def exec_expr(node,
execExpr,
resultKey="Result.hex",
timeoutSecs=10,
ignoreH2oError=False):
start = time.time()
# FIX! Exec has 'escape_nan' arg now. should we test?
# 5/14/13 removed escape_nan=0
resultExec = h2o_cmd.runExecOnly(node,
expression=execExpr,
timeoutSecs=timeoutSecs,
ignoreH2oError=ignoreH2oError)
h2o.verboseprint(resultExec)
h2o.verboseprint('exec took', time.time() - start, 'seconds')
### print 'exec took', time.time() - start, 'seconds'
h2o.verboseprint("\nfirst look at the default Result key")
# new offset=-1 to get the metadata?
defaultInspectM1 = h2o_cmd.runInspect(None, "Result.hex", offset=-1)
checkScalarResult(defaultInspectM1, "Result.hex")
h2o.verboseprint("\nNow look at the assigned " + resultKey + " key")
resultInspectM1 = h2o_cmd.runInspect(None, resultKey, offset=-1)
min_value = checkScalarResult(resultInspectM1, resultKey)
return resultInspectM1, min_value
def exec_expr(node, execExpr, resultKey="Result.hex", timeoutSecs=10):
start = time.time()
# FIX! Exec has 'escape_nan' arg now. should we test?
resultExec = h2o_cmd.runExecOnly(node, expression=execExpr, timeoutSecs=timeoutSecs, escape_nan=0)
h2o.verboseprint(resultExec)
h2o.verboseprint('exec took', time.time() - start, 'seconds')
### print 'exec took', time.time() - start, 'seconds'
h2o.verboseprint("\nfirst look at the default Result key")
# new offset=-1 to get the metadata?
defaultInspectM1 = h2o_cmd.runInspect(None, "Result.hex", offset=-1)
checkScalarResult(defaultInspectM1, "Result.hex")
h2o.verboseprint("\nNow look at the assigned " + resultKey + " key")
resultInspectM1 = h2o_cmd.runInspect(None, resultKey, offset=-1)
min_value = checkScalarResult(resultInspectM1, resultKey)
return resultInspectM1, min_value
def test_loop_random_exec_covtype(self):
lenNodes = len(h2o.nodes)
csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
key2 = 'c.hex'
parseKey = h2o_cmd.parseFile(None, csvPathname, 'covtype.data', key2,
10)
print "\nParse key is:", parseKey['destination_key']
h2b.browseTheCloud()
# for trial in range(53):
trial = 0
while (trial < 100):
for exprTemplate in exprList:
trial = trial + 1
n = trial
colX = random.randint(1, 54)
row = random.randint(1, 400000)
execExpr = exprTemplate
execExpr = re.sub('<col1>', str(colX), execExpr)
execExpr = re.sub('<col2>', str(colX + 1), execExpr)
execExpr = re.sub('<n>', str(n), execExpr)
execExpr = re.sub('<row>', str(row), execExpr)
execExpr = re.sub('<keyX>', str(key2), execExpr)
# pick a random node to execute it on
randNode = random.randint(0, lenNodes - 1)
print "\nexecExpr:", execExpr, "on node", randNode
start = time.time()
resultExec = h2o_cmd.runExecOnly(node=h2o.nodes[randNode],
expression=execExpr,
timeoutSecs=15)
h2o.verboseprint(h2o.dump_json(resultExec))
# print(h2o.dump_json(resultExec))
# FIX! race conditions. If json is done, does that mean you can inspect it??
# wait until the 2nd iteration, which will guarantee both Result1 and Result2 exist
if trial > 1:
inspectMe = random.choice(inspectList)
resultInspect = h2o.nodes[0].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
resultInspect = h2o.nodes[1].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
resultInspect = h2o.nodes[2].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
# FIX! if we race the browser doing the exec too..it shouldn't be a problem?
# might be a bug?
# WARNING! we can't browse the Exec url history, since that will
# cause the Exec to execute again thru the browser..i.e. it has side effects
# just look at the last inspect, which should be the resultInspect!
# h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
h2b.browseJsonHistoryAsUrlLastMatch("Exec")
# url = "http://192.168.0.37:54321/Exec?Expr=Result3+%3D+c.hex%5B26%5D+%2B+Result1&Key=Result"
# webbrowser.open_new_tab(url)
# FIX! I suppose we have the problem of stdout/stderr not having flushed?
# should hook in some way of flushing the remote node stdout/stderr
h2o.check_sandbox_for_errors()
print "exec end on ", "covtype.data", 'took', time.time(
) - start, 'seconds'
print "Trial #", trial, "completed\n"
def test_rf_covtype20x(self):
importFolderPath = '/home/0xdiag/datasets/standard'
importFolderResult = h2i.setupImportFolder(None, importFolderPath)
csvFilenameTrain = 'covtype20x.data'
key2 = 'covtype20x.data.A.hex'
parseKeyTrain = h2i.parseImportFolderFile(None, csvFilenameTrain, importFolderPath, key2=key2, timeoutSecs=500)
print csvFilenameTrain, 'parse time:', parseKeyTrain['response']['time']
inspect = h2o_cmd.runInspect(key=parseKeyTrain['destination_key'])
dataKeyTrain = parseKeyTrain['destination_key']
print "Parse end", dataKeyTrain
# have to re import since source key is gone
# we could just copy the key, but sometimes we change the test/train data to covtype.data
importFolderResult = h2i.setupImportFolder(None, importFolderPath)
csvFilenameTest = 'covtype20x.data'
key2 = 'covtype20x.data.B.hex'
parseKeyTest = h2i.parseImportFolderFile(None, csvFilenameTest, importFolderPath, key2=key2, timeoutSecs=500)
print csvFilenameTest, 'parse time:', parseKeyTest['response']['time']
print "Parse result['destination_key']:", parseKeyTest['destination_key']
inspect = h2o_cmd.runInspect(key=parseKeyTest['destination_key'])
dataKeyTest = parseKeyTest['destination_key']
dataKeyTest2 = 'covtype20x.data.C.hex'
print "Parse end", dataKeyTest
# make a 3rd key so the predict is uncached too!
execExpr = dataKeyTest2 + "=" + dataKeyTest
resultExec = h2o_cmd.runExecOnly(expression=execExpr, timeoutSecs=15)
# train
# this does RFView to understand when RF completes, so the time reported for RFView here, should be
# considered the "first RFView" times..subsequent have some caching?.
# unless the no_confusion_matrix works
# params is mutable. This is default.
print "RF with no_confusion_matrix=1, so we can 'time' the RFView separately after job completion?"
params = {
'ntree': 6,
'parallel': 1,
'out_of_bag_error_estimate': 0,
'no_confusion_matrix': 1,
'model_key': 'RF_model'
}
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'] * 60 * (kwargs['parallel'] and 1 or 5)
start = time.time()
rfv = h2o_cmd.runRFOnly(parseKey=parseKeyTrain,
timeoutSecs=timeoutSecs, retryDelaySecs=1, noPoll=True, **kwargs)
print "rf job dispatch end on ", dataKeyTrain, 'took', time.time() - start, 'seconds'
### print "rf response:", h2o.dump_json(rfv)
start = time.time()
h2o_jobs.pollWaitJobs(pattern='RF_model', timeoutSecs=180, pollTimeoutSecs=500, retryDelaySecs=5)
print "rf job end on ", dataKeyTrain, 'took', time.time() - start, 'seconds'
print "\nRFView start after job completion"
model_key = kwargs['model_key']
ntree = kwargs['ntree']
start = time.time()
h2o_cmd.runRFView(None, dataKeyTrain, model_key, ntree, timeoutSecs)
print "First rfview end on ", dataKeyTrain, 'took', time.time() - start, 'seconds'
for trial in range(3):
# scoring
start = time.time()
h2o_cmd.runRFView(None, dataKeyTest, model_key, ntree, timeoutSecs, out_of_bag_error_estimate=0, retryDelaySecs=1)
print "rfview", trial, "end on ", dataKeyTest, 'took', time.time() - start, 'seconds.'
start = time.time()
predict = h2o.nodes[0].generate_predictions(model_key=model_key, data_key=dataKeyTest2)
print "predict", trial, "end on ", dataKeyTest, 'took', time.time() - start, 'seconds.'
print "Trial #", trial, "completed"
def test_loop_random_exec_covtype(self):
lenNodes = len(h2o.nodes)
csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
key2 = 'c.hex'
parseKey = h2o_cmd.parseFile(None, csvPathname, 'covtype.data', key2, 10)
print "\nParse key is:", parseKey['destination_key']
h2b.browseTheCloud()
# for trial in range(53):
trial = 0
while (trial < 100):
for exprTemplate in exprList:
trial = trial + 1
n = trial
colX = random.randint(1,54)
row = random.randint(1,400000)
execExpr = exprTemplate
execExpr = re.sub('<col1>',str(colX),execExpr)
execExpr = re.sub('<col2>',str(colX+1),execExpr)
execExpr = re.sub('<n>',str(n),execExpr)
execExpr = re.sub('<row>',str(row),execExpr)
execExpr = re.sub('<keyX>',str(key2),execExpr)
# pick a random node to execute it on
randNode = random.randint(0,lenNodes-1)
print "\nexecExpr:", execExpr, "on node", randNode
start = time.time()
resultExec = h2o_cmd.runExecOnly(node=h2o.nodes[randNode],
expression=execExpr, timeoutSecs=15)
h2o.verboseprint(h2o.dump_json(resultExec))
# print(h2o.dump_json(resultExec))
# FIX! race conditions. If json is done, does that mean you can inspect it??
# wait until the 2nd iteration, which will guarantee both Result1 and Result2 exist
if trial > 1:
inspectMe = random.choice(inspectList)
resultInspect = h2o.nodes[0].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
resultInspect = h2o.nodes[1].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
resultInspect = h2o.nodes[2].inspect(inspectMe)
h2o.verboseprint(h2o.dump_json(resultInspect))
# FIX! if we race the browser doing the exec too..it shouldn't be a problem?
# might be a bug?
# WARNING! we can't browse the Exec url history, since that will
# cause the Exec to execute again thru the browser..i.e. it has side effects
# just look at the last inspect, which should be the resultInspect!
# h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
h2b.browseJsonHistoryAsUrlLastMatch("Exec")
# url = "http://192.168.0.37:54321/Exec?Expr=Result3+%3D+c.hex%5B26%5D+%2B+Result1&Key=Result"
# webbrowser.open_new_tab(url)
# FIX! I suppose we have the problem of stdout/stderr not having flushed?
# should hook in some way of flushing the remote node stdout/stderr
h2o.check_sandbox_for_errors()
print "exec end on ", "covtype.data" , 'took', time.time() - start, 'seconds'
print "Trial #", trial, "completed\n"
