def test_kmeans_benign(self):
h2o.beta_features = True
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
# FIX! hex_key isn't working with Parse2 ? parseResult['destination_key'] not right?
print "\nStarting", csvFilename
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
hex_key=hex_key,
header=1,
timeoutSecs=180,
doSummary=False)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
expected = [
([
8.86, 2.43, 35.53, 0.31, 13.22, 1.47, 1.33, 20.06, 13.08, 0.53,
2.12, 128.61, 35.33, 1.57
], 49, None),
([
33.47, 2.29, 50.92, 0.34, 12.82, 1.33, 1.36, 21.43, 13.30,
0.37, 2.52, 125.40, 43.91, 1.79
], 87, None),
([
27.64, 2.87, 48.11, 0.09, 11.80, 0.98, 1.51, 21.02, 12.53,
0.58, 2.89, 171.27, 42.73, 1.53
], 55, None),
([
26.00, 2.67, 46.67, 0.00, 13.00, 1.33, 1.67, 21.56, 11.44,
0.22, 2.89, 234.56, 39.22, 1.56
], 9, None),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01, 0.01)
# loop, to see if we get same centers
for trial in range(1):
kmeansSeed = random.randint(0, sys.maxint)
# kmeansSeed = 6655548259421773879
kwargs = {
'k': 4,
'initialization': 'PlusPlus',
'destination_key': 'benign_k.hex',
# 'seed': 265211114317615310,
'max_iter': 50,
'seed': kmeansSeed,
}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=5,
**kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def kmeans_doit(self, csvFilename, bucket, csvPathname, num_rows, timeoutSecs=30):
print "\nStarting KMeans of", csvFilename
parseResult = h2i.import_parse(
bucket=bucket, path=csvPathname, schema="put", hex_key=csvFilename + ".hex", timeoutSecs=10
)
# hastie has two values, 1 and -1.
# we could not specify cols, but this is more fun
kwargs = {
"k": 1,
"initialization": "Furthest",
"destination_key": "KMeansModel.hex",
"max_iter": 25,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
"seed": 265211114317615310,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(
parseResult=parseResult, timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs
)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, "took", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100
)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, "d", **kwargs)
expected = [
(
[
-0.0006628900000000158,
-0.0004671200060434639,
0.0009330300069879741,
0.0007883800000000272,
0.0007548200000000111,
0.0005617899864856153,
0.0013246499999999897,
0.0004036299999999859,
-0.0014307100000000314,
0.0021324000161308796,
0.00154,
],
num_rows,
None,
)
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=0)
# compare this kmeans to the first one. since the files are replications, the results
# should be similar?
inspect = h2o_cmd.runInspect(None, key=kmeans["destination_key"])
KMeansModel = inspect["KMeansModel"]
clusters = KMeansModel["centers"][0]
print "clusters:", h2o.dump_json(clusters)
if self.clusters1:
h2o_kmeans.compareToFirstKMeans(self, clusters, self.clusters1)
else:
self.clusters1 = copy.deepcopy(clusters)
def test_KMeans_constant_col_fvec(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100, 11, 'cA', 10),
(100, 10, 'cB', 10),
(100, 9, 'cC', 10),
(100, 8, 'cD', 10),
(100, 7, 'cE', 10),
(100, 6, 'cF', 10),
(100, 5, 'cG', 10),
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
cnum = 0
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
print "Generate synthetic dataset with first column constant = 0 and see what KMeans does"
cnum += 1
csvFilename = 'syn_' + str(SEED) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEED)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=csvFilename + ".hex")
print "Parse result['destination_key']:", parseResult['destination_key']
kwargs = {'k': 2, 'initialization': 'Furthest', 'destination_key': 'benign_k.hex', 'max_iter': 25}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# check center list (first center) has same number of cols as source data
self.assertEqual(colCount, len(centers[0]),
"kmeans first center doesn't have same # of values as dataset row %s %s" % (colCount, len(centers[0])))
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' : 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_KMeans_covtype_cols_fvec(self):
h2o.beta_features = True
# just do the import folder once
# make the timeout variable per dataset. it can be 10 secs for covtype 20x (col key creation)
# so probably 10x that for covtype200
csvFilenameList = [
("covtype.binary.svm", "cC", 30, 1),
# normal csv
]
### csvFilenameList = random.sample(csvFilenameAll,1)
# h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
firstDone = False
importFolderPath = "libsvm"
for (csvFilename, hex_key, timeoutSecs, resultMult) in csvFilenameList:
# have to import each time, because h2o deletes source after parse
csvPathname = importFolderPath + "/" + csvFilename
# PARSE******************************************
# creates csvFilename.hex from file in importFolder dir
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname,
hex_key=hex_key, timeoutSecs=2000)
print "Parse result['destination_key']:", parseResult['destination_key']
# INSPECT******************************************
start = time.time()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'], timeoutSecs=360)
print "Inspect:", parseResult['destination_key'], "took", time.time() - start, "seconds"
h2o_cmd.infoFromInspect(inspect, csvFilename)
numRows = inspect['numRows']
numCols = inspect['numCols']
# KMEANS******************************************
for trial in range(1):
kwargs = {
'k': 3,
'initialization': 'Furthest',
'ignored_cols': range(11, numCols),
'max_iter': 10,
# 'normalize': 0,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
# fails if I put this in kwargs..i.e. source = dest
# 'destination_key': parseResult['destination_key'],
for trial2 in range(3):
timeoutSecs = 600
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# this does an inspect of the model and prints the clusters
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_KMeans2_enum(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100, 11, 'cA', 5),
(100, 10, 'cB', 5),
(100, 9, 'cC', 5),
(100, 8, 'cD', 5),
(100, 7, 'cE', 5),
(100, 6, 'cF', 5),
(100, 5, 'cG', 5),
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
cnum = 0
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
cnum += 1
csvFilename = 'syn_' + str(SEED) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEED)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=csvFilename + ".hex")
print "Parse result['destination_key']:", parseResult['destination_key']
kwargs = {
'k': 2,
'initialization': 'Furthest',
'destination_key': 'benign_k.hex',
'max_iter': 10,
}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_KMeans_constant_col_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100, 11, 'cA', 5),
(100, 10, 'cB', 5),
(100, 9, 'cC', 5),
(100, 8, 'cD', 5),
(100, 7, 'cE', 5),
(100, 6, 'cF', 5),
(100, 5, 'cG', 5),
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
cnum = 0
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
print "Generate synthetic dataset with first column constant = 0 and see what KMeans does"
cnum += 1
csvFilename = 'syn_' + str(SEED) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEED)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=csvFilename + ".hex")
print "Parse result['destination_key']:", parseResult['destination_key']
kwargs = {'k': 2, 'initialization': 'Furthest', 'destination_key': 'benign_k.hex', 'max_iter': 25}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# check center list (first center) has same number of cols as source data
self.assertEqual(colCount, len(centers[0]),
"kmeans first center doesn't have same # of values as dataset row %s %s" % (colCount, len(centers[0])))
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': "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)
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")
# loop, to see if we get same centers
# this was sklearn.cluster.Kmeans with first col removed. num_rows and error is 0 here
expected = [
([0.36, 66.44, 1.09, 2.21, 1.06, 10.84, 34.16, 6.31], 136, 46045),
([0.37, 65.77, 1.07, 2.23, 1.11, 10.49, 4.24, 6.31], 215, 36956),
([0.83, 66.17, 1.21, 2.86, 1.34, 73.30, 15.57, 7.31], 29, 33412),
]
# all are multipliers of expected tuple value
allowedDelta = (0.1, 0.1, 0.1)
# try saving best!
bestError = None
for trial in range(10):
seed = random.randint(0, sys.maxint)
seed = 7509839924844349324
if h2o.beta_features:
params = {'k': 3,
# 'initialization': 'Furthest',
'initialization': 'PlusPlus',
'ignored_cols': "ID",
'destination_key': 'prostate_k.hex',
'max_iter': 1000,
'seed': seed
}
else:
params = {'k': 3,
# 'initialization': 'Furthest',
'initialization': 'PlusPlus',
'cols': 'CAPSULE, AGE, RACE, DPROS, DCAPS, PSA, VOL, GLEASON',
'destination_key': 'prostate_k.hex',
'max_iter': 100,
'seed': seed
}
kwargs = params.copy()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvFilename, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
error = kmeans['model']['error']
if not bestError or error < bestError:
print 'Found smaller error:', error
bestError = error
bestCenters = centers
bestSeed = seed
bestTrial = trial
print "bestTrial:", bestTrial
print "bestError:", bestError
print "bestCenters:", bestCenters
print "bestSeed:", bestSeed
def test_libsvm(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
for trial in range(2):
csvFilename = "syn_ints.csv"
hex_key = "1.hex"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
write_syn_dataset(csvPathname, trial)
timeoutSecs = 10
# have to import each time, because h2o deletes source after parse
# PARSE******************************************
# creates csvFilename.hex from file in importFolder dir
# parseResult = h2i.import_parse(path=csvPathname, parser_type='SVMLight', hex_key=hex_key, timeoutSecs=2000)
parseResult = h2i.import_parse(parser_type=PARSER_TYPE,
path=csvPathname,
hex_key=hex_key,
timeoutSecs=2000)
# INSPECT******************************************
start = time.time()
inspect = h2o_cmd.runInspect(key=hex_key, timeoutSecs=360)
print "Inspect:", hex_key, "took", time.time() - start, "seconds"
h2o_cmd.infoFromInspect(inspect, csvFilename)
numRows = inspect['numRows']
numCols = inspect['numCols']
summaryResult = h2o_cmd.runSummary(key=hex_key)
h2o_cmd.infoFromSummary(summaryResult)
if DO_KMEANS:
# KMEANS******************************************
kwargs = {
'k': 3,
'initialization': 'Furthest',
'ignored_cols':
None, #range(11, numCols), # THIS BREAKS THE REST API
'max_iter': 10,
# 'normalize': 0,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
# fails if I put this in kwargs..i.e. source = dest
# 'destination_key': parseResult['destination_key'],
timeoutSecs = 600
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# this does an inspect of the model and prints the clusters
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_KMeans2_winesPCA(self):
h2o.beta_features = True
csvPathname = 'winesPCA.csv'
start = time.time()
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put', timeoutSecs=10)
print "parse end on ", csvPathname, 'took', time.time() - start, 'seconds'
h2o.check_sandbox_for_errors()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
kwargs = {
'initialization': 'Furthest',
# 'initialization': '',
# 'initialization': 'PlusPlus',
'max_iter': 50,
'k': 3,
'seed': '265211114317615310',
}
timeoutSecs = 480
# try the same thing 5 times
for trial in range (10):
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans #", trial, "end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = \
h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# tupleResultList has tuples = center, rows_per_cluster, sqr_error_per_cluster
# now compare expected vs actual. By sorting on center, we should be able to compare
# since the centers should be separated enough to have the order be consistent
if OLD_KMEANS:
expected = [
([-2.25977535371875, -0.8631572635625001], 64, 83.77800617624794),
([0.16232721958461543, 1.7626161107230771], 65, 111.64440134649745),
([2.7362112930204074, -1.2107751495102044], 49, 62.6290553489474),
]
else:
# error: 258.051462872
expected = [
([-2.23406681758209, -0.7729819755373136], 67, 96.85372611195429),
([0.25174392601612905, 1.792222172419355], 62, 99.21823733913352),
([2.7362112930204074, -1.2107751495102044], 49, 62.6290553489474),
]
# multipliers on the expected values for allowed
# within 2% of best with random seeds?
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial)
def test_kmeans_prostate(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket="smalldata", path=csvPathname, hex_key=hex_key, header=1, timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseResult["destination_key"])
print "\nStarting", csvFilename
# loop, to see if we get same centers
expected = [
([0.37, 65.77, 1.07, 2.23, 1.11, 10.49, 4.24, 6.31], 215, 36955),
([0.36, 66.44, 1.09, 2.21, 1.06, 10.84, 34.16, 6.31], 136, 46045),
([0.83, 66.17, 1.21, 2.86, 1.34, 73.30, 15.57, 7.31], 29, 33412),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
for trial in range(1):
# kmeansSeed = random.randint(0, sys.maxint)
# actually can get a slightly better error sum with a different seed
# this seed gets the same result as scikit
kmeansSeed = 6655548259421773879
kwargs = {
"ignored_cols": "ID",
"k": 3,
# 'initialization': 'Furthest',
"initialization": "PlusPlus",
"destination_key": "prostate_k.hex",
"max_iter": 500,
"seed": kmeansSeed,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
# 'seed': 265211114317615310}
}
# for fvec only?
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
# FIX! how do I get the kmeans result?
### print "kmeans result:", h2o.dump_json(kmeans)
# can't do this
# inspect = h2o_cmd.runInspect(key='prostate_k.hex')
modelView = h2o.nodes[0].kmeans_view(model="prostate_k.hex")
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView["model"]
clusters = model["centers"]
within_cluster_variances = model["within_cluster_variances"]
total_within_SS = model["total_within_SS"]
print "within_cluster_variances:", within_cluster_variances
print "total_within_SS:", total_within_SS
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, "d", **kwargs
)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
def test_kmeans_sphere5(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
CLUSTERS = 5
SPHERE_PTS = 10000
csvFilename = 'syn_spheres100.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
centersList = write_spheres_dataset(csvPathname, CLUSTERS, SPHERE_PTS)
print "\nStarting", csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=csvFilename + ".hex")
# try 5 times, to see if all inits by h2o are good
for trial in range(5):
# pass SEED so it's repeatable
kwargs = {
'k': CLUSTERS,
'max_iter': 10,
'initialization': 'Furthest',
'cols': None,
'destination_key': 'syn_spheres100.hex',
'seed': SEED
}
timeoutSecs = 30
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.',\
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
kmeansResult = h2o_cmd.runInspect(key='syn_spheres100.hex')
### print h2o.dump_json(kmeans)
### print h2o.dump_json(kmeansResult)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
# cluster centers can return in any order
clusters = kmeansResult['KMeansModel']['clusters']
clustersSorted = sorted(clusters, key=itemgetter(0))
### print clustersSorted
print "\nh2o result, centers sorted"
print clustersSorted
print "\ngenerated centers"
print centersList
for i,center in enumerate(centersList):
a = center
b = clustersSorted[i]
print "\nexpected:", a
print "h2o:", b # h2o result
aStr = ",".join(map(str,a))
bStr = ",".join(map(str,b))
iStr = str(i)
self.assertAlmostEqual(a[0], b[0], delta=1, msg=aStr+"!="+bStr+". Sorted cluster center "+iStr+" x not correct.")
self.assertAlmostEqual(a[1], b[1], delta=1, msg=aStr+"!="+bStr+". Sorted cluster center "+iStr+" y not correct.")
self.assertAlmostEqual(a[2], b[2], delta=1, msg=aStr+"!="+bStr+". Sorted cluster center "+iStr+" z not correct.")
print "Trial #", trial, "completed"
def test_kmeans_benign(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
# FIX! hex_key isn't working with Parse2 ? parseResult['destination_key'] not right?
print "\nStarting", csvFilename
parseResult = h2i.import_parse(
bucket="smalldata", path=csvPathname, hex_key=hex_key, header=1, timeoutSecs=180, doSummary=False
)
inspect = h2o_cmd.runInspect(None, parseResult["destination_key"])
print "\nStarting", csvFilename
expected = [
([8.86, 2.43, 35.53, 0.31, 13.22, 1.47, 1.33, 20.06, 13.08, 0.53, 2.12, 128.61, 35.33, 1.57], 49, None),
([33.47, 2.29, 50.92, 0.34, 12.82, 1.33, 1.36, 21.43, 13.30, 0.37, 2.52, 125.40, 43.91, 1.79], 87, None),
([27.64, 2.87, 48.11, 0.09, 11.80, 0.98, 1.51, 21.02, 12.53, 0.58, 2.89, 171.27, 42.73, 1.53], 55, None),
([26.00, 2.67, 46.67, 0.00, 13.00, 1.33, 1.67, 21.56, 11.44, 0.22, 2.89, 234.56, 39.22, 1.56], 9, None),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01, 0.01)
# loop, to see if we get same centers
for trial in range(1):
kmeansSeed = random.randint(0, sys.maxint)
# kmeansSeed = 6655548259421773879
kwargs = {
"k": 4,
"initialization": "PlusPlus",
"destination_key": "benign_k.hex",
# 'seed': 265211114317615310,
"max_iter": 50,
"seed": kmeansSeed,
}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
## h2o.verboseprint("kmeans result:", h2o.dump_json(kmeans))
modelView = h2o.nodes[0].kmeans_view(model="benign_k.hex")
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView["model"]
clusters = model["centers"]
within_cluster_variances = model["within_cluster_variances"]
total_within_SS = model["total_within_SS"]
print "within_cluster_variances:", within_cluster_variances
print "total_within_SS:", total_within_SS
# make this fvec legal?
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, "d", **kwargs
)
def test_KMeans_twit_fvec(self):
h2o.beta_features = True
csvFilename = "Twitter2DB.txt"
print "\nStarting", csvFilename
# h2b.browseTheCloud()
parseResult = h2i.import_parse(bucket='smalldata',
path=csvFilename,
hex_key=csvFilename + ".hex",
schema='put')
# both of these centers match what different R/Scikit packages get
expected1 = [
# expected centers are from R. rest is just from h2o
([310527.2, 13433.89], 11340, None),
([5647967.1, 40487.76], 550, None),
([21765291.7, 93129.26], 14, None),
]
# this is what we get with Furthest
expected2 = [
([351104.74065255735,
15421.749823633158], 11340, 5021682274541967.0),
([7292636.589090909, 7575.630909090909], 550, 6373072701775582.0),
([34406781.071428575, 244878.0], 14, 123310713697348.92),
]
# all are multipliers of expected tuple value
allowedDelta = (0.0001, 0.0001, 0.0001)
for trial in range(2):
kwargs = {
'k': 3,
'max_iter': 50,
'normalize': 0,
'initialization': 'Furthest',
# 'initialization': 'PlusPlus',
'destination_key': 'kmeans_dest_key',
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310
}
init_choices = ['Furthest', 'PlusPlus']
kwargs['initialization'] = init_choices[trial % len(init_choices)]
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=5,
**kwargs)
# can't inspect a kmeans2 model?
# inspect = h2o_cmd.runInspect(None, key=kmeans['model']['_key'], verbose=True)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvFilename, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected2,
allowedDelta,
trial=trial)
def test_B_kmeans_benign(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
# FIX! hex_key isn't working with Parse2 ? parseResult['destination_key'] not right?
print "\nStarting", csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, header=1,
timeoutSecs=180, noPoll=not DO_POLL, doSummary=False)
if not DO_POLL:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
parseResult['destination_key'] = hex_key
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
expected = [
([10.5, 2.8, 40.3, 0.0, 12.0, 0.8, 1.6, 21.1, 11.4, 0.7, 2.9, 206.2, 36.7, 1.5], 15, 0) ,
([23.72897196261682, 2.3271028037383177, 44.81308411214953, 0.34579439252336447, 13.093457943925234, 1.4579439252336448, 1.3177570093457944, 24.16129367150993, 13.317757009345794, 0.5071931108136043, 2.6604011393039024, 121.6822429906542, 40.13084112149533, 1.691588785046729], 110, 0) ,
([29.2625, 2.7, 48.5125, 0.1625, 12.0625, 1.0375, 1.4875, 23.023665714263917, 12.6875, 0.5073033705353737, 3.090870788693428, 160.95, 43.3, 1.65], 71, 0) ,
([38.333333333333336, 2.3333333333333335, 52.666666666666664, 0.0, 14.333333333333334, 2.3333333333333335, 1.6666666666666667, 25.85955047607422, 12.0, 0.5056179761886597, 3.2846442063649497, 261.6666666666667, 43.0, 1.0], 4, 0) ,
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01, 0.01)
# loop, to see if we get same centers
if DO_IGNORE:
kwargs = {'k': 4, 'ignored_cols': 'STR', 'destination_key': 'benign_k.hex', 'seed': 265211114317615310, 'max_iter': 50}
else:
kwargs = {'k': 4, 'ignored_cols': None, 'destination_key': 'benign_k.hex', 'seed': 265211114317615310, 'max_iter': 50}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, noPoll=not DO_POLL, **kwargs)
if not DO_POLL:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
# hack..supposed to be there like va
kmeans['destination_key'] = 'benign_k.hex'
## h2o.verboseprint("kmeans result:", h2o.dump_json(kmeans))
modelView = h2o.nodes[0].kmeans_model_view(model='benign_k.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['clusters']
cluster_variances = model['cluster_variances']
error = model['error']
print "cluster_variances:", cluster_variances
print "error:", error
# make this fvec legal?
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=0)
def test_KMeans_winesPCA(self):
csvPathname = 'winesPCA.csv'
start = time.time()
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
schema='put',
timeoutSecs=10)
print "parse end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
h2o.check_sandbox_for_errors()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" num_rows:", "{:,}".format(inspect['num_rows']), \
" num_cols:", "{:,}".format(inspect['num_cols'])
kwargs = {
#appears not to take 'cols'?
'cols': None,
'initialization': 'Furthest',
'k': 3,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
timeoutSecs = 480
# try the same thing 5 times
for trial in range(10):
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans #", trial, "end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = \
h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# tupleResultList has tuples = center, rows_per_cluster, sqr_error_per_cluster
# now compare expected vs actual. By sorting on center, we should be able to compare
# since the centers should be separated enough to have the order be consistent
expected = [
([-2.25977535371875,
-0.8631572635625001], 64, 83.77800617624794),
([0.16232721958461543,
1.7626161107230771], 65, 111.64440134649745),
([2.7362112930204074,
-1.2107751495102044], 49, 62.6290553489474),
]
# multipliers on the expected values for allowed
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList,
expected, allowedDelta, trial)
def test_KMeansGrid_basic_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path='standard/covtype.data',
schema='local',
timeoutSecs=2000,
pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "python_source:", parseResult['python_source']
csvPathname = parseResult['python_source']
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
destination_key = 'd.hex'
params = {
'k': '2,3',
# 'initialization': 'Furthest',
'initialization': None,
'seed': 3923021996079663354,
'normalize': 0,
'max_iter': '2',
'destination_key': destination_key
}
for trial in range(3):
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans (with grid) end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
print "FIX! have to interrogate each job result to see kmeans grid results"
### h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
# This doesn't work (inspecting the model)
# inspect = h2o_cmd.runInspect(None,key=destination_key)
# print h2o.dump_json(inspect)
print "Trial #", trial, "completed\n"
def test_KMeansGrid_params_rand2_fvec(self):
if h2o.localhost:
csvFilenameList = [
# ('covtype.data', 60),
("covtype.data", 800)
]
else:
csvFilenameList = [("covtype.data", 800)]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(
bucket="home-0xdiag-datasets", path=csvPathname, timeoutSecs=2000, pollTimeoutSecs=60
)
inspect = h2o_cmd.runInspect(None, parseResult["destination_key"])
print "\n" + csvPathname, " numRows:", "{:,}".format(inspect["numRows"]), " numCols:", "{:,}".format(
inspect["numCols"]
)
paramDict = define_params(SEED)
for trial in range(3):
# default
destinationKey = csvFilename + "_" + str(trial) + ".hex"
params = {"k": "2,3", "destination_key": destinationKey}
h2o_kmeans.pickRandKMeansParams(paramDict, params)
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(
parseResult=parseResult,
timeoutSecs=timeoutSecs,
retryDelaySecs=2,
pollTimeoutSecs=60,
noPoll=True,
**kwargs
)
h2j.pollWaitJobs(timeoutSecs=timeoutSecs, pollTimeoutSecs=timeoutSecs)
elapsed = time.time() - start
print "FIX! how do we get results..need redirect_url"
print "Have to inspect different models? (grid)"
print "kmeans end on ", csvPathname, "took", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100
)
# h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
# destination_key is ignored by kmeans...what are the keys for the results
# inspect = h2o_cmd.runInspect(None,key=destinationKey)
# print h2o.dump_json(inspect)
print "Trial #", trial, "completed\n"
def test_kmeans_prostate(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
hex_key=hex_key,
header=1,
timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
# loop, to see if we get same centers
expected = [
([0.37, 65.77, 1.07, 2.23, 1.11, 10.49, 4.24, 6.31], 215, 36955),
([0.36, 66.44, 1.09, 2.21, 1.06, 10.84, 34.16, 6.31], 136, 46045),
([0.83, 66.17, 1.21, 2.86, 1.34, 73.30, 15.57, 7.31], 29, 33412),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
for trial in range(1):
# kmeansSeed = random.randint(0, sys.maxint)
# actually can get a slightly better error sum with a different seed
# this seed gets the same result as scikit
kmeansSeed = 6655548259421773879
kwargs = {
'ignored_cols': 'ID',
'k': 3,
# 'initialization': 'Furthest',
'initialization': 'PlusPlus',
'destination_key': 'prostate_k.hex',
'max_iter': 500,
'seed': kmeansSeed,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
# 'seed': 265211114317615310}
}
# for fvec only?
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=5,
**kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
trial=trial)
def test_C_kmeans_prostate(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, header=1, timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
# loop, to see if we get same centers
expected = [
([43.07058823529412, 0.36470588235294116, 67.70588235294117, 1.1058823529411765, 2.3529411764705883, 1.2117647058823529, 17.33529411764706, 14.201176470588232, 6.588235294117647], 103, 0) ,
([166.04347826086956, 0.4658385093167702, 66.09316770186335, 1.0807453416149069, 2.3043478260869565, 1.0807453416149069, 15.0632298136646, 16.211118012422357, 6.527950310559007], 136, 0) ,
([313.4029850746269, 0.35074626865671643, 64.91791044776119, 1.0820895522388059, 2.1791044776119404, 1.0746268656716418, 14.601492537313437, 16.35686567164179, 6.082089552238806], 141, 0) ,
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
kwargs = {'k': 3, 'initialization': 'Furthest', 'destination_key': 'prostate_k.hex', 'max_iter': 50,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310}
# for fvec only?
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, noPoll=not DO_POLL, **kwargs)
if not DO_POLL:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
# hack..supposed to be there like va
kmeans['destination_key'] = 'prostate_k.hex'
# FIX! how do I get the kmeans result?
### print "kmeans result:", h2o.dump_json(kmeans)
# can't do this
# inspect = h2o_cmd.runInspect(key='prostate_k.hex')
modelView = h2o.nodes[0].kmeans_model_view(model='prostate_k.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['clusters']
cluster_variances = model['cluster_variances']
error = model['error']
print "cluster_variances:", cluster_variances
print "error:", error
# variance of 0 might be legal with duplicated rows. wasn't able to remove the duplicate rows of NAs at
# bottom of benign.csv in ec2
# for i,c in enumerate(cluster_variances):
# if c < 0.1:
# raise Exception("cluster_variance %s for cluster %s is too small. Doesn't make sense. Ladies and gentlemen, this is Chewbacca. Chewbacca is a Wookiee from the planet Kashyyyk. But Chewbacca lives on the planet Endor. Now think about it...that does not make sense!" % (c, i))
# make this fvec legal?
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=0)
def test_kmeans_sphere3_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = 'syn_spheres3_' + str(SEED) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
write_syn_dataset(csvPathname, 1000000, SEED)
print "\nStarting", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key)
for trial in range(10):
# reuse the same seed, to get deterministic results (otherwise sometimes fails
kwargs = {
'k': 3,
'max_iter': 25,
'initialization': 'Furthest',
'destination_key': 'spheres3.hex',
# 'seed': 265211114317615310,
'seed': 0,
}
timeoutSecs = 90
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
expected = [
([100, 100, 100], 1000000, 60028168),
([200, 200, 200], 2000000, 479913618),
([300, 300, 300], 3000000, 1619244994),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
trial=trial)
gs = h2o.nodes[0].gap_statistic(source=hex_key,
k_max=5,
timeoutSecs=300)
print "gap_statistic:", h2o.dump_json(gs)
def test_KMeansGrid_params_rand2_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000,
pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
paramDict = define_params(SEED)
for trial in range(3):
# default
destinationKey = csvFilename + "_" + str(trial) + '.hex'
params = {'k': '2,3', 'destination_key': destinationKey}
h2o_kmeans.pickRandKMeansParams(paramDict, params)
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, noPoll=True, **kwargs)
h2j.pollWaitJobs(timeoutSecs=timeoutSecs,
pollTimeoutSecs=timeoutSecs)
elapsed = time.time() - start
print "FIX! how do we get results..need redirect_url"
print "Have to inspect different models? (grid)"
print "kmeans grid end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
# destination_key is ignored by kmeans...what are the keys for the results
# inspect = h2o_cmd.runInspect(None,key=destinationKey)
# print h2o.dump_json(inspect)
print "Trial #", trial, "completed\n"
def test_KMeans_twit(self):
csvFilename = "Twitter2DB.txt"
print "\nStarting", csvFilename
# h2b.browseTheCloud()
parseResult = h2i.import_parse(bucket='smalldata', path=csvFilename, hex_key=csvFilename + ".hex", schema='put')
# both of these centers match what different R/Scikit packages get
expected1 = [
# expected centers are from R. rest is just from h2o
([310527.2, 13433.89], 11340, None),
([5647967.1, 40487.76], 550, None),
([21765291.7, 93129.26], 14, None),
]
# this is what we get with Furthest
expected2 = [
([351104.74065255735, 15421.749823633158], 11340, 5021682274541967.0) ,
([7292636.589090909, 7575.630909090909], 550, 6373072701775582.0) ,
([34406781.071428575, 244878.0], 14, 123310713697348.92) ,
]
# all are multipliers of expected tuple value
allowedDelta = (0.0001, 0.0001, 0.0001)
for trial in range(2):
kwargs = {
'k': 3,
'max_iter': 50,
'normalize': 0,
'cols': '0,1',
'initialization': 'Furthest',
# 'initialization': 'PlusPlus',
'destination_key': 'kmeans_dest_key',
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310
}
init_choices = ['Furthest', 'PlusPlus']
kwargs['initialization'] = init_choices[trial % len(init_choices)]
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
inspect = h2o_cmd.runInspect(None, key=kmeans['destination_key'], verbose=True)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvFilename, parseResult, 'd', **kwargs)
if 1==0:
h2b.browseJsonHistoryAsUrlLastMatch("KMeansScore")
h2b.browseJsonHistoryAsUrlLastMatch("KMeansApply")
h2b.browseJsonHistoryAsUrlLastMatch("KMeans")
# Comment sleep out to get a clean grep.
# time.sleep(3600)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected2, allowedDelta, trial=trial)
def test_libsvm(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
for trial in range(2):
csvFilename = "syn_ints.csv"
hex_key = "1.hex"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
write_syn_dataset(csvPathname, trial)
timeoutSecs = 10
# have to import each time, because h2o deletes source after parse
# PARSE******************************************
# creates csvFilename.hex from file in importFolder dir
# parseResult = h2i.import_parse(path=csvPathname, parser_type='SVMLight', hex_key=hex_key, timeoutSecs=2000)
parseResult = h2i.import_parse(parser_type=PARSER_TYPE, path=csvPathname, hex_key=hex_key, timeoutSecs=2000)
# INSPECT******************************************
start = time.time()
inspect = h2o_cmd.runInspect(key=hex_key, timeoutSecs=360)
print "Inspect:", hex_key, "took", time.time() - start, "seconds"
h2o_cmd.infoFromInspect(inspect, csvFilename)
numRows = inspect['numRows']
numCols = inspect['numCols']
summaryResult = h2o_cmd.runSummary(key=hex_key)
h2o_cmd.infoFromSummary(summaryResult)
if DO_KMEANS:
# KMEANS******************************************
kwargs = {
'k': 3,
'initialization': 'Furthest',
'ignored_cols': None, #range(11, numCols), # THIS BREAKS THE REST API
'max_iter': 10,
# 'normalize': 0,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
# fails if I put this in kwargs..i.e. source = dest
# 'destination_key': parseResult['destination_key'],
timeoutSecs = 600
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# this does an inspect of the model and prints the clusters
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_KMeans_covtype20x_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# 68 secs on my laptop?
('covtype20x.data', 1200, 'cA'),
]
else:
# None is okay for hex_key
csvFilenameList = [
('covtype20x.data', 1200, 'cA'),
# ('covtype200x.data', 1000,'cE'),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs, hex_key in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
# creates csvFilename.hex from file in importFolder dir
start = time.time()
parseResult = h2i.import_parse(
bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000,
hex_key=hex_key) # noise=('JStack', None)
print "parse end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
h2o.check_sandbox_for_errors()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
k = 2
kwargs = {
'max_iter': 25,
'initialization': 'Furthest',
'k': k,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_KMeansGrid_basic_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path='standard/covtype.data', schema='local',
timeoutSecs=2000, pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "python_source:", parseResult['python_source']
csvPathname = parseResult['python_source']
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
destination_key = 'd.hex'
params = {
'k': '2,3',
# 'initialization': 'Furthest',
'initialization': None,
'seed': 3923021996079663354,
'normalize': 0,
'max_iter': '2',
'destination_key': destination_key
}
for trial in range(3):
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans (with grid) end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
print "FIX! have to interrogate each job result to see kmeans grid results"
### h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
# This doesn't work (inspecting the model)
# inspect = h2o_cmd.runInspect(None,key=destination_key)
# print h2o.dump_json(inspect)
print "Trial #", trial, "completed\n"
def test_kmeans_iris_fvec(self):
h2o.beta_features = True
csvFilename = 'iris.csv'
csvPathname = 'iris/' + csvFilename
print "\nStarting", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put', hex_key=hex_key)
k = 3
ignored_cols = 'C5'
for trial in range(3):
# reuse the same seed, to get deterministic results (otherwise sometimes fails
kwargs = {
'ignored_cols': ignored_cols, # ignore the output
'k': k,
'max_iter': 25,
'initialization': 'Furthest',
'destination_key': 'iris.hex',
'seed': 0,
}
timeoutSecs = 90
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
expected = [
# if ignored_cols isn't used
# ([5, 3.4, 1.46, 0.244, 0.0], 50, 15.24) ,
# ([5.9, 2.76, 4.26, 1.33, 1.02], 51, 32.9) ,
# ([6.6, 2.98, 5.57, 2.03, 2.0], 49, 39.15) ,
([5.005999999999999, 3.4180000000000006, 1.464, 0.2439999999999999], 50, 15.240400000000003) ,
([5.901612903225807, 2.748387096774194, 4.393548387096775, 1.4338709677419357], 62, 39.82096774193549) ,
([6.8500000000000005, 3.073684210526315, 5.742105263157894, 2.0710526315789473], 38, 23.87947368421053) ,
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
gs = h2o.nodes[0].gap_statistic(source=hex_key, ignored_cols=ignored_cols, k_max=k)
print "gap_statistic:", h2o.dump_json(gs)
k_best = gs['gap_model']['k_best']
self.assertTrue(k_best!=0, msg="k_best shouldn't be 0: %s" % k_best)
def test_KMeans_covtype20x_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# 68 secs on my laptop?
('covtype20x.data', 1200, 'cA'),
]
else:
# None is okay for hex_key
csvFilenameList = [
('covtype20x.data', 1200,'cA'),
# ('covtype200x.data', 1000,'cE'),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs, hex_key in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
# creates csvFilename.hex from file in importFolder dir
start = time.time()
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname,
timeoutSecs=2000, hex_key=hex_key) # noise=('JStack', None)
print "parse end on ", csvPathname, 'took', time.time() - start, 'seconds'
h2o.check_sandbox_for_errors()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
k = 2
kwargs = {
'max_iter': 25,
'initialization': 'Furthest',
'k': k,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
gs = h2o.nodes[0].gap_statistic(source=hex_key, k_max=8)
print "gap_statistic:", h2o.dump_json(gs)
def test_B_kmeans_benign(self):
importFolderPath = "standard"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
# FIX! hex_key isn't working with Parse2 ? parseResult['destination_key'] not right?
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, hex_key=hex_key, header=1,
timeoutSecs=180, noPoll=h2o.beta_features, doSummary=False)
if h2o.beta_features:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
parseResult['destination_key'] = hex_key
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
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 k in range(2, 6):
kwargs = {'k': k, 'ignored_cols_by_name': None, 'destination_key': 'benign_k.hex',
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310}
# for fvec only?
kwargs.update({'max_iter': 10})
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, noPoll=h2o.beta_features, **kwargs)
if h2o.beta_features:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
# hack..supposed to be there like va
kmeans['destination_key'] = 'benign_k.hex'
## h2o.verboseprint("kmeans result:", h2o.dump_json(kmeans))
modelView = h2o.nodes[0].kmeans_model_view(model='benign_k.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['clusters']
cluster_variances = model['cluster_variances']
error = model['error']
print "cluster_variances:", cluster_variances
print "error:", error
def test_KMeansGrid_params_rand2(self):
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname,
timeoutSecs=2000, pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" num_rows:", "{:,}".format(inspect['num_rows']), \
" num_cols:", "{:,}".format(inspect['num_cols'])
paramDict = define_params(SEED)
h2o.beta_features = True # no grid for VA
for trial in range(3):
# default
destinationKey = csvFilename + "_" + str(trial) + '.hex'
params = {'k': 'c(2,3)', 'destination_key': destinationKey}
h2o_kmeans.pickRandKMeansParams(paramDict, params)
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, noPoll=True, **kwargs)
h2j.pollWaitJobs(timeoutSecs=timeoutSecs, pollTimeoutSecs=timeoutSecs)
elapsed = time.time() - start
print "FIX! how do we get results..need redirect_url"
print "Have to inspect different models? (grid)"
print "kmeans grid end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
# destination_key is ignored by kmeans...what are the keys for the results
# inspect = h2o_cmd.runInspect(None,key=destinationKey)
# print h2o.dump_json(inspect)
print "Trial #", trial, "completed\n"
def test_C_kmeans_prostate(self):
importFolderPath = "standard"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, hex_key=hex_key, header=1, timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
# 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 k in range(2, 6):
kwargs = {'k': k, 'initialization': 'Furthest', 'destination_key': 'prostate_k.hex',
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310}
# for fvec only?
kwargs.update({'max_iter': 50})
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, noPoll=h2o.beta_features, **kwargs)
if h2o.beta_features:
h2o_jobs.pollWaitJobs(timeoutSecs=300, pollTimeoutSecs=300, retryDelaySecs=5)
# hack..supposed to be there like va
kmeans['destination_key'] = 'prostate_k.hex'
# FIX! how do I get the kmeans result?
### print "kmeans result:", h2o.dump_json(kmeans)
# can't do this
# inspect = h2o_cmd.runInspect(key='prostate_k.hex')
modelView = h2o.nodes[0].kmeans_model_view(model='prostate_k.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['clusters']
cluster_variances = model['cluster_variances']
error = model['error']
print "cluster_variances:", cluster_variances
print "error:", error
for i,c in enumerate(cluster_variances):
if c < 0.1:
raise Exception("cluster_variance %s for cluster %s is too small. Doesn't make sense. Ladies and gentlemen, this is Chewbacca. Chewbacca is a Wookiee from the planet Kashyyyk. But Chewbacca lives on the planet Endor. Now think about it...that does not make sense!" % (c, i))
def test_KMeans_params_rand2_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000,
pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
paramDict = define_params(SEED)
for trial in range(3):
# default
params = {
'max_iter': 20,
'k': 1,
'destination_key': csvFilename + "_" + str(trial) + '.hex'
}
h2o_kmeans.pickRandKMeansParams(paramDict, params)
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
print "Trial #", trial, "completed\n"
def test_KMeans_winesPCA(self):
csvPathname = 'winesPCA.csv'
start = time.time()
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put', timeoutSecs=10)
print "parse end on ", csvPathname, 'took', time.time() - start, 'seconds'
h2o.check_sandbox_for_errors()
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" num_rows:", "{:,}".format(inspect['num_rows']), \
" num_cols:", "{:,}".format(inspect['num_cols'])
kwargs = {
#appears not to take 'cols'?
'cols': None,
'initialization': 'Furthest',
'k': 3,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
timeoutSecs = 480
# try the same thing 5 times
for trial in range (10):
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans #", trial, "end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = \
h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# tupleResultList has tuples = center, rows_per_cluster, sqr_error_per_cluster
# now compare expected vs actual. By sorting on center, we should be able to compare
# since the centers should be separated enough to have the order be consistent
expected = [
([-2.25977535371875, -0.8631572635625001], 64, 83.77800617624794) ,
([0.16232721958461543, 1.7626161107230771], 65, 111.64440134649745) ,
([2.7362112930204074, -1.2107751495102044], 49, 62.6290553489474) ,
]
# multipliers on the expected values for allowed
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial)
def kmeans_doit(self, csvFilename, bucket, csvPathname, numRows, timeoutSecs=30):
print "\nStarting KMeans of", csvFilename
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='put', hex_key=csvFilename + ".hex", timeoutSecs=20)
# hastie has two values, 1 and -1.
# we could not specify cols, but this is more fun
kwargs = {
'k': 1,
'initialization': 'Furthest',
'destination_key': 'KMeansModel.hex',
'max_iter': 25,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
expected = [
([-0.0006628900000000158, -0.0004671200060434639, 0.0009330300069879741, 0.0007883800000000272, 0.0007548200000000111, 0.0005617899864856153, 0.0013246499999999897, 0.0004036299999999859, -0.0014307100000000314, 0.0021324000161308796, 0.00154], numRows, None)
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=0)
# compare this kmeans to the first one. since the files are replications, the results
# should be similar?
# inspect doesn't work
# inspect = h2o_cmd.runInspect(None, key=kmeans['model']['_key'])
# KMeansModel = inspect['KMeansModel']
modelView = h2o.nodes[0].kmeans_view(model='KMeansModel.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['centers']
within_cluster_variances = model['within_cluster_variances']
total_within_SS = model['total_within_SS']
print "within_cluster_variances:", within_cluster_variances
print "total_within_SS:", total_within_SS
if self.clusters1:
h2o_kmeans.compareToFirstKMeans(self, clusters, self.clusters1)
else:
self.clusters1 = copy.deepcopy(clusters)
def test_kmeans_sphere3_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_spheres3_" + str(SEED) + ".csv"
csvPathname = SYNDATASETS_DIR + "/" + csvFilename
write_syn_dataset(csvPathname, 1000000, SEED)
print "\nStarting", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(path=csvPathname, schema="put", hex_key=hex_key)
for trial in range(10):
# reuse the same seed, to get deterministic results (otherwise sometimes fails
kwargs = {
"k": 3,
"max_iter": 25,
"initialization": "Furthest",
"destination_key": "spheres3.hex",
# 'seed': 265211114317615310,
"seed": 0,
}
timeoutSecs = 90
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, "took", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100
)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, "d", **kwargs
)
expected = [
([100, 100, 100], 1000000, 60028168),
([200, 200, 200], 2000000, 479913618),
([300, 300, 300], 3000000, 1619244994),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
gs = h2o.nodes[0].gap_statistic(source=hex_key, k_max=5, timeoutSecs=300)
print "gap_statistic:", h2o.dump_json(gs)
def test_KMeans_params_rand2_fvec(self):
h2o.beta_features = True
if localhost:
csvFilenameList = [
# ('covtype.data', 60),
('covtype.data', 800),
]
else:
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname,
timeoutSecs=2000, pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
paramDict = define_params(SEED)
for trial in range(3):
# default
params = {
'max_iter': 20,
'k': 1,
'destination_key': csvFilename + "_" + str(trial) + '.hex'
}
h2o_kmeans.pickRandKMeansParams(paramDict, params)
kwargs = params.copy()
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
print "Trial #", trial, "completed\n"
def test_kmeans_prostate(self):
h2o.beta_features = True # fvec
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, header=1, timeoutSecs=180)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
# loop, to see if we get same centers
expected = [
([0.37,65.77,1.07,2.23,1.11,10.49,4.24,6.31], 215, 36955),
([0.36,66.44,1.09,2.21,1.06,10.84,34.16,6.31], 136, 46045),
([0.83,66.17,1.21,2.86,1.34,73.30,15.57,7.31], 29, 33412),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
for trial in range(1):
# kmeansSeed = random.randint(0, sys.maxint)
# actually can get a slightly better error sum with a different seed
# this seed gets the same result as scikit
kmeansSeed = 6655548259421773879
kwargs = {
'ignored_cols': 'ID',
'k': 3,
# 'initialization': 'Furthest',
'initialization': 'PlusPlus',
'destination_key': 'prostate_k.hex',
'max_iter': 500,
'seed': kmeansSeed,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
# 'seed': 265211114317615310}
}
# for fvec only?
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
def test_kmeans_benign(self):
h2o.beta_features = True
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
# FIX! hex_key isn't working with Parse2 ? parseResult['destination_key'] not right?
print "\nStarting", csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, header=1,
timeoutSecs=180, doSummary=False)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\nStarting", csvFilename
expected = [
([8.86, 2.43, 35.53, 0.31, 13.22, 1.47, 1.33, 20.06, 13.08, 0.53, 2.12, 128.61, 35.33, 1.57], 49, None),
([33.47, 2.29, 50.92, 0.34, 12.82, 1.33, 1.36, 21.43, 13.30, 0.37, 2.52, 125.40, 43.91, 1.79], 87, None),
([27.64, 2.87, 48.11, 0.09, 11.80, 0.98, 1.51, 21.02, 12.53, 0.58, 2.89, 171.27, 42.73, 1.53], 55, None),
([26.00, 2.67, 46.67, 0.00, 13.00, 1.33, 1.67, 21.56, 11.44, 0.22, 2.89, 234.56, 39.22, 1.56], 9, None),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01, 0.01)
# loop, to see if we get same centers
for trial in range(1):
kmeansSeed = random.randint(0, sys.maxint)
# kmeansSeed = 6655548259421773879
kwargs = {
'k': 4,
'initialization': 'PlusPlus',
'destination_key': 'benign_k.hex',
# 'seed': 265211114317615310,
'max_iter': 50,
'seed': kmeansSeed,
}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=5, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def notest_B_kmeans_benign(self):
h2o.beta_features = True
csvPathname = "logreg"
csvFilename = "benign.csv"
hex_key = csvFilename + ".hex"
print "\nStarting", csvFilename
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname + "/"+csvFilename, schema='local', hex_key=hex_key)
# FIX! have to fill in expected rows and error here
# this is from sklearn.cluster.KMeans, with NA's converted to 0
expected = [
([ 8.86, 2.43, 35.53, 0.31, 13.22, 1.47, 1.33, 20.06, 13.08, 0.53, 2.12, 128.61, 35.33, 1.57], None, None),
([33.47, 2.29, 50.92, 0.34, 12.82, 1.33, 1.36, 21.43, 13.30, 0.37, 2.52, 125.40, 43.91, 1.79], None, None),
([27.64, 2.87, 48.11, 0.09, 11.80, 0.98, 1.51, 21.02, 12.53, 0.58, 2.89, 171.27, 42.73, 1.53], None, None),
([26.00, 2.67, 46.67, 0.00, 13.00, 1.33, 1.67, 21.56, 11.44, 0.22, 2.89, 234.56, 39.22, 1.56], None, None),
]
for i in range(14):
execExpr = '%s[,%s] = is.na(%s[,%s]) ? 0.0 : %s[,%s]' % (hex_key,i+1,hex_key,i+1,hex_key,i+1)
h2e.exec_expr(execExpr=execExpr, resultKey=None, timeoutSecs=4)
# all are multipliers of expected tuple value
allowedDelta = (0.1, 0.1, 0.1)
# loop, to see if we get same centers
for trial in range(2):
params = {'k': 4,
# 'initialization': 'Furthest',
'initialization': 'PlusPlus',
'destination_key': 'benign_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)
def test_KMeans_covtype_fvec(self):
h2o.beta_features = True
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000,
pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
for trial in range(3):
kwargs = {
'source': u'covtype.hex',
'destination_key': 'covtype.data_2.hex',
'initialization': 'Furthest',
# 'max_iter': 20,
'max_iter': 50,
'k': 2,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
### print h2o.dump_json(kmeans)
print "Trial #", trial, "completed\n"
def test_kmeans_sphere3_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = 'syn_spheres3_' + str(SEED) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
write_syn_dataset(csvPathname, 1000000, SEED)
print "\nStarting", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key)
for trial in range(10):
# reuse the same seed, to get deterministic results (otherwise sometimes fails
kwargs = {
'k': 3,
'max_iter': 25,
'initialization': 'Furthest',
'destination_key': 'spheres3.hex',
# 'seed': 265211114317615310,
'seed': 0,
}
timeoutSecs = 90
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
expected = [
([100, 100, 100], 1000000, 60028168),
([200, 200, 200], 2000000, 479913618),
([300, 300, 300], 3000000, 1619244994),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, trial=trial)
def test_KMeans_allstate_s3n_thru_hdfs(self):
bucket = 'home-0xdiag-datasets'
importFolderPath = 'allstate'
csvFilename = "train_set.csv"
csvPathname = importFolderPath + "/" + csvFilename
timeoutSecs = 600
trialMax = 3
for trial in range(trialMax):
trialStart = time.time()
hex_key = csvFilename + "_" + str(trial) + ".hex"
start = time.time()
parseResult = h2i.import_parse(bucket=bucket,
path=csvPathname,
schema='s3n',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
retryDelaySecs=10,
pollTimeoutSecs=60)
elapsed = time.time() - start
print 'h2o reported parse time:', parseResult['response']['time']
print "parse end on ", csvPathname, 'took', elapsed, 'seconds',\
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
print "parse result:", parseResult['destination_key']
kwargs = {'cols': None, 'initialization': 'Furthest', 'k': 12}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=120, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvFilename, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
inspect = h2o_cmd.runInspect(None, key=kmeans['destination_key'])
print h2o.dump_json(inspect)
print "Trial #", trial, "completed in", time.time() - trialStart, "seconds.", \
def test_c5_KMeans_sphere_67MB_fvec(self):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
csvFilename = 'syn_sphere_gen_h1m_no_na.csv'
totalBytes = 67306997
if FROM_HDFS:
importFolderPath = "datasets/kmeans_big"
csvPathname = importFolderPath + '/' + csvFilename
else:
importFolderPath = "/home3/0xdiag/datasets/kmeans_big"
csvPathname = importFolderPath + '/' + csvFilename
# FIX! put right values in
# will there be different expected for random vs the other inits?
expected = [
([0.0, -113.00566692375459, -89.99595447985321, -455.9970643424373, 4732.0, 49791778.0, 36800.0], 248846122, 1308149283316.2988) ,
([0.0, 1.0, 1.0, -525.0093818313685, 2015.001629398412, 25654042.00592703, 28304.0], 276924291, 1800760152555.98) ,
([0.0, 5.0, 2.0, 340.0, 1817.995920197288, 33970406.992053084, 31319.99486705394], 235089554, 375419158808.3253) ,
([0.0, 10.0, -72.00113070337981, -171.0198611715457, 4430.00952228909, 37007399.0, 29894.0], 166180630, 525423632323.6474) ,
([0.0, 11.0, 3.0, 578.0043558141306, 1483.0163188052604, 22865824.99639042, 5335.0], 167234179, 1845362026223.1094) ,
([0.0, 12.0, 3.0, 168.0, -4066.995950679284, 41077063.00269915, -47537.998050740985], 195420925, 197941282992.43475) ,
([0.0, 19.00092954923767, -10.999565572612255, 90.00028669073289, 1928.0, 39967190.0, 27202.0], 214401768, 11868360232.658035) ,
([0.0, 20.0, 0.0, 141.0, -3263.0030236302937, 6163210.990273981, 30712.99115201907], 258853406, 598863991074.3276) ,
([0.0, 21.0, 114.01584574295777, 242.99690338815898, 1674.0029079209912, 33089556.0, 36415.0], 190979054, 1505088759456.314) ,
([0.0, 25.0, 1.0, 614.0032787274755, -2275.9931284021022, -48473733.04122273, 47343.0], 87794427, 1124697008162.3955) ,
([0.0, 39.0, 3.0, 470.0, -3337.9880599007597, 28768057.98852736, 16716.003410920028], 78226988, 1151439441529.0215) ,
([0.0, 40.0, 1.0, 145.0, 950.9990795199593, 14602680.991458317, -14930.007919032574], 167273589, 693036940951.0249) ,
([0.0, 42.0, 4.0, 479.0, -3678.0033024834297, 8209673.001421165, 11767.998552236539], 148426180, 35942838893.32379) ,
([0.0, 48.0, 4.0, 71.0, -951.0035145455234, 49882273.00063991, -23336.998167498707], 157533313, 88431531357.62982) ,
([0.0, 147.00394564757505, 122.98729664236723, 311.0047920137008, 2320.0, 46602185.0, 11212.0], 118361306, 1111537045743.7646) ,
]
benchmarkLogging = ['cpu','disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu','disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk', 'network']
benchmarkLogging = []
for trial in range(6):
# IMPORT**********************************************
# since H2O deletes the source key, re-import every iteration.
# PARSE ****************************************
print "Parse starting: " + csvFilename
hex_key = csvFilename + "_" + str(trial) + ".hex"
start = time.time()
timeoutSecs = 2 * 3600
kwargs = {}
if FROM_HDFS:
parseResult = h2i.import_parse(path=csvPathname, schema='hdfs', hex_key=hex_key,
timeoutSecs=timeoutSecs, pollTimeoutSecs=60, retryDelaySecs=2,
benchmarkLogging=benchmarkLogging, **kwargs)
else:
parseResult = h2i.import_parse(path=csvPathname, schema='local', hex_key=hex_key,
timeoutSecs=timeoutSecs, pollTimeoutSecs=60, retryDelaySecs=2,
benchmarkLogging=benchmarkLogging, **kwargs)
elapsed = time.time() - start
fileMBS = (totalBytes/1e6)/elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, 'Parse', csvPathname, fileMBS, elapsed)
print "\n"+l
h2o.cloudPerfH2O.message(l)
# clear out all NAs (walk across cols)..clear to 0
# temp
## execExpr = '%s=apply(%s,2,function(x){ifelse(is.na(x),0,x)})' % (hex_key, hex_key)
## h2e.exec_expr(h2o.nodes[0], execExpr, resultKey=None, timeoutSecs=10)
inspect = h2o_cmd.runInspect(key=hex_key, timeoutSecs=500)
h2o_cmd.infoFromInspect(inspect, csvPathname)
summary = h2o_cmd.runSummary(key=hex_key, timeoutSecs=500)
h2o_cmd.infoFromSummary(summary)
# KMeans ****************************************
if not DO_KMEANS:
continue
print "col 0 is enum in " + csvFilename + " but KMeans should skip that automatically?? or no?"
kwargs = {
'k': 15,
'max_iter': 10,
'normalize': 1,
'initialization': 'Furthest',
'destination_key': 'junk.hex',
# reuse the same seed, to get deterministic results
'seed': 265211114317615310,
# 'ignored_cols': 'C0', # get NaNs if col with all NAs is left in. the exec2 clear doesn't seem to work
}
if (trial%3)==0:
kwargs['initialization'] = 'PlusPlus'
elif (trial%3)==1:
kwargs['initialization'] = 'Furthest'
else:
kwargs['initialization'] = None
timeoutSecs = 4 * 3600
params = kwargs
paramsString = json.dumps(params)
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs,
benchmarkLogging=benchmarkLogging, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
print "kmeans result:", h2o.dump_json(kmeans)
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:s} for {:.2f} secs {:s}' .format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, "KMeans", "trial "+str(trial), csvFilename, elapsed, paramsString)
print l
h2o.cloudPerfH2O.message(l)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self, tupleResultList, expected, allowedDelta, allowError=True, trial=trial)
h2i.delete_keys_at_all_nodes()
def test_kmeans_sphere5(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
CLUSTERS = 5
SPHERE_PTS = 10000
csvFilename = 'syn_spheres100.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
centersList = write_spheres_dataset(csvPathname, CLUSTERS, SPHERE_PTS)
print "\nStarting", csvFilename
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=csvFilename + ".hex")
# try 5 times, to see if all inits by h2o are good
for trial in range(5):
# pass SEED so it's repeatable
kwargs = {
'k': CLUSTERS,
'max_iter': 10,
'initialization': 'Furthest',
'cols': None,
'destination_key': 'syn_spheres100.hex',
'seed': SEED
}
timeoutSecs = 30
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.',\
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
kmeansResult = h2o_cmd.runInspect(key='syn_spheres100.hex')
### print h2o.dump_json(kmeans)
### print h2o.dump_json(kmeansResult)
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
# cluster centers can return in any order
clusters = kmeansResult['KMeansModel']['clusters']
clustersSorted = sorted(clusters, key=itemgetter(0))
### print clustersSorted
print "\nh2o result, centers sorted"
print clustersSorted
print "\ngenerated centers"
print centersList
for i, center in enumerate(centersList):
a = center
b = clustersSorted[i]
print "\nexpected:", a
print "h2o:", b # h2o result
aStr = ",".join(map(str, a))
bStr = ",".join(map(str, b))
iStr = str(i)
self.assertAlmostEqual(a[0],
b[0],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
" x not correct.")
self.assertAlmostEqual(a[1],
b[1],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
" y not correct.")
self.assertAlmostEqual(a[2],
b[2],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
" z not correct.")
print "Trial #", trial, "completed"
def test_c5_KMeans_sphere_26GB_fvec(self):
h2o.beta_features = True
# a kludge
h2o.setup_benchmark_log()
# csvFilename = 'syn_sphere15_2711545732row_6col_180GB_from_7x.csv'
csvFilename = 'syn_sphere15_gen_26GB.csv'
# csvFilename = 'syn_sphere_gen_h1m.csv'
# csvFilename = 'syn_sphere_gen_real_1.49M.csv'
# csvFilename = 'syn_sphere_gen_h1m_no_na.csv'
totalBytes = 183538602156
if FROM_HDFS:
importFolderPath = "datasets/kmeans_big"
csvPathname = importFolderPath + '/' + csvFilename
else:
importFolderPath = "/home3/0xdiag/datasets/kmeans_big"
csvPathname = importFolderPath + '/' + csvFilename
# FIX! put right values in
# will there be different expected for random vs the other inits?
if NA_COL_BUG:
expected = [
# the centers are the same for the 26GB and 180GB. The # of rows is right for 180GB,
# so shouldn't be used for 26GB
# or it should be divided by 7
# the distribution is the same, obviously.
([
-113.00566692375459, -89.99595447985321,
-455.9970643424373, 4732.0, 49791778.0, 36800.0
], 248846122, 1308149283316.2988),
([
1.0, 1.0, -525.0093818313685, 2015.001629398412,
25654042.00592703, 28304.0
], 276924291, 1800760152555.98),
([
5.0, 2.0, 340.0, 1817.995920197288, 33970406.992053084,
31319.99486705394
], 235089554, 375419158808.3253),
([
10.0, -72.00113070337981, -171.0198611715457,
4430.00952228909, 37007399.0, 29894.0
], 166180630, 525423632323.6474),
([
11.0, 3.0, 578.0043558141306, 1483.0163188052604,
22865824.99639042, 5335.0
], 167234179, 1845362026223.1094),
([
12.0, 3.0, 168.0, -4066.995950679284, 41077063.00269915,
-47537.998050740985
], 195420925, 197941282992.43475),
([
19.00092954923767, -10.999565572612255, 90.00028669073289,
1928.0, 39967190.0, 27202.0
], 214401768, 11868360232.658035),
([
20.0, 0.0, 141.0, -3263.0030236302937, 6163210.990273981,
30712.99115201907
], 258853406, 598863991074.3276),
([
21.0, 114.01584574295777, 242.99690338815898,
1674.0029079209912, 33089556.0, 36415.0
], 190979054, 1505088759456.314),
([
25.0, 1.0, 614.0032787274755, -2275.9931284021022,
-48473733.04122273, 47343.0
], 87794427, 1124697008162.3955),
([
39.0, 3.0, 470.0, -3337.9880599007597, 28768057.98852736,
16716.003410920028
], 78226988, 1151439441529.0215),
([
40.0, 1.0, 145.0, 950.9990795199593, 14602680.991458317,
-14930.007919032574
], 167273589, 693036940951.0249),
([
42.0, 4.0, 479.0, -3678.0033024834297, 8209673.001421165,
11767.998552236539
], 148426180, 35942838893.32379),
([
48.0, 4.0, 71.0, -951.0035145455234, 49882273.00063991,
-23336.998167498707
], 157533313, 88431531357.62982),
([
147.00394564757505, 122.98729664236723, 311.0047920137008,
2320.0, 46602185.0, 11212.0
], 118361306, 1111537045743.7646),
]
else:
expected = [
([
0.0, -113.00566692375459, -89.99595447985321,
-455.9970643424373, 4732.0, 49791778.0, 36800.0
], 248846122, 1308149283316.2988),
([
0.0, 1.0, 1.0, -525.0093818313685, 2015.001629398412,
25654042.00592703, 28304.0
], 276924291, 1800760152555.98),
([
0.0, 5.0, 2.0, 340.0, 1817.995920197288,
33970406.992053084, 31319.99486705394
], 235089554, 375419158808.3253),
([
0.0, 10.0, -72.00113070337981, -171.0198611715457,
4430.00952228909, 37007399.0, 29894.0
], 166180630, 525423632323.6474),
([
0.0, 11.0, 3.0, 578.0043558141306, 1483.0163188052604,
22865824.99639042, 5335.0
], 167234179, 1845362026223.1094),
([
0.0, 12.0, 3.0, 168.0, -4066.995950679284,
41077063.00269915, -47537.998050740985
], 195420925, 197941282992.43475),
([
0.0, 19.00092954923767, -10.999565572612255,
90.00028669073289, 1928.0, 39967190.0, 27202.0
], 214401768, 11868360232.658035),
([
0.0, 20.0, 0.0, 141.0, -3263.0030236302937,
6163210.990273981, 30712.99115201907
], 258853406, 598863991074.3276),
([
0.0, 21.0, 114.01584574295777, 242.99690338815898,
1674.0029079209912, 33089556.0, 36415.0
], 190979054, 1505088759456.314),
([
0.0, 25.0, 1.0, 614.0032787274755, -2275.9931284021022,
-48473733.04122273, 47343.0
], 87794427, 1124697008162.3955),
([
0.0, 39.0, 3.0, 470.0, -3337.9880599007597,
28768057.98852736, 16716.003410920028
], 78226988, 1151439441529.0215),
([
0.0, 40.0, 1.0, 145.0, 950.9990795199593,
14602680.991458317, -14930.007919032574
], 167273589, 693036940951.0249),
([
0.0, 42.0, 4.0, 479.0, -3678.0033024834297,
8209673.001421165, 11767.998552236539
], 148426180, 35942838893.32379),
([
0.0, 48.0, 4.0, 71.0, -951.0035145455234,
49882273.00063991, -23336.998167498707
], 157533313, 88431531357.62982),
([
0.0, 147.00394564757505, 122.98729664236723,
311.0047920137008, 2320.0, 46602185.0, 11212.0
], 118361306, 1111537045743.7646),
]
benchmarkLogging = ['cpu', 'disk', 'network', 'iostats', 'jstack']
benchmarkLogging = ['cpu', 'disk', 'network', 'iostats']
# IOStatus can hang?
benchmarkLogging = ['cpu', 'disk', 'network']
benchmarkLogging = []
for trial in range(6):
# IMPORT**********************************************
# since H2O deletes the source key, re-import every iteration.
# PARSE ****************************************
print "Parse starting: " + csvFilename
hex_key = csvFilename + "_" + str(trial) + ".hex"
start = time.time()
timeoutSecs = 2 * 3600
kwargs = {}
if FROM_HDFS:
parseResult = h2i.import_parse(
path=csvPathname,
schema='hdfs',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
pollTimeoutSecs=60,
retryDelaySecs=2,
benchmarkLogging=benchmarkLogging,
doSummary=False,
**kwargs)
else:
parseResult = h2i.import_parse(
path=csvPathname,
schema='local',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
pollTimeoutSecs=60,
retryDelaySecs=2,
benchmarkLogging=benchmarkLogging,
doSummary=False,
**kwargs)
elapsed = time.time() - start
fileMBS = (totalBytes / 1e6) / elapsed
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, 'Parse',
csvPathname, fileMBS, elapsed)
print "\n" + l
h2o.cloudPerfH2O.message(l)
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'],
timeoutSecs=300)
numRows = inspect['numRows']
numCols = inspect['numCols']
summary = h2o_cmd.runSummary(key=parseResult['destination_key'],
numRows=numRows,
numCols=numCols,
timeoutSecs=300)
h2o_cmd.infoFromSummary(summary)
# KMeans ****************************************
if not DO_KMEANS:
continue
print "col 0 is enum in " + csvFilename + " but KMeans should skip that automatically?? or no?"
kwargs = {
'k': 15,
'max_iter': 500,
# 'normalize': 1,
'normalize': 0, # temp try
'initialization': 'Furthest',
'destination_key': 'junk.hex',
# we get NaNs if whole col is NA
'ignored_cols': 'C1',
'normalize': 0,
# reuse the same seed, to get deterministic results
'seed': 265211114317615310,
}
if (trial % 3) == 0:
kwargs['initialization'] = 'PlusPlus'
elif (trial % 3) == 1:
kwargs['initialization'] = 'Furthest'
else:
kwargs['initialization'] = None
timeoutSecs = 4 * 3600
params = kwargs
paramsString = json.dumps(params)
start = time.time()
kmeansResult = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
benchmarkLogging=benchmarkLogging,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
print "kmeans result:", h2o.dump_json(kmeansResult)
l = '{!s} jvms, {!s}GB heap, {:s} {:s} {:s} for {:.2f} secs {:s}'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, "KMeans",
"trial " + str(trial), csvFilename, elapsed, paramsString)
print l
h2o.cloudPerfH2O.message(l)
# his does predict
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeansResult, csvPathname, parseResult, 'd', **kwargs)
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
# these clusters were sorted compared to the cluster order in training
h2o_kmeans.showClusterDistribution(self,
tupleResultList,
expected,
trial=trial)
# why is the expected # of rows not right in KMeans2. That means predictions are wrong
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
allowError=False,
allowRowError=True,
trial=trial)
# the tupleResultList has the size during predict? compare it to the sizes during training
# I assume they're in the same order.
model = kmeansResult['model']
size = model['size']
size2 = [t[1] for t in tupleResultList]
if 1 == 1: # debug
print "training size:", size
print "predict size2:", size2
print "training sorted(size):", sorted(size)
print "predict sorted(size2):", sorted(size2)
print h2o.nodes[0].http_addr
print h2o.nodes[0].port
clusters = model["centers"]
cluster_variances = model["within_cluster_variances"]
error = model["total_within_SS"]
iterations = model["iterations"]
normalized = model["normalized"]
max_iter = model["max_iter"]
print "iterations", iterations
if iterations >= (
max_iter -
1): # h2o hits the limit at max_iter-1..shouldn't hit it
raise Exception(
"trial: %s KMeans unexpectedly took %s iterations..which was the full amount allowed by max_iter %s",
(trial, iterations, max_iter))
# this size stuff should be compared now in compareResultsToExpected()..leave it here to make sure
# can't do this compare, because size2 is sorted by center order..
# so we don't know how to reorder size the same way
# we could just sort the two of them, for some bit of comparison.
if sorted(size) != sorted(size2):
raise Exception(
"trial: %s training cluster sizes: %s not the same as predict on same data: %s"
% (trial, size, size2))
# our expected result is sorted by cluster center ordered. but the sizes are from the predicted histogram
expectedSize = [t[1] / SCALE_SIZE for t in expected]
if size2 != expectedSize:
raise Exception(
"trial: %s training cluster sizes: %s not the same as expected: %s"
% (trial, size, expectedSize))
if DELETE_KEYS_EACH_ITER:
h2i.delete_keys_at_all_nodes()
def test_KMeans2_sphere5_inits(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
CLUSTERS = 5
SPHERE_PTS = 10000
csvFilename = 'syn_spheres100.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
expectedCenters = write_spheres_dataset(csvPathname, CLUSTERS,
SPHERE_PTS)
print "\nStarting", csvFilename
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=csvFilename + ".hex")
# try 5 times, to see if all inits by h2o are good
savedResults = []
Result = collections.namedtuple(
'Result',
'trial clusters size cluster_variances error iterations normalized max_iter clustersSorted'
)
# save the best for comparison. Print messages when we update best
sameAsBest = 0
# big number? to init
bestResult = Result(None, None, None, None, None, None, None, None,
None)
for trial in range(TRIALS):
# pass SEED so it's repeatable
kwargs = {
'normalize': 0,
'k': CLUSTERS,
'max_iter': MAX_ITER,
'initialization': INIT,
# 'initialization': 'PlusPlus',
'destination_key': 'syn_spheres100.hex',
'seed': SEED
}
timeoutSecs = 30
start = time.time()
kmeansResult = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.',\
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# see if we took the full limit to get an answer
# inspect of model doesn't work
# kmeansResult = h2o_cmd.runInspect(key='syn_spheres100.hex')
### print h2o.dump_json(kmeans)
### print h2o.dump_json(kmeansResult)
h2o_kmeans.simpleCheckKMeans(self, kmeansResult, **kwargs)
model = kmeansResult['model']
clusters = model["centers"]
size = model["size"]
cluster_variances = model["within_cluster_variances"]
# round to int to avoid fp error when saying "same"
error = int(model["total_within_SS"])
iterations = model["iterations"]
normalized = model["normalized"]
max_iter = model["max_iter"]
# clustersSorted = sorted(clusters, key=itemgetter(2))
clustersSorted = sorted(clusters)
r = Result(
trial,
clusters,
size,
cluster_variances,
error,
iterations,
normalized,
max_iter,
clustersSorted,
)
savedResults.append(r)
if iterations >= (
max_iter -
1): # h2o hits the limit at max_iter-1..shouldn't hit it
raise Exception(
"KMeans unexpectedly took %s iterations..which was the full amount allowed by max_iter %s",
(iterations, max_iter))
print "iterations", iterations
### print clustersSorted
# For now, just analyze the one with the lowest error
# we could analyze how many are not best, and how many are best (maybe just look at error
print "savedResults, error"
print r.error
if bestResult.error and r.error <= bestResult.error:
sameAsBest += 1
# we can check that if it has the same error, the sizes should be the same (integer) and reflects centers?
# should
if r.size != bestResult.size:
raise Exception(
"Would expect that if two trials got the same error (rounded to int), the cluster sizes would likely be the same? %s %s"
% (r.size, bestResult.size))
if not bestResult.error: # init case
bestResult = r
elif r.error < bestResult.error:
print "Trial", r.trial, "has a lower error", r.error, "than current lowest error", bestResult.error
print "Using it for best now"
bestResult = r
print "Trial #", trial, "completed"
print "\nApparently, %s out of %s trials, got the same best error: %s (lowest) " % (
sameAsBest, TRIALS, bestResult.error)
print "\nh2o best result was from trial %s, centers sorted:" % bestResult.trial
print bestResult.clustersSorted
print "\ngenerated centers for comparison"
print expectedCenters
for i, center in enumerate(expectedCenters):
a = center
bb = bestResult.clustersSorted
print "bb:", bb
b = bb[i]
print "\nexpected:", a
print "h2o:", b # h2o result
aStr = ",".join(map(str, a))
bStr = ",".join(map(str, b))
iStr = str(i)
self.assertAlmostEqual(a[0],
b[0],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
"; x not correct.")
self.assertAlmostEqual(a[1],
b[1],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
"; y not correct.")
self.assertAlmostEqual(a[2],
b[2],
delta=1,
msg=aStr + "!=" + bStr +
". Sorted cluster center " + iStr +
"; z not correct.")
def test_KMeans_fuzzy_centers_fvec(self):
h2o.beta_features = True
SYNDATASETS_DIR = h2o.make_syn_dir()
if DO_TWO_CLUSTER:
genCenters = [
[100, 100, 100, 100, 100, 100],
[200, 200, 200, 200, 200, 200],
]
genCenters = [
[100, 100],
[200, 200],
]
else:
genCenters = [
[100, 100, 100, 100, 100, 100],
[110, 110, 110, 110, 110, 110],
[120, 120, 120, 120, 120, 120],
[130, 130, 130, 130, 130, 130],
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
rowCount = 10000
expected = [(g, rowCount, None) for g in genCenters]
allowedDelta = (0.2, 0.2, 0.2, 0.2, 0.2, 0.2)
allowedDelta = (0.2, 0.2)
worstError = None
bestError = None
timeoutSecs = 60
hex_key = 'cA'
print "Generate synthetic dataset with first column constant = 0 and see what KMeans does"
csvFilename = 'syn_' + str(SEED) + "_" + str(rowCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
dataset = write_syn_dataset(csvPathname, rowCount, genCenters, SEED)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=csvFilename + ".hex")
print "Parse result['destination_key']:", parseResult[
'destination_key']
allErrors = []
for trial in range(10):
seed = random.randint(0, sys.maxint)
kwargs = {
'k': len(genCenters),
'initialization': 'PlusPlus',
'destination_key': 'k.hex',
'max_iter': 1000
}
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=60,
**kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
# save the predicted
h2o.nodes[0].csv_download(src_key='d',
csvPathname='kmeans_predict.csv')
# check center list (first center) has same number of cols as source data
self.assertEqual(
len(genCenters[0]), len(centers[0]),
"kmeans first center doesn't have same # of values as dataset row %s %s"
% (len(genCenters[0]), len(centers[0])))
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
trial=trial)
if h2o.beta_features:
error = kmeans['model']['total_within_SS']
within_cluster_variances = kmeans['model'][
'within_cluster_variances']
print "trial:", trial, "within_cluster_variances:", within_cluster_variances
else:
model_key = kmeans["_key"]
kmeansResult = h2o_cmd.runInspect(key=model_key)
error = kmeansResult['KMeansModel']['error']
# compute the sum of the squares of the distance for each cluster
# for each row, we
# returns a tuple of numers for each center
genDistances = calc_best_distance(centers, dataset)
print "trial:", trial, "genDistances:", genDistances
print "trial:", trial, "centers:", centers
print "trial:", trial, "error:", error
if (abs(genDistances - error)) > (.001 * genDistances):
raise Exception(
"genDistances: %s error: %s are too different" %
(genDistances, error))
if not bestError or error < bestError:
print 'Found smaller error:', error
bestError = error
bestCenters = centers
bestSeed = seed
bestTrial = trial
if not worstError or error > worstError:
print 'Found larger error:', error
worstError = error
allErrors.append(error)
print "bestTrial:", bestTrial
print "bestError:", bestError
print "worstError:", worstError
print "bestCenters:", bestCenters
print "bestSeed:", bestSeed
print "allErrors:", allErrors
def test_four_billion_rows(self):
timeoutSecs = 1500
importFolderPath = "billions"
csvFilenameList = [
("four_billion_rows.csv", "a.hex"),
("four_billion_rows.csv", "b.hex"),
]
for (csvFilename, hex_key) in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
start = time.time()
# Parse*********************************
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='local',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
pollTimeoutSecs=60)
elapsed = time.time() - start
print csvFilename, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult[
'destination_key']
print csvFilename, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
# Inspect*********************************
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
num_cols = inspect['num_cols']
num_rows = inspect['num_rows']
value_size_bytes = inspect['value_size_bytes']
row_size = inspect['row_size']
print "\n" + csvFilename, \
" num_rows:", "{:,}".format(num_rows), \
" num_cols:", "{:,}".format(num_cols), \
" value_size_bytes:", "{:,}".format(value_size_bytes), \
" row_size:", "{:,}".format(row_size)
expectedRowSize = num_cols * 1 # plus output
expectedValueSize = expectedRowSize * num_rows
self.assertEqual(row_size, expectedRowSize,
msg='row_size %s is not expected num_cols * 1 byte: %s' % \
(row_size, expectedRowSize))
self.assertEqual(value_size_bytes, expectedValueSize,
msg='value_size_bytes %s is not expected row_size * rows: %s' % \
(value_size_bytes, expectedValueSize))
summaryResult = h2o_cmd.runSummary(
key=parseResult['destination_key'], timeoutSecs=timeoutSecs)
h2o_cmd.infoFromSummary(summaryResult, noPrint=True)
self.assertEqual(
2,
num_cols,
msg="generated %s cols (including output). parsed to %s cols"
% (2, num_cols))
self.assertEqual(4 * 1000000000,
num_rows,
msg="generated %s rows, parsed to %s rows" %
(4 * 1000000000, num_rows))
# KMeans*********************************
kwargs = {
'k': 3,
'initialization': 'Furthest',
'epsilon': 1e-6,
'max_iter': 20,
'cols': None,
'normalize': 0,
'destination_key': 'junk.hex',
'seed': 265211114317615310,
}
timeoutSecs = 900
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
# GLM*********************************
print "\n" + csvFilename
kwargs = {
'x': 0,
'y': 1,
'n_folds': 0,
'case_mode': '=',
'case': 1
}
# one coefficient is checked a little more
colX = 0
# L2
timeoutSecs = 900
kwargs.update({'alpha': 0, 'lambda': 0})
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "glm (L2) end on ", csvFilename, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
h2o_glm.simpleCheckGLM(self, glm, colX, **kwargs)
def test_four_billion_rows_fvec(self):
h2o.beta_features = True
timeoutSecs = 1500
importFolderPath = "billions"
csvFilenameList = [
"four_billion_rows.csv",
]
for csvFilename in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
start = time.time()
# Parse*********************************
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='local',
timeoutSecs=timeoutSecs,
pollTimeoutSecs=180,
retryDelaySecs=3)
elapsed = time.time() - start
print "Parse result['destination_key']:", parseResult[
'destination_key']
print csvFilename, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
# Inspect*********************************
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
numCols = inspect['numCols']
numRows = inspect['numRows']
byteSize = inspect['byteSize']
print "\n" + csvFilename, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols), \
" byteSize:", "{:,}".format(byteSize)
expectedRowSize = numCols * 1 # plus output
# expectedValueSize = expectedRowSize * numRows
expectedValueSize = 8001271520
self.assertEqual(byteSize, expectedValueSize,
msg='byteSize %s is not expected: %s' % \
(byteSize, expectedValueSize))
summaryResult = h2o_cmd.runSummary(
key=parseResult['destination_key'], timeoutSecs=timeoutSecs)
h2o_cmd.infoFromSummary(summaryResult, noPrint=True)
self.assertEqual(
2,
numCols,
msg="generated %s cols (including output). parsed to %s cols"
% (2, numCols))
self.assertEqual(4 * 1000000000,
numRows,
msg="generated %s rows, parsed to %s rows" %
(4 * 1000000000, numRows))
# KMeans*********************************
kwargs = {
'k': 3,
'initialization': 'Furthest',
'max_iter': 10,
'normalize': 0,
'destination_key': 'junk.hex',
'seed': 265211114317615310,
}
timeoutSecs = 900
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
retryDelaySecs=4,
**kwargs)
# GLM*********************************
print "\n" + csvFilename
kwargs = {
'response': 'C1',
'n_folds': 0,
'family': 'binomial',
}
# one coefficient is checked a little more
colX = 1
# convert to binomial
execExpr = "A.hex=%s" % parseResult['destination_key']
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
execExpr = "A.hex[,%s]=(A.hex[,%s]==%s)" % ('1', '1', 1)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=180)
aHack = {'destination_key': "A.hex"}
# L2
timeoutSecs = 900
kwargs.update({'alpha': 0, 'lambda': 0})
start = time.time()
glm = h2o_cmd.runGLM(parseResult=aHack,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "glm (L2) end on ", csvFilename, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
h2o_glm.simpleCheckGLM(self, glm, "C" + str(colX), **kwargs)
def test_KMeans_libsvm_fvec(self):
h2o.beta_features = True
# just do the import folder once
# make the timeout variable per dataset. it can be 10 secs for covtype 20x (col key creation)
# so probably 10x that for covtype200
csvFilenameList = [
# FIX! fails KMeansScore
("colon-cancer.svm", "cA", 30, 1),
("connect4.svm", "cB", 30, 1),
("covtype.binary.svm", "cC", 30, 1),
# multi-label class
# ("tmc2007_train.svm", "cJ", 30, 1),
("mnist_train.svm", "cM", 30, 1),
("duke.svm", "cD", 30, 1),
# too many features? 150K inspect timeout?
# ("E2006.train.svm", "cE", 30, 1),
("gisette_scale.svm", "cF", 120, 1
), #Summary2 is slow with 5001 columns
("mushrooms.svm", "cG", 30, 1),
# ("news20.svm", "cH", 120, 1), #Summary2 is very slow - disable for now
("syn_6_1000_10.svm", "cK", 30, 1),
("syn_0_100_1000.svm", "cL", 30, 1),
]
### csvFilenameList = random.sample(csvFilenameAll,1)
# h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
firstDone = False
importFolderPath = "libsvm"
for (csvFilename, hex_key, timeoutSecs, resultMult) in csvFilenameList:
# have to import each time, because h2o deletes source after parse
csvPathname = importFolderPath + "/" + csvFilename
# PARSE******************************************
# creates csvFilename.hex from file in importFolder dir
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
hex_key=hex_key,
timeoutSecs=2000)
print "Parse result['destination_key']:", parseResult[
'destination_key']
# INSPECT******************************************
start = time.time()
inspect = h2o_cmd.runInspect(None,
parseResult['destination_key'],
timeoutSecs=360)
print "Inspect:", parseResult[
'destination_key'], "took", time.time() - start, "seconds"
h2o_cmd.infoFromInspect(inspect, csvFilename)
numRows = inspect['numRows']
numCols = inspect['numCols']
# KMEANS******************************************
for trial in range(1):
kwargs = {
'k': 3,
'initialization': 'Furthest',
'ignored_cols':
None, #range(11, numCols), # THIS BREAKS THE REST API
'max_iter': 10,
# 'normalize': 0,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
# fails if I put this in kwargs..i.e. source = dest
# 'destination_key': parseResult['destination_key'],
timeoutSecs = 600
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# this does an inspect of the model and prints the clusters
h2o_kmeans.simpleCheckKMeans(self, kmeans, **kwargs)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
def test_kmeans_iris_fvec(self):
h2o.beta_features = True
csvFilename = 'iris.csv'
csvPathname = 'iris/' + csvFilename
print "\nStarting", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
schema='put',
hex_key=hex_key)
k = 3
ignored_cols = 'C5'
for trial in range(3):
# reuse the same seed, to get deterministic results (otherwise sometimes fails
kwargs = {
'ignored_cols': ignored_cols, # ignore the output
'k': k,
'max_iter': 25,
'initialization': 'Furthest',
'destination_key': 'iris.hex',
'seed': 0,
}
timeoutSecs = 90
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeans, csvPathname, parseResult, 'd', **kwargs)
expected = [
# if ignored_cols isn't used
# ([5, 3.4, 1.46, 0.244, 0.0], 50, 15.24) ,
# ([5.9, 2.76, 4.26, 1.33, 1.02], 51, 32.9) ,
# ([6.6, 2.98, 5.57, 2.03, 2.0], 49, 39.15) ,
([
5.005999999999999, 3.4180000000000006, 1.464,
0.2439999999999999
], 50, 15.240400000000003),
([
5.901612903225807, 2.748387096774194, 4.393548387096775,
1.4338709677419357
], 62, 39.82096774193549),
([
6.8500000000000005, 3.073684210526315, 5.742105263157894,
2.0710526315789473
], 38, 23.87947368421053),
]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
trial=trial)
gs = h2o.nodes[0].gap_statistic(source=hex_key,
ignored_cols=ignored_cols,
k_max=k)
print "gap_statistic:", h2o.dump_json(gs)
k_best = gs['gap_model']['k_best']
self.assertTrue(k_best != 0,
msg="k_best shouldn't be 0: %s" % k_best)
def test_kmeans2_sphere100(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = 'syn_spheres100.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
centersList = write_spheres_dataset(csvPathname, CLUSTERS, SPHERE_PTS)
if SHUFFLE_SPHERES:
# since we create spheres in order
csvFilename2 = 'syn_spheres100_shuffled.csv'
csvPathname2 = SYNDATASETS_DIR + '/' + csvFilename2
h2o_util.file_shuffle(csvPathname, csvPathname2)
else:
csvFilename2 = csvFilename
csvPathname2 = csvPathname
print "\nStarting", csvFilename
parseResult = h2i.import_parse(path=csvPathname2, schema='put', hex_key=csvFilename2 + ".hex")
### h2b.browseTheCloud()
# try 5 times, to see if all inits by h2o are good
# does it break if cols is not specified?
cols = ",".join(map(str,range(DIMENSIONS)))
for trial in range(10):
kwargs = {
'k': CLUSTERS,
'initialization': 'Furthest',
'destination_key': 'syn_spheres100.hex',
'max_iter': 15,
}
timeoutSecs = 100
start = time.time()
kmeansResult = h2o_cmd.runKMeans(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.',\
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
# can't inspect a kmeans2 model
# kmeansResult = h2o_cmd.runInspect(key='syn_spheres100.hex')
# print h2o.dump_json(kmeansResult)
### print h2o.dump_json(kmeans)
### print h2o.dump_json(kmeansResult)
h2o_kmeans.simpleCheckKMeans(self, kmeansResult, **kwargs)
# cluster centers can return in any order
model = kmeansResult['model']
clusters = model["centers"]
cluster_variances = model["within_cluster_variances"]
error = model["total_within_SS"]
iterations = model["iterations"]
normalized = model["normalized"]
max_iter = model["max_iter"]
# the way we create the centers above, if we sort on the sum of xyz
# we should get the order the same as when they were created.
# to be safe, we'll sort the centers that were generated too, the same way
clustersSorted = sorted(clusters, key=sum)
centersSorted = sorted(centersList, key=sum)
### print clustersSorted
print "\ntrial #", trial, "h2o result, centers (sorted by key=sum)"
cf = '{0:6.2f}'
for c in clustersSorted:
print ' '.join(map(cf.format,c))
print "\ngenerated centers (sorted by key=sum)"
for c in centersSorted:
print ' '.join(map(cf.format,c))
for i,center in enumerate(centersSorted):
# Doing the compare of gen'ed/actual centers is kind of a hamming distance problem.
# Assuming that the difference between adjacent sums of all center values,
# is greater than 2x the sum of all max allowed variance on each value,
# Then the sums will be unique and non-overlapping with allowed variance.
# So a sort of the centers, keyed on sum of all values for a center.
# will create an ordering that can be compared.
# sort gen'ed and actual separately.
# Adjacent center hamming distance check is done during gen above.
a = center
b = clustersSorted[i]
print "\nexpected:", a
print "h2o:", b # h2o result
aStr = ",".join(map(str,a))
bStr = ",".join(map(str,b))
iStr = str(i)
for i, v in enumerate(a):
emsg = aStr+" != "+bStr+". Sorted cluster center "+iStr+" axis "+str(i)+" not correct."
self.assertAlmostEqual(a[i], b[i], delta=ALLOWED_CENTER_DELTA, msg=emsg)
print "Trial #", trial, "completed"
def test_KMeans_covtype_fvec(self):
csvFilenameList = [
('covtype.data', 800),
]
importFolderPath = "standard"
for csvFilename, timeoutSecs in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000,
pollTimeoutSecs=60)
inspect = h2o_cmd.runInspect(None, parseResult['destination_key'])
print "\n" + csvPathname, \
" numRows:", "{:,}".format(inspect['numRows']), \
" numCols:", "{:,}".format(inspect['numCols'])
for trial in range(2):
kwargs = {
'k': 6,
'initialization': 'Furthest',
# 'initialization': '',
# 'ignored_cols': range(11, inspect['numCols']),
# ignore the response
'ignored_cols_by_name': 'C55',
'max_iter': 100,
# 'normalize': 0,
# reuse the same seed, to get deterministic results
'seed': 265211114317615310
}
start = time.time()
kmeansResult = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
h2o_kmeans.simpleCheckKMeans(self, kmeansResult, **kwargs)
expected = [
([
2781.64184460309, 162.69950733599902,
16.545275983574268, 243.73547234768156,
50.48239522121315, 942.4480922085701,
208.3915356763203, 218.7135425941215,
140.10956243018794, 1040.6795741397266,
0.22024185323685105, 0.0845245225799837,
0.4957505706376572, 0.19948305354550802,
0.01635558145683929, 0.033196811983660604,
0.026025394050259283, 0.04566180477986607,
0.008617572941792261, 0.03547936261257615, 0.0, 0.0,
0.006189327591882107, 0.13606268110663236,
0.037222303163733886, 0.024007252359445064,
0.040891651692487006, 0.003232264365769295,
1.6188302332734367e-05, 0.004667627172605076,
0.00910861811255187, 9.173371321882807e-05,
0.0025415634662392956, 0.008946735089224526,
0.0023095311328034363, 0.04957397784361021,
0.09252154393235448, 0.03887890610245037, 0.0, 0.0,
0.0010792201555156243, 0.004867282901375466,
0.08281935473426902, 0.045640220376755754,
0.04933654940939677, 0.08426550974265995,
0.07772003949945769, 0.001327440791284218,
0.0014191745045030462, 0.0, 0.0, 0.009513325670870229,
0.010970272880816322, 0.009443176360761713
], 185319, 116283720155.37769),
([
2892.8730376693256, 119.94759695676377,
11.22516236778623, 189.0301354611245,
24.621525329374652, 2631.9842642419744,
219.94967526442753, 223.3794395991835,
135.71226572647987, 5409.1797365002785,
0.883243644460939, 0.11675635553906105, 0.0, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0015587307478196325,
0.0, 0.0, 0.0, 0.23410651326776769, 0.0, 0.0, 0.0,
0.026498422712933754, 0.0, 0.04152904063833735,
0.005158656522545927, 0.0695490814622379, 0.0,
0.0634997216552236, 0.05418444980515866,
0.010391538318797551, 0.0002969010948227871, 0.0, 0.0,
0.0, 0.3677862312117276, 0.07596956763778066, 0.0,
0.01109667841900167, 0.005641120801632956, 0.0,
0.0018185192057895714, 0.0, 0.0, 0.0021154203006123586,
0.018444980515865652, 0.010354425681944703
], 26945, 46932273891.61873),
([
3022.020861415003, 137.8546989122598, 13.3449108178427,
282.99227296949937, 45.23691263596753,
1606.0215197015768, 216.64941537882825,
222.64791856054669, 137.40339644525253,
2529.4366555907336, 0.4113429046111407,
0.08617284724616782, 0.5024842481426914, 0.0, 0.0,
0.0052506191028494405, 0.0, 0.014176671577693489, 0.0,
0.0, 0.0, 0.0, 0.0, 0.018949249239835743,
0.029850161436945546, 0.05403435628977148,
0.020892761982382997, 0.0, 0.0, 0.0018494718033917432,
0.011731607159650168, 0.005979436381304661,
0.0047098837027052445, 0.013714303626845553,
0.0007601642581737249, 0.047788470580859534,
0.10631328171530674, 0.04641704021817498,
0.0036519231372057308, 0.011872668568383437, 0.0,
0.00034481677690354536, 0.17267483777937995,
0.044473527475627724, 0.05637754302372967,
0.1292435973793925, 0.11970627880003762,
0.0013871038525438075, 0.004858781856368139, 0.0, 0.0,
0.03151155136202627, 0.028988119494686687,
0.012491771417823892
], 127604, 95229063588.02844),
([
3051.365089986695, 168.1268450579292,
14.114846831985933, 287.6101588092033,
50.702549817536706, 2835.266162979793,
209.89460702308608, 226.92302305495684,
148.84282479633362, 1461.8985753079312,
0.3284728328107128, 0.0006069141527711857,
0.670920253036516, 0.0, 0.0, 0.0054700083256172235,
0.0, 0.01653452018767653, 0.0, 0.0, 0.0, 0.0, 0.0,
0.03886584862938554, 0.013250959002170886,
0.04277966681969203, 0.05480901656564399, 0.0, 0.0,
0.0010426473906581905, 0.0018440853103432178, 0.0,
0.0035014278044491476, 0.011671426014830491,
0.002435437561761296, 0.044405885511091744,
0.10662236712081483, 0.042756323967662366, 0.0,
0.007384122192049426, 0.006263665294625696, 0.0,
0.14390868276285998, 0.022152366576148275,
0.07071327974851968, 0.14799368186805065,
0.1011367968938445, 0.009111493242244337,
0.006427065258833325, 0.0009259331305098857,
0.002318723301612991, 0.03055579330682623,
0.041044514818820564, 0.024074261393257027
], 128519, 106432862495.53804),
([
3052.088693852026, 149.15056174929376,
11.549996765359152, 328.4748452763461,
44.2420589567205, 4786.68757682272, 215.8348392383499,
226.91413106764713, 143.9780260065124,
4192.589071226791, 0.8949819938326181, 0.0,
0.10501800616738188, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
0.0022642485929312314, 0.002415198499126647, 0.0,
0.00012938563388178466, 0.0, 0.1351648588618377, 0.0,
0.0, 0.0, 0.014836219351777974, 0.0, 0.0,
0.010674314795247235, 0.03553792077286352, 0.0,
0.039290104155435275, 0.09289888512712138,
0.03864317598602636, 0.0, 0.0, 0.0, 0.0,
0.4371509283419232, 0.08636491061609126,
0.0003665926293317232, 0.002717098311517478,
0.017100467944709204, 0.0, 0.0028249196730856323, 0.0,
0.0, 0.03226015138119164, 0.017316110667845514,
0.03204450865805533
], 46373, 77991941653.19676),
([
3119.4885286481917, 165.13178470083923,
11.672206122079334, 271.2690333876713,
39.407851838435064, 4959.81440560285,
212.5861709835175, 227.95909557447322,
148.6725381875264, 1613.4457676749382,
0.9052556903942522, 0.0, 0.09474430960574776, 0.0, 0.0,
0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.00037734709895550323,
0.0, 0.0, 0.0, 0.008346917828895732,
0.0021584254060254783, 0.0, 0.0, 0.0031395278633097865,
0.0, 0.0, 0.02815009358208054, 0.012512829801364487,
0.0, 0.13355068526233171, 0.11424560767976816,
0.008799734347642335, 0.0, 0.0018867354947775161,
0.0012226046006158305, 0.0, 0.44056028497252914,
0.10774014369377528, 0.0033810300066413087,
0.014580691903640641, 0.02313892410795146,
0.0002565960272897422, 3.018776791644026e-05, 0.0, 0.0,
0.06503954597597053, 0.022625732053371973,
0.008256354525146411
], 66252, 74666940350.2879),
]
### print h2o.dump_json(kmeans)
predictKey = 'd'
(centers, tupleResultList) = h2o_kmeans.bigCheckResults(
self, kmeansResult, csvPathname, parseResult, predictKey,
**kwargs)
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
# these clusters were sorted compared to the cluster order in training
h2o_kmeans.showClusterDistribution(self,
tupleResultList,
expected,
trial=trial)
# why is the expected # of rows not right in KMeans2. That means predictions are wrong
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
allowError=False,
allowRowError=True,
trial=trial)
print "Trial #", trial, "completed\n"
def test_four_billion_rows(self):
timeoutSecs = 1500
importFolderPath = "billions"
csvFilenameList = [
("four_billion_rows.csv", "a.hex"),
("four_billion_rows.csv", "b.hex"),
]
for (csvFilename, hex_key) in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
start = time.time()
# Parse*********************************
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='local',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
pollTimeoutSecs=60)
elapsed = time.time() - start
print "Parse result['destination_key']:", parseResult[
'destination_key']
print csvFilename, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
# Inspect*********************************
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
numCols = inspect['numCols']
numRows = inspect['numRows']
byteSize = inspect['byteSize']
print "\n" + csvFilename, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
summaryResult = h2o_cmd.runSummary(
key=parseResult['destination_key'], timeoutSecs=timeoutSecs)
h2o_cmd.infoFromSummary(summaryResult, noPrint=True)
self.assertEqual(
2,
numCols,
msg="generated %s cols (including output). parsed to %s cols"
% (2, numCols))
self.assertEqual(4 * 1000000000,
numRows,
msg="generated %s rows, parsed to %s rows" %
(4 * 1000000000, numRows))
# KMeans*********************************
kwargs = {
'k': 3,
'initialization': 'Furthest',
'max_iter': 20,
'normalize': 0,
'destination_key': 'junk.hex',
'seed': 265211114317615310,
}
timeoutSecs = 900
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
# Exec to make binomial########################
execExpr = "%s[,%s]=(%s[,%s]==%s)" % (hex_key, 1 + 1, hex_key,
1 + 1, 0)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=30)
# GLM*********************************
print "\n" + csvFilename
colX = 0
kwargs = {
'response': 'C2',
'n_folds': 0,
'cols': colX,
'alpha': 0,
'lambda': 0,
'family': 'binomial',
# 'link' can be family_default, identity, logit, log, inverse, tweedie
}
# one coefficient is checked a little more
# L2
timeoutSecs = 900
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "glm (L2) end on ", csvFilename, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
def kmeans_doit(self,
csvFilename,
bucket,
csvPathname,
numRows,
timeoutSecs=30):
print "\nStarting KMeans of", csvFilename
parseResult = h2i.import_parse(bucket=bucket,
path=csvPathname,
schema='put',
hex_key=csvFilename + ".hex",
timeoutSecs=20)
# hastie has two values, 1 and -1.
# we could not specify cols, but this is more fun
kwargs = {
'k': 1,
'initialization': 'Furthest',
'destination_key': 'KMeansModel.hex',
'max_iter': 25,
# reuse the same seed, to get deterministic results (otherwise sometimes fails
'seed': 265211114317615310,
}
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult, \
timeoutSecs=timeoutSecs, retryDelaySecs=2, pollTimeoutSecs=60, **kwargs)
elapsed = time.time() - start
print "kmeans end on ", csvPathname, 'took', elapsed, 'seconds.', \
"%d pct. of timeout" % ((elapsed/timeoutSecs) * 100)
(centers,
tupleResultList) = h2o_kmeans.bigCheckResults(self, kmeans, csvPathname,
parseResult, 'd', **kwargs)
expected = [([
-0.0006628900000000158, -0.0004671200060434639, 0.0009330300069879741,
0.0007883800000000272, 0.0007548200000000111, 0.0005617899864856153,
0.0013246499999999897, 0.0004036299999999859, -0.0014307100000000314,
0.0021324000161308796, 0.00154
], numRows, None)]
# all are multipliers of expected tuple value
allowedDelta = (0.01, 0.01, 0.01)
h2o_kmeans.compareResultsToExpected(self,
tupleResultList,
expected,
allowedDelta,
trial=0)
# compare this kmeans to the first one. since the files are replications, the results
# should be similar?
# inspect doesn't work
# inspect = h2o_cmd.runInspect(None, key=kmeans['model']['_key'])
# KMeansModel = inspect['KMeansModel']
modelView = h2o.nodes[0].kmeans_view(model='KMeansModel.hex')
h2o.verboseprint("KMeans2ModelView:", h2o.dump_json(modelView))
model = modelView['model']
clusters = model['centers']
within_cluster_variances = model['within_cluster_variances']
total_within_SS = model['total_within_SS']
print "within_cluster_variances:", within_cluster_variances
print "total_within_SS:", total_within_SS
if self.clusters1:
h2o_kmeans.compareToFirstKMeans(self, clusters, self.clusters1)
else:
self.clusters1 = copy.deepcopy(clusters)
def test_four_billion_rows(self):
h2o.beta_features = False
timeoutSecs = 1500
importFolderPath = "billions"
csvFilenameList = [
"four_billion_rows.csv",
]
for csvFilename in csvFilenameList:
csvPathname = importFolderPath + "/" + csvFilename
start = time.time()
# Parse*********************************
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
schema='local',
timeoutSecs=timeoutSecs,
pollTimeoutSecs=180)
elapsed = time.time() - start
print "Parse result['destination_key']:", parseResult[
'destination_key']
print csvFilename, "completed in", elapsed, "seconds.", "%d pct. of timeout" % (
(elapsed * 100) / timeoutSecs)
# Inspect*********************************
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
num_cols = inspect['num_cols']
num_rows = inspect['num_rows']
# forget about checking the bytesize
print "\n" + csvFilename, \
" num_rows:", "{:,}".format(num_rows), \
" num_cols:", "{:,}".format(num_cols)
expectedRowSize = num_cols * 1 # plus output
# expectedValueSize = expectedRowSize * num_rows
summaryResult = h2o_cmd.runSummary(
key=parseResult['destination_key'], timeoutSecs=timeoutSecs)
h2o_cmd.infoFromSummary(summaryResult, noPrint=True)
self.assertEqual(
2,
num_cols,
msg="generated %s cols (including output). parsed to %s cols"
% (2, num_cols))
self.assertEqual(4 * 1000000000,
num_rows,
msg="generated %s rows, parsed to %s rows" %
(4 * 1000000000, num_rows))
# KMeans*********************************
kwargs = {
'k': 3,
'cols': 'C1, C2',
'initialization': 'Furthest',
'max_iter': 4,
'normalize': 0,
'destination_key': 'junk.hex',
'seed': 265211114317615310,
}
timeoutSecs = 900
start = time.time()
kmeans = h2o_cmd.runKMeans(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
# GLM*********************************
print "\n" + csvFilename
kwargs = {
'y': 'C2',
'n_folds': 0,
'family': 'binomial',
'case_mode': '=',
'case': 1
}
# L2
timeoutSecs = 900
kwargs.update({'alpha': 0, 'lambda': 0})
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
elapsed = time.time() - start
print "glm (L2) end on ", csvFilename, 'took', elapsed, 'seconds.', "%d pct. of timeout" % (
(elapsed / timeoutSecs) * 100)
h2o_glm.simpleCheckGLM(self, glm, 'C1', **kwargs)
