本文整理汇总了Python中utils.Util.get_ml_results_form_hdfs方法的典型用法代码示例。如果您正苦于以下问题：Python Util.get_ml_results_form_hdfs方法的具体用法？Python Util.get_ml_results_form_hdfs怎么用？Python Util.get_ml_results_form_hdfs使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类utils.Util的用法示例。
在下文中一共展示了Util.get_ml_results_form_hdfs方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _get_dns_results
# 需要导入模块: from utils import Util [as 别名]
# 或者: from utils.Util import get_ml_results_form_hdfs [as 别名]
def _get_dns_results(self):
self._logger.info("Getting {0} Machine Learning Results from HDFS".format(self._date))
dns_results = "{0}/dns_results.csv".format(self._data_path)
# get hdfs path from conf file.
HUSER = self._oni_conf.get('conf','HUSER').replace("'","").replace('"','')
hdfs_path = "{0}/dns/scored_results/{1}/scores/dns_results.csv".format(HUSER,self._date)
# get results file from hdfs.
get_command = Util.get_ml_results_form_hdfs(hdfs_path,self._data_path)
self._logger.info("{0}".format(get_command))
# valdiate files exists
if os.path.isfile(dns_results):
# read number of results based in the limit specified.
self._logger.info("Reading {0} dns results file: {1}".format(self._date,dns_results))
self._dns_results = Util.read_results(dns_results,self._limit,self._results_delimiter)[:]
if len(self._dns_results) == 0: self._logger.error("There are not flow results.");sys.exit(1)
else:
self._logger.error("There was an error getting ML results from HDFS")
sys.exit(1)
# add headers.
self._logger.info("Adding headers")
self._dns_scores_headers = [ str(key) for (key,value) in self._conf['dns_score_fields'].items() ]
# add dns content.
self._dns_scores = [ conn[:] for conn in self._dns_results][:] 示例2: _get_flow_results
# 需要导入模块: from utils import Util [as 别名]
# 或者: from utils.Util import get_ml_results_form_hdfs [as 别名]
def _get_flow_results(self):
self._logger.info("Getting {0} Machine Learning Results from HDFS".format(self._date))
flow_results = "{0}/flow_results.csv".format(self._data_path)
# get hdfs path from conf file
HUSER = self._oni_conf.get('conf','HUSER').replace("'","").replace('"','')
hdfs_path = "{0}/flow/scored_results/{1}/scores/flow_results.csv".format(HUSER,self._date)
# get results file from hdfs
get_command = Util.get_ml_results_form_hdfs(hdfs_path,self._data_path)
self._logger.info("{0}".format(get_command))
# valdiate files exists
if os.path.isfile(flow_results):
# read number of results based in the limit specified.
self._logger.info("Reading {0} flow results file: {1}".format(self._date,flow_results))
self._flow_results = Util.read_results(flow_results,self._limit,self._results_delimiter)
if len(self._flow_results) == 0: self._logger.error("There are not flow results.");sys.exit(1)
else:
self._logger.error("There was an error getting ML results from HDFS")
sys.exit(1)
# add headers.
self._logger.info("Adding headers based on configuration file: score_fields.json")
self._flow_scores = [ [ str(key) for (key,value) in self._conf['flow_score_fields'].items()] ]
ldaab_index = self._conf["flow_results_fields"]["lda_score_ab"]
ldaba_index = self._conf["flow_results_fields"]["lda_score_ba"]
# filter results add sev and rank.
self._logger.info("Filtering required columns based on configuration")
self._flow_scores.extend([ [0] + [ conn[i] for i in self._conf['column_indexes_filter'] ] + [(conn[ldaab_index] if (conn[ldaab_index]<= conn[ldaba_index]) else conn[ldaba_index])] + [n] for n, conn in enumerate(self._flow_results) ])示例3: _get_flow_results
# 需要导入模块: from utils import Util [as 别名]
# 或者: from utils.Util import get_ml_results_form_hdfs [as 别名]
def _get_flow_results(self):
self._logger.info("Getting {0} Machine Learning Results from HDFS".format(self._date))
flow_results = "{0}/flow_results.csv".format(self._data_path)
# get hdfs path from conf file
HUSER = self._spot_conf.get('conf', 'HUSER').replace("'", "").replace('"', '')
hdfs_path = "{0}/flow/scored_results/{1}/scores/flow_results.csv".format(HUSER,self._date)
# get results file from hdfs
get_command = Util.get_ml_results_form_hdfs(hdfs_path,self._data_path)
self._logger.info("{0}".format(get_command))
# valdiate files exists
if os.path.isfile(flow_results):
# read number of results based in the limit specified.
self._logger.info("Reading {0} flow results file: {1}".format(self._date,flow_results))
self._flow_results = Util.read_results(flow_results,self._limit,self._results_delimiter)
if len(self._flow_results) == 0: self._logger.error("There are not flow results.");sys.exit(1)
else:
self._logger.error("There was an error getting ML results from HDFS")
sys.exit(1)
# filter results add rank.
self._logger.info("Filtering required columns based on configuration")
self._flow_scores.extend([ [ conn[i] for i in self._conf['column_indexes_filter'] ] + [n] for n, conn in enumerate(self._flow_results) ])