def test_B_benign(self):
print "\nStarting benign.csv"
csvFilename = "benign.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
# columns start at 0
y = "3"
x = ""
# cols 0-13. 3 is output
# no member id in this one
for appendx in xrange(14):
if (appendx == 3):
print "\n3 is output."
else:
if x == "":
x = str(appendx)
else:
x = x + "," + str(appendx)
csvFilename = "benign.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
print "\nx:", x
print "y:", y
kwargs = {'x': x, 'y': y}
# fails with num_cross_validation_folds
print "Not doing num_cross_validation_folds with benign. Fails with 'unable to solve?'"
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=5, **kwargs)
# no longer look at STR?
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
def test_R(self):
rScript = h2o.find_file('R/tests/test_R_GLM_basic.R')
rLibrary = h2o.find_file('R/H2O_S4.R')
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
h2o.spawn_wait(ps, outpath, errpath, timeout=10)
def test_R_RF_diff_class(self):
print "\nStarting iris.csv class weight test"
rScript = h2o.find_file('R/tests/test_R_RF_diff_class.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Compare results from different class weights
h2o_R.do_R(rScript, rLibrary)
def test_R(self):
rScript = h2o.find_file('R/tests/test_R_GLM_basic.R')
rLibrary = h2o.find_file('R/H2O_S4.R')
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
h2o.spawn_wait(ps, outpath, errpath, timeout=10)
def test_rf_model_key_unique(self):
modelKeyDict = {}
for trial in range(1, 5):
if trial == 1:
csvPathname = h2o.find_file('smalldata/iris/iris.csv')
else:
csvPathname = h2o.find_file('smalldata/iris/iris2.csv')
start = time.time()
rfResult = h2o_cmd.runRF(trees=6,
timeoutSecs=10,
rfView=False,
csvPathname=csvPathname)
print "RF #%d" % trial, "started on ", csvPathname, 'took', time.time(
) - start, 'seconds'
model_key = rfResult['model_key']
print "model_key:", model_key
if model_key in modelKeyDict:
raise Exception(
"same model_key used in RF #%d that matches prior RF #%d" %
(trial, modelKeyDict[model_key]))
modelKeyDict[model_key] = trial
# just show the jobs still going, if any. maybe none, because short (iris)
a = h2o.nodes[0].jobs_admin()
print "jobs_admin():", h2o.dump_json(a)
def test_R_RF_diff_ignore(self):
print "\nStarting iris.csv ignore predictor(s) test"
rScript = h2o.find_file('R/tests/test_R_RF_diff_ignore.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Ignore successively more predictor columns
h2o_R.do_R(rScript, rLibrary)
def test_R_C_kmeans_prostate(self):
print "\nStarting prostate.csv"
rScript = h2o.find_file('R/tests/test_R_C_kmeans_prostate.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Run k-means with k = 5 on column 2 (Age)
# Loop to see if we get same centers
h2o_R.do_R(rScript, rLibrary)
def test_R_B_kmeans_benign(self):
print "\nStarting benign.csv"
rScript = h2o.find_file('R/tests/test_R_B_kmeans_benign.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Run k-means with k = 3 on all columns
# Loop to see if we get same centers
h2o_R.do_R(rScript, rLibrary)
def test_R_RF_diff_class(self):
print "\nStarting iris.csv class weight test"
rScript = h2o.find_file('R/tests/test_R_RF_diff_class.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Compare results from different class weights
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if(rc != 0): raise Exception("R exited with non-zero return code %s" % rc)
def test_R_RF_diff_ignore(self):
print "\nStarting iris.csv ignore predictor(s) test"
rScript = h2o.find_file('R/tests/test_R_RF_diff_ignore.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Ignore successively more predictor columns
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if(rc != 0): raise Exception("R exited with non-zero return code %s" % rc)
def test_R_C_kmeans_prostate(self):
print "\nStarting prostate.csv"
rScript = h2o.find_file('R/tests/test_R_C_kmeans_prostate.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Run k-means with k = 5 on column 2 (Age)
# Loop to see if we get same centers
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if(rc != 0): raise Exception("R exited with non-zero return code %s" % rc)
def test_R_C_prostate(self):
print "\nStarting prostate.csv"
rScript = h2o.find_file('R/tests/test_R_C_prostate.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Columns start at 0
# Test columns 1-8, with 1 as response
# (Skip 0 because member ID)
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if(rc != 0): raise Exception("R exited with non-zero return code %s" % rc)
def test_R_B_benign(self):
print "\nStarting benign.csv"
rScript = h2o.find_file('R/tests/test_R_B_benign.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Columns start at 0
# Test columns 0-13, with 3 as response
# N-fold cross-validation = 5
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o', shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if(rc != 0): raise Exception("R exited with non-zero return code %s" % rc)
def test_R_C_kmeans_prostate(self):
print "\nStarting prostate.csv"
rScript = h2o.find_file('R/tests/test_R_C_kmeans_prostate.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Run k-means with k = 5 on column 2 (Age)
# Loop to see if we get same centers
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[
0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o',
shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if (rc != 0):
raise Exception("R exited with non-zero return code %s" % rc)
def test_R_C_prostate(self):
print "\nStarting prostate.csv"
rScript = h2o.find_file('R/tests/test_R_C_prostate.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Columns start at 0
# Test columns 1-8, with 1 as response
# (Skip 0 because member ID)
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[
0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o',
shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if (rc != 0):
raise Exception("R exited with non-zero return code %s" % rc)
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_B_benign(self):
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
print "\nStarting benign.csv"
csvFilename = "benign.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
# columns start at 0
y = "3"
# cols 0-13. 3 is output
# no member id in this one
for maxx in range(11,14):
x = range(maxx)
x.remove(3) # 3 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
kwargs = {'x': x, 'y': y}
# fails with n_folds
print "Not doing n_folds with benign. Fails with 'unable to solve?'"
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=15, **kwargs)
# no longer look at STR?
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
sys.stdout.write('.')
sys.stdout.flush()
def test_GLM_params_rand2_newargs(self):
# csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
csvPathname = h2o.find_file('smalldata/covtype/covtype.20k.data')
key = 'covtype.20k'
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key=key)
paramDict = define_params()
for trial in range(20):
# params is mutable. This is default.
params = {
'y': 54,
'case': 1,
'lambda': 0,
'alpha': 0,
'n_folds': 1
}
colX = h2o_glm.pickRandGlmParams(paramDict, params)
kwargs = params.copy()
start = time.time()
glm = h2o_cmd.runGLMOnly(timeoutSecs=70,
parseKey=parseKey,
**kwargs)
# pass the kwargs with all the params, so we know what we asked for!
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.check_sandbox_for_errors()
print "glm end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
print "Trial #", trial, "completed\n"
def test_C_hhp_107_01(self):
csvPathname = h2o.find_file("smalldata/hhp_107_01.data.gz")
print "\n" + csvPathname
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, timeoutSecs=15)
# pop open a browser on the cloud
h2b.browseTheCloud()
# build up the parameter string in X
y = "106"
x = ""
# go right to the big X and iterate on that case
### for trial in range(2):
for trial in range(2):
print "\nTrial #", trial, "start"
print "\nx:", x
print "y:", y
start = time.time()
kwargs = {'y': y}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey,
timeoutSecs=200,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, 57, **kwargs)
h2o.check_sandbox_for_errors()
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
print "\nTrial #", trial
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 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 inspect_columns(self,
filename,
rows=1,
cols=26,
columnNames=crange('A', 'Z'),
columnTypes=None):
cvsfile = h2o.find_file(filename)
node = h2o.nodes[0]
res = h2o_cmd.parseFile(node=node, csvPathname=cvsfile)
ary = node.inspect(res['destination_key'])
self.assertEqual(rows, ary['num_rows'])
self.assertEqual(cols, ary['num_cols'])
# check column names
if not columnNames is None:
for (col, expName) in zip(ary['cols'], columnNames):
self.assertEqual(expName, col['name'])
# check column types
if not columnTypes is None:
for (col, expType) in zip(ary['cols'], columnTypes):
self.assertEqual(expType, col['type'])
return ary
def test_many_cols_with_syn(self):
### h2b.browseTheCloud()
csvFilename = "logreg_trisum_int_cat_10000x10.csv"
csvPathname = "smalldata/logreg/" + csvFilename
key2 = csvFilename + ".hex"
parseKey = h2o_cmd.parseFile(None, h2o.find_file(csvPathname), key2=key2, timeoutSecs=10)
print csvFilename, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey['destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(None, parseKey['destination_key'])
print "\n" + csvFilename
paramDict = define_params()
paramDict2 = {}
for k in paramDict:
# sometimes we have a list to pick from in the value. now it's just list of 1.
paramDict2[k] = paramDict[k][0]
y = 10
# FIX! what should we have for case? 1 should be okay because we have 1's in output col
kwargs = {'y': y, 'max_iter': 50}
kwargs.update(paramDict2)
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=20, **kwargs)
print "glm end on ", csvPathname, 'took', time.time() - start, 'seconds'
h2o_glm.simpleCheckGLM(self, glm, 8, **kwargs)
if not h2o.browse_disable:
h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
time.sleep(5)
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 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 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_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_A_putfile(self):
cvsfile = h2o.find_file(file_to_put())
node = h2o.nodes[0]
key = node.put_file(cvsfile)
resultSize = node.inspect(key)['value_size_bytes']
origSize = h2o.get_file_size(cvsfile)
self.assertEqual(origSize,resultSize)
def test_R_B_benign(self):
print "\nStarting benign.csv"
rScript = h2o.find_file('R/tests/test_R_B_benign.R')
rLibrary = h2o.find_file('R/H2O_Load.R')
# Columns start at 0
# Test columns 0-13, with 3 as response
# N-fold cross-validation = 5
shCmdString = "R -f " + rScript + " --args " + rLibrary + " " + h2o.nodes[
0].http_addr + ":" + str(h2o.nodes[0].port)
(ps, outpath, errpath) = h2o.spawn_cmd('rtest_with_h2o',
shCmdString.split())
rc = h2o.spawn_wait(ps, outpath, errpath, timeout=10)
if (rc != 0):
raise Exception("R exited with non-zero return code %s" % rc)
def test_C_hhp_107_01(self):
csvPathname = h2o.find_file("smalldata/hhp_107_01.data.gz")
print "\n" + csvPathname
y = "106"
x = ""
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, timeoutSecs=15)
for trial in xrange(3):
sys.stdout.write('.')
sys.stdout.flush()
print "\nx:", x
print "y:", y
start = time.time()
kwargs = {'x': x, 'y': y, 'n_folds': 6}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey,
timeoutSecs=300,
**kwargs)
# pass the kwargs with all the params, so we know what we asked for!
h2o_glm.simpleCheckGLM(self, glm, 57, **kwargs)
print "glm end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
print "\nTrial #", trial
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_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"
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
key2 = csvFilename + "_" + str(trial) + ".hex"
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=key2, timeoutSecs=30)
h2o.verboseprint("Trial", trial)
start = time.time()
cmd.runRFOnly(parseKey=parseKey, trees=1000, 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 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
parseKey = h2o_cmd.parseFile(None, csvPathname)
h2o.verboseprint("Trial", trial)
h2o_cmd.runRFOnly(parseKey=parseKey,
trees=237,
depth=45,
timeoutSecs=120)
# don't change tree count yet
## trees += 10
### timeoutSecs += 2
trial += 1
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 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_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 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 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_A_putfile(self):
cvsfile = h2o.find_file(file_to_put())
node = h2o.nodes[0]
key = node.put_file(cvsfile)
resultSize = node.inspect(key)['value_size_bytes']
origSize = h2o.get_file_size(cvsfile)
self.assertEqual(origSize, resultSize)
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_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_prostate_then_prostate_long_parse(self):
print "\nput and parse of same file, but both key and key2 are the h2o defaults..always different"
for trial in range(10):
start = time.time()
key = h2o_cmd.parseFile(csvPathname=h2o.find_file("smalldata/logreg/prostate_long.csv.gz"))
print "trial #", trial, "parse end on ", "prostate_long.csv.gz", "took", time.time() - start, "seconds"
h2o.check_sandbox_for_errors()
def test_E_ParseManyCols(self):
csvPathname = h2o.find_file('smalldata/fail1_100x11000.csv.gz')
parseKey = h2o_cmd.parseFile(None, csvPathname, timeoutSecs=10)
inspect = h2o_cmd.runInspect(None,
parseKey['destination_key'],
offset=-1,
view=5)
def test_import_file(self):
timeoutSecs = 500
cAll = [
'smalldata/jira/v-3.csv',
'smalldata/jira/v-3.csv',
'smalldata/jira/v-3.csv',
'smalldata/jira/v-3.csv',
]
# pop open a browser on the cloud
# h2b.browseTheCloud()
for c in cAll:
for i in range(10):
# race between remove and import?
csvPathname = h2o.find_file('smalldata/jira/v-3.csv')
h2o.nodes[0].remove_all_keys()
importResult = h2o.nodes[0].import_files(csvPathname,
timeoutSecs=15)
h2o.verboseprint(h2o.dump_json(importResult))
files = importResult['files']
keys = importResult['keys']
fails = importResult['fails']
dels = importResult['dels']
if len(files) == 0:
raise Exception("empty files: %s after import" % files)
if len(keys) == 0:
raise Exception("empty keys: %s after import" % keys)
if len(fails) != 0:
raise Exception("non-empty fails: %s after import" % fails)
if len(dels) != 0:
raise Exception("non-empty dels: %s after import" % dels)
def testAll(self):
try:
h2o.build_cloud(node_count=2)
# we don't have the port or ip configuration here
# that util/h2o.py does? Keep this in synch with spawn_h2o there.
# also don't have --nosigar here?
(ps, stdout, stderr) = h2o.spawn_cmd('junit', [
'java',
'-Dh2o.arg.ice_root='+h2o.tmp_dir('ice.'),
'-Dh2o.arg.name=pytest-'+getpass.getuser(),
'-Dh2o.arg.ip='+h2o.get_ip_address(),
'-ea', '-jar', h2o.find_file('target/h2o.jar'),
'-mainClass', 'org.junit.runner.JUnitCore',
# The tests
'water.parser.ParserTest',
])
rc = ps.wait(None)
out = file(stdout).read()
err = file(stderr).read()
if rc is None:
ps.terminate()
raise Exception("junit timed out.\nstdout:\n%s\n\nstderr:\n%s" % (out, err))
elif rc != 0:
raise Exception("junit failed.\nstdout:\n%s\n\nstderr:\n%s" % (out, err))
finally:
h2o.tear_down_cloud()
def test_rf_big1_nopoll(self):
csvPathname = h2o.find_file("smalldata/hhp_107_01.data.gz")
print "\n" + csvPathname
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, timeoutSecs=15)
rfViewInitial = []
# dispatch multiple jobs back to back
for jobDispatch in range(1):
start = time.time()
kwargs = {}
# FIX! what model keys do these get?
rfView = h2o_cmd.runRFOnly(parseKey=parseKey, model_key="RF_model"+str(jobDispatch),\
timeoutSecs=300, noPoll=True, **kwargs)
rfViewInitial.append(rfView)
print "rf job dispatch end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
print "\njobDispatch #", jobDispatch
h2o_jobs.pollWaitJobs(pattern='GLMModel',
timeoutSecs=30,
pollTimeoutSecs=120,
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
for rfView in rfViewInitial:
print "Checking completed job, with no polling:", rfView
a = h2o.nodes[0].poll_url(rf['response'], noPoll=True)
h2o_rf.simpleCheckRFView(None, a)
def test_B_benign_w_predict(self):
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
print "\nStarting benign.csv"
csvFilename = "benign.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
# columns start at 0
y = "3"
# cols 0-13. 3 is output
# no member id in this one
for maxx in range(11,14):
x = range(maxx)
x.remove(3) # 3 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
kwargs = {'x': x, 'y': y}
# fails with n_folds
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=15, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
GLMModel = glm['GLMModel']
modelKey = GLMModel['model_key']
print "Doing predict with same dataset, and the GLM model"
h2o.nodes[0].generate_predictions(model_key=modelKey, data_key=parseKey['destination_key'])
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_C_prostate_w_predict(self):
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
print "\nStarting prostate.csv"
# columns start at 0
y = "1"
x = ""
csvFilename = "prostate.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
for maxx in range(2,6):
x = range(maxx)
x.remove(0) # 0 is member ID. not used
x.remove(1) # 1 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
kwargs = {'x': x, 'y': y, 'n_folds': 5}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=15, **kwargs)
# ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON
h2o_glm.simpleCheckGLM(self, glm, 'AGE', **kwargs)
GLMModel = glm['GLMModel']
modelKey = GLMModel['model_key']
print "Doing predict with same dataset, and the GLM model"
h2o.nodes[0].generate_predictions(model_key=modelKey, data_key=parseKey['destination_key'])
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
def test_GLM_params_rand2(self):
# csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
csvPathname = h2o.find_file('smalldata/covtype/covtype.20k.data')
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key="covtype.20k")
# 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
paramDict = define_params()
for trial in range(20):
# params is mutable. This is default.
params = {'y': 54, 'case': 1, 'alpha': 0, 'lambda': 0, 'n_folds': 1}
colX = h2o_glm.pickRandGlmParams(paramDict, params)
kwargs = params.copy()
start = time.time()
glm = h2o_cmd.runGLMOnly(timeoutSecs=70, parseKey=parseKey, **kwargs)
# pass the kwargs with all the params, so we know what we asked for!
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.check_sandbox_for_errors()
print "glm end on ", csvPathname, 'took', time.time() - start, 'seconds'
print "Trial #", trial, "completed\n"
def test_B_benign(self):
print "\nStarting benign.csv"
csvFilename = "benign.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
# columns start at 0
y = "3"
# cols 0-13. 3 is output
# no member id in this one
for maxx in range(4,14):
x = range(maxx)
x.remove(3) # 3 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
# solver can be ADMM
kwargs = {'x': x, 'y': y,\
'expert': 1, 'lsm_solver': 'GenGradient', 'standardize': 1, 'n_folds': 1}
# fails with n_folds
print "Not doing n_folds with benign. Fails with 'unable to solve?'"
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=30, **kwargs)
# no longer look at STR?
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_C_prostate(self):
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
print "\nStarting prostate.csv"
# columns start at 0
y = "1"
x = ""
csvFilename = "prostate.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
for maxx in range(2,6):
x = range(maxx)
x.remove(0) # 0 is member ID. not used
x.remove(1) # 1 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
kwargs = {'x': x, 'y': y, 'n_folds': 5}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=15, **kwargs)
# ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON
h2o_glm.simpleCheckGLM(self, glm, 'AGE', **kwargs)
sys.stdout.write('.')
sys.stdout.flush()
h2o.nodes[0].log_view()
namelist = h2o.nodes[0].log_download()
def test_C_prostate(self):
print "\nStarting prostate.csv"
# columns start at 0
y = "1"
csvFilename = "prostate.csv"
csvPathname = h2o.find_file('smalldata/logreg' + '/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex")
for maxx in range(2,9):
x = range(maxx)
x.remove(0) # 0 is member ID. not used
x.remove(1) # 1 is output
x = ",".join(map(str,x))
print "\nx:", x
print "y:", y
# solver can be ADMM. standardize normalizes the data.
kwargs = {'x': x, 'y': y, 'n_folds': 5,\
'expert': 1, 'lsm_solver': 'GenGradient', 'standardize':1}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=30, **kwargs)
# ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON
h2o_glm.simpleCheckGLM(self, glm, 'AGE', **kwargs)
h2o.check_sandbox_for_errors()
sys.stdout.write('.')
sys.stdout.flush()
def test_C_hhp_107_01(self):
csvPathname = h2o.find_file("smalldata/hhp_107_01.data.gz")
print "\n" + csvPathname
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, timeoutSecs=15)
# pop open a browser on the cloud
h2b.browseTheCloud()
# build up the parameter string in X
y = "106"
x = ""
# go right to the big X and iterate on that case
### for trial in range(2):
for trial in range(2):
print "\nTrial #", trial, "start"
print "\nx:", x
print "y:", y
start = time.time()
kwargs = {'y': y}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=200, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, 57, **kwargs)
h2o.check_sandbox_for_errors()
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
print "\nTrial #", trial
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