def test_loop_random_param_covtype(self):
csvPathname = h2o.find_file('smalldata/poisson/Goalies.csv')
print "\nParsing", csvPathname
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname)
inspect = h2o_cmd.runInspect(None, parseKey['destination_key'])
# need more info about the dataset for debug
h2o_cmd.info_from_inspect(inspect, csvPathname)
# 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)
paramDict = define_params()
print "\nUsing random seed:", SEED
for trial in range(20):
# params is mutable. This is default.
# FIX! does it never end if we don't have alpha specified?
params = {
'y': 6,
'num_cross_validation_folds': 3,
'family': "binomial",
'case_mode': ['>'],
'case': ['20'],
'alpha': 0,
'lambda': 0,
'beta_epsilon': 0.001,
'max_iter': 8
}
colX = h2o_glm.pickRandGlmParams(paramDict, params)
kwargs = params.copy()
# make timeout bigger with xvals
timeoutSecs = 120 + (kwargs['num_cross_validation_folds']*30)
# or double the 4 seconds per iteration (max_iter+1 worst case?)
timeoutSecs = max(timeoutSecs, (8 * (kwargs['max_iter']+1)))
start = time.time()
print "May not solve. Expanded categorical columns causing a large # cols, small # of rows"
glm = h2o_cmd.runGLMOnly(timeoutSecs=timeoutSecs, parseKey=parseKey, **kwargs)
elapsed = time.time()-start
print "glm end on ", csvPathname, "Trial #", trial, "completed in", elapsed, "seconds.",\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
start = time.time()
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
print "simpleCheckGLM end on ", csvPathname, 'took', time.time() - start, 'seconds'
print "Trial #", trial, "completed\n"
def test_mixed_causes_NA(self):
csvFilename = 'mixed_causes_NA.csv'
csvPathname = h2o.find_file('smalldata/' + csvFilename)
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, timeoutSecs=15)
inspect = h2o_cmd.runInspect(None, parseKey['destination_key'])
sum_num_missing_values = h2o_cmd.info_from_inspect(inspect, csvPathname)
self.assertEqual(sum_num_missing_values, 0,
"Single column of data with mixed number/string should not have NAs")
def test_rf_covtype_train_oobe(self):
if (1==0):
csvFilename = 'train.csv'
csvPathname = h2o.find_dataset('bench/covtype/h2o/' + csvFilename)
print "\nUsing header=1 even though I shouldn't have to. Otherwise I get NA in first row and RF bad\n"
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex", header=1,
timeoutSecs=180)
# FIX! maybe try specifying column header with column name
### kwargs['response_variable'] = A55
else:
csvFilename = 'covtype.data'
print "\nUsing header=0 on the normal covtype.data"
csvPathname = h2o.find_dataset('UCI/UCI-large/covtype/covtype.data')
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex", header=0,
timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseKey['destination_key'])
h2o_cmd.info_from_inspect(inspect, csvPathname)
for trial in range(1):
# params is mutable. This is default.
kwargs = paramDict
# adjust timeoutSecs with the number of trees
# seems ec2 can be really slow
timeoutSecs = 30 + kwargs['ntree'] * 20
start = time.time()
rfView = h2o_cmd.runRFOnly(parseKey=parseKey, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "RF end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
classification_error = rfView['confusion_matrix']['classification_error']
self.assertGreater(classification_error, 0.01,
"train.csv should have out of bag error estimate greater than 0.01")
print "Trial #", trial, "completed"