def test_create_frame_rand1(self):
h2o.beta_features = True
# default
params = {'rows': 1, 'cols': 1}
for trial in range(20):
h2o_util.pickRandParams(paramDict, params)
i = params.get('integer_fraction', None)
c = params.get('categorical_fraction', None)
r = params.get('randomize', None)
v = params.get('value', None)
# h2o does some strict checking on the combinations of these things
# fractions have to add up to <= 1 and only be used if randomize
# h2o default randomize=1?
if r:
if not i:
i = 0
if not c:
c = 0
if (i and c) and (i + c) >= 1.0:
c = 1.0 - i
params['integer_fraction'] = i
params['categorical_fraction'] = c
params['value'] = None
else:
params['randomize'] = 0
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
kwargs = params.copy()
print kwargs
timeoutSecs = 300
parseResult = h2i.import_parse(bucket='smalldata',
path='poker/poker1000',
hex_key='temp1000.hex',
schema='put',
timeoutSecs=timeoutSecs)
cfResult = h2o.nodes[0].create_frame(key='temp1000.hex',
timeoutSecs=timeoutSecs,
**kwargs)
if DO_DOWNLOAD:
csvPathname = SYNDATASETS_DIR + '/' + 'temp1000.csv'
h2o.nodes[0].csv_download(src_key='temp1000.hex',
csvPathname=csvPathname,
timeoutSecs=60)
if DO_INSPECT:
h2o_cmd.runInspect(key='temp1000.hex')
h2o_cmd.runSummary(key='temp1000.hex', timeoutSecs=300)
print h2o.dump_json(cfResult)
print "Trial #", trial, "completed"
def test_create_frame_rand1(self):
h2o.beta_features = True
# default
params = {
'rows': 1,
'cols': 1
}
for trial in range(20):
h2o_util.pickRandParams(paramDict, params)
i = params.get('integer_fraction', None)
c = params.get('categorical_fraction', None)
r = params.get('randomize', None)
v = params.get('value', None)
# h2o does some strick checking on the combinations of these things
# fractions have to add up to <= 1 and only be used if randomize
# h2o default randomize=1?
if r:
if not i:
i = 0
if not c:
c = 0
if (i and c) and (i + c) >= 1.0:
c = 1.0 - i
params['integer_fraction'] = i
params['categorical_fraction'] = c
params['value'] = None
else:
params['randomize'] = 0
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
kwargs = params.copy()
print kwargs
timeoutSecs = 300
parseResult = h2i.import_parse(bucket='smalldata', path='poker/poker1000', hex_key='temp1000.hex',
schema='put', timeoutSecs=timeoutSecs)
cfResult = h2o.nodes[0].create_frame(key='temp1000.hex', timeoutSecs=timeoutSecs, **kwargs)
if DO_DOWNLOAD:
csvPathname = SYNDATASETS_DIR + '/' + 'temp1000.csv'
h2o.nodes[0].csv_download(src_key='temp1000.hex', csvPathname=csvPathname, timeoutSecs=60)
if DO_INSPECT:
h2o_cmd.runInspect(key='temp1000.hex')
h2o_cmd.runSummary(key='temp1000.hex')
print h2o.dump_json(cfResult)
print "Trial #", trial, "completed"
def test_speedrf_params_rand2_fvec(self):
h2o.beta_features = True
csvPathname = 'standard/covtype.data'
hex_key = 'covtype.data.hex'
for trial in range(10):
# params is mutable. This is default.
# response is required for SpeeERF
params = {
'response': 'C55',
'ntrees': 1, 'mtries': 7,
'balance_classes': 0,
# never run with unconstrained balance_classes size if random sets balance_classes..too slow
'max_after_balance_size': 2,
'importance': 0}
colX = h2o_util.pickRandParams(paramDict, params)
if 'cols' in params and params['cols']:
# exclusion
if 'ignored_cols_by_name' in params:
params['ignored_cols_by_name'] = None
else:
if 'ignored_cols_by_name' in params and params['ignored_cols_by_name']:
params['mtries'] = random.randint(1,53)
else:
params['mtries'] = random.randint(1,54)
kwargs = params.copy()
# adjust timeoutSecs with the number of trees
timeoutSecs = 80 + ((kwargs['ntrees']*80) * max(1,kwargs['mtries']/60) )
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, schema='put', hex_key=hex_key)
h2o_cmd.runSpeeDRF(parseResult=parseResult, timeoutSecs=timeoutSecs, retryDelaySecs=1, **kwargs)
elapsed = time.time()-start
print "Trial #", trial, "completed in", elapsed, "seconds.", "%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
def test_create_frame_rand1(self):
h2o.beta_features = True
# default
params = {
'rows': 1,
'cols': 1
}
for trial in range(10):
h2o_util.pickRandParams(paramDict, params)
i = params.get('integer_fraction', 0)
c = params.get('categorical_fraction', 0)
r = params.get('randomize', 0)
v = params.get('value', None)
if r:
if v is not None:
# if these are None, they are treated as >0 (default > 0?)
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
elif (i and c) and (i + c) >= 1.0:
params['integer_fraction'] = i
params['categorical_fraction'] = 1.0 - i
else:
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
params['value'] = None
kwargs = params.copy()
print kwargs
timeoutSecs = 300
parseResult = h2i.import_parse(bucket='smalldata', path='poker/poker1000', hex_key='temp1000.hex',
schema='put', timeoutSecs=timeoutSecs)
cfResult = h2o.nodes[0].create_frame(key='temp1000.hex', timeoutSecs=timeoutSecs, **kwargs)
if DO_DOWNLOAD:
csvPathname = SYNDATASETS_DIR + '/' + 'temp1000.csv'
h2o.nodes[0].csv_download(src_key='temp1000.hex', csvPathname=csvPathname, timeoutSecs=60)
if DO_INSPECT:
h2o_cmd.runInspect(key='temp1000.hex')
h2o_cmd.runSummary(key='temp1000.hex')
print h2o.dump_json(cfResult)
print "Trial #", trial, "completed"
def test_bayes_and2(self):
h2o.beta_features = True
csvPathname = 'standard/covtype.data'
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='put')
paramDict = define_params()
for trial in range(1):
response = 'C55'
params = {
'response': response,
}
colX = h2o_util.pickRandParams(paramDict, params)
kwargs = params.copy()
timeoutSecs = 120
# chagne response to factor
execExpr = 'covtype.hex[,54+1] = factor(covtype.hex[,54+1] != 5)' # turn 7-class problem into binomial such that AUC can work below..
resultExec, ncols = h2e.exec_expr(execExpr=execExpr)
start = time.time()
bayesResult = h2o.nodes[0].naive_bayes(timeoutSecs=timeoutSecs,
source='covtype.hex',
**kwargs)
print "bayes end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
print "bayes result:", h2o.dump_json(bayesResult)
nb_model = bayesResult['nb_model']
ncats = nb_model['ncats']
nnums = nb_model['nnums']
pcond = nb_model['pcond']
pprior = nb_model['pprior']
rescnt = nb_model['rescnt']
modelClassDist = nb_model['_modelClassDist']
names = nb_model['_names']
domains = nb_model['_domains']
priorClassDist = nb_model['_priorClassDist']
model_key = nb_model['_key']
# is it an error to get std dev of 0 after predicting?
print "Doing predict with same dataset, and the bayes model"
h2o.nodes[0].generate_predictions(model_key=model_key,
data_key='covtype.hex',
prediction='Predict.hex')
# just get a predict and AUC on the same data. has to be binomial result
resultAUC = h2o.nodes[0].generate_auc(thresholds=None,
actual='covtype.hex',
predict='Predict.hex',
vactual=response,
vpredict=1)
print "AUC result:", h2o.dump_json(resultAUC)
print "Trial #", trial, "completed\n"
def test_bayes_and2(self):
h2o.beta_features = True
csvPathname = 'standard/covtype.data'
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, schema='put')
paramDict = define_params()
for trial in range(1):
response = 'C55'
params = {
'response': response,
}
colX = h2o_util.pickRandParams(paramDict, params)
kwargs = params.copy()
timeoutSecs = 120
# chagne response to factor
execExpr = 'covtype.hex[,54+1] = factor(covtype.hex[,54+1] != 5)' # turn 7-class problem into binomial such that AUC can work below..
resultExec, ncols = h2e.exec_expr(execExpr=execExpr)
start = time.time()
bayesResult = h2o.nodes[0].naive_bayes(timeoutSecs=timeoutSecs, source='covtype.hex', **kwargs)
print "bayes end on ", csvPathname, 'took', time.time() - start, 'seconds'
print "bayes result:", h2o.dump_json(bayesResult)
nb_model = bayesResult['nb_model']
ncats = nb_model['ncats']
nnums = nb_model['nnums']
pcond = nb_model['pcond']
pprior = nb_model['pprior']
rescnt = nb_model['rescnt']
modelClassDist = nb_model['_modelClassDist']
names = nb_model['_names']
domains = nb_model['_domains']
priorClassDist = nb_model['_priorClassDist']
model_key = nb_model['_key']
# is it an error to get std dev of 0 after predicting?
print "Doing predict with same dataset, and the bayes model"
h2o.nodes[0].generate_predictions(model_key=model_key, data_key='covtype.hex', prediction='Predict.hex')
# just get a predict and AUC on the same data. has to be binomial result
resultAUC = h2o.nodes[0].generate_auc(thresholds=None, actual='covtype.hex', predict='Predict.hex',
vactual=response, vpredict=1)
print "AUC result:", h2o.dump_json(resultAUC)
print "Trial #", trial, "completed\n"
def test_speedrf_params_rand2_fvec(self):
h2o.beta_features = True
csvPathname = 'standard/covtype.data'
hex_key = 'covtype.data.hex'
for trial in range(10):
# params is mutable. This is default.
# response is required for SpeeERF
params = {
'response': 'C55',
'ntrees': 1,
'mtries': 7,
'balance_classes': 0,
# never run with unconstrained balance_classes size if random sets balance_classes..too slow
'max_after_balance_size': 2,
'importance': 0
}
colX = h2o_util.pickRandParams(paramDict, params)
if 'cols' in params and params['cols']:
# exclusion
if 'ignored_cols_by_name' in params:
params['ignored_cols_by_name'] = None
else:
if 'ignored_cols_by_name' in params and params[
'ignored_cols_by_name']:
params['mtries'] = random.randint(1, 53)
else:
params['mtries'] = random.randint(1, 54)
kwargs = params.copy()
# adjust timeoutSecs with the number of trees
timeoutSecs = 80 + (
(kwargs['ntrees'] * 80) * max(1, kwargs['mtries'] / 60))
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='put',
hex_key=hex_key)
h2o_cmd.runSpeeDRF(parseResult=parseResult,
timeoutSecs=timeoutSecs,
retryDelaySecs=1,
**kwargs)
elapsed = time.time() - start
print "Trial #", trial, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
def test_create_rebalance_2enum(self):
# default
params = {'rows': 100, 'cols': 1}
for trial in range(20):
# CREATE FRAME params################################################################
h2o_util.pickRandParams(paramDict, params)
i = params.get('integer_fraction', None)
c = params.get('categorical_fraction', None)
r = params.get('randomize', None)
v = params.get('value', None)
# h2o does some strict checking on the combinations of these things
# fractions have to add up to <= 1 and only be used if randomize
# h2o default randomize=1?
if r:
if not i:
i = 0
if not c:
c = 0
if (i and c) and (i + c) >= 1.0:
c = 1.0 - i
params['integer_fraction'] = i
params['categorical_fraction'] = c
params['value'] = None
else:
params['randomize'] = 0
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
# CREATE FRAME*****************************************************
kwargs = params.copy()
print kwargs
timeoutSecs = 300
hex_key = 'temp1000.hex'
cfResult = h2o.nodes[0].create_frame(key=hex_key,
timeoutSecs=timeoutSecs,
**kwargs)
# REBALANCE*****************************************************
print "Rebalancing it to create an artificially large # of chunks"
rb_key = "rb_%s" % (hex_key)
start = time.time()
print "Rebalancing %s to %s with %s chunks" % (hex_key, rb_key,
REBALANCE_CHUNKS)
SEEDPERFILE = random.randint(0, sys.maxint)
rebalanceResult = h2o.nodes[0].rebalance(source=hex_key,
after=rb_key,
chunks=REBALANCE_CHUNKS)
elapsed = time.time() - start
print "rebalance end on ", hex_key, 'to', rb_key, 'took', elapsed, 'seconds',\
# TO ENUM*****************************************************
print "Now doing to_enum across all columns of %s" % rb_key
for column_index in range(params['cols']):
# is the column index 1-base in to_enum
result = h2o.nodes[0].to_enum(None,
src_key=rb_key,
column_index=column_index + 1)
# print "\nto_enum result:", h2o.dump_json(result)
summaryResult = h2o_cmd.runSummary(key=hex_key)
# check that it at least is an enum column now, with no na's
# just look at the column we touched
column = summaryResult['summaries'][column_index]
colname = column['colname']
coltype = column['type']
nacnt = column['nacnt']
stats = column['stats']
stattype = stats['type']
# we have some # of na's in the columns...but there should not be 100% NA
if nacnt >= params['rows']:
raise Exception(
"column %s, which has name '%s', somehow too many NAs after convert to Enum %s %s"
% (column_index, colname, nacnt, params['rows']))
print "I suspect that columns that are constant, maybe with NAs also, don't convert to Enum"
if stattype != 'Enum':
raise Exception(
"column %s, which has name '%s', didn't convert to Enum, is %s %s %s"
% (column_index, colname, stattype, coltype,
h2o.dump_json(column)))
cardinality = stats['cardinality']
# don't know the cardinality expected
# if cardinality!=4:
# raise Exception("column %s, which has name '%s', should have cardinality 4, got: %s" %
# (column_index, colname, cardinality))
h2o_cmd.infoFromSummary(summaryResult)
print "Trial #", trial, "completed"
def test_KMeans_create_frame_fvec(self):
for trial in range(20):
cfParamDict = define_create_frame_params(SEED)
# default
params = {
'rows': 5,
'cols': 10
}
h2o_util.pickRandParams(cfParamDict, params)
i = params.get('integer_fraction', None)
c = params.get('categorical_fraction', None)
r = params.get('randomize', None)
v = params.get('value', None)
# h2o does some strict checking on the combinations of these things
# fractions have to add up to <= 1 and only be used if randomize
# h2o default randomize=1?
if r:
if not i:
i = 0
if not c:
c = 0
if (i and c) and (i + c) >= 1.0:
c = 1.0 - i
params['integer_fraction'] = i
params['categorical_fraction'] = c
params['value'] = None
else:
params['randomize'] = 0
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
kwargs = params.copy()
timeoutSecs = 300
hex_key = 'temp_%s.hex' % trial
cfResult = h2o.nodes[0].create_frame(key=hex_key, timeoutSecs=timeoutSecs, **kwargs)
inspect = h2o_cmd.runInspect(None, hex_key)
print "\n%s" % hex_key, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
kmeansParamDict = define_KMeans_params(SEED)
# default
params = {
'max_iter': 20,
'k': 1,
'destination_key': "KM_" + str(trial) + '.hex'
}
h2o_kmeans.pickRandKMeansParams(kmeansParamDict, params)
kwargs = params.copy()
start = time.time()
parseResult = {'destination_key': hex_key }
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans trial %s end on ", trial, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
print "Trial #", trial, "completed\n"
def test_create_rebalance_2enum(self):
h2o.beta_features = True
# default
params = {
'rows': 100,
'cols': 1
}
for trial in range(20):
# CREATE FRAME params################################################################
h2o_util.pickRandParams(paramDict, params)
i = params.get('integer_fraction', None)
c = params.get('categorical_fraction', None)
r = params.get('randomize', None)
v = params.get('value', None)
# h2o does some strict checking on the combinations of these things
# fractions have to add up to <= 1 and only be used if randomize
# h2o default randomize=1?
if r:
if not i:
i = 0
if not c:
c = 0
if (i and c) and (i + c) >= 1.0:
c = 1.0 - i
params['integer_fraction'] = i
params['categorical_fraction'] = c
params['value'] = None
else:
params['randomize'] = 0
params['integer_fraction'] = 0
params['categorical_fraction'] = 0
# CREATE FRAME*****************************************************
kwargs = params.copy()
print kwargs
timeoutSecs = 300
hex_key='temp1000.hex'
cfResult = h2o.nodes[0].create_frame(key=hex_key, timeoutSecs=timeoutSecs, **kwargs)
# REBALANCE*****************************************************
print "Rebalancing it to create an artificially large # of chunks"
rb_key = "rb_%s" % (hex_key)
start = time.time()
print "Rebalancing %s to %s with %s chunks" % (hex_key, rb_key, REBALANCE_CHUNKS)
SEEDPERFILE = random.randint(0, sys.maxint)
rebalanceResult = h2o.nodes[0].rebalance(source=hex_key, after=rb_key, chunks=REBALANCE_CHUNKS)
elapsed = time.time() - start
print "rebalance end on ", hex_key, 'to', rb_key, 'took', elapsed, 'seconds',\
# TO ENUM*****************************************************
print "Now doing to_enum across all columns of %s" % rb_key
for column_index in range(params['cols']):
# is the column index 1-base in to_enum
result = h2o.nodes[0].to_enum(None, src_key=rb_key, column_index=column_index+1)
# print "\nto_enum result:", h2o.dump_json(result)
summaryResult = h2o_cmd.runSummary(key=hex_key)
# check that it at least is an enum column now, with no na's
# just look at the column we touched
column = summaryResult['summaries'][column_index]
colname = column['colname']
coltype = column['type']
nacnt = column['nacnt']
stats = column['stats']
stattype = stats['type']
# we have some # of na's in the columns...but there should not be 100% NA
if nacnt>=params['rows']:
raise Exception("column %s, which has name '%s', somehow too many NAs after convert to Enum %s %s" %
(column_index, colname, nacnt, params['rows']))
print "I suspect that columns that are constant, maybe with NAs also, don't convert to Enum"
if stattype != 'Enum':
raise Exception("column %s, which has name '%s', didn't convert to Enum, is %s %s %s" %
(column_index, colname, stattype, coltype, h2o.dump_json(column)))
cardinality = stats['cardinality']
# don't know the cardinality expected
# if cardinality!=4:
# raise Exception("column %s, which has name '%s', should have cardinality 4, got: %s" %
# (column_index, colname, cardinality))
h2o_cmd.infoFromSummary(summaryResult)
print "Trial #", trial, "completed"