def test_RF(self):
trainKey1 = self.loadData(trainDS1)
kwargs = paramsTrainRF.copy()
trainResult1 = h2o_rf.trainRF(trainKey1, **kwargs)
scoreKey1 = self.loadData(scoreDS1)
kwargs = paramsScoreRF.copy()
scoreResult1 = h2o_rf.scoreRF(scoreKey1, trainResult1, **kwargs)
print "\nTrain1\n=========={0}".format(
h2o_rf.pp_rf_result(trainResult1))
print "\nScore1\n========={0}".format(
h2o_rf.pp_rf_result(scoreResult1))
trainKey2 = self.loadData(trainDS2)
kwargs = paramsTrainRF.copy()
trainResult2 = h2o_rf.trainRF(trainKey2, **kwargs)
scoreKey2 = self.loadData(scoreDS2)
kwargs = paramsScoreRF.copy()
scoreResult2 = h2o_rf.scoreRF(scoreKey2, trainResult2, **kwargs)
print "\nTrain2\n=========={0}".format(
h2o_rf.pp_rf_result(trainResult2))
print "\nScore2\n========={0}".format(
h2o_rf.pp_rf_result(scoreResult2))
print "\nTraining: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(trainResult1, trainResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
print "\nScoring: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(scoreResult1, scoreResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
def test_RF(self):
trainKey1 = self.loadData(trainDS1)
kwargs = paramsTrainRF.copy()
trainResult1 = h2o_rf.trainRF(trainKey1, **kwargs)
scoreKey1 = self.loadData(scoreDS1)
kwargs = paramsScoreRF.copy()
scoreResult1 = h2o_rf.scoreRF(scoreKey1, trainResult1, **kwargs)
print "\nTrain1\n=========={0}".format(h2o_rf.pp_rf_result(trainResult1))
print "\nScore1\n========={0}".format(h2o_rf.pp_rf_result(scoreResult1))
trainKey2 = self.loadData(trainDS2)
kwargs = paramsTrainRF.copy()
trainResult2 = h2o_rf.trainRF(trainKey2, **kwargs)
scoreKey2 = self.loadData(scoreDS2)
kwargs = paramsScoreRF.copy()
scoreResult2 = h2o_rf.scoreRF(scoreKey2, trainResult2, **kwargs)
print "\nTrain2\n=========={0}".format(h2o_rf.pp_rf_result(trainResult2))
print "\nScore2\n========={0}".format(h2o_rf.pp_rf_result(scoreResult2))
print "\nTraining: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(trainResult1, trainResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
print "\nScoring: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(scoreResult1, scoreResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
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)
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(self):
normalRF = False
#normalRF = True
print """
Normal RF : {0}
Train data: {1}
Test data : {2}""".format(normalRF, trainDS['filename'], scoreDS['filename'])
print "Loading data...."
trainKey = self.loadTrainData()
kwargs = paramsTrainRF.copy()
print "Running normal RF: {0}".format(normalRF)
if normalRF:
trainResult = h2o_rf.trainRF(trainKey, model_key="rfm_normal", **kwargs)
else:
trainResult = h2o_rf.trainRF(trainKey, refine=1, model_key="rfm_refined", **kwargs)
scoreKey = self.loadScoreData()
kwargs = paramsScoreRF.copy()
scoreResult = h2o_rf.scoreRF(scoreKey, trainResult, **kwargs)
print """
Normal RF : {0}
Train data: {1}
Test data : {2}""".format(normalRF, trainDS['filename'], scoreDS['filename'])
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(h2o_rf.pp_rf_result(scoreResult))
def test_RF(self):
trainKey = self.loadTrainData()
kwargs = paramsTrainRF.copy()
trainResult = h2o_rf.trainRF(trainKey, **kwargs)
scoreKey = self.loadScoreData()
kwargs = paramsScoreRF.copy()
scoreResult = h2o_rf.scoreRF(scoreKey, trainResult, **kwargs)
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(h2o_rf.pp_rf_result(scoreResult))
def test_c8_rf_airlines_hdfs(self):
trainParseResult = self.loadTrainData()
kwargs = paramsTrainRF.copy()
trainResult = h2o_rf.trainRF(trainParseResult, **kwargs)
scoreParseResult = self.loadScoreData()
kwargs = paramsScoreRF.copy()
scoreResult = h2o_rf.scoreRF(scoreParseResult, trainResult, **kwargs)
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(h2o_rf.pp_rf_result(scoreResult))
def test_RF(self):
trainKey = self.loadTrainData()
kwargs = paramsTrainRF.copy()
trainResult = h2o_rf.trainRF(trainKey, **kwargs)
scoreKey = self.loadScoreData()
kwargs = paramsScoreRF.copy()
scoreResult = h2o_rf.scoreRF(scoreKey, trainResult, **kwargs)
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(h2o_rf.pp_rf_result(scoreResult))
def test_rf_iris(self):
# Train RF
trainParseResult = h2i.import_parse(bucket='smalldata', path='iris/iris2.csv', hex_key='train_iris2.hex', schema='put')
kwargs = paramsTrainRF.copy()
trainResult = h2o_rf.trainRF(trainParseResult, **kwargs)
scoreParseResult = h2i.import_parse(bucket='smalldata', path='iris/iris2.csv', hex_key='score_iris2.hex', schema='put')
kwargs = paramsTestRF.copy()
scoreResult = h2o_rf.scoreRF(scoreParseResult, trainResult, **kwargs)
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(h2o_rf.pp_rf_result(scoreResult))
def test_rf_iris(self):
# Train RF
trainParseResult = h2i.import_parse(bucket='smalldata',
path='iris/iris2.csv',
hex_key='train_iris2.hex',
schema='put')
kwargs = paramsTrainRF.copy()
trainResult = h2o_rf.trainRF(trainParseResult, **kwargs)
scoreParseResult = h2i.import_parse(bucket='smalldata',
path='iris/iris2.csv',
hex_key='score_iris2.hex',
schema='put')
kwargs = paramsTestRF.copy()
scoreResult = h2o_rf.scoreRF(scoreParseResult, trainResult, **kwargs)
print "\nTrain\n=========={0}".format(h2o_rf.pp_rf_result(trainResult))
print "\nScoring\n========={0}".format(
h2o_rf.pp_rf_result(scoreResult))
def test_RF(self):
trainKey = self.loadTrainData()
scoreKey = self.loadScoreData()
#time.sleep(3600)
executeNormalRF = True
executeNormalRF = False
if executeNormalRF:
kwargs = paramsTrainRF.copy()
trainResultNormal = h2o_rf.trainRF(trainKey, model_key="rfm_normal", **kwargs)
#print h2o_rf.pp_rf_result(trainResultNormal)
kwargs = paramsScoreRF.copy()
scoreResultNormal = h2o_rf.scoreRF(scoreKey, trainResultNormal, **kwargs)
print "\nScoring normal forest\n========={0}".format(h2o_rf.pp_rf_result(scoreResultNormal))
kwargs = paramsTrainRF.copy()
trainResultRefined = h2o_rf.trainRF(trainKey, refine=1, model_key="rfm_refined", **kwargs)
#print h2o_rf.pp_rf_result(trainResultRefined)
kwargs = paramsScoreRF.copy()
scoreResultRefined = h2o_rf.scoreRF(scoreKey, trainResultRefined, **kwargs)
print "\nScoring refined forest\n========={0}".format(h2o_rf.pp_rf_result(scoreResultRefined))
time.sleep(3600)
def test_RF(self):
h2o.beta_features = True
if h2o.beta_features:
paramsTrainRF = {
'ntrees': 10,
'max_depth': 300,
'nbins': 200,
'timeoutSecs': 600,
'response': 'C54',
}
paramsScoreRF = {
'vactual': 'C54',
'timeoutSecs': 600,
}
else:
paramsTrainRF = {
'use_non_local_data' : 1,
'ntree' : 10,
'depth' : 300,
'parallel' : 1,
'bin_limit' : 20000,
'stat_type' : 'ENTROPY',
'out_of_bag_error_estimate': 1,
'exclusive_split_limit' : 0,
'timeoutSecs': 60,
}
paramsScoreRF = {
# scoring requires the response_variable. it defaults to last, so normally
# we don't need to specify. But put this here and (above if used)
# in case a dataset doesn't use last col
'response_variable': None,
'timeoutSecs': 60,
'out_of_bag_error_estimate': 0,
}
trainKey1 = self.loadData(trainDS1)
kwargs = paramsTrainRF.copy()
trainResult1 = h2o_rf.trainRF(trainKey1, **kwargs)
scoreKey1 = self.loadData(scoreDS1)
kwargs = paramsScoreRF.copy()
scoreResult1 = h2o_rf.scoreRF(scoreKey1, trainResult1, **kwargs)
print "\nTrain1\n=========={0}".format(h2o_rf.pp_rf_result(trainResult1))
print "\nScore1\n========={0}".format(h2o_rf.pp_rf_result(scoreResult1))
trainKey2 = self.loadData(trainDS2)
kwargs = paramsTrainRF.copy()
trainResult2 = h2o_rf.trainRF(trainKey2, **kwargs)
scoreKey2 = self.loadData(scoreDS2)
kwargs = paramsScoreRF.copy()
scoreResult2 = h2o_rf.scoreRF(scoreKey2, trainResult2, **kwargs)
print "\nTrain2\n=========={0}".format(h2o_rf.pp_rf_result(trainResult2))
print "\nScore2\n========={0}".format(h2o_rf.pp_rf_result(scoreResult2))
print "\nTraining: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(trainResult1, trainResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
print "\nScoring: JsonDiff sorted data results, to non-sorted results (json responses)"
df = h2o_util.JsonDiff(scoreResult1, scoreResult2, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)