def notest_RF_poker100(self):
h2o.beta_features = True
trees = 6
timeoutSecs = 20
csvPathname = 'poker/poker100'
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=trees, timeoutSecs=timeoutSecs)
def test_RFhhp(self):
# NAs cause CM to zero..don't run for now
csvPathname = 'hhp_9_17_12.predict.data.gz'
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=6, timeoutSecs=30)
def test_rf_float_rand2_fvec(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_prostate.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON"
totalRows = 10000
write_syn_dataset(csvPathname, totalRows, headerData)
for trial in range(5):
rowData = rand_rowData()
num = random.randint(4096, 10096)
append_syn_dataset(csvPathname, num)
totalRows += num
start = time.time()
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
hex_key = csvFilename + "_" + str(trial) + ".hex"
# On EC2 once we get to 30 trials or so, do we see polling hang? GC or spill of heap or ??
kwargs = {'ntrees': 5, 'max_depth': 5}
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key)
h2o_cmd.runRF(parseResult=parseResult,
timeoutSecs=60,
pollTimeoutSecs=60,
**kwargs)
print "trial #", trial, "totalRows:", totalRows, "num:", num, "RF end on ", csvFilename, \
'took', time.time() - start, 'seconds'
### h2o_cmd.runInspect(key=hex_key)
### h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
h2o.check_sandbox_for_errors()
def test_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
parityPl = h2o.find_file('syn_scripts/parity.pl')
# two row dataset gets this. Avoiding it for now
# java.lang.ArrayIndexOutOfBoundsException: 1
# at hex.rf.Data.sample_fair(Data.java:149)
# always match the run below!
print "\nAssuming two row dataset is illegal. avoiding"
for x in xrange (10,100,10):
shCmdString = "perl " + parityPl + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split())
# algorithm for creating the path and filename is hardwired in parity.pl.
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# FIX! we fail if min is 3
for x in xrange (10,100,10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=trees, timeoutSecs=timeoutSecs)
trees += 10
timeoutSecs += 2
def test_B_randomdata2_1_lineend(self):
csvPathname = 'datagen1.csv'
# change lineend, case 1
csvPathname1 = h2i.find_folder_and_filename('smalldata',
csvPathname,
returnFullPath=True)
print "Using datagen1.csv to create", SYNDATASETS_DIR, "/datagen1.csv with different line ending"
csvPathname2 = SYNDATASETS_DIR + '/datagen1_crlf.csv'
infile = open(csvPathname1, 'r')
outfile = open(csvPathname2, 'w') # existing file gets erased
# assume all the test files are unix lineend.
# I guess there shouldn't be any "in-between" ones
# okay if they change I guess.
for line in infile.readlines():
outfile.write(line.strip("\n") + "\r")
infile.close()
outfile.close()
parseResult = h2i.import_parse(path=csvPathname2,
schema='put',
timeoutSecs=10,
header=0,
separator=44)
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
numCols = inspect['numCols']
h2o_cmd.runRF(parseResult=parseResult,
trees=1,
response='C' + str(numCols),
timeoutSecs=20)
def test_B_randomdata2_1_lineend(self):
csvPathname = 'datagen1.csv'
# change lineend, case 1
csvPathname1 = h2i.find_folder_and_filename('smalldata', csvPathname, returnFullPath=True)
print "Using datagen1.csv to create", SYNDATASETS_DIR, "/datagen1.csv with different line ending"
csvPathname2 = SYNDATASETS_DIR + '/datagen1_crlf.csv'
infile = open(csvPathname1, 'r')
outfile = open(csvPathname2,'w') # existing file gets erased
# assume all the test files are unix lineend.
# I guess there shouldn't be any "in-between" ones
# okay if they change I guess.
for line in infile.readlines():
outfile.write(line.strip("\n") + "\r")
infile.close()
outfile.close()
parseResult = h2i.import_parse(path=csvPathname2, schema='put',
timeoutSecs=10, header=0, separator=44)
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
numCols = inspect['numCols']
h2o_cmd.runRF(parseResult=parseResult,
trees=1,
response_variable='C'+str(numCols),
timeoutSecs=20)
def test_rf_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.
params = {"ntrees": 13, "mtries": 7}
colX = h2o_rf.pickRandRfParams(paramDict, params)
if "cols" in params and params["cols"]:
pass
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 = 30 + ((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.runRF(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 notest_B_RF_iris2(self):
csvPathname = h2o.find_file('smalldata/iris/iris2.csv')
h2o_cmd.runRF(trees=6,
model_key="iris2",
timeoutSecs=10,
retryDelaySecs=1,
csvPathname=csvPathname)
def test_rf_strata_fail(self):
csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
timeoutSecs = 60
kwargs = {
'response_variable': 54,
'ntree': 50,
'features': '',
'depth': 2147483647,
'stat_type': 'ENTROPY',
'ignore': '',
'class_weights': '1=1.0,2=1.0,3=1.0,4=1.0,5=1.0,6=1.0,7=1.0',
'sampling_strategy': 'RANDOM',
'strata_samples':
'undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined',
'sample': '67',
'out_of_bag_error_estimate': 1,
'model_key': '',
'bin_limit': 1024,
'seed': 784834182943470027,
'parallel': 1,
'exclusive_split_limit': '',
'iterative_cm': 1,
'use_non_local_data': 0,
}
h2o_cmd.runRF(timeoutSecs=timeoutSecs,
csvPathname=csvPathname,
**kwargs)
def test_hex_443(self):
h2o.beta_features = True
csvPathname = 'hex-443.parsetmp_1_0_0_0.data'
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
schema='put')
h2o_cmd.runRF(parseResult=parseResult, ntrees=1, timeoutSecs=5)
def test_GenParity1(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
parityPl = h2o.find_file('syn_scripts/parity.pl')
# two row dataset gets this. Avoiding it for now
# java.lang.ArrayIndexOutOfBoundsException: 1
# at hex.rf.Data.sample_fair(Data.java:149)
# always match the run below!
print "\nAssuming two row dataset is illegal. avoiding"
for x in xrange(10, 100, 10):
shCmdString = "perl " + parityPl + " 128 4 " + str(
x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split())
# algorithm for creating the path and filename is hardwired in parity.pl.
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# FIX! we fail if min is 3
for x in xrange(10, 100, 10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult,
trees=trees,
timeoutSecs=timeoutSecs)
trees += 10
timeoutSecs += 2
def test_D_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange (11,100,10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 " + str(x) + " quad"
# FIX! as long as we're doing a couple, you'd think we wouldn't have to
# wait for the last one to be gen'ed here before we start the first below.
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),timeout=3)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange (11,60,10):
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
# FIX! TBD do we always have to kick off the run from node 0?
# what if we do another node?
# FIX! do we need or want a random delay here?
h2o_cmd.runRF( trees=trees, timeoutSecs=timeoutSecs,
csvPathname=csvPathname)
trees += 10
sys.stdout.write('.')
sys.stdout.flush()
def test_A_randomdata2(self):
print "Using smalldata/datagen1.csv as is"
csvPathname = h2o.find_file('smalldata/datagen1.csv')
h2o_cmd.runRF(trees=1,
response_variable=2,
timeoutSecs=10,
csvPathname=csvPathname)
def test_A_randomdata2(self):
print "Using datagen1.csv as-is"
csvPathname = 'datagen1.csv'
# have to give the separator == comma...otherwise H2O can't deduce it on this dataset
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put',
timeoutSecs=10, header=1, separator=44)
h2o_cmd.runRF(parseResult=parseResult, trees=1, response_variable=2, timeoutSecs=20)
def tryThemAll(self,set,rows):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
for tokenCase in range(len(self.tokenChangeDict)):
newRows1 = self.changeTokens(rows,tokenCase)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1,sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname,newRows2,eol)
if "'" in self.tokenChangeDict[tokenCase][0]:
single_quotes = 1
else:
single_quotes = 0
parseResult = h2i.import_parse(path=csvPathname, schema='put', single_quotes=single_quotes,
noPrint=not h2o.verbose)
if DO_RF:
h2o_cmd.runRF(parseResult=parseResult, trees=1, timeoutSecs=30, retryDelaySecs=0.1)
h2o.verboseprint("Set", set)
sys.stdout.write('.')
sys.stdout.flush()
def test_rf_strata_fail(self):
csvPathname ='UCI/UCI-large/covtype/covtype.data'
timeoutSecs = 60
kwargs = {
'response_variable': 54,
'ntree': 50,
'features': '',
'depth': 2147483647,
'stat_type': 'ENTROPY',
'ignore': '',
'class_weights': '1=1.0,2=1.0,3=1.0,4=1.0,5=1.0,6=1.0,7=1.0',
'sampling_strategy': 'RANDOM',
'strata_samples': 'undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined,undefined=undefined',
'sample': '67',
'out_of_bag_error_estimate': 1,
'model_key': '',
'bin_limit': 1024,
'seed': 784834182943470027,
'parallel': 1,
'exclusive_split_limit': '',
'iterative_cm': 1,
'use_non_local_data': 0,
}
parseResult = h2i.import_parse(bucket='datasets', path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
def test_A_c1_fvec(self):
h2o.beta_features = True
parseResult = h2i.import_parse(bucket='smalldata',
path='iris/iris2.csv',
schema='put',
timeoutSecs=60)
h2o_cmd.runRF(parseResult=parseResult, trees=6, timeoutSecs=60)
def test_D_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange(11, 100, 10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file(
"syn_scripts/parity.pl") + " 128 4 " + str(x) + " quad"
h2o.spawn_cmd_and_wait('parity.pl',
shCmdString.split(),
timeout=30)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange(11, 60, 10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
h2o_cmd.runRF(trees=trees,
timeoutSecs=timeoutSecs,
csvPathname=csvPathname)
trees += 10
def test_poker_xlsx(self):
# maybe can get stuck during polling for parse progress?
# break it out for pollTimeoutSecs
parseResult = h2i.import_parse(
bucket="datasets", path="poker/poker-hand-testing.xlsx", schema="put", timeoutSecs=120, pollTimeoutSecs=60
)
h2o_cmd.runRF(None, parseResult=parseResult, timeoutSecs=120)
def test_rf_big_rand_tree_fvec(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
rowCount = 5000
colCount = 1000
write_syn_dataset(csvPathname, rowCount, colCount)
for trial in range (1):
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
src_key = csvFilename + "_" + str(trial)
hex_key = csvFilename + "_" + str(trial) + ".hex"
seed = random.randint(0,sys.maxint)
# some cols can be dropped due to constant 0 or 1. make sure data set has all 0's and all 1's above
# to guarantee no dropped cols!
# kwargs = {'ntree': 3, 'depth': 50, 'seed': seed}
# out of memory/GC errors with the above. reduce depth
kwargs = {'ntrees': 3, 'max_depth': 20, 'seed': seed}
start = time.time()
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=90)
h2o_cmd.runRF(parseResult=parseResult, timeoutSecs=600, pollTimeoutSecs=180, **kwargs)
print "trial #", trial, "rowCount:", rowCount, "colCount:", colCount, "RF end on ", csvFilename, \
'took', time.time() - start, 'seconds'
inspect = h2o_cmd.runInspect(key=hex_key)
h2o_cmd.infoFromInspect(inspect, csvPathname)
cols = inspect['cols']
numCols = inspect['numCols']
for i,c in enumerate(cols):
colType = c['type']
self.assertEqual(colType, 'Int', msg="col %d should be type in: %s" % (i, colType))
h2o.check_sandbox_for_errors()
def test_D_GenParity1(self):
trees = 50
h2o_cmd.runRF(
trees=50,
timeoutSecs=15,
csvPathname=h2o.find_file('smalldata/parity_128_4_100_quad.data'),
noise=('StoreView', None))
def test_rf_params_rand2(self):
# for determinism, I guess we should spit out the seed?
# random.seed(SEED)
SEED = random.randint(0, sys.maxint)
# if you have to force to redo a test
# SEED =
random.seed(SEED)
print "\nUsing random seed:", SEED
csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
for trial in range(10):
# params is mutable. This is default.
params = {'ntree': 13, 'parallel': 1, 'features': 7}
colX = h2o_rf.pickRandRfParams(paramDict, params)
kwargs = params.copy()
# adjust timeoutSecs with the number of trees
timeoutSecs = 30 + (
(kwargs['ntree'] * 20) * max(1, kwargs['features'] / 15) *
(kwargs['parallel'] and 1 or 3))
start = time.time()
h2o_cmd.runRF(timeoutSecs=timeoutSecs,
retryDelaySecs=1,
csvPathname=csvPathname,
**kwargs)
elapsed = time.time() - start
print "Trial #", trial, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
def test_C_RF_poker100(self):
parseResult = h2i.import_parse(bucket='smalldata', path='poker/poker100', schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=6, timeoutSecs=10)
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange (11,100,10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),timeout=30)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 60
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange (11,60,10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, ntrees=trees, timeoutSecs=timeoutSecs)
trees += 10
def tryThemAll(self, set, rows, enumsOnly=False):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
if enumsOnly:
tcd = self.tokenChangeDict
else:
tcd = self.tokenChangeDictEnumsOnly
for tokenCase in range(len(tcd)):
newRows1 = self.changeTokens(rows, tokenCase, tcd)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1,sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname,newRows2,eol)
if "'" in tcd[tokenCase][0]:
singleQuotes = 1
else:
singleQuotes = 0
parseResult = h2i.import_parse(path=csvPathname, schema='local', singleQuotes=singleQuotes,
noPrint=not h2o_args.verbose, retryDelaySecs=0.1,
doSummary=DO_SUMMARY, intermediateResults=DO_INTERMEDIATE_RESULTS)
if DO_RF:
h2o_cmd.runRF(parseResult=parseResult, trees=1,
timeoutSecs=10, retryDelaySecs=0.1, noPrint=True, print_params=True)
verboseprint("Set", set)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_badchars(self):
print "badchars.csv has some 0x0 (<NUL>) characters."
print "They were created by a dd that filled out to buffer boundary with <NUL>"
print "They are visible using vim/vi"
csvPathname = h2o.find_file('smalldata/badchars.csv')
h2o_cmd.runRF(trees=50, timeoutSecs=10, csvPathname=csvPathname)
def test_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
# just using one file for now
for x in [1000]:
shCmdString = (
"perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 " + str(x) + " quad " + SYNDATASETS_DIR
)
h2o.spawn_cmd_and_wait("parity.pl", shCmdString.split(), 4)
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
# always match the gen above!
for trial in range(1, 3):
sys.stdout.write(".")
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(1000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + "/" + csvFilename
hex_key = csvFilename + "_" + str(trial) + ".hex"
parseResult = h2o_cmd.parseResult = h2i.import_parse(
path=csvPathname, schema="put", hex_key=hex_key, timeoutSecs=30
)
h2o.verboseprint("Trial", trial)
start = time.time()
h2o_cmd.runRF(parseResult=parseResult, trees=10000, depth=2, timeoutSecs=900, retryDelaySecs=3)
print "RF #", trial, "end on ", csvFilename, "took", time.time() - start, "seconds"
print "Waiting 60 secs for TIME_WAIT sockets to go away"
time.sleep(60)
def tryThemAll(self,set,rows):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
for tokenCase in range(len(self.tokenChangeDict)):
newRows1 = self.changeTokens(rows,tokenCase)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1,sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname,newRows2,eol)
parseResult = h2i.import_parse(path=csvPathname, schema='local', noPrint=not h2o.verbose)
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
print "\n" + csvPathname, \
" num_rows:", "{:,}".format(inspect['num_rows']), \
" num_cols:", "{:,}".format(inspect['num_cols'])
num_rows = inspect['num_rows']
num_cols = inspect['num_cols']
self.assertEqual(num_cols, 4, "Parsed wrong number of cols: %s" % num_cols)
self.assertEqual(num_rows, 29, "Parsed wrong number of rows: %s" % num_rows)
h2o_cmd.runRF(parseResult=parseResult, trees=1,
timeoutSecs=10, retryDelaySecs=1.0, noPrint=True)
h2o.verboseprint("Set", set)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_rf_1ktrees_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
# just using one file for now
for x in [500]:
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),4)
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
# always match the gen above!
for trial in range (1,5):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(1000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
hex_key = csvFilename + "_" + str(trial) + ".hex"
parseResult = h2o_cmd.parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30)
h2o.verboseprint("Trial", trial)
start = time.time()
h2o_cmd.runRF(parseResult=parseResult, trees=1000, max_depth=2, timeoutSecs=600, retryDelaySecs=3)
print "RF #", trial, "end on ", csvFilename, 'took', time.time() - start, 'seconds'
print "Waiting 60 secs for TIME_WAIT sockets to go away"
time.sleep(60)
def tryThemAll(self, set, rows, enumsOnly=False):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
if enumsOnly:
tcd = self.tokenChangeDict
else:
tcd = self.tokenChangeDictEnumsOnly
for tokenCase in range(len(tcd)):
newRows1 = self.changeTokens(rows, tokenCase, tcd)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1,sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname,newRows2,eol)
parseResult = h2i.import_parse(path=csvPathname, schema='put', noPrint=not h2o.verbose)
h2o_cmd.runRF(parseResult=parseResult, trees=1,
timeoutSecs=10, retryDelaySecs=0.1, noPrint=True, print_params=False)
h2o.verboseprint("Set", set)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def tryThemAll(self, set, rows):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
for tokenCase in range(len(self.tokenChangeDict)):
newRows1 = self.changeTokens(rows, tokenCase)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1, sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname, newRows2, eol)
if "'" in self.tokenChangeDict[tokenCase]:
single_quotes = 1
else:
single_quotes = 0
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
single_quotes=single_quotes,
noPrint=not h2o.verbose)
h2o_cmd.runRF(parseResult=parseResult,
trees=1,
timeoutSecs=30,
retryDelaySecs=0.1)
h2o.verboseprint("Set", set)
sys.stdout.write('.')
sys.stdout.flush()
def test_1ktrees_job_cancel_many(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
# just using one file for now
for x in [1000]:
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad"
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),4)
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvFilename = "parity_128_4_" + str(1000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2o_cmd.parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30)
print "Kick off twenty, then cancel them all..there's a timeout on the wait after cancelling"
for trial in range (1,20):
h2o.verboseprint("Trial", trial)
start = time.time()
h2o_cmd.runRF(parseResult=parseResult, trees=trial, depth=50, rfView=False, noPoll=True,
timeoutSecs=600, retryDelaySecs=3)
print "RF #", trial, "started on ", csvFilename, 'took', time.time() - start, 'seconds'
h2o.check_sandbox_for_errors()
h2o_jobs.cancelAllJobs(timeoutSecs=10)
def test_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in [10000]:
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad"
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),4)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
# always match the gen above!
trial = 1
for x in xrange (1,10,1):
sys.stdout.write('.')
sys.stdout.flush()
# just use one file for now
csvFilename = "parity_128_4_" + str(10000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
# broke out the put separately so we can iterate a test just on the RF
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o.verboseprint("Trial", trial)
h2o_cmd.runRF(parseResult=parseResult, trees=237, depth=45, timeoutSecs=480)
# don't change tree count yet
## trees += 10
### timeoutSecs += 2
trial += 1
def test_cs_test(self):
parseResult = h2i.import_parse(bucket='smalldata', path='kaggle/creditsample-training.csv.gz', schema='put')
h2o_cmd.runRF(parseResult=parseResult, ntrees=5, max_depth=100, timeoutSecs=500,
response='SeriousDlqin2yrs')
# h2b.browseJsonHistoryAsUrlLastMatch("RFView")
time.sleep(5)
def test_rf_big1_nopoll_fvec(self):
h2o.beta_features = True
csvFilename = 'hhp_107_01.data.gz'
hex_key = csvFilename + ".hex"
print "\n" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvFilename,
hex_key=hex_key, timeoutSecs=30, schema='put')
rfViewInitial = []
# dispatch multiple jobs back to back
for jobDispatch in range(3):
start = time.time()
kwargs = {}
if OVERWRITE_RF_MODEL:
print "Since we're overwriting here, we have to wait for each to complete noPoll=False"
model_key = 'RF_model'
else:
model_key = 'RF_model' + str(jobDispatch)
kwargs['ntrees'] = 1
if OVERWRITE_RF_MODEL:
print "Change the number of trees, while keeping the rf model key name the same"
print "Checks that we correctly overwrite previous rf model"
kwargs['ntrees'] += 1
kwargs['seed'] = random.randint(0, sys.maxint)
# FIX! what model keys do these get?
randomNode = h2o.nodes[random.randint(0,len(h2o.nodes)-1)]
h2o_cmd.runRF(node=randomNode, parseResult=parseResult, destination_key=model_key,
timeoutSecs=300, noPoll=False if OVERWRITE_RF_MODEL else True, **kwargs)
print "rf job dispatch end on ", csvFilename, 'took', time.time() - start, 'seconds'
print "\njobDispatch #", jobDispatch
h2o_jobs.pollWaitJobs(pattern='RF_model', timeoutSecs=300, pollTimeoutSecs=10, retryDelaySecs=5)
# we saved the initial response?
# if we do another poll they should be done now, and better to get it that
# way rather than the inspect (to match what simpleCheckGLM is expected
first = None
print "rfViewInitial", rfViewInitial
for rfView in rfViewInitial:
print "Checking completed job:", rfView
print "rfView", h2o.dump_json(rfView)
data_key = rfView['_dataKey']
model_key = rfView['_key']
ntree = rfView['ntree']
print "Temporary hack: need to do two rf views minimum, to complete a RF (confusion matrix creation)"
# allow it to poll to complete
rfViewResult = h2o_cmd.runRFView(None, data_key, model_key, ntree=ntree, timeoutSecs=60, noPoll=False)
if first is None: # we'll use this to compare the others
first = rfViewResult.copy()
firstModelKey = model_key
print "first", h2o.dump_json(first)
else:
print "Comparing", model_key, "to", firstModelKey
df = h2o_util.JsonDiff(rfViewResult, first, vice_versa=True, with_values=True)
print "df.difference:", h2o.dump_json(df.difference)
def test_D_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange(50, 200, 10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file(
"syn_scripts/parity.pl") + " 128 4 " + str(x) + " quad"
# FIX! as long as we're doing a couple, you'd think we wouldn't have to
# wait for the last one to be gen'ed here before we start the first below.
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(), timeout=3)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
# bump this up too if you do?
# always match the gen above!
### for x in xrange (50,200,10):
for x in xrange(50, 200, 10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + "100" + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
h2o_cmd.runRF(csvPathname=csvPathname,
trees=100,
timeoutSecs=5,
retryDelaySecs=0.1)
def test_D_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange(11, 100, 10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file(
"syn_scripts/parity.pl") + " 128 4 " + str(
x) + " quad " + SYNDATASETS_DIR
# FIX! as long as we're doing a couple, you'd think we wouldn't have to
# wait for the last one to be gen'ed here before we start the first below.
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(), timeout=3)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange(11, 60, 10):
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult,
ntrees=trees,
timeoutSecs=timeoutSecs)
trees += 10
def test_RFhhp(self):
csvPathnamegz = h2o.find_file('smalldata/hhp_107_01.data.gz')
print "\nRF start on ", csvPathnamegz, "this will probably take a minute.."
start = time.time()
h2o_cmd.runRF(csvPathname=csvPathnamegz, trees=23,
timeoutSecs=120, retryDelaySecs=10)
print "RF end on ", csvPathnamegz, 'took', time.time() - start, 'seconds'
def tryThemAll(self, set, rows):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
for tokenCase in range(len(self.tokenChangeDict)):
newRows1 = self.changeTokens(rows, tokenCase)
for sepCase in range(len(self.sepChangeDict)):
newRows2 = self.changeSep(newRows1, sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname, newRows2, eol)
h2o_cmd.runRF(trees=1,
csvPathname=csvPathname,
timeoutSecs=10,
retryDelaySecs=0.1,
noPrint=True,
print_params=False)
h2o.verboseprint("Set", set)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_D_GenParity1(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange(11, 100, 10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file(
"syn_scripts/parity.pl") + " 128 4 " + str(x) + " quad"
# FIX! as long as we're doing a couple, you'd think we wouldn't have to
# wait for the last one to be gen'ed here before we start the first below.
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(), timeout=3)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 20
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange(11, 60, 10):
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
# FIX! TBD do we always have to kick off the run from node 0?
# what if we do another node?
# FIX! do we need or want a random delay here?
h2o_cmd.runRF(trees=trees,
timeoutSecs=timeoutSecs,
csvPathname=csvPathname)
trees += 10
sys.stdout.write('.')
sys.stdout.flush()
def test_1ktrees_job_cancel_many_fvec(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
# just using one file for now
for x in [1000]:
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),4)
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvFilename = "parity_128_4_" + str(1000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2o_cmd.parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30)
print "kick off jobs, then cancel them"
for trial in range (1,5):
# random 0 or 1 delay
delay = random.uniform(0,1)
time.sleep(delay)
h2o.verboseprint("Trial", trial)
start = time.time()
h2o_cmd.runRF(parseResult=parseResult, trees=trial, max_depth=50, rfView=False, noPoll=True, timeoutSecs=30, retryDelaySecs=0.25)
print "RF #", trial, "started on ", csvFilename, 'took', time.time() - start, 'seconds'
### h2o_jobs.cancelAllJobs(timeoutSecs=10)
h2o.check_sandbox_for_errors()
# do one last good one
rfView = h2o_cmd.runRF(parseResult=parseResult, trees=trial, max_depth=50, timeoutSecs=600, retryDelaySecs=3)
(classification_error, classErrorPctList, totalScores) = h2o_rf.simpleCheckRFView(rfv=rfView, ntree=trial)
def notest_RF_iris2(self):
trees = 6
timeoutSecs = 20
csvPathname = h2o.find_file('smalldata/iris/iris2.csv')
h2o_cmd.runRF(trees=trees,
timeoutSecs=timeoutSecs,
csvPathname=csvPathname)
def test_rf3_fvec(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in [10000]:
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),4)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
# always match the gen above!
trial = 1
for x in range (1):
sys.stdout.write('.')
sys.stdout.flush()
# just use one file for now
csvFilename = "parity_128_4_" + str(10000) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
# broke out the put separately so we can iterate a test just on the RF
parseResult = h2i.import_parse(path=csvPathname, schema='put', pollTimeoutSecs=60, timeoutSecs=60)
h2o.verboseprint("Trial", trial)
h2o_cmd.runRF(parseResult=parseResult, trees=237, max_depth=45, timeoutSecs=480)
# don't change tree count yet
## trees += 10
### timeoutSecs += 2
trial += 1
def notest_RF_poker100(self):
trees = 6
timeoutSecs = 20
csvPathname = h2o.find_file('smalldata/poker/poker100')
h2o_cmd.runRF(trees=trees,
timeoutSecs=timeoutSecs,
csvPathname=csvPathname)
def test_B_c1_fvec(self):
print "Since the python is not necessarily run as user=0xcust..., can't use a schema='put' here"
print "Want to be able to run python as jenkins"
print "I guess for big 0xcust files, we don't need schema='put'"
print "For files that we want to put (for testing put), we can get non-private files"
parseResult = h2i.import_parse(bucket='0xcustomer-datasets', path='c1/iris2.csv', schema='local', timeoutSecs=60)
h2o_cmd.runRF(parseResult=parseResult, trees=6, timeoutSecs=60)
def test_rf_params_rand2_ncaa(self):
csvPathname = 'ncaa/Players.csv'
for trial in range(4):
# params is mutable. This is default.
params = {'ntree': 13, 'features': 4}
colX = h2o_rf.pickRandRfParams(paramDict, params)
kwargs = params.copy()
# adjust timeoutSecs with the number of trees
# seems ec2 can be really slow
timeoutSecs = 30 + (
(kwargs['ntree'] * 20) * max(1, kwargs['features'] / 15))
# hack to NA the header (duplicate header names)
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='put',
header=0)
start = time.time()
h2o_cmd.runRF(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_badchars(self):
print "badchars.csv has some 0x0 (<NUL>) characters."
print "They were created by a dd that filled out to buffer boundary with <NUL>"
print "They are visible using vim/vi"
csvPathname = h2o.find_file('smalldata/badchars.csv')
h2o_cmd.runRF(trees=50, timeoutSecs=10, csvPathname=csvPathname)
def tryThemAll(self, set, rows):
for eolCase in range(len(self.eolDict)):
eol = self.eolDict[eolCase]
# change tokens must be first
for tokenCase in range(len(self.tokenChangeDict)):
newRows1 = self.changeTokens(rows, tokenCase)
for sepCase in range(len(self.sepChangeDict)):
(newSep, newRows2) = self.changeSep(newRows1, sepCase)
csvPathname = SYNDATASETS_DIR + '/parsetmp_' + \
str(set) + "_" + \
str(eolCase) + "_" + \
str(tokenCase) + "_" + \
str(sepCase) + \
'.data'
self.writeRows(csvPathname, newRows2, eol)
# give h2o the separator, to be nice. (integerized)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
separator=ord(newSep),
noPrint=not h2o.verbose)
h2o_cmd.runRF(parseResult=parseResult,
trees=1,
response_variable='C1',
timeoutSecs=10,
retryDelaySecs=0.1,
noPrint=True)
h2o.verboseprint("Set", set)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_C_RF_poker100(self):
parseResult = h2i.import_parse(bucket='smalldata', path='poker/poker100', schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=6, timeoutSecs=10)
SYNDATASETS_DIR = h2o.make_syn_dir()
# always match the run below!
for x in xrange (11,100,10):
# Have to split the string out to list for pipe
shCmdString = "perl " + h2o.find_file("syn_scripts/parity.pl") + " 128 4 "+ str(x) + " quad " + SYNDATASETS_DIR
h2o.spawn_cmd_and_wait('parity.pl', shCmdString.split(),timeout=30)
# the algorithm for creating the path and filename is hardwired in parity.pl..i.e
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
trees = 6
timeoutSecs = 60
# always match the gen above!
# reduce to get intermittent failures to lessen, for now
for x in xrange (11,60,10):
sys.stdout.write('.')
sys.stdout.flush()
csvFilename = "parity_128_4_" + str(x) + "_quad.data"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, ntrees=trees, timeoutSecs=timeoutSecs)
trees += 10
def test_rf_float_rand2_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_prostate.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON"
totalRows = 10000
write_syn_dataset(csvPathname, totalRows, headerData)
for trial in range (5):
rowData = rand_rowData()
num = random.randint(4096, 10096)
append_syn_dataset(csvPathname, num)
totalRows += num
start = time.time()
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
hex_key = csvFilename + "_" + str(trial) + ".hex"
# On EC2 once we get to 30 trials or so, do we see polling hang? GC or spill of heap or ??
kwargs = {'ntrees': 5, 'max_depth': 5}
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key)
h2o_cmd.runRF(parseResult=parseResult, timeoutSecs=60, pollTimeoutSecs=60, **kwargs)
print "trial #", trial, "totalRows:", totalRows, "num:", num, "RF end on ", csvFilename, \
'took', time.time() - start, 'seconds'
### h2o_cmd.runInspect(key=hex_key)
### h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
h2o.check_sandbox_for_errors()
def test_poker_xlsx(self):
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path='xls/poker-hand-testing.xlsx',
schema='put',
timeoutSecs=120,
pollTimeoutSecs=60)
h2o_cmd.runRF(None, parseResult=parseResult, timeoutSecs=120)
def notest_C_RF_poker100(self):
# RFview consumes cycles. Only retry once a second, to avoid slowing things down
csvPathname = h2o.find_file('smalldata/poker/poker100')
h2o_cmd.runRF(trees=6,
model_key="poker100",
timeoutSecs=10,
retryDelaySecs=1,
csvPathname=csvPathname)
def test_cs_training(self):
h2o_cmd.runRF(trees=100,
depth=100,
csvPathname=h2o.find_file(
'smalldata/kaggle/creditsample-training.csv.gz'),
timeoutSecs=300,
response_variable=1)
h2b.browseJsonHistoryAsUrlLastMatch("RFView")
def test_stedo_testing_data(self):
csvPathname = h2o.find_file('smalldata/stego/stego_training.data')
# Prediction class is the second column => class=1
h2o_cmd.runRF(trees=50,
timeoutSecs=30,
csvPathname=csvPathname,
response_variable=1,
out_of_bag_error_estimate=1)
def test_badchars(self):
print "badchars.csv has some 0x0 (<NUL>) characters."
print "They were created by a dd that filled out to buffer boundary with <NUL>"
print "They are visible using vim/vi"
csvPathname = 'badchars.csv'
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=50, timeoutSecs=10)
def test_tree_view(self):
parseResult = h2i.import_parse(
bucket="smalldata", path="poker/poker1000", hex_key="poker1000.hex", schema="put"
)
h2o_cmd.runRF(parseResult=parseResult, trees=50, model_key="model0", timeoutSecs=10)
for n in range(1):
a = h2o_cmd.runRFTreeView(n=n, data_key="poker1000.hex", model_key="model0", timeoutSecs=10)
print(h2o.dump_json(a))
def test_RFhhp(self):
csvPathname = 'hhp.cut3.214.data.gz'
print "RF start on ", csvPathname, "this will probably take 1 minute.."
start = time.time()
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, trees=10,
timeoutSecs=400, retryDelaySecs=15)
print "RF end on ", csvPathname, 'took', time.time() - start, 'seconds'
def test_rf_200x4_fvec(self):
csvPathname = 'hhp.cut3.214.data.gz'
print "RF start on ", csvPathname
start = time.time()
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
h2o_cmd.runRF(parseResult=parseResult, ntrees=3,
timeoutSecs=1200, retryDelaySecs=15)
print "RF end on ", csvPathname, 'took', time.time() - start, 'seconds'
def test_rf_params_rand1_fvec(self):
csvPathname = 'poker/poker1000'
for trial in range(10):
# params is mutable. This is default.
kwargs = params.copy()
timeoutSecs = 180
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put', timeoutSecs=timeoutSecs)
h2o_cmd.runRF(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
print "Trial #", trial, "completed"
