gang_id in hbk_tweets_by_gang if hbk_tweets_by_gang[gang_id] != 0])
print 'Total tweets from all users: %s' % sum([hbk_tweets_by_gang[gang_id] for gang_id in hbk_tweets_by_gang])
def see_rivalry_list():
# See Rivalry list
tty_polys, hbk_poly = load.loadLocPoly()
hbk_all_tweets = load.loadAllTweets()
hbk_user_home_loc = load.loadAllHomeLoc(hbk_poly)
hbk_users_in_gang_t = load.loadUsersInGangTty(tty_polys, hbk_user_home_loc)
tty_names = load.loadLocNames()
visit_mat_1 = calc.calcVisitationMat(hbk_all_tweets, tty_polys, hbk_users_in_gang_t)
dist_norm = calc.calcDistNormCDF()
visit_mat = calc.calcVisitationMat(hbk_all_tweets, tty_polys, hbk_users_in_gang_t, dist_norm, hbk_user_home_loc)
rivalry_list = {}
for gang_id in my.HBK_GANG_AND_RIVAL_IDS:
for rival_id in [to_id for to_id in my.HBK_GANG_ID_LIST if to_id != gang_id]:
if visit_mat_1[gang_id][rival_id] >= 5 and str(gang_id)+str(rival_id) not in rivalry_list and str(rival_id)+str(gang_id) not in rivalry_list:
this_row = [gang_id, tty_names[gang_id], rival_id, tty_names[rival_id], \
int(visit_mat[gang_id][rival_id]), \
int(visit_mat[rival_id][gang_id])]
this_row.append('rival') if rival_id in my.HBK_GANG_AND_RIVAL_IDS[gang_id] else this_row.append('nonrival')
affinity = round(1.0/abs(visit_mat[gang_id][rival_id]-visit_mat[rival_id][gang_id]), 3) if visit_mat[gang_id][rival_id] != visit_mat[rival_id][gang_id] else 0
this_row.append(affinity)
this_row.append(int((visit_mat[gang_id][rival_id]+visit_mat[rival_id][gang_id])/2))
rivalry_list[str(gang_id)+str(rival_id)] = this_row
rivalry_list = rivalry_list.values()
rivals = [row for row in rivalry_list if row[6] == 'rival']
nonrivals = [row for row in rivalry_list if row[6] == 'nonrival']
rivalry_list = rivals + nonrivals
val = ['A#', 'GANG A', 'B#', 'GANG B', 'A>B', 'B>A', 'RnR', 'Affinity', 'AvgTw']
print '%2s %20s => %2s %20s \t %4s \t %4s \t %8s \t %8s \t %5s' % tuple(val)
for val in rivalry_list:
print '%2s %20s => %2s %20s \t %4s \t %4s \t %8s \t %8s \t %5s' % tuple(val)
