def parseS3File(self, s3bucket, filename, **kwargs):
start = time.time()
parseKey = h2o_cmd.parseS3File(bucket=s3bucket, filename=filename, **kwargs)
parse_time = time.time() - start
h2o.verboseprint("py-S3 parse took {0} sec".format(parse_time))
parseKey['python_call_timer'] = parse_time
return parseKey
def parseS3File(self, s3bucket, filename, **kwargs):
start = time.time()
parseResult = h2o_cmd.parseS3File(bucket=s3bucket, filename=filename, **kwargs)
parse_time = time.time() - start
h2o.verboseprint("py-S3 parse took {0} sec".format(parse_time))
parseResult['python_call_timer'] = parse_time
return parseResult
def test_RF_1000trees(self):
# NAs cause CM to zero..don't run for now
### csvPathnamegz = h2o.find_file('smalldata/hhp_9_17_12.predict.100rows.data.gz')
s3bucket = self.s3_default_bucket()
s3dataset = 'covtype20x.data.gz'
s3dataset = 'covtype.data'
s3dataset = 'covtype200x.data.gz'
s3dataset = 'covtype50x.data'
s3dataset = 'covtype100x.data'
s3dataset = 'covtype.20k.data'
s3dataset = 'covtype.data'
start = time.time()
parseResult = h2o_cmd.parseS3File(bucket=s3bucket,
filename=s3dataset,
timeoutSecs=14800)
print "Parsing took {0}".format(time.time() - start)
start = time.time()
rf_train = h2o_cmd.runRF(parseResult=parseResult,
ntree=100,
timeoutSecs=14800,
bin_limit=20000,
out_of_bag_error_estimate=1,
stat_type='ENTROPY',
depth=100,
exclusive_split_limit=0)
print "Computation took {0} sec".format(time.time() - start)
print h2o_rf.pp_rf_result(rf_train)
def test_RF_1000trees(self):
# NAs cause CM to zero..don't run for now
### csvPathnamegz = h2o.find_file('smalldata/hhp_9_17_12.predict.100rows.data.gz')
s3bucket = self.s3_default_bucket()
s3dataset = "covtype20x.data.gz"
s3dataset = "covtype.data"
s3dataset = "covtype200x.data.gz"
s3dataset = "covtype50x.data"
s3dataset = "covtype100x.data"
s3dataset = "covtype.20k.data"
s3dataset = "covtype.data"
start = time.time()
parseKey = h2o_cmd.parseS3File(bucket=s3bucket, filename=s3dataset, timeoutSecs=14800)
print "Parsing took {0}".format(time.time() - start)
start = time.time()
rf_train = h2o_cmd.runRFOnly(
parseKey=parseKey,
ntree=100,
timeoutSecs=14800,
bin_limit=20000,
out_of_bag_error_estimate=1,
gini=0,
depth=100,
exclusive_split_limit=0,
)
print "Computation took {0} sec".format(time.time() - start)
print h2o_rf.pp_rf_result(rf_train)
