forked from h2oai/h2o-2
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' of github.com:0xdata/h2o
- Loading branch information
Showing
8 changed files
with
265 additions
and
23 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1 @@ | ||
| 1382158596 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,65 @@ | ||
| #!/bin/bash | ||
|
|
||
| #ssh into each of the machines from ${JSON} (passed as first argument) | ||
| MACHINES=`cat BMscripts/$1 | python -c 'import sys, json; print json.load(sys.stdin)[sys.argv[1]]' ip | awk -F, 'OFS="," {gsub("[ u\x27\[\]]","", $0); print}'` | ||
| IFS="," | ||
| MACHINES=($MACHINES) | ||
|
|
||
| function startBigLoggers { | ||
| for i in ${MACHINES[@]} | ||
| do | ||
| echo "Starting bigLogger on ${i}" | ||
| scp BMLogs/starttime spencer@$i:/home/spencer/h2o/bench/BMLogs | ||
| # ssh spencer@$i "cd /home/spencer/h2o/bench/BMLogs; bash bigLogger.sh" & | ||
| done | ||
| } | ||
|
|
||
| function startLittleLoggers { | ||
| for i in ${MACHINES[@]} | ||
| do | ||
| echo "Starting littleLogger on ${i} on phase $1" | ||
| ssh spencer@$i "cd /home/spencer/h2o/bench/BMLogs; bash littleLogger.sh $1" & | ||
| done | ||
| } | ||
|
|
||
| function stopLittleLoggers { | ||
| for i in ${MACHINES[@]} | ||
| do | ||
| ssh spencer@$i ps ax|grep bash|grep littleLogger|awk '{print $1}'| xargs kill | ||
| done | ||
| } | ||
|
|
||
| function stopAllLoggers { | ||
| for i in ${MACHINES[@]} | ||
| do | ||
| ssh spencer@$i ps ax|grep bash|grep Logger|awk '{print $1}'| xargs kill | ||
| done | ||
| } | ||
|
|
||
| function changePhase { | ||
| echo "Stopping little loggers" | ||
| stopLittleLoggers >/dev/null | ||
| newPhase=$1 | ||
| startLittleLoggers $1 >/dev/null | ||
| } | ||
|
|
||
| if [ $2 = "big" ] | ||
| then | ||
| startBigLoggers >/dev/null | ||
| fi | ||
|
|
||
| if [ $2 = "little" ] | ||
| then | ||
| startLittleLoggers START >/dev/null | ||
| fi | ||
|
|
||
| if [ $2 = "changePhase" ] | ||
| then | ||
| changePhase $3 >/dev/null | ||
| fi | ||
|
|
||
| if [ $2 = "stop_" ] | ||
| then | ||
| stopAllLoggers | ||
| fi | ||
|
|
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,67 @@ | ||
| import unittest, random, sys, time | ||
| sys.path.extend(['.','..','py']) | ||
|
|
||
| import h2o, h2o_cmd, h2o_hosts, h2o_import as h2i, h2o_exec, h2o_glm, h2o_jobs | ||
|
|
||
| class Basic(unittest.TestCase): | ||
| def tearDown(self): | ||
| h2o.check_sandbox_for_errors() | ||
|
|
||
| @classmethod | ||
| def setUpClass(cls): | ||
| global localhost | ||
| localhost = h2o.decide_if_localhost() | ||
| if (localhost): | ||
| h2o.build_cloud(node_count=1, java_heap_GB=10) | ||
| else: | ||
| h2o_hosts.build_cloud_with_hosts(node_count=1, java_heap_GB=10) | ||
|
|
||
| @classmethod | ||
| def tearDownClass(cls): | ||
| h2o.tear_down_cloud() | ||
|
|
||
| def test_GLM_prostate(self): | ||
| h2o.beta_features=True | ||
| importFolderPath = "logreg" | ||
| csvFilename = 'prostate.csv' | ||
| csvPathname = importFolderPath + "/" + csvFilename | ||
| hex_key = csvFilename + ".hex" | ||
|
|
||
| parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='local', hex_key=hex_key, | ||
| timeoutSecs=180, noPoll=True, doSummary=False) | ||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
| inspect = h2o_cmd.runInspect(None, parseResult['destination_key']) | ||
| print inspect | ||
| print "\n" + csvPathname, \ | ||
| " numRows:", "{:,}".format(inspect['numRows']), \ | ||
| " numCols:", "{:,}".format(inspect['numCols']) | ||
|
|
||
| x = 'ID' | ||
| y = 'CAPSULE' | ||
| family = 'binomial' | ||
| alpha = '0.5' | ||
| lambda_ = '1E-4' | ||
| nfolds = '5' | ||
| case_mode = '=' | ||
| case_val = '1' | ||
| f = 'prostate' | ||
|
|
||
| kwargs = { 'vresponse' : y, | ||
| 'ignored_cols' : x, | ||
| 'family' : family, | ||
| 'lambda' : lambda_, | ||
| 'alpha' : alpha, | ||
| 'n_folds' : nfolds, | ||
| #'case_mode' : case_mode, | ||
| #'case_val' : case_val, | ||
| 'destination_key' : "GLM("+f+")", | ||
| } | ||
| timeoutSecs = 60 | ||
|
|
||
| start = time.time() | ||
| glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, pollTimeoutSecs=180, noPoll=True, **kwargs) | ||
|
|
||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
|
|
||
| if __name__ == '__main__': | ||
| h2o.unit_main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,87 @@ | ||
| import unittest, time, sys | ||
| sys.path.extend(['.','..','py']) | ||
| import h2o, h2o_cmd, h2o_kmeans, h2o_hosts, h2o_import as h2i, h2o_jobs | ||
|
|
||
| class Basic(unittest.TestCase): | ||
| def tearDown(self): | ||
| h2o.check_sandbox_for_errors() | ||
|
|
||
| @classmethod | ||
| def setUpClass(cls): | ||
| global localhost | ||
| localhost = h2o.decide_if_localhost() | ||
| if (localhost): | ||
| h2o.build_cloud(1) | ||
| else: | ||
| h2o_hosts.build_cloud_with_hosts(1) | ||
|
|
||
| @classmethod | ||
| def tearDownClass(cls): | ||
| h2o.tear_down_cloud() | ||
|
|
||
| def test_B_kmeans_benign(self): | ||
| h2o.beta_features = True | ||
| csvPathname = "logreg" | ||
| csvFilename = "benign.csv" | ||
| print "\nStarting", csvFilename | ||
|
|
||
| parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname + "/"+csvFilename, schema='local', hex_key=csvFilename+".hex", noPoll=True, doSummary=False) | ||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
|
|
||
| expected = [ | ||
| ([24.538961038961038, 2.772727272727273, 46.89032467532467, 0.1266233766233766, 12.012142857142857, 1.0105194805194804, 1.5222727272727272, 22.26039690646432, 12.582467532467534, 0.5275062016635049, 2.9477601050634767, 162.52136363636365, 41.94558441558441, 1.661883116883117], 77, 46889.32010560476) , | ||
| ([25.587719298245613, 2.2719298245614037, 45.64035087719298, 0.35964912280701755, 13.026315789473685, 1.4298245614035088, 1.3070175438596492, 24.393307707470925, 13.333333333333334, 0.5244431302976542, 2.7326039818647745, 122.46491228070175, 40.973684210526315, 1.6754385964912282], 114, 64011.20272144667) , | ||
| ([30.833333333333332, 2.9166666666666665, 46.833333333333336, 0.0, 13.083333333333334, 1.4166666666666667, 1.5833333333333333, 24.298220973782772, 11.666666666666666, 0.37640449438202245, 3.404494382022472, 224.91666666666666, 39.75, 1.4166666666666667], 12, 13000.485226507595) , | ||
|
|
||
| ] | ||
| # all are multipliers of expected tuple value | ||
| allowedDelta = (0.01, 0.01, 0.01) | ||
|
|
||
| # loop, to see if we get same centers | ||
| for trial in range(2): | ||
| params = {'k' : 3, | ||
| 'initialization' : 'Furthest', | ||
| 'ignored_cols_by_name' : None, | ||
| 'destination_key' : 'benign_k.hex', | ||
| 'max_iter' : 50, | ||
| 'seed' : 265211114317615310, | ||
| } | ||
| kwargs = params.copy() | ||
| kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs) | ||
| (centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvFilename, parseResult, 'd', **kwargs) | ||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
| h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial) | ||
|
|
||
|
|
||
| def test_C_kmeans_prostate(self): | ||
| h2o.beta_features = True | ||
| csvFilename = "prostate.csv" | ||
| print "\nStarting", csvFilename | ||
| parseResult = h2i.import_parse(bucket='smalldata', path='logreg/'+csvFilename, schema='local', hex_key=csvFilename+".hex") | ||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
|
|
||
| # loop, to see if we get same centers | ||
| expected = [ | ||
| ([55.63235294117647], 68, 667.8088235294117) , | ||
| ([63.93984962406015], 133, 611.5187969924812) , | ||
| ([71.55307262569832], 179, 1474.2458100558654) , | ||
| ] | ||
|
|
||
| # all are multipliers of expected tuple value | ||
| allowedDelta = (0.01, 0.01, 0.01) | ||
| for trial in range(2): | ||
| params = {'k' : 3, | ||
| 'initialization' : 'Furthest', | ||
| 'ignored_cols_by_name' : "ID", | ||
| 'destination_key' : 'prostate_k.hex', | ||
| 'max_iter' : 100, | ||
| 'seed' : 265211114317615310 | ||
| } | ||
| kwargs = params.copy() | ||
| kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs) | ||
| (centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvFilename, parseResult, 'd', **kwargs) | ||
| h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5) | ||
| h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial) | ||
|
|
||
| if __name__ == '__main__': | ||
| h2o.unit_main() |