def exp_draw():
config = Config()
dataloader = DataLoader()
#read a
with open(sys.path[0] + "/../a") as a_in:
aid = a_in.read().split('\n')[0]
#read
with open(sys.path[0] + "/../n") as n_in:
nids = n_in.read().split('\n')
#nids.remove('None')
if '' in nids:
nids.remove('')
cate_trees = generate_category_tree(dataloader)
rlt_dist = {1.:[], 0.1:[], 0.01:[], 0.001:[], 0.0001:[]}
x_axis = ['0%', '20%', '40%', '60%', '80%', '100%']
fig, axs = plt.subplots(ncols=5)
sigmas = [1., 0.1, 0.01, 0.001, 0.0001]
for row, sigma in enumerate(sigmas):
ax = axs[row]
data = dataloader.load(vectorized_convertor, pivots = cate_trees, sigma=sigma, valid_uid=[aid] + nids)
avec = data[0]
nvecs = data[1:]
for nv in nvecs:
rlt_dist[sigma].append(vectorized_dist_calculator(np.array(avec), np.array(nv)))
print rlt_dist[sigma]
ax.bar(x_axis, rlt_dist[sigma] + [0.0], width = 0.4)
for a, b in zip(x_axis, rlt_dist[sigma] + [0.0]):
ax.text(a, b+0.000000001, '%f'%b, ha='center', va= 'bottom',fontsize=7)
ax.set_title(str(sigma))
plt.show()
def __init__(self, data_file_name=None, cate_file_name=None, business_file_name=None):
'''
load config and category information from processed data
'''
#load config
config = Config().config
self.data_file_name = config['data_file_name'] if data_file_name is None else data_file_name
self.cate_file_name = config['cate_file_name'] if cate_file_name is None else cate_file_name
self.business_file_name = config['business_file_name'] if business_file_name is None else business_file_name
#load category
self.cate_parent = {}
with open(self.cate_file_name) as cate_csv:
try:
cate_rec = csv.reader(cate_csv)
for row in cate_rec:
self.cate_parent[row[0]] = row[1]
except Exception as e:
raise e
#load business's category info
with open(self.business_file_name) as businss_cate_f:
if 'line' in self.business_file_name:
self.business_cate = {}
line = businss_cate_f.readline()
while line!='' and line!='\n':
item = json.loads(line)
self.business_cate[item['bid']] = item['category']
line = businss_cate_f.readline()
else:
self.business_cate = json.load(businss_cate_f)
def __init__(self, business_file, user_business_file, top_level):
'''
init function of LocDataLoader
@business_file: str, name of business_file
@user_business_file: str, name of user_business_file
@top_level: int, state,0 => city,1 => neighborhood,2 => street,3
'''
self.config = Config().config
self.business_file = self.config['processed_data_path'] + business_file
self.user_business_file = self.config['processed_data_path'] + user_business_file
self.top_level = top_level
with open(self.business_file) as business_in:
self.business = json.load(business_in)
def merge_config(args_config):
config_file_path = args_config.config_path
config_dict = yaml.safe_load(open(config_file_path))
config = Config(config_dict[args_config.config_name])
config.update_args(args_config)
LOGGING.info("=" * 10 + "... Model Configs ..." + "=" * 10)
LOGGING.info("{}".format(config.to_json_string()))
bert_config = Config.from_json_file(
os.path.join(args_config.bert_model, "config.json"))
LOGGING.info("=" * 10 + "... PRETRAINED Model Configs ..." + "=" * 10)
LOGGING.info("{}".format(bert_config.to_json_string()))
return config
def __init__(self, data_file_name=None, cate_file_name=None, business_file_name=None):
'''
load config and category information from processed data
'''
#load config
config = Config().config
self.data_file_name = config['data_file_name'] if data_file_name is None else data_file_name
self.cate_file_name = config['cate_file_name'] if cate_file_name is None else cate_file_name
self.business_file_name = config['business_file_name'] if business_file_name is None else business_file_name
#load category
self.cate_parent = {}
with open(self.cate_file_name) as cate_csv:
try:
cate_rec = csv.reader(cate_csv)
for row in cate_rec:
self.cate_parent[row[0]] = row[1]
except Exception, e:
raise e
@dist: float
'''
#parameter modified here#
sigma = config['rbf_sigma']
return np.exp(-(dist**2) / (2 * (10000**2)))
def latlon_to_3857(lat, lon):
p1 = Proj(init='epsg:4326')
p2 = Proj(init='epsg:3857')
x1, y1 = p1(lon, lat)
x2, y2 = transform(p1, p2, x1, y1, radians=True)
return [x2, y2]
config = Config().config
# with open(config['processed_data_path'] + 'lasvegas_user_latlon.json') as latlon_in:
# user_latlon = json.load(latlon_in)
# with open(config['processed_data_path'] + 'lasvegas_X.json', 'r') as X_in:
# X = json.load(X_in)
# uids = X['uids']
# X_3857 = []
# for uid in uids:
# tmp_loc = [ latlon_to_3857(loc[0], loc[1]) for loc in user_latlon[uid] ]
# X_3857.append(tmp_loc)
# X['user_3857_all'] = X_3857
# with open(config['processed_data_path'] + 'lasvegas_X.json', 'w') as X_out:
# json.dump(X,X_out)
#load data
with open(config['processed_data_path'] + 'lasvegas_X.json', 'r') as X_in:
def setUp(self):
self.data_loader = DataLoader()
self.data = self.data_loader.load(bottomup_edit_dist_converter)
config = Config().config
self.data_file_name = config['data_file_name']
self.cate_file_name = config['cate_file_name']
def __init__(self):
self.__config = Config().config
def merge_config(args_config):
config_file_path = args_config.config_path
config_dict = yaml.safe_load(open(config_file_path))
config = Config(config_dict[args_config.config_name])
config.update_args(args_config)
return config