Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
def test_cs_training(self):
parseResult = h2i.import_parse(bucket='smalldata', path='kaggle/creditsample-training.csv.gz', schema='put', timeoutSecs=120)
h2o_cmd.runRF(parseResult=parseResult, ntrees=5, max_depth=100, timeoutSecs=500,
response='SeriousDlqin2yrs')
# h2b.browseJsonHistoryAsUrlLastMatch("RFView")
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)
if __name__ == '__main__':
h2o.unit_main()
csvPathname = 'airlines/year2013.csv'
hexKey = 'i.hex'
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='put', hex_key=hexKey)
for resultKey, execExpr in initList:
h2e.exec_expr(h2o.nodes[0], execExpr, resultKey=None, timeoutSecs=10)
start = time.time()
# h2e.exec_expr_list_rand(len(h2o.nodes), exprList, 'r1.hex', maxTrials=200, timeoutSecs=10)
h2e.exec_expr_list_rand(len(h2o.nodes), exprList, None, maxTrials=200, timeoutSecs=30, allowEmptyResult=True, nanOkay=True)
h2o.check_sandbox_for_errors()
print "exec end on ", "operators" , 'took', time.time() - start, 'seconds'
if __name__ == '__main__':
h2o.unit_main()
if not h2o.beta_features:
print csvFilename, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult['destination_key']
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
if not h2o.beta_features:
RFview = h2o_cmd.runRF(trees=1,depth=25,parseResult=parseResult, timeoutSecs=timeoutSecs)
## h2b.browseJsonHistoryAsUrlLastMatch("RFView")
## time.sleep(10)
# just to make sure we test this
h2i.delete_keys_at_all_nodes(pattern=hex_key)
if __name__ == '__main__':
h2o.unit_main()
cm = predictCMResult['cm']
print h2o_gbm.pp_cm(cm)
actualErr = h2o_gbm.pp_cm_summary(cm)/100.;
print "actual classification error:" + format(actualErr)
print "expected classification error:" + format(expectedErr)
if actualErr != expectedErr and abs((expectedErr - actualErr)/expectedErr) > relTol:
raise Exception("Scored classification error of %s is not within %s %% relative error of %s" %
(actualErr, float(relTol)*100, expectedErr))
h2o.beta_features = False
if __name__ == '__main__':
h2o.unit_main()
elapsed = time.time() - start
print "RFView in", elapsed, "secs", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
(classification_error, classErrorPctList, totalScores) = h2o_rf.simpleCheckRFView(None, rfView, **params)
self.assertAlmostEqual(classification_error, 0.03, delta=0.5, msg="Classification error %s differs too much" % classification_error)
# Predict (on test)****************************************
start = time.time()
predict = h2o.nodes[0].generate_predictions(model_key=modelKey, data_key=testKey2, timeoutSecs=timeoutSecs)
elapsed = time.time() - start
print "generate_predictions in", elapsed, "secs", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
if __name__ == '__main__':
h2o.unit_main()
plt.ylabel('Jstack completion latency (millisecs)')
plt.title(label)
plt.draw()
plt.figure()
plt.plot (xList, sList)
plt.xlabel('trial')
plt.ylabel('node['+str(NODE)+'] Jstack response string length')
plt.title(label)
plt.draw()
plt.show()
if __name__ == '__main__':
h2o.unit_main()
predict=predictKey,
vpredict='predict',
)
cm = predictCMResult['cm']
# These will move into the h2o_gbm.py
pctWrong = h2o_gbm.pp_cm_summary(cm);
self.assertLess(pctWrong, 9,"Should see less than 9% error (class = 4)")
print "\nTest\n==========\n"
print h2o_gbm.pp_cm(cm)
if __name__ == '__main__':
h2o.unit_main()
# Predict (on test)****************************************
start = time.time()
predict = h2o.nodes[0].generate_predictions(model_key=modelKey, data_key=testKey2, timeoutSecs=timeoutSecs)
elapsed = time.time() - start
print "generate_predictions in", elapsed, "secs", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
# Done *******************************************************
print "\nShowing the results again from all the trials, to see variance"
for d in allDelta:
print d
if __name__ == '__main__':
h2o.unit_main()
# fails
execExpr="A.hex=c(0,1)"
# execExpr="A.hex=0;"
h2e.exec_expr(execExpr=execExpr, timeoutSecs=20)
h2o_cmd.runInspect(key='A.hex')
print "\nTrying StoreView after the exec "
h2o_cmd.runStoreView(timeoutSecs=30, view=10000)
# for node in h2o.nodes:
# h2o_cmd.runStoreView(node=node, timeoutSecs=30, view=10000)
print "Trial #", trial, "completed in", time.time() - trialStart, "seconds."
trial += 1
if __name__ == '__main__':
h2o.unit_main()
# 'hex.rf.RFRunner',
# ])
#
# 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))
if __name__ == '__main__':
h2o.unit_main()