evalIdx_names = []
areaPct = {}
for eval_tup in eval_tuplist:
interval_params = list(map(
float, eval_tup[1].split())) # convert string to list of numbers
intervals = np.linspace(interval_params[0], interval_params[1],
interval_params[2])
ev_idx = eval_tup[0].rstrip()
evalIdx_names.append(ev_idx)
areaPct[ev_idx] = intervals
#------------------ Load data ----------------------------------------
_, grd_x, grd_y, _, mask_grdInCity, _ = ld.load_grid(grid_pkl)
grid_2d = (grd_x, grd_y)
groups_test = ld.load_train_test_group(group_pkl)['test_groups']
CrimeData = ld.load_crime_data(crime_pkl)
baseline_test = ld.load_baseline_data(baseline_pkl, target_crime)
score_list = []
for p_file, m_file in zip(predscore_filelist, samplemask_filelist):
with open(m_file, 'rb') as input_file:
samplemask = pickle.load(input_file)
predscores = np.loadtxt(p_file, delimiter=',')
predscores_city = np.tile(np.zeros(np.sum(mask_grdInCity)),
len(groups_test))
#assign prediction scores to the entire city
predscores_city[samplemask['test']] = predscores
score_list.append(predscores_city)
def pair_train_test_sample(filenames,
mask_sample_region={
'train': None,
'test': None
},
cluster_Nos={
'train': None,
'test': None
},
district_Nos={
'train': None,
'test': None
},
chunk_size={
'train': None,
'test': None
}):
"""
filenames: a dict with keys 'district'/'cluster' and 'group' with their filenames being the corresponding values
"""
# load cluster info
if 'cluster' in filenames.keys():
cluster_label, _ = ld.load_clusters(filenames['cluster'])
cluster_mask = {
'train':
np.in1d(cluster_label, cluster_Nos['train'])
if cluster_Nos['train'] is not None else None,
'test':
np.in1d(cluster_label, cluster_Nos['test'])
if cluster_Nos['test'] is not None else None
}
# load district info
if 'district' in filenames.keys():
district_label = ld.load_districts(filenames['district'])
district_mask = {
'train':
np.in1d(district_label, district_Nos['train'])
if district_Nos['train'] is not None else None,
'test':
np.in1d(district_label, district_Nos['test'])
if district_Nos['test'] is not None else None
}
# load time interval info
group_info = ld.load_train_test_group(filenames['group'])
groups_train, groups_test = group_info['train_groups'], group_info[
'test_groups']
sample_mask = {'train': [], 'test': []}
if mask_sample_region['train'] == 'cluster':
M = cluster_mask['train']
elif mask_sample_region['train'] == 'district':
M = district_mask['train']
for i in range(groups_train[0], groups_train[-1], chunk_size['train']):
if i < groups_train[-1] and i + chunk_size['train'] > groups_train[-1]:
# the end chunk may has smaller size
sample_mask['train'].append(np.tile(M, groups_train[-1] + 1 - i))
else:
sample_mask['train'].append(np.tile(M, chunk_size['train']))
if mask_sample_region['test'] == 'cluster':
M = cluster_mask['test']
elif mask_sample_region['test'] == 'district':
M = district_mask['test']
for i in range(groups_test[0], groups_test[-1], chunk_size['test']):
if i < groups_test[-1] and i + chunk_size['test'] > groups_test[-1]:
# the end chunk may has smaller size
sample_mask['test'].append(np.tile(M, groups_test[-1] + 1 - i))
else:
sample_mask['test'].append(np.tile(M, chunk_size['test']))
return sample_mask