def generate_colocation_single(checkins, config, p, k, t_diff, s_diff):
dataset_name = config['dataset'][p]
kwargs = config['kwargs']
n_core = kwargs['n_core']
start = kwargs['colocation']['start']
finish = kwargs['colocation']['finish']
order = kwargs['colocation']['order']
working_directory = '/'.join(
[config['directory']['intermediate'], dataset_name])
make_sure_path_exists(working_directory)
kdtree_intermediate = '/'.join([
working_directory,
config['intermediate']['colocation']['kdtree'].format(p, k)
])
if is_file_exists(kdtree_intermediate):
st_tree = sk_joblib.load(kdtree_intermediate)
else:
st_tree = create_spatiotemporal_kd_tree(checkins, kdtree_intermediate,
t_diff, s_diff)
other = extract_spatiotemporal_normalized(checkins, t_diff, s_diff)
begins, ends = init_begin_end(n_core,
len(checkins),
start=start,
finish=finish)
### Generate colocation based on extracted checkins
prepare_colocation(config, p, k, t_diff, s_diff, begins, ends)
### Start from bottom
if order == 'ascending':
Parallel(n_jobs=n_core)(delayed(execute_parallel_st_tree_single)(checkins, config, st_tree, other[begins[i]:ends[i]], \
p, k, t_diff, s_diff, begins[i], ends[i]) \
for i in range(len(begins)))
else:
Parallel(n_jobs=n_core)(delayed(execute_parallel_st_tree_single)(checkins, config, st_tree, other[begins[i-1]:ends[i-1]], \
p, k, t_diff, s_diff, begins[i-1], ends[i-1]) \
for i in xrange(len(begins), 0, -1))
def extract_popularity(checkins, config, p, k):
intermediate_root = config['directory']['intermediate']
dataset_names = config['dataset']
modes = config['mode']
popularity_intermediate_file = config['intermediate']['sci']['popularity']
pickle_directory = '/'.join([intermediate_root, dataset_names[p]])
make_sure_path_exists(pickle_directory)
pickle_filename = '/'.join(
[pickle_directory,
popularity_intermediate_file.format(modes[k])])
if not is_file_exists(pickle_filename):
stat_lp = {} ### Popularity score for location l
visit_per_venue, p_l = extract_visit_per_venue(checkins, config)
p_ul = extract_aggregated_visit(visit_per_venue, p_l)
### Evaluate the weight for each venue
for vid, arr in p_ul.items():
if len(arr) > 0:
ent = entropy(arr)
stat_lp[vid] = ent
else:
stat_lp[vid] = 0.0
### Memory management
del p_l[:]
del p_l
visit_per_venue.clear()
p_ul.clear()
del visit_per_venue, p_ul
### Write to pickle intermediate file
with open(pickle_filename, 'wb') as handle:
pickle.dump(stat_lp, handle, protocol=pickle.HIGHEST_PROTOCOL)
else:
with open(pickle_filename, 'rb') as handle:
stat_lp = pickle.load(handle)
### Return the result
return stat_lp
def temporal_factor(config, p, k, t, d, g2):
g4 = None
### Intermediate file -- check if exists
pgt_root = config['directory']['pgt']
dataset_names = config['dataset']
modes = config['mode']
pgt_root = config['directory']['pgt']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
g4_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g4'].format(modes[k], t, d)])
if is_file_exists(g4_file) is True:
g4 = pd.read_csv(g4_file)
else:
global_df = transform_colocation_pgt(config, p, k, t, d, 'global')
colocation_df = read_colocation_file(config, p, k, t, d, \
usecols=['user1', 'user2', 'time1', 'time2'])
colocation_df['wg'] = global_df['wg'].values
colocation_df['time'] = (colocation_df['time1'] +
colocation_df['time2']) / 2
colocation_df.drop(columns=['time1', 'time2'], inplace=True)
groups = colocation_df.groupby(['user1', 'user2'])
g4 = applyParallel(config, groups, lambda_temporal)
g4 = g4.groupby(['user1', 'user2'])['wt'].agg(['sum'])
g4.reset_index(inplace=True)
g4.sort_values(['user1', 'user2'], inplace=True)
g4['g4'] = g2['g2'] * g4['sum']
g4[g4 < 0] = 0.0 ### Prevent negatives in values
g4['g4'] = g4['g4'] / max(g4['g4'])
g4.to_csv(g4_file, header=True, index=False, compression='bz2')
del colocation_df, groups
return g4
def extract_pi_loc_k(checkins, grouped, venues, user_visit, config, p, k,
start, finish, feature):
pgt_part_root = config['directory']['pgt_temp']
dataset_names = config['dataset']
modes = config['mode']
make_sure_path_exists('/'.join([pgt_part_root, dataset_names[p]]))
pgt_file_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['%s_part' % feature].format(modes[k], start, finish)])
if is_file_exists(pgt_file_part) is True:
pass
else:
user_visit = user_visit[(user_visit['visit_count'] > 0)]
#debug('start', start, 'finish', finish)
if feature == 'personal':
ids = grouped['user'].values
grouping = 'user'
result = pd.DataFrame(columns=['user', 'location', 'p_i'])
elif feature == 'global':
ids = grouped['location'].values
grouping = 'location'
result = pd.DataFrame(columns=['location', 'p_i'])
t0 = time.time()
for i in range(start, finish):
u_i = ids[i]
df = df_uid(checkins, u_i, config, grouping)
visit_match = user_visit.isin({grouping: df[grouping].unique()})
visit_temp = user_visit[visit_match[grouping]]
if len(visit_temp > 0):
if feature == 'personal':
### Extract the p_i of each user's visit
visit_temp['p_i'] = visit_temp.apply(
lambda x: calculate_density(x, cd, df, venues), axis=1)
visit_temp = visit_temp[['user', 'location', 'p_i']]
result = result.append(visit_temp, ignore_index=True)
elif feature == 'global':
### Aggregate visit on each location
aggregations = {
'user_count': {
'entropy': lambda x: calculate_entropy(x)
},
}
grouped = visit_temp.groupby(['location']) \
.agg(aggregations)
grouped.columns = [
"_".join(x) for x in grouped.columns.ravel()
]
grouped.rename(columns={"user_count_entropy": "p_i"},
inplace=True)
grouped.reset_index(inplace=True)
# debug(grouped.columns.values)
# debug(grouped.head())
grouped = grouped[['location', 'p_i']]
result = result.append(grouped, ignore_index=True)
t1 = time.time()
### Writing to temp file
if feature == 'personal':
result.drop_duplicates(subset=['user', 'location'], inplace=True)
result.to_csv(pgt_file_part, index=False, header=True)
debug('Finished density calculation into %s in %s seconds' %
(pgt_file_part, str(t1 - t0)))
def parallel_sampling(config, p, k, t, d):
debug('Start sampling', 'p', p, 'k', k, 't', t, 'd', d)
kwargs = config['kwargs']
is_read_compressed = kwargs['read_compressed']
colocation_root = config['directory']['colocation']
make_sure_path_exists(colocation_root)
if is_read_compressed is False:
sample_name = config['intermediate']['colocation']['sample_csv']
compression = None
else:
sample_name = config['intermediate']['colocation']['sample_compressed']
compression = 'bz2'
sample_rate = kwargs['preprocessing']['sampling']['rate']
sample_fullname = '/'.join(
[colocation_root,
sample_name.format(p, k, t, d, sample_rate)])
df = read_colocation_file(config, p, k, t, d)
df = df.sample(frac=sample_rate, random_state=1)
df.to_csv(sample_fullname,
header=True,
index=False,
compression=compression,
mode='w')
debug('Finished sampling', 'p', p, 'k', k, 't', t, 'd', d, '#sample: ',
len(df))
def run_pgt_evaluation(config):
kwargs = config['kwargs']
n_core = kwargs['n_core']
all_datasets = config['dataset']
all_modes = config['mode']
datasets = kwargs['active_dataset']
modes = kwargs['active_mode']
t_diffs = kwargs['ts']
s_diffs = kwargs['ds']
report_directory = config['directory']['report']
make_sure_path_exists(report_directory)
for dataset_name in datasets:
p = all_datasets.index(dataset_name)
for mode in modes:
k = all_modes.index(mode)
debug('Run PGT Evaluation on Dataset', dataset_name, p, 'Mode',
mode, k, '#Core', n_core)
### Creating the report file
result_filename = '/'.join(
[report_directory, 'PGT_result_p{}_k{}.csv'.format(p, k)])
remove_file_if_exists(result_filename)
with open(result_filename, 'ab') as fw:
fw.write(
'p,k,t,d,auc,precision,recall,f1,#friends,#data,feature_set,preprocessing\n'
)
for t_diff in t_diffs:
for s_diff in s_diffs:
pgt_evaluation(config, p, k, t_diff, s_diff)
gc.collect()
def write_statistics(df, config, p, k, t, d):
dataset_names = config['dataset']
compressed = config['kwargs']['compress_output']
sci_root = config['directory']['sci']
make_sure_path_exists('/'.join([sci_root, dataset_names[p]]))
if compressed is True:
sci_name = config['intermediate']['sci']['evaluation_compressed']
compression = 'bz2'
else:
sci_name = config['intermediate']['sci']['evaluation']
compression = None
df.to_csv('/'.join([sci_root, dataset_names[p], sci_name.format(p, k, t, d)]), \
header=True, index=False, compression=compression)
def extract_pgt(config, p, k, t, d):
dataset_names = config['dataset']
compressed = config['kwargs']['compress_output']
pgt_root = config['directory']['pgt']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
if compressed is True:
pgt_name = config['intermediate']['pgt']['pgt_output_compressed']
compression = 'bz2'
else:
pgt_name = config['intermediate']['pgt']['pgt_output']
compression = None
intermediate_file = '/'.join(
[pgt_root, dataset_names[p],
pgt_name.format(p, k, t, d)])
if is_file_exists(intermediate_file) is False:
### Extracting each feature
if config['kwargs']['pgt']['extract_pgt']['run'] is True:
g1 = None
g2 = None
g3 = None
g4 = None
if config['kwargs']['pgt']['extract_pgt']['personal'] is True:
g1, g2 = personal_factor(config, p, k, t, d) ### P in PGT
debug('Finished loading personal factor', 'p', p, 'k', k, 't',
t, 'd', d)
if config['kwargs']['pgt']['extract_pgt']['global'] is True:
g3 = global_factor(config, p, k, t, d, g2) ### PG in PGT
debug('Finished loading global factor', 'p', p, 'k', k, 't', t,
'd', d)
if config['kwargs']['pgt']['extract_pgt']['temporal'] is True:
g4 = temporal_factor(config, p, k, t, d, g2) ### PGT in PGT
debug('Finished loading temporal factor', 'p', p, 'k', k, 't',
t, 'd', d)
### Merging all together
if config['kwargs']['pgt']['extract_pgt']['merge'] is True:
if g1 is not None and g2 is not None and g3 is not None and g4 is not None:
df = g1[['user1', 'user2',
'g1']].merge(g2[['user1', 'user2', 'g2']],
on=['user1', 'user2'])
df = df.merge(g3[['user1', 'user2', 'g3']],
on=['user1', 'user2'])
df = df.merge(g4[['user1', 'user2', 'g4']],
on=['user1', 'user2'])
friend_df = extract_friendships(dataset_names[p], config)
df = determine_social_tie(df, friend_df)
df.to_csv(intermediate_file,
header=True,
index=False,
compression=compression)
def prepare_colocation(config, p, k, t_diff, s_diff, begins, ends):
working_directory = config['directory']['colocation']
filename = config['intermediate']['colocation']['part']
dataset_name = config['dataset'][p]
make_sure_path_exists('/'.join([working_directory, dataset_name]))
clear_dir = config['kwargs']['colocation']['clear_dir']
if clear_dir is True:
remove_all_files('/'.join([working_directory, dataset_name]))
### Prepare the files
for i in range(len(begins)):
with open(
'/'.join([
working_directory, dataset_name,
filename.format(p, k, t_diff, s_diff, begins[i], ends[i])
]), 'wb'):
pass
debug('Each colocation part file has been created')
def pgt_evaluation(config, p, k, t, d):
debug('Evaluating PGT for p{}, k{}, t{}, d{}'.format(p, k, t, d))
dataset_names = config['dataset']
compressed = config['kwargs']['read_compressed']
pgt_root = config['directory']['pgt']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
if compressed is True:
pgt_name = config['intermediate']['pgt']['pgt_output_compressed']
else:
pgt_name = config['intermediate']['pgt']['pgt_output']
evaluation_name = '/'.join(
[pgt_root, dataset_names[p],
pgt_name.format(p, k, t, d)])
if is_file_exists(evaluation_name) is True:
dataset = pd.read_csv(evaluation_name)
# Format: 'user1', 'user2', 'g1', 'g2', 'g3', 'g4', 'link'
X = dataset[['g1', 'g2', 'g3', 'g4']].values
y = dataset[['link']].values
### Normalize unexpected values
X[np.isinf(X)] = 0
X[np.isnan(X)] = 0
y[np.isinf(y)] = 0
y[np.isnan(y)] = 0
selected_feature_set = config['kwargs']['pgt_eval']['features']
if selected_feature_set == 'all':
notes = ["PGT+", "PGT", "P0", "P", "PG"]
assign = [[0, 1, 2, 3], [3], [0], [1], [2]]
else: ### Summary only
notes = ["PGT+", "PGT"]
assign = [[0, 1, 2, 3], [3]]
debug(notes, assign)
texts = generate_report(config, X, y, assign, notes, p, k, t, d)
del X, y
report_directory = config['directory']['report']
result_filename = '/'.join(
[report_directory, 'PGT_result_p{}_k{}.csv'.format(p, k)])
for text in texts:
if text is not None:
with open(result_filename, 'ab') as fw:
fw.write(text + '\n')
else:
debug('File not found', evaluation_name)
def personal_factor(config, p, k, t, d):
g1 = None
g2 = None
### Intermediate file -- check if exists
pgt_root = config['directory']['pgt']
dataset_names = config['dataset']
modes = config['mode']
pgt_root = config['directory']['pgt']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
g1_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g1'].format(modes[k], t, d)])
g2_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g2'].format(modes[k], t, d)])
if is_file_exists(g1_file) is True and is_file_exists(g2_file) is True:
g1 = pd.read_csv(g1_file)
g2 = pd.read_csv(g2_file)
else:
### If it does not exist
feature = 'personal'
colocation_df = transform_colocation_pgt(config, p, k, t, d, feature)
### Aggregate the weight for each user pair
g1 = colocation_df.groupby(['user1',
'user2'])['wp'].agg(['mean', 'count'])
g2 = colocation_df.groupby(['user1',
'user2'])['wp'].agg(['max', 'count'])
g1.reset_index(inplace=True)
g2.reset_index(inplace=True)
g1.sort_values(['user1', 'user2'], inplace=True)
g2.sort_values(['user1', 'user2'], inplace=True)
g1['g1'] = g1['mean'] * g1['count']
g2['g2'] = g2['max'] * g2['count']
g1['g1'] = g1['g1'] / max(g1['g1'])
g2['g2'] = g2['g2'] / max(g2['g2'])
g1.to_csv(g1_file, header=True, index=False, compression='bz2')
g2.to_csv(g2_file, header=True, index=False, compression='bz2')
# debug(g1.head())
# debug(g2.head())
del colocation_df
return g1, g2
def global_factor(config, p, k, t, d, g2):
g3 = None
### Intermediate file -- check if exists
pgt_root = config['directory']['pgt']
dataset_names = config['dataset']
modes = config['mode']
pgt_root = config['directory']['pgt']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
g3_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g3'].format(modes[k], t, d)])
if is_file_exists(g3_file) is True:
g3 = pd.read_csv(g3_file)
else:
feature = 'global'
colocation_df = transform_colocation_pgt(config, p, k, t, d, feature)
g3 = colocation_df.groupby(['user1', 'user2'])['wg'].agg(['sum'])
g3.reset_index(inplace=True)
g3.sort_values(['user1', 'user2'], inplace=True)
g3['g3'] = g2['g2'] * g3['sum']
g3['g3'] = g3['g3'] / max(g3['g3'])
g3.to_csv(g3_file, header=True, index=False, compression='bz2')
del colocation_df
return g3
def extract_colocation_features(stat_lp, config, p, k, t, d):
debug('p', p, 'k', k, 't', t, 'd', d)
### Check if SCI intermediate exists
dataset_names = config['dataset']
compressed = config['kwargs']['compress_output']
sci_root = config['directory']['sci']
make_sure_path_exists('/'.join([sci_root, dataset_names[p]]))
if compressed is True:
sci_name = config['intermediate']['sci']['evaluation_compressed']
else:
sci_name = config['intermediate']['sci']['evaluation']
sci_name = '/'.join(
[sci_root, dataset_names[p],
sci_name.format(p, k, t, d)])
if is_file_exists(sci_name):
debug('File %s exists' % sci_name)
else:
### Read (original) friendship from file
friend_df = extract_friendships(dataset_names[p], config)
colocation_df = read_colocation_file(config, p, k, t, d)
### Find if the two users in the colocated check-ins are friends / stranger
colocation_df = determine_social_tie(colocation_df, friend_df)
debug('#colocations', len(colocation_df), 'p', p, 'k', k, 't', t, 'd',
d)
### Find the stability value for each co-location pairs
groups = colocation_df.groupby(['user1', 'user2', 'link'])
grouped = aggregate_stats(groups, stat_lp, p, k, t, d)
### Write the result into a csv output
write_statistics(grouped, config, p, k, t, d)
### Memory management
del friend_df
del colocation_df
del grouped
debug('Finished extract_colocation_features', 'p', p, 'k', k, 't', t, 'd',
d)
def process_reduce(config, p, k, t_diff, s_diff):
out_format = config['intermediate']['colocation']['csv']
re_format = config['intermediate']['colocation']['re']
working_directory = config['directory']['colocation']
dataset_name = config['dataset'][p]
make_sure_path_exists('/'.join([working_directory, dataset_name]))
pattern = re.compile(re_format.format(p, k, t_diff, s_diff))
file_list = []
for fname in os.listdir('/'.join([working_directory, dataset_name])):
if fname.endswith(".csv"):
if pattern.match(fname):
file_list.append('/'.join(
[working_directory, dataset_name, fname]))
output = '/'.join([
working_directory, dataset_name,
out_format.format(p, k, t_diff, s_diff)
])
with open(output, 'wb') as fw:
fw.write('%s' % colocation_header)
with open(output, 'ab') as wfd:
for f in file_list:
with open(f, 'rb') as fd:
shutil.copyfileobj(fd, wfd, 1024 * 1024 * 10)
#10MB per writing chunk to avoid reading big file into memory.
def prepare_extraction(config, feature, p, k):
### Check if PGT intermediate exists
dataset_names = config['dataset']
modes = config['mode']
pgt_root = config['directory']['pgt']
pgt_part_root = config['directory']['pgt_temp']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
pgt_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt'][feature].format(modes[k])])
if is_file_exists(pgt_file) is True:
debug('PGT %s exists' % feature)
else:
if feature == 'personal':
checkins, grouped = extract_checkins_per_user(
dataset_names[p], modes[k], config)
elif feature == 'global':
checkins, grouped = extract_checkins_per_venue(
dataset_names[p], modes[k], config)
user_visit_dir = '/'.join(
[config['directory']['intermediate'], config['dataset'][p]])
user_visit_name = config['intermediate']['pgt']['user_visit'].format(
config['mode'][k])
final_name = '/'.join([user_visit_dir, user_visit_name])
### Using user visit database
if is_file_exists(final_name) is True:
user_visit = pd.read_csv(final_name, compression='bz2')
venues = checkins[['location', 'latitude', 'longitude'
]].drop_duplicates(subset=['location'])
debug('#Venues', len(venues), 'p', p, 'k', k)
kwargs = config['kwargs']
n_core = kwargs['n_core']
start = kwargs['pgt'][feature]['start']
finish = kwargs['pgt'][feature]['finish']
begins, ends = init_begin_end(n_core,
len(grouped),
start=start,
finish=finish)
if feature == 'personal':
function = density_location
elif feature == 'global':
function = entropy_location
### Map step
Parallel(n_jobs=n_core)(delayed(function)(checkins, grouped, venues, user_visit, \
config, p, k, begins[i-1], ends[i-1]) \
for i in xrange(len(begins), 0, -1))
### Reduce step
if feature == 'personal':
result = pd.DataFrame(columns=['user', 'location', 'p_i'])
elif feature == 'global':
result = pd.DataFrame(columns=['location', 'p_i'])
for i in range(len(begins)):
start = begins[i]
finish = ends[i]
pgt_file_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['%s_part' % feature].format(modes[k], start, finish)])
temp = pd.read_csv(pgt_file_part)
result = result.append(temp, ignore_index=True)
if feature == 'personal':
result.drop_duplicates(subset=['user', 'location'],
inplace=True)
result.sort_values(['user', 'location'], inplace=True)
elif feature == 'global':
result.sort_values(['location'], inplace=True)
debug('#User Visits', len(result))
result.to_csv(pgt_file, index=False, header=True)
### Clean up mess if needed
if config['kwargs']['pgt'][feature]['clean_temp'] is True:
for i in range(len(begins)):
start = begins[i]
finish = ends[i]
pgt_file_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['%s_part' % feature].format(modes[k], start, finish)])
remove_file_if_exists(pgt_file_part)
else:
debug(
'Please generate the user visit first through preprocessing/read.py',
'(function: generate_user_visit)')
def transform_colocation_pgt(config, p, k, t, d, feature):
dataset_names = config['dataset']
modes = config['mode']
pgt_root = config['directory']['pgt']
pgt_part_root = config['directory']['pgt_temp']
make_sure_path_exists('/'.join([pgt_root, dataset_names[p]]))
make_sure_path_exists('/'.join([pgt_part_root, dataset_names[p]]))
pgt_file = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt'][feature].format(modes[k])])
### Check if PGT intermediate exists
if is_file_exists(pgt_file) is False:
debug('PGT %s does not exists' % feature)
debug('Please run PGT %s factor extraction first' % feature)
return None
else:
g0 = '/'.join([pgt_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g0_%s' % feature].format(modes[k], t, d)])
if is_file_exists(g0) is False:
if feature == 'personal':
### columns=['user', 'location', 'p_i']
personal_density = pd.read_csv(pgt_file)
col_name = 'wp'
elif feature == 'global':
### columns=['location', 'p_i']
entropy_location = pd.read_csv(pgt_file)
col_name = 'wg'
### user1,user2,location1,location2,time1,time2,lat1,lon1,lat2,lon2,t_diff,s_diff
### Evaluate the weight for each colocation
### Map step
i = 0
chunksize = 10**5
debug('chunksize for transform_colocation_pgt', chunksize)
for colocation_df in read_colocation_file(
config,
p,
k,
t,
d,
chunksize=chunksize,
usecols=['user1', 'user2', 'location1', 'location2']):
g0_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g0_%s_part' % feature].format(modes[k], t, d, i)])
debug('Processing', feature, 'part', g0_part)
if is_file_exists(g0_part) is False:
if feature == 'personal':
colocation_df[col_name] = colocation_df.apply(
lambda x: calculate_personal(x, personal_density),
axis=1)
elif feature == 'global':
colocation_df[col_name] = colocation_df.apply(
lambda x: calculate_global(x, entropy_location),
axis=1)
colocation_df.to_csv(g0_part,
index=False,
header=True,
compression='bz2')
i += 1
### Reduce step
colocation_df = pd.DataFrame(
columns=['user1', 'user2', 'location1', 'location2', col_name])
condition = True
i = 0
while (condition is True):
### Iterate over all chunks
g0_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g0_%s_part' % feature].format(modes[k], t, d, i)])
if is_file_exists(g0_part) is False:
condition = False
break
temp = pd.read_csv(g0_part)
colocation_df = colocation_df.append(temp, ignore_index=True)
i += 1
if config['kwargs']['pgt'][feature]['clean_temp'] is True:
condition = True
i = 0
while (condition is True):
g0_part = '/'.join([pgt_part_root, dataset_names[p], \
config['intermediate']['pgt']['pgt_g0_%s_part' % feature].format(modes[k], t, d, i)])
if is_file_exists(g0_part) is False:
condition = False
break
remove_file_if_exists(g0_part)
i += 1
colocation_df.replace([np.inf, -np.inf], np.nan, inplace=True)
colocation_df.fillna(0, inplace=True)
colocation_df.to_csv(g0,
index=False,
header=True,
compression='bz2')
gc.collect()
else:
colocation_df = pd.read_csv(g0)
debug('Loaded g0 %s successfully [%s]' % (feature, g0))
return colocation_df
def sci_evaluation(config, p, k, t, d):
debug('Evaluating SCI for p{}, k{}, t{}, d{}'.format(p, k, t, d))
dataset_names = config['dataset']
compressed = config['kwargs']['read_compressed']
sci_root = config['directory']['sci']
make_sure_path_exists('/'.join([sci_root, dataset_names[p]]))
if compressed is True:
sci_name = config['intermediate']['sci']['evaluation_compressed']
else:
sci_name = config['intermediate']['sci']['evaluation']
evaluation_name = '/'.join(
[sci_root, dataset_names[p],
sci_name.format(p, k, t, d)])
if is_file_exists(evaluation_name) is True:
dataset = pd.read_csv(evaluation_name)
# Format: 'uid1', 'uid2', 'frequency', 'diversity', 'duration', 'stability', 'popularity', 'link'
X = dataset[[
'frequency', 'diversity', 'duration', 'stability_std',
'popularity', 'stability_avg', 'stability_old'
]].values
y = dataset[['link']].values
### Selecting the feature set
selected_feature_set = config['kwargs']['sci_eval']['features']
### PAKDD 2017 Submission
if selected_feature_set == 'pakdd_2017_all':
notes = [
"SCI", "frequency", "diversity", "duration", "stability",
"F+D", "F+TD", "F+TS", "D+TD", "D+TS", "TD+TS", "F+D+TD",
"F+D+TS", "F+TD+TS", "D+TD+TS"
]
assign = [[0, 1, 2, 6], [0], [1], [2], [6], [0, 1], [0, 2], [0, 6],
[1, 2], [1, 6], [2, 6], [0, 1, 2], [0, 1, 6], [0, 2, 6],
[1, 2, 6]]
### PAKDD 2017 Submission (All)
elif selected_feature_set == 'pakdd_2017_summary':
notes = ['SCI']
assign = [[0, 1, 2, 6]]
## New Feature added (Popularity)
elif selected_feature_set == 'all_features':
notes = [
'SCI+', 'Frequency', 'Diversity', 'Duration', 'Stability',
'Popularity', 'F+D', 'F+TD', 'F+TS', 'F+P', 'D+TD', 'D+TS',
'D+P', 'TD+TS', 'TD+P', 'TS+P', 'F+D+TD', 'F+D+TS', 'F+D+P',
'F+TD+TS', 'F+TD+P', 'F+TS+P', 'D+TD+TS', 'D+TD+P', 'D+TS+P',
'TD+TS+P', 'F+D+TD+TS', 'F+D+TD+P', 'F+D+TS+P', 'F+TD+TS+P',
'D+TD+TS+P', 'SCI'
]
assign = [[0, 1, 2, 3, 4], [0], [1], [2], [3], [4], [0, 1], [0, 2],
[0, 3], [0, 4], [1, 2], [1, 3], [1, 4], [2, 3], [2, 4],
[3, 4], [0, 1, 2], [0, 1, 3], [0, 1, 4], [0, 2, 3],
[0, 2, 4], [0, 3, 4], [1, 2, 3], [1, 2, 4], [1, 3, 4],
[2, 3, 4], [0, 1, 2, 3], [0, 1, 2, 4], [0, 1, 3, 4],
[0, 2, 3, 4], [1, 2, 3, 4], [0, 1, 2, 3]]
### Only All features
elif selected_feature_set == 'summary':
notes = ['SCI+']
assign = [[0, 1, 2, 3, 4]]
### Added Popularity,
elif selected_feature_set == 'sci_plus_all':
notes = [
'All', 'F', 'D', 'TD', 'TSD', 'P', 'TSA', 'TS', 'F+D', 'F+TD',
'F+TSD', 'F+P', 'F+TSA', 'F+TS', 'D+TD', 'D+TSD', 'D+P',
'D+TSA', 'D+TS', 'TD+TSD', 'TD+P', 'TD+TSA', 'TD+TS', 'TSD+P',
'TSD+TSA', 'TSD+TS', 'P+TSA', 'P+TS', 'TSA+TS', 'F+D+TD',
'F+D+TSD', 'F+D+P', 'F+D+TSA', 'F+D+TS', 'F+TD+TSD', 'F+TD+P',
'F+TD+TSA', 'F+TD+TS', 'F+TSD+P', 'F+TSD+TSA', 'F+TSD+TS',
'F+P+TSA', 'F+P+TS', 'F+TSA+TS', 'D+TD+TSD', 'D+TD+P',
'D+TD+TSA', 'D+TD+TS', 'D+TSD+P', 'D+TSD+TSA', 'D+TSD+TS',
'D+P+TSA', 'D+P+TS', 'D+TSA+TS', 'TD+TSD+P', 'TD+TSD+TSA',
'TD+TSD+TS', 'TD+P+TSA', 'TD+P+TS', 'TD+TSA+TS', 'TSD+P+TSA',
'TSD+P+TS', 'TSD+TSA+TS', 'P+TSA+TS', 'F+D+TD+TSD', 'F+D+TD+P',
'F+D+TD+TSA', 'F+D+TD+TS', 'F+D+TSD+P', 'F+D+TSD+TSA',
'F+D+TSD+TS', 'F+D+P+TSA', 'F+D+P+TS', 'F+D+TSA+TS',
'F+TD+TSD+P', 'F+TD+TSD+TSA', 'F+TD+TSD+TS', 'F+TD+P+TSA',
'F+TD+P+TS', 'F+TD+TSA+TS', 'F+TSD+P+TSA', 'F+TSD+P+TS',
'F+TSD+TSA+TS', 'F+P+TSA+TS', 'D+TD+TSD+P', 'D+TD+TSD+TSA',
'D+TD+TSD+TS', 'D+TD+P+TSA', 'D+TD+P+TS', 'D+TD+TSA+TS',
'D+TSD+P+TSA', 'D+TSD+P+TS', 'D+TSD+TSA+TS', 'D+P+TSA+TS',
'TD+TSD+P+TSA', 'TD+TSD+P+TS', 'TD+TSD+TSA+TS', 'TD+P+TSA+TS',
'TSD+P+TSA+TS', 'F+D+TD+TSD+P', 'F+D+TD+TSD+TSA',
'F+D+TD+TSD+TS', 'F+D+TD+P+TSA', 'F+D+TD+P+TS',
'F+D+TD+TSA+TS', 'F+D+TSD+P+TSA', 'F+D+TSD+P+TS',
'F+D+TSD+TSA+TS', 'F+D+P+TSA+TS', 'F+TD+TSD+P+TSA',
'F+TD+TSD+P+TS', 'F+TD+TSD+TSA+TS', 'F+TD+P+TSA+TS',
'F+TSD+P+TSA+TS', 'D+TD+TSD+P+TSA', 'D+TD+TSD+P+TS',
'D+TD+TSD+TSA+TS', 'D+TD+P+TSA+TS', 'D+TSD+P+TSA+TS',
'TD+TSD+P+TSA+TS', 'F+D+TD+TSD+P+TSA', 'F+D+TD+TSD+P+TS',
'F+D+TD+TSD+TSA+TS', 'F+D+TD+P+TSA+TS', 'F+D+TSD+P+TSA+TS',
'F+TD+TSD+P+TSA+TS', 'D+TD+TSD+P+TSA+TS'
]
assign = [[0, 1, 2, 3, 4, 5, 6], [0], [1], [2], [3], [4], [5], [6],
[0, 1], [0, 2], [0, 3], [0, 4], [0, 5], [0, 6], [1, 2],
[1, 3], [1, 4], [1, 5], [1, 6], [2, 3], [2, 4], [2, 5],
[2, 6], [3, 4], [3, 5], [3, 6], [4, 5], [4, 6], [5, 6],
[0, 1, 2], [0, 1, 3], [0, 1, 4], [0, 1, 5], [0, 1, 6],
[0, 2, 3], [0, 2, 4], [0, 2, 5], [0, 2, 6], [0, 3, 4],
[0, 3, 5], [0, 3, 6], [0, 4, 5], [0, 4, 6], [0, 5, 6],
[1, 2, 3], [1, 2, 4], [1, 2, 5], [1, 2, 6], [1, 3, 4],
[1, 3, 5], [1, 3, 6], [1, 4, 5], [1, 4, 6], [1, 5, 6],
[2, 3, 4], [2, 3, 5], [2, 3, 6], [2, 4, 5], [2, 4, 6],
[2, 5, 6], [3, 4, 5], [3, 4, 6], [3, 5, 6], [4, 5, 6],
[0, 1, 2, 3], [0, 1, 2, 4], [0, 1, 2, 5], [0, 1, 2, 6],
[0, 1, 3, 4], [0, 1, 3, 5], [0, 1, 3, 6], [0, 1, 4, 5],
[0, 1, 4, 6], [0, 1, 5, 6], [0, 2, 3, 4], [0, 2, 3, 5],
[0, 2, 3, 6], [0, 2, 4, 5], [0, 2, 4, 6], [0, 2, 5, 6],
[0, 3, 4, 5], [0, 3, 4, 6], [0, 3, 5, 6], [0, 4, 5, 6],
[1, 2, 3, 4], [1, 2, 3, 5], [1, 2, 3, 6], [1, 2, 4, 5],
[1, 2, 4, 6], [1, 2, 5, 6], [1, 3, 4, 5], [1, 3, 4, 6],
[1, 3, 5, 6], [1, 4, 5, 6], [2, 3, 4, 5], [2, 3, 4, 6],
[2, 3, 5, 6], [2, 4, 5, 6],
[3, 4, 5, 6], [0, 1, 2, 3, 4], [0, 1, 2, 3, 5],
[0, 1, 2, 3, 6], [0, 1, 2, 4, 5], [0, 1, 2, 4, 6],
[0, 1, 2, 5, 6], [0, 1, 3, 4, 5], [0, 1, 3, 4, 6],
[0, 1, 3, 5, 6], [0, 1, 4, 5, 6], [0, 2, 3, 4, 5],
[0, 2, 3, 4, 6], [0, 2, 3, 5, 6], [0, 2, 4, 5, 6],
[0, 3, 4, 5, 6], [1, 2, 3, 4, 5], [1, 2, 3, 4, 6],
[1, 2, 3, 5, 6], [1, 2, 4, 5, 6], [1, 3, 4, 5, 6],
[2, 3, 4, 5, 6], [0, 1, 2, 3, 4, 5], [0, 1, 2, 3, 4, 6],
[0, 1, 2, 3, 5, 6], [0, 1, 2, 4, 5,
6], [0, 1, 3, 4, 5, 6],
[0, 2, 3, 4, 5, 6], [1, 2, 3, 4, 5, 6]]
### SCI and SCI+
else: ### 'summary_old_new'
notes = ['SCI+', 'SCI']
assign = [[0, 1, 2, 3, 4], [0, 1, 2, 6]]
### Generate the report
debug(notes, assign)
texts = generate_report(config, X, y, assign, notes, p, k, t, d)
del X, y
report_directory = config['directory']['report']
result_filename = '/'.join(
[report_directory, 'SCI_result_p{}_k{}.csv'.format(p, k)])
for text in texts:
if text is not None:
with open(result_filename, 'ab') as fw:
fw.write(text + '\n')
else:
debug('File not found', evaluation_name)
def generate_walk2friend(config):
kwargs = config['kwargs']
datasets = kwargs['active_dataset']
modes = kwargs['active_mode']
t_diffs = kwargs['ts']
s_diffs = kwargs['ds']
for dataset_name in datasets:
p = config['dataset'].index(dataset_name)
for mode in modes:
k = config['mode'].index(mode)
for t in t_diffs:
for d in s_diffs:
output_dir = config['directory']['walk2friend']
make_sure_path_exists(output_dir)
debug('p', p, 'k', k, 't', t, 'd', d)
checkin_name = '/'.join([
output_dir,
'{}_{}_t{}_d{}.checkin'.format(dataset_name, mode, t,
d)
])
friends_name = '/'.join([
output_dir,
'{}_{}_t{}_d{}.friends'.format(dataset_name, mode, t,
d)
])
if is_file_exists(checkin_name) is False or is_file_exists(
friends_name) is False:
checkins, _ = extract_checkins_all(
dataset_name, mode, config)
friends = extract_friendships(dataset_name, config)
user_unique = []
for colocations in read_colocation_file(
config,
p,
k,
t,
d,
chunksize=10**6,
usecols=['user1', 'user2']):
user_unique.append(colocations['user1'].unique())
user_unique.append(colocations['user2'].unique())
# user_unique = np.array(user_unique)
user_unique = np.ravel(user_unique)
debug(user_unique)
user_unique = np.unique(user_unique)
debug('Before', '#checkins', len(checkins), '#friends',
len(friends))
checkins = checkins.loc[(
checkins['user'].isin(user_unique))]
friends = friends.loc[
(friends['user1'].isin(user_unique))
& (friends['user2'].isin(user_unique))]
debug('After', '#checkins', len(checkins), '#friends',
len(friends))
checkins.sort_values(['user', 'location'],
inplace=True)
checkins.rename(columns={
"user": "******",
"location": "locid"
},
inplace=True)
checkins['mid'] = range(len(checkins))
checkins = checkins[['mid', 'uid', 'locid']]
checkins.to_csv(checkin_name, index=False, header=True)
friends.rename(columns={
"user1": "u1",
"user2": "u2"
},
inplace=True)
friends.sort_values(['u1', 'u2'], inplace=True)
friends = friends[['u1', 'u2']]
friends.to_csv(friends_name, index=False, header=True)
del user_unique
gc.collect()