def get_router_manual_list() -> []:
"""
Read the Router Manual Config file
:return: List with any Router objects from the file
"""
output = ConfigManager.get_router_manual_config()
router_list = []
for i in range(0, len(output)):
router_info = output[i]
if not len(router_info) == 9:
Logger().error(
"List must be length of 9 but has a length of {0}".format(
len(output)))
return
try:
v = Router(i, router_info['Name'], router_info['Id'],
router_info['IP'], router_info['IP_Mask'],
router_info['CONFIG_IP'],
router_info['CONFIG_IP_MASK'],
router_info['Username'], router_info['Password'],
router_info['PowerSocket'])
router_list.append(v)
except Exception as ex:
Logger().error(
"Error at building the list of Router's\nError: {0}".
format(ex))
return router_list
def import_firmwares(self, release_model: str):
"""
Imports the stored Firmwares, so the firmware_handler can use them.
:param release_model: stable, beta, experimental
"""
path = self.FIRMWARE_PATH + '/' + release_model + '/' + self.UPDATE_TYPE + '/'
Logger().debug("Import Firmwares from '" + path + "'", 2)
count = 0
try:
files = os.listdir(path)
except Exception:
Logger().debug(
"No Firmwares available for download at path '" + path + "'",
3)
return
for firmware_name in files:
try:
freifunk_verein = firmware_name.split('-')[1]
firmware_version = firmware_name.split('-')[2]
file = path + firmware_name
url = self.url + '/' + release_model + '/' + self.UPDATE_TYPE + '/' + firmware_name
self.firmwares.append(
Firmware(firmware_name, firmware_version, freifunk_verein,
release_model, file, url))
count += 1
except Exception:
Logger().warning("[-] Couldn't import " + firmware_name, 3)
continue
Logger().debug(str(count) + " Firmwares imported", 3)
def get_invest_month(self,cost):
bottom = VauleConfig.fluctuation_bottom
top = VauleConfig.fluctuation_top
rate = random.uniform(bottom,top)
msg = '[fluctuation_rate]{}'.format(rate)
Logger.log(msg, tag_name=LogConst.FLUCTUATION_RATE)
return cost * (1+rate)
def run(self):
Logger().info("Start WebServer on port " + str(WebServer.PORT_WEBSERVER) + " ...", 1)
try:
self.httpd.serve_forever()
except Exception as e:
Logger().debug("[-] WebServer couldn't get started", 2)
raise e
class TestNotifier(object):
def __init__(self):
self.service_name = 'test_service'
self.meta = meta
self.request_body = {
'jobId': 1,
'stepId': 1,
'batchId': 0,
'retry': 0,
'status': 3,
'message': 'RUNNING',
'groupName': 'TestGroupName'
}
self.is_notifiable = True
#self.is_notifiable = False
self.logger = Logger(log_level="info",
vendor_key=20,
retailer_key=100)
self.logger.info(
'tttttttttttttttteeeeeeeeeeeeeeeeeeessssssssssstttttttttttttt')
@Notifier
def test(self):
print('yoyo')
@Notifier
def test_failure(self):
raise RuntimeError('Calling error.')
def main(self):
self.test()
#self.test_failure()
print('done')
class ImportCSV(SparkOperator):
'''import csv formate data'''
OP_NAME = 'import-csv'
OP_CATEGORY = 'data-import'
def __init__(self):
super(ImportCSV, self).__init__()
self.op_input_num = 0
self.op_output_num = 1
self.op_status = OperatorStatus.INIT
self.op_script_location = 'resources/spark_operators/data_import/import_csv.py'
self.op_backend = 'spark'
self.input_path = None
self.delimiter = None
def init_operator(self, op_json_param):
self.op_json_param = op_json_param
self.op_running_mode = self.op_json_param['running-mode'] if 'running-mode' in self.op_json_param else 'script'
self.op_local = bool(self.op_json_param['local']) if 'local' in self.op_json_param else True
if self.op_local:
self.op_script_location = os.getcwd() + '/' + self.op_script_location
self.op_working_directory = self.op_json_param['op-working-directory'] if 'op-working-directory' in self.op_json_param else None
self.op_logger = Logger(self.op_working_directory + '/log/import-csv_' + str(self.op_json_param['op-index']))
self.input_path = self.op_json_param['input-path']
self.delimiter = self.op_json_param['delimiter'] if 'delimiter' in self.op_json_param else ','
def run_function_mode(self):
return self.op_status
def run_script_mode(self):
run_command = 'spark-submit --master '
if self.op_local:
run_command = run_command + 'local[2] '
self.op_result.append(self.op_working_directory + 'output/' + self.op_json_param['op-index'] + '-output')
run_command = run_command + self.op_script_location + ' ' + self.input_path + ' ' + self.op_result[0] + ' ' + self.delimiter
sub_proc = subprocess.Popen(run_command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
for line in iter(sub_proc.stdout.readline, b''):
self.op_logger.info(line)
sub_proc.stdout.close()
sub_proc.wait()
self.op_status = sub_proc.returncode
return self.op_status
def azkaban_script(self):
run_command = 'spark-submit --master '
if self.op_local:
run_command = run_command + 'local[2] '
self.op_result.append(self.op_working_directory + 'output/' + self.op_json_param['op-index'] + '-output')
run_command = run_command + self.op_script_location + ' ' + self.input_path + ' ' + self.op_result[0] + ' ' + self.delimiter
return run_command
def year_end_tax(salary):
taxRates = {
36000: 0.03,
144000: 0.1,
300000: 0.2,
420000: 0.25,
660000: 0.3,
960000: 0.35,
99999999999: 0.45
}
START = 0 * 12
temp = salary - START
idvTax = 0
preBar = 0
for bar, rate in taxRates.items():
if temp <= 0:
break
if temp - (bar - preBar) <= 0:
idvTax += rate * temp
break
else:
idvTax += rate * (bar - preBar)
temp -= bar - preBar
preBar = bar
msg = "税前年收入: {} 年纳税额: {} 税后年收入: {}".format(salary, idvTax,
salary - idvTax)
Logger.log(msg, tag_name=LogConst.YEAR_END_INCOME)
return salary - idvTax
def _verified_download(self, firmware: Firmware, hash_firmware: str,
max_attempts: int) -> bool:
"""
Downloads the given Firmware and checks if the download was correct and if the hash is matching
:param firmware:
:param hash_firmware:
:param max_attempts: max number of attemps to download a firmware
:return: bool
"""
valid_download = False
count = 0
while (not valid_download) & (count < max_attempts):
valid_download = self._download_file(firmware.url, firmware.file,
firmware.release_model)
if valid_download:
valid_download = firmware.check_hash(hash_firmware)
count += 1
if count >= max_attempts:
Logger().debug(
"[-] The Firmware(" + firmware.name +
") couldn't be downloaded", 3)
return False
else:
Logger().debug(
"[+] The Firmware(" + firmware.name +
") was successfully downloaded", 3)
return True
def svr_xml_converter(raw_data):
'''
This method converts the supplied xml file-object to a python dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@list_observation_label, is a list containing dependent variable
labels.
'''
feature_count = None
list_dataset = []
list_observation_label = []
logger = Logger(__name__, 'error', 'error')
# convert xml file to python 'dict'
dataset = xmltodict.parse(raw_data)
# build 'list_dataset'
for observation in dataset['dataset']['observation']:
for key in observation:
if key == 'criterion':
observation_label = observation['criterion']
list_observation_label.append(observation[key])
elif key == 'predictor':
for predictor in observation[key]:
predictor_label = predictor['label']
predictor_value = predictor['value']
validate_value = Validate_Dataset(predictor_value)
validate_value.validate_value()
list_error_value = validate_value.get_errors()
if list_error_value:
logger.log(list_error_value)
return None
else:
list_dataset.append({
'dep_variable_label':
str(observation_label),
'indep_variable_label':
str(predictor_label),
'indep_variable_value':
predictor_value
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(observation['predictor'])
# save observation labels, and return
raw_data.close()
return {
'dataset': list_dataset,
'observation_labels': list_observation_label,
'feature_count': feature_count
}
def send_data(self, local_file: str, remote_file: str):
"""
Sends Data via sftp to the RemoteSystem
:param local_file: Path to the local file
:param remote_file: Path on the Router, where the file should be saved
"""
try:
# TODO: If sftp is installed on the Router
'''
sftp = self.ssh.open_sftp()
sftp.put(local_file, remote_file)
sftp.close()
'''
command = 'sshpass -p' + str(self.remote_system.usr_password) + ' scp ' + local_file + ' ' + \
str(self.remote_system.usr_name) + '@' + str(self.remote_system.ip) + ':' + remote_file
os.system(command)
# TODO: Paramiko_scp have to installed
'''
scp = SCPClient(self.ssh.get_transport())
scp.put(local_file, remote_file)
'''
Logger().debug("[+] Sent data '" + local_file + "' to RemoteSystem '" +
str(self.remote_system.usr_name) + "@" + str(self.remote_system.ip) +
":" + remote_file + "'", 2)
except Exception as e:
Logger().error("[-] Couldn't send '" + local_file + "' to RemoteSystem '" +
str(self.remote_system.usr_name) + "@" + str(self.remote_system.ip) +
":" + remote_file + "'", 2)
Logger().error(str(e), 2)
def __init__(self, nsp_name: str, ipdb: IPDB):
"""
Creats a namespace for a specific vlan_iface
:param nsp_name:
:param vlan_iface_name:
:param ipdb: IPDB is a transactional database, containing records, representing network stack objects.
Any change in the database is not reflected immidiately in OS, but waits until commit() is called.
"""
Logger().debug("Create Namespace ...", 2)
self.nsp_name = nsp_name
self.id = id
self.vlan_iface_name = ""
self.vlan_iface_ip = "0.0.0.0"
self.ipdb = ipdb
self.ipdb_netns = None
try:
self.ipdb_netns = IPDB(nl=NetNS(nsp_name))
netns.setns(nsp_name)
self.ipdb_netns.interfaces['lo'].up().commit()
Logger().debug("[+] Namespace(" + nsp_name + ") successfully created", 3)
# self.encapsulate_interface()
except Exception as e:
Logger().debug("[-] Couldn't create Namespace(" + nsp_name + ")", 3)
for tb in traceback.format_tb(sys.exc_info()[2]):
Logger().error(tb, 3)
Logger().error(str(e), 3)
self.remove()
def create_interface(self,
vlan_iface_ip: str = None,
vlan_iface_ip_mask: int = None):
"""
Creats a virtual interface on a existing interface (like eth0)
:param vlan_iface_ip: ip of the virtual interface
:param vlan_iface_ip_mask: network-mask of the virtual interface
"""
Logger().debug("Create VLAN Interface ...", 2)
try:
link_iface = self.ipdb.interfaces[self.link_iface_name]
with self.ipdb.create(kind="vlan",
ifname=self.vlan_iface_name,
link=link_iface,
vlan_id=self.vlan_iface_id).commit() as i:
if vlan_iface_ip:
i.add_ip(vlan_iface_ip, vlan_iface_ip_mask)
i.mtu = 1400
if not vlan_iface_ip:
self._wait_for_ip_assignment()
vlan_iface_ip = self._get_ipv4_from_dictionary(
self.ipdb.interfaces[self.vlan_iface_name])
Logger().debug(
"[+] " + self.vlan_iface_name + " created with: Link=" +
self.link_iface_name + ", VLAN_ID=" + str(self.vlan_iface_id) +
", IP=" + vlan_iface_ip, 3)
except Exception as e:
Logger().debug(
"[-] " + self.vlan_iface_name + " couldn't be created", 3)
Logger().error(str(e), 3)
def do_tax(salary, gongjijin_rate=0.07):
res_insuranced = after_insurance(salary, gongjijin_rate=gongjijin_rate)
res = after_tax(res_insuranced)
msg = 'salary {} after_insurance {} after tax {}'.format(
salary, res_insuranced, res)
Logger.log(msg, tag_name=LogConst.MONTHLY_INCOME)
return res
def generate_report(self):
if self._steps_output is not None:
for step_output in self._steps_output:
self._ordered_steps[step_output.get_title()[:step_output.get_title().index('_', 4)]]\
.append(step_output)
count = 0
for group in TextPrinter._OWASP_STEP_GROUPS:
Logger.get_logger().info('\n[{0}] {1}'.format(
group, TextPrinter._OWASP_STEP_GROUPS_DESC[count]),
bold=True)
self._ordered_steps[group].sort(key=lambda x: x.get_title(),
reverse=False)
for step_output in self._ordered_steps[group]:
output_msg = '[{0}] {1}: {2}'.format(
step_output.get_title(), step_output.get_description(),
step_output.get_msg())
if step_output.get_status(
) == OwaspStepBase.status.error.value:
Logger.get_logger().error(output_msg)
elif step_output.get_status(
) == OwaspStepBase.status.warning.value:
Logger.get_logger().warn(output_msg)
elif step_output.get_status(
) == OwaspStepBase.status.passed.value:
Logger.get_logger().passed(output_msg)
elif step_output.get_status(
) == OwaspStepBase.status.info.value:
Logger.get_logger().info(output_msg)
count += 1
def __init__(self, host=None, user=None, passwd=None):
'''@__init__
This constructor is responsible for defining class variables.
'''
self.db_settings = Database()
self.list_error = []
self.proceed = True
# database logger
self.logger = Logger(__name__, 'database', 'database', 'debug')
# host address
if host:
self.host = host
else:
self.host = self.db_settings.get_db_host()
# sql username for above host address
if user:
self.user = user
else:
self.user = self.db_settings.get_db_username()
# sql password for above username
if passwd:
self.passwd = passwd
else:
self.passwd = self.db_settings.get_db_password()
def __init__(self, stock_id, db_conn = None, redis_conn = None):
self.stock_id = stock_id
self.stock_name = 'Not Set'
self.pair_queue = PairQueue(stock_id)
self.logger = Logger('engine')
self.db_conn = db_conn
self.limit = 2
self.close_price = 10
now = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(time.time()))
self.stock_name = 'sss'
if redis_conn is None:
self.r = redis.Redis()
else:
self.r = redis_conn
cursor = self.db_conn.cursor()
try:
cursor.execute('select stock_name from stock_set where stock_id=%s',
[str(self.stock_id)])
result = cursor.fetchall()[0]
self.stock_name = result[0]
cursor.execute('select gains,decline,status,close_price from stock_state where stock_id=%s',[str(self.stock_id)])
result = cursor.fetchall()
self.limit = result[0][0]
self.gains = self.limit
self.decline = result[0][1]
status = int(result[0][2])
self.close_price = float(result[0][3])
self.last_price = self.close_price
self.exist = True
self.r.hset(stock_id, 'engine_exist', True)
if status == 1:
self.redis_init(True,True,self.gains,self.decline,self.close_price)
self.on = True
print(str(stock_id) + " is running")
else:
self.redis_init(False,True,self.gains,self.decline,self.close_price)
self.on = False
print(str(stock_id) + " is pending")
# self.last_price = float(self.r.hget(self.stock_id,'newest_price').decode('utf-8'))
# self.close_price = self.last_price
# if self.close_price == 0:
# self.close_price = 10
except Exception as e:
self.redis_init(False,False,0,0,0)
self.close_price = 0
self.on = False
self.last_price = 0
print( str(stock_id) +" fails: " + str(e))
self.exist = False
finally:
self.set_open_price()
# cursor.execute('insert into today_stock (stock_id,stock_name,price,date) values (%s,%s,%s,%s)',
# [self.stock_id, self.stock_name, self.close_price, now])
self.db_conn.commit()
cursor.close()
def call(self, cfg, dataset, train_brick):
acc = train_brick.metric['train_accurency'].get_avg()
loss = train_brick.metric['train_loss'].get_avg()
message = f'[{train_brick.epoch}/{cfg.MAX_EPOCH} {train_brick.step}] acc={acc[0]}/{acc[1]} loss={loss[0]}/{loss[1]}'
Logger.debug(message,
show_type=Logger.LOG_STYLE.DEFAULT,
forground=Logger.LOG_FRONT_COLOR.GREEN,
background=Logger.LOG_BACK_COLOR.DEFAULT)
def test_log(self):
"""
Tests critical
:return: Tests results
"""
Logger().log(20, "Log from Logger() {0}".format(Logger()))
Logger().close()
self.assertEqual(True, True)
def join(self):
Logger().info("Stop WebServer ...", 1)
time.sleep(2)
try:
self.httpd.shutdown()
Logger().debug("[+] WebServer successfully stoped", 2)
except Exception as e:
Logger().debug("[-] WebServer couldn't stoped", 2)
Logger().error(str(e), 1)
def process_year_end(self):
income = self.income_manager.calc_income_year_end()
outcome = self.outcome_manager.calc_outcome_year_end()
invest = income - outcome
msg = '[income]{} [outcome]{} [invest]{}'.format(
income, outcome, invest)
Logger.log(msg, tag_name=LogConst.EXPECTATION_LOG_NAME)
self.invest_manager.throw_money(income)
self.print_account()
def test_warning(self):
"""
Tests warning
:return: Tests results
"""
Logger().warning("Warning from Logger() {0}".format(Logger()))
Logger().close()
self.assertEqual(True, True)
def test_debug(self):
"""
Tests debug
:return: Tests results
"""
Logger().debug("Debug from Logger() {0}".format(Logger()))
Logger().close()
self.assertEqual(True, True)
def test_info(self):
"""
Tests info
:return: Tests results
"""
Logger().info("Hello from logger: {0}".format(Logger()))
Logger().close()
self.assertEqual(True, True)
def test_log_level_tab(self):
"""
Test log level tab
:return: Test results
"""
tabs = Logger().get_log_level_tab(2)
Logger().close()
self.assertEqual(True, tabs == "\t\t")
def test_error(self):
"""
Tests error
:return: Tests results
"""
Logger().error("Error from Logger() {0}".format(Logger()))
Logger().close()
self.assertEqual(True, True)
def create_app():
# define configuration
with open('hiera/settings.yaml', 'r') as stream:
try:
# local variables
app = Flask(
__name__,
template_folder='interface/templates',
static_folder='interface/static'
)
settings = yaml.load(stream)
# register blueprint
app.register_blueprint(blueprint)
# local logger: used for this module
root = settings['general']['root']
LOG_PATH = root + '/' + settings['webserver']['flask_log_path']
HANDLER_LEVEL = settings['application']['log_level']
# flask attributes: accessible across application
app.config.update(
HOST=settings['general']['host'],
PORT_REDIS=settings['redis']['port'],
ROOT=settings['general']['root'],
DB_LOG_PATH=settings['database']['log_path'],
DB_ML=settings['database']['name'],
DB_USERNAME=settings['database']['username'],
DB_PASSWORD=settings['database']['password'],
LOG_LEVEL=HANDLER_LEVEL,
FLASK_LOG_PATH=settings['webserver']['flask_log_path'],
ERROR_LOG_PATH=settings['application']['error_log_path'],
WARNING_LOG_PATH=settings['application']['warning_log_path'],
INFO_LOG_PATH=settings['application']['info_log_path'],
DEBUG_LOG_PATH=settings['application']['debug_log_path'],
MODEL_TYPE=settings['application']['model_type']
)
except yaml.YAMLError as error:
logger = Logger('error', 'yaml')
logger.log(error)
# log handler: requires the below logger
formatter = logging.Formatter(
"[%(asctime)s] {%(pathname)s:%(lineno)d} %(levelname)s - %(message)s")
handler = RotatingFileHandler(LOG_PATH, maxBytes=10000000, backupCount=5)
handler.setLevel(HANDLER_LEVEL)
handler.setFormatter(formatter)
app.logger.addHandler(handler)
# logger: complements the log handler
log = logging.getLogger('werkzeug')
log.setLevel(logging.DEBUG)
log.addHandler(handler)
# return
return app
def test_close(self):
"""
Tests close
:return: Tests results
"""
logger = Logger()
logger.setup()
logger.close()
self.assertEqual(False, logger.is_loaded)
def print_details(self):
msg = '{}: 总借{:.2f} 总还{:.2f} 每月还{:.2f} 年数{} 利率{} 折扣{}' \
''.format(self.tag_name,
self.loan_money,
self.final_repayment(),
self.repay_per_month(),
self.years,
self.year_percent,
self.discount)
Logger.log(msg, tag_name=LogConst.LOAN_LOG_NAME)
def test_import_stock():
log = Logger("import_data.log")
try:
stock_data = BasicData()
stock_num = stock_data.import_stock()
log.print_info("导入" + str(stock_num) + "条股票数据")
log.write_info("导入" + str(stock_num) + "条股票数据")
except Exception as err:
log.print_error("导入股票基础信息错误：" + str(err))
log.write_error("导入股票基础信息错误：" + str(err))
def test_is_loaded(self):
"""
Tests is loaded
:return: Tests results
"""
Logger().setup()
result = Logger().is_loaded
Logger().close()
self.assertEqual(True, result)
def test_logger(self):
"""
Tests logger
:return: Tests results
"""
result = Logger().logger
self.assertEqual(True, Logger().logger is result)
Logger().close()
def __init__(self,
service=None,
endpoint=None,
api_key=None,
export=EXPORT_CLIPBOARD):
self.export = export
self.api_request = ApiRequest(service=service,
endpoint=endpoint,
api_key=api_key)
self.logger = Logger().get_logger()
def svr_xml_converter(raw_data):
"""
This method converts the supplied xml file-object to a python dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@list_observation_label, is a list containing dependent variable
labels.
"""
feature_count = None
list_dataset = []
list_observation_label = []
logger = Logger(__name__, "error", "error")
# convert xml file to python 'dict'
dataset = xmltodict.parse(raw_data)
# build 'list_dataset'
for observation in dataset["dataset"]["observation"]:
for key in observation:
if key == "criterion":
observation_label = observation["criterion"]
list_observation_label.append(observation[key])
elif key == "predictor":
for predictor in observation[key]:
predictor_label = predictor["label"]
predictor_value = predictor["value"]
validate_value = Validate_Dataset(predictor_value)
validate_value.validate_value()
list_error_value = validate_value.get_errors()
if list_error_value:
logger.log(list_error_value)
return None
else:
list_dataset.append(
{
"dep_variable_label": str(observation_label),
"indep_variable_label": str(predictor_label),
"indep_variable_value": predictor_value,
}
)
# generalized feature count in an observation
if not feature_count:
feature_count = len(observation["predictor"])
# save observation labels, and return
raw_data.close()
return {"dataset": list_dataset, "observation_labels": list_observation_label, "feature_count": feature_count}
def test_setup(self):
"""
Tests setup
:return: Tests results
"""
l = Logger()
l.setup(10)
self.assertEqual(True, l.is_loaded)
l.close()
def test_debug_level(self):
"""
Test debug level
:return: Test results
"""
logger = Logger()
logger.setup(10, 10, 10, "logger.log", "", "", 5, None)
level = logger.max_detail_log_level()
logger.close()
self.assertEqual(True, level == 5)
def svm_xml_converter(raw_data):
'''@svm_xml_converter
This method converts the supplied xml file-object to a python dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@list_observation_label, is a list containing dependent variable
labels.
'''
feature_count = None
list_dataset = []
list_observation_label = []
logger = Logger(__name__, 'error', 'error')
# convert xml file to python 'dict'
dataset = xmltodict.parse(raw_data)
# build 'list_dataset'
for observation in dataset['dataset']['observation']:
observation_label = observation['dependent-variable']
validate = Validate_Dataset(observation_label)
validate.validate_label()
list_error = validate.get_errors()
if list_error:
logger.log(list_error)
return None
else:
list_observation_label.append(observation_label)
for feature in observation['independent-variable']:
feature_label = feature['label']
feature_value = feature['value']
validate_label = Validate_Dataset(feature_label)
validate_value = Validate_Dataset(feature_value)
validate_label.validate_label()
validate_value.validate_value()
list_error_label = validate.get_errors()
list_error_value = validate.get_errors()
if list_error_label or list_error_value:
logger.log(list_error_label)
logger.log(list_error_value)
return None
else:
list_dataset.append({
'dep_variable_label': observation_label,
'indep_variable_label': feature_label,
'indep_variable_value': feature_value
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(observation['independent-variable'])
# save observation labels, and return
raw_data.close()
return {
'dataset': list_dataset,
'observation_labels': list_observation_label,
'feature_count': feature_count
}
def process_response(self, request, response, spider):
Logger.log({"response_status": response.status, "url": response.url}, "response")
return response
def svm_csv_converter(raw_data):
'''
This method converts the supplied csv file-object, intended for an svm
model, to a python dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@list_observation_label, is a list containing dependent variable labels.
Note: we use the 'Universal Newline Support' with the 'U' parameter when
opening 'raw_data'. This allows newlines to be understood regardless,
if the newline character was created in osx, windows, or linux.
Note: since 'row' is a list, with one comma-delimited string element, the
following line is required in this method:
row = row[0].split(',')
'''
feature_count = None
list_dataset = []
list_observation_label = []
list_feature_label = []
logger = Logger(__name__, 'error', 'error')
# open temporary 'csvfile' reader object
dataset_reader = csv.reader(
raw_data,
delimiter=' ',
quotechar='|'
)
# iterate first row of csvfile
for row in islice(dataset_reader, 0, 1):
# iterate each column in a given row
row_indep_label = row[0].split(',')
for value in islice(row_indep_label, 1, None):
list_feature_label.append(str(value))
# iterate all rows of csvfile
for dep_index, row in enumerate(islice(dataset_reader, 0, None)):
# iterate first column of each row (except first)
row_dep_label = row[0].split(',')
for value in row_dep_label[:1]:
list_observation_label.append(str(value))
# generalized feature count in an observation
row_indep_variable = row[0].split(',')
if not feature_count:
feature_count = len(row_indep_variable) - 1
# iterate each column in a given row
for indep_index, value in enumerate(
islice(row_indep_variable, 1, None)
):
try:
validate = Validate_Dataset(value)
validate.validate_value()
list_error = validate.get_errors()
if list_error:
logger.log(list_error)
return None
else:
value = float(value)
except Exception as error:
logger.log(error)
return False
list_dataset.append({
'dep_variable_label': list_observation_label[dep_index],
'indep_variable_label': list_feature_label[indep_index],
'indep_variable_value': value
})
# close file, save observation labels, and return
raw_data.close()
return {
'dataset': list_dataset,
'observation_labels': list_observation_label,
'feature_count': feature_count
}
def svm_json_converter(raw_data, is_json):
'''
This method converts the supplied json file-object to a python
dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@is_json, flag indicating 'raw_data' is a json string.
@observation_labels, is a list containing dependent variable labels.
'''
# local variables
feature_count = None
list_dataset = []
observation_labels = []
logger = Logger(__name__, 'error', 'error')
# web-interface
if not is_json:
dataset = json.load(raw_data)
for observation_label in dataset:
# variables
observations = dataset[observation_label]
# dependent variable with single observation
if type(observations) == dict:
for feature_label, feature_value in observations.items():
# validation
validate_fvalue = Validate_Dataset(feature_value)
validate_fvalue.validate_value()
if validate_fvalue.get_errors():
logger.log(validate_fvalue.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(observation_label),
'indep_variable_label': str(feature_label),
'indep_variable_value': feature_value
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(observations)
# dependent variable with multiple observations
elif type(observations) == list:
for observation in observations:
for feature_label, feature_value in observation.items():
# validation
validate_fvalue = Validate_Dataset(feature_value)
validate_fvalue.validate_value()
if validate_fvalue.get_errors():
logger.log(validate_fvalue.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(observation_label),
'indep_variable_label': str(feature_label),
'indep_variable_value': feature_value
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(observation)
# list of observation label
observation_labels.append(observation_label)
# programmatic-interface
else:
dataset = raw_data
observation_label = raw_data[0]
# list of observation label
observation_labels.append(observation_label)
# dependent variable with single observation
if type(raw_data[1]) == dict:
for label, feature in raw_data[1].items():
# validation
validate_fvalue = Validate_Dataset(feature)
validate_fvalue.validate_value()
if validate_fvalue.get_errors():
logger.log(validate_fvalue.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(observation_label),
'indep_variable_label': str(label),
'indep_variable_value': feature
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(raw_data[1])
# dependent variable with multiple observations
if type(raw_data[1]) == list:
for feature_set in raw_data[1]:
for feature_label, feature_value in feature_set.items():
# validation
validate_fvalue = Validate_Dataset(feature_value)
validate_fvalue.validate_value()
if validate_fvalue.get_errors():
logger.log(validate_fvalue.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(observation_label),
'indep_variable_label': str(feature_label),
'indep_variable_value': feature_value
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(feature_set)
# close file
if not is_json:
raw_data.close()
# save observation labels, and return
return {
'dataset': list_dataset,
'observation_labels': observation_labels,
'feature_count': feature_count
}
def svr_json_converter(raw_data, is_json):
'''@svr_json_converter
This method converts the supplied json file-object to a python
dictionary.
@raw_data, generally a file (or json string) containing the raw dataset(s),
to be used when computing a corresponding model. If this argument is a
file, it needs to be closed.
@is_json, flag indicating 'raw_data' is a json string.
@observation_labels, is a list containing dependent variable labels.
'''
# local variables
feature_count = None
list_dataset = []
observation_labels = []
logger = Logger(__name__, 'error', 'error')
# web-interface
if not is_json:
dataset = json.load(raw_data)
for criterion, predictors in dataset.items():
observation_label = criterion
# list of observation label
observation_labels.append(criterion)
# criterion with single observation
if type(predictors) == dict:
for label, predictor in predictors.items():
# validation (part 1)
validate_predictor = Validate_Dataset(str(predictor))
validate_predictor.validate_value()
if validate_predictor.get_errors():
logger.log(validate_predictor.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': observation_label,
'indep_variable_label': str(label),
'indep_variable_value': predictor
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(predictors)
# criterion with multiple observation
if type(predictors) == list:
for criterion in predictors:
for label, predictor in criterion.items():
# validation (part 1)
validate_predictor = Validate_Dataset(predictor)
validate_predictor.validate_value()
if validate_predictor.get_errors():
logger.log(validate_predictor.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(observation_label),
'indep_variable_label': str(label),
'indep_variable_value': predictor
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(criterion.items())
# programmatic-interface
else:
dataset = raw_data
for criterion, predictors in dataset.items():
# list of observation label
observation_labels.append(criterion)
# criterion with single observation
if type(predictors) == dict:
for label, predictor in predictors.items():
# validation (part 1)
validate_predictor = Validate_Dataset(predictor)
validate_predictor.validate_value()
if validate_predictor.get_errors():
logger.log(validate_predictor.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(criterion),
'indep_variable_label': str(label),
'indep_variable_value': predictor
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(predictors.items())
# criterion with multiple observation
if type(predictors) == list:
for single_predictors in predictors:
for label, predictor in single_predictors.items():
# validation (part 1)
validate_predictor = Validate_Dataset(predictor)
validate_predictor.validate_value()
if validate_predictor.get_errors():
logger.log(validate_predictor.get_errors())
else:
# restructured data
list_dataset.append({
'dep_variable_label': str(criterion),
'indep_variable_label': str(label),
'indep_variable_value': predictor
})
# generalized feature count in an observation
if not feature_count:
feature_count = len(single_predictors.items())
# close file
if not is_json:
raw_data.close()
# save observation labels, and return
return {
'dataset': list_dataset,
'observation_labels': observation_labels,
'feature_count': feature_count
}
def svm_model(kernel_type, session_id, feature_request, list_error):
'''@svm_model
This method generates an svm prediction using the provided prediction
feature input(s), and the stored corresponding model, within the NoSQL
datastore.
@grouped_features, a matrix of observations, where each nested vector,
or python list, is a collection of features within the containing
observation.
@encoded_labels, observation labels (dependent variable labels),
encoded into a unique integer representation.
'''
# local variables
dataset = feature_request.get_dataset(session_id)
feature_count = feature_request.get_count(session_id)
label_encoder = preprocessing.LabelEncoder()
logger = Logger(__name__, 'error', 'error')
# get dataset
if dataset['error']:
logger.log(dataset['error'])
list_error.append(dataset['error'])
dataset = None
else:
dataset = numpy.asarray(dataset['result'])
# get feature count
if feature_count['error']:
logger.log(feature_count['error'])
list_error.append(feature_count['error'])
feature_count = None
else:
feature_count = feature_count['result'][0][0]
# check dataset integrity, build model
if len(dataset) % feature_count == 0:
features_list = dataset[:, [[0], [2], [1]]]
current_features = []
grouped_features = []
observation_labels = []
feature_labels = []
# group features into observation instances, record labels
for index, feature in enumerate(features_list):
if not (index+1) % feature_count == 0:
# observation labels
current_features.append(feature[1][0])
# general feature labels in every observation
if not len(feature_labels) == feature_count:
feature_labels.append(feature[2][0])
else:
# general feature labels in every observation
if not len(feature_labels) == feature_count:
feature_labels.append(feature[2][0])
current_features.append(feature[1][0])
grouped_features.append(current_features)
observation_labels.append(feature[0][0])
current_features = []
# convert observation labels to a unique integer representation
label_encoder = preprocessing.LabelEncoder()
label_encoder.fit(dataset[:, 0])
encoded_labels = label_encoder.transform(observation_labels)
# create svm model
clf = svm.SVC(kernel=kernel_type)
clf.fit(grouped_features, encoded_labels)
# get svm title, and cache (model, encoded labels, title)
entity = Retrieve_Entity()
title = entity.get_title(session_id)['result'][0][0]
Cache_Model(clf).cache(
'svm_rbf_model',
str(session_id) + '_' + title
)
Cache_Model(label_encoder).cache('svm_rbf_labels', session_id)
Cache_Hset().cache('svm_rbf_title', session_id, title)
# cache svm feature labels, with respect to given session id
Cache_Hset().cache(
'svm_rbf_feature_labels',
str(session_id),
json.dumps(feature_labels)
)
# return error(s) if exists
return {'error': list_error}
def sv_model(model, kernel_type, session_id, feature_request, list_error):
'''
This method generates an sv (i.e. svm, or svr) model using feature data,
retrieved from the database. The generated model, is then stored within the
NoSQL datastore.
@grouped_features, a matrix of observations, where each nested vector,
or python list, is a collection of features within the containing
observation.
@encoded_labels, observation labels (dependent variable labels),
encoded into a unique integer representation.
'''
# local variables
dataset = feature_request.get_dataset(session_id, model)
get_feature_count = feature_request.get_count(session_id)
label_encoder = preprocessing.LabelEncoder()
logger = Logger(__name__, 'error', 'error')
list_model_type = current_app.config.get('MODEL_TYPE')
# get dataset
if dataset['error']:
logger.log(dataset['error'])
list_error.append(dataset['error'])
dataset = None
else:
dataset = numpy.asarray(dataset['result'])
# get feature count
if get_feature_count['error']:
logger.log(get_feature_count['error'])
list_error.append(get_feature_count['error'])
feature_count = None
else:
feature_count = get_feature_count['result'][0][0]
# check dataset integrity, build model
if len(dataset) % feature_count == 0:
features_list = dataset[:, [[0], [2], [1]]]
current_features = []
grouped_features = []
observation_labels = []
feature_labels = []
# group features into observation instances, record labels
for index, feature in enumerate(features_list):
# svm: observation labels
if model == list_model_type[0]:
current_features.append(feature[1][0])
if (index+1) % feature_count == 0:
grouped_features.append(current_features)
observation_labels.append(feature[0][0])
current_features = []
# svr: observation labels
elif model == list_model_type[1]:
current_features.append(float(feature[1][0]))
if (index+1) % feature_count == 0:
grouped_features.append(current_features)
observation_labels.append(float(feature[0][0]))
current_features = []
# general feature labels in every observation
if not len(feature_labels) == feature_count:
feature_labels.append(feature[2][0])
# case 1: svm model
if model == list_model_type[0]:
# convert observation labels to a unique integer representation
label_encoder = preprocessing.LabelEncoder()
label_encoder.fit(dataset[:, 0])
encoded_labels = label_encoder.transform(observation_labels)
# create model
clf = svm.SVC(kernel=kernel_type, probability=True)
# cache encoded labels
Cache_Model(label_encoder).cache(model + '_labels', session_id)
# fit model
clf.fit(grouped_features, encoded_labels)
# case 2: svr model
elif model == list_model_type[1]:
# create model
clf = svm.SVR(kernel=kernel_type)
# fit model
clf.fit(grouped_features, observation_labels)
# compute, and cache coefficient of determination
r2 = clf.score(grouped_features, observation_labels)
Cache_Hset().cache(
model + '_r2',
session_id,
r2
)
# get title
entity = Retrieve_Entity()
title = entity.get_title(session_id)['result'][0][0]
# cache model, title
Cache_Model(clf).cache(
model + '_model',
str(session_id) + '_' + title
)
Cache_Hset().cache(model + '_title', session_id, title)
# cache feature labels, with respect to given session id
Cache_Hset().cache(
model + '_feature_labels',
str(session_id),
json.dumps(feature_labels)
)
# return error(s) if exists
return {'error': list_error}
