def test_parse_manyfile_hack(self):
for trial in range(2):
importFolderPath = "/home/0xdiag/datasets/manyfiles-nflx-gz"
importList = []
maxi = 50
# 4-9 don't exist?
for i in range(10, 10+maxi+1):
csvFilename = "file_%s.dat.gz" % i
csvPathname = importFolderPath + "/" + csvFilename
importResult = h2o.n0.import_files(path=csvPathname)
# just 1!
import_key = importResult['keys'][0]
assert len(importResult['keys'])==1
assert len(importResult['files'])==1
assert len(importResult['fails'])==0
assert len(importResult['dels'])==0
importList.append(import_key)
timeoutSecs = 800
parseResult = h2o.n0.parse(key=importList, timeoutSecs=timeoutSecs)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
assert numRows == (maxi * 100000)
assert numCols == 542
def test_parse_rand_utf8(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
print "HACK: reduce rows to 10 for debug"
tryList = [
# do two cols to detect bad eol behavior
(10, 2, 'cA', 120),
(10, 2, 'cG', 120),
(10, 2, 'cH', 120),
]
print "What about messages to log (INFO) about unmatched quotes (before eol)"
# got this ..trying to avoid for now
# Exception: rjson error in parse: Argument 'source_key' error: Parser setup appears to be broken, got AUTO
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "\nCreating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEED=SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname, schema='put', check_header=0,
hex_key=hex_key, timeoutSecs=timeoutSecs, doSummary=False)
print "parseResult:", dump_json(parseResult)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert len(missingList) == 0
# FIX! check type?
# print "inspect:", h2o.dump_json(inspect)
self.assertEqual(numRows, rowCount, msg='Wrong numRows: %s %s' % (numRows, rowCount))
self.assertEqual(numCols, colCount, msg='Wrong numCols: %s %s' % (numCols, colCount))
def test_parse_rand_utf8(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
print "HACK: reduce rows to 10 for debug"
tryList = [
# do two cols to detect bad eol behavior
(10, 2, 'cA', 120),
(10, 2, 'cG', 120),
(10, 2, 'cH', 120),
]
print "What about messages to log (INFO) about unmatched quotes (before eol)"
# got this ..trying to avoid for now
# Exception: rjson error in parse: Argument 'source_key' error: Parser setup appears to be broken, got AUTO
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "\nCreating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEED=SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname, schema='put', checkHeader=0,
hex_key=hex_key, timeoutSecs=timeoutSecs, doSummary=False)
print "parseResult:", dump_json(parseResult)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert len(missingList) == 0
# FIX! check type?
# print "inspect:", h2o.dump_json(inspect)
self.assertEqual(numRows, rowCount, msg='Wrong numRows: %s %s' % (numRows, rowCount))
self.assertEqual(numCols, colCount, msg='Wrong numCols: %s %s' % (numCols, colCount))
def test_kmeans_benign(self):
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, checkHeader=1,
timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
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
# no cols ignored
labelListUsed = list(labelList)
numColsUsed = numCols
for trial in range(5):
kmeansSeed = random.randint(0, sys.maxint)
# kmeansSeed = 6655548259421773879
parameters = {
'validation_frame': parse_key,
'ignored_columns': None,
'score_each_iteration': False,
'K': 4,
'max_iters': 50,
'normalize': False,
'seed': kmeansSeed,
'init': 'PlusPlus',
}
model_key = 'benign_k.hex'
kmeansResult = h2o.n0.build_model(
algo='kmeans',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
modelResult = h2o.n0.models(key=model_key)
# this prints too
tuplesSorted, iters, mse, names = \
h2o_kmeans.simpleCheckKMeans(self, modelResult, parameters, numRows, numColsUsed, labelListUsed)
h2o_cmd.runStoreView()
# zip with * is it's own inverse here. It's sorted by centers for easy comparisons
ids, mses, rows, clusters = zip(*tuplesSorted)
def test_parse_manyfile_hack(self):
for trial in range(2):
importFolderPath = "/home/0xdiag/datasets/manyfiles-nflx-gz"
importList = []
maxi = 50
# 4-9 don't exist?
for i in range(10, 10 + maxi + 1):
csvFilename = "file_%s.dat.gz" % i
csvPathname = importFolderPath + "/" + csvFilename
importResult = h2o.n0.import_files(path=csvPathname)
# just 1!
import_key = importResult['keys'][0]
assert len(importResult['keys']) == 1
assert len(importResult['files']) == 1
assert len(importResult['fails']) == 0
assert len(importResult['dels']) == 0
importList.append(import_key)
timeoutSecs = 800
parseResult = h2o.n0.parse(key=importList, timeoutSecs=timeoutSecs)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspectResult)
assert numRows == (maxi * 100000)
assert numCols == 542
def test_GBM_covtype_train_test(self):
bucket = 'home-0xdiag-datasets'
importFolderPath = 'standard'
trainFilename = 'covtype.shuffled.90pct.data'
train_key = 'covtype.train.hex'
model_key = 'GBMModelKey'
timeoutSecs = 1800
csvPathname = importFolderPath + "/" + trainFilename
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key=train_key, timeoutSecs=timeoutSecs)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
labelListUsed = list(labelList)
numColsUsed = numCols
parameters = {
'validation_frame': train_key,
'ignored_columns': None,
'score_each_iteration': True,
'response_column': 'C55',
'do_classification': True,
# 'balance_classes':
# 'max_after_balance_size':
'ntrees': 2,
'max_depth': 10,
'min_rows': 3,
'nbins': 40,
'learn_rate': 0.2,
# FIX! doesn't like it?
# 'loss': 'Bernoulli',
# FIX..no variable importance for GBM yet?
'variable_importance': False,
# 'seed':
}
model_key = 'benign_gbm.hex'
bmResult = h2o.n0.build_model(
algo='gbm',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=60)
bm = OutputObj(bmResult, 'bm')
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0]['output'], 'model')
cmmResult = h2o.n0.compute_model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
cmm = OutputObj(cmmResult, 'cmm')
mmResult = h2o.n0.model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
mm = OutputObj(mmResult, 'mm')
prResult = h2o.n0.predict(model=model_key, frame=parse_key, timeoutSecs=60)
pr = OutputObj(prResult['model_metrics'][0]['predictions'], 'pr')
def test_parse_syn_gz_cat(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
# summary fails with 100000 cols
# overwrite the key each time to save space?
(100, 100, 'cF', 600),
(100, 5000, 'cF', 600),
(100, 10000, 'cF', 600),
# (100, 12000, 'cF', 600),
# (100, 15000, 'cF', 600),
# (100, 17000, 'cF', 600),
(100, 20000, 'cF', 600),
(100, 40000, 'cF', 600),
]
# h2b.browseTheCloud()
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
csvFilenamegz = csvFilename + ".gz"
csvPathnamegz = SYNDATASETS_DIR + '/' + csvFilenamegz
h2o_util.file_gzip(csvPathname, csvPathnamegz)
start = time.time()
print "Parse start:", csvPathnamegz
parseResult = h2i.import_parse(path=csvPathnamegz, schema='put', hex_key=hex_key,
timeoutSecs=timeoutSecs, doSummary=DOSUMMARY)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
if DOSUMMARY:
algo = "Parse and Summary:"
else:
algo = "Parse:"
print algo , parse_key, "took", time.time() - start, "seconds"
print "Inspecting.."
start = time.time()
inspect = h2o_cmd.runInspect(key=parse_key, timeoutSecs=timeoutSecs)
print "Inspect:", parse_key, "took", time.time() - start, "seconds"
missingValuesList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
print "\n" + csvPathnamegz, \
"\n numRows:", "{:,}".format(numRows), \
"\n numCols:", "{:,}".format(numCols)
self.assertEqual(len(missingValuesList), 0,
"Don't expect any missing values. These cols had some: %s" % missingValuesList)
# should match # of cols in header or ??
self.assertEqual(numCols, colCount,
"parse created result with the wrong number of cols %s %s" % (numCols, colCount))
self.assertEqual(numRows, rowCount,
"parse created result with the wrong number of rows (header shouldn't count) %s %s" % \
(numRows, rowCount))
def test_50_nongz_fvec(self):
avgMichalSize = 237270000 * 2
bucket = 'home-0xdiag-datasets'
importFolderPath = "many_many"
print "Using non-gz'ed files in", importFolderPath
csvFilenameList= [
("*.dat", "file_18_A.dat", 18 * avgMichalSize, 1800),
]
pollTimeoutSecs = 120
retryDelaySecs = 10
for trial, (csvFilepattern, csvFilename, totalBytes, timeoutSecs) in enumerate(csvFilenameList):
csvPathname = importFolderPath + "/" + csvFilepattern
(importResult, importPattern) = h2i.import_only(bucket=bucket, path=csvPathname, schema='local')
importFullList = importResult['files']
importFailList = importResult['fails']
print "\n Problem if this is not empty: importFailList:", h2o.dump_json(importFailList)
start = time.time()
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='local',
hex_key=csvFilename + ".hex", timeoutSecs=timeoutSecs,
retryDelaySecs=retryDelaySecs,
pollTimeoutSecs=pollTimeoutSecs)
elapsed = time.time() - start
print "Parse #", trial, "completed in", "%6.2f" % elapsed, "seconds.", \
"%d pct. of timeout" % ((elapsed*100)/timeoutSecs)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
h2o_cmd.columnInfoFromInspect(parse_key, exceptionOnMissingValues=False)
if totalBytes is not None:
fileMBS = (totalBytes/1e6)/elapsed
msg = '{!s} jvms, {!s}GB heap, {:s} {:s} {:6.2f} MB/sec for {:.2f} secs'.format(
len(h2o.nodes), h2o.nodes[0].java_heap_GB, csvFilepattern, csvFilename, fileMBS, elapsed)
print msg
def test_exec2_enums_rand_cut(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
n = ROWS
tryList = [
(n, 10, 9, 'cE', 300),
]
# create key names to use for exec
eKeys = ['e%s' % i for i in range(10)]
# h2b.browseTheCloud()
trial = 0
for (rowCount, iColCount, oColCount, hex_key, timeoutSecs) in tryList:
colCount = iColCount + oColCount
hex_key = 'p'
colEnumList = create_col_enum_list(iColCount)
# create 100 possible cut expressions here, so we don't waste time below
rowExprList = []
print "Creating", CUT_EXPR_CNT, 'cut expressions'
for j in range(CUT_EXPR_CNT):
# init cutValue. None means no compare
cutValue = [None for i in range(iColCount)]
# build up a random cut expression
cols = random.sample(range(iColCount),
random.randint(1, iColCount))
for c in cols:
# possible choices within the column
cel = colEnumList[c]
# for now the cutValues are numbers for the enum mappings
# FIX! hack. don't use encoding 0, maps to NA here? h2o doesn't like
# celChoice = str(random.choice(range(len(cel))))
celChoice = random.choice(range(len(cel)))
cutValue[c] = celChoice
cutExprList = []
pKey = Key('p')
for i, c in enumerate(cutValue):
if c is None:
continue
else:
# new ...ability to reference cols
# src[ src$age<17 && src$zip=95120 && ... , ]
# cutExprList.append('p$C'+str(i+1)+'=='+c)
# all column indexing in h2o-dev is with number
e = Fcn('==', c, pKey[:, i])
cutExprList.append(e)
cutExpr = None
for ce in cutExprList:
if cutExpr:
cutExpr = Fcn('&', cutExpr, ce)
else:
cutExpr = ce
print "cutExpr:", cutExpr
# should be two different keys in the sample
e = random.sample(eKeys, 2)
fKey = e[0]
eKey = e[1]
# rowExpr = '%s[%s,];' % (hex_key, cutExpr)
hKey = Key(hex_key)
rowExpr = hKey[cutExpr, :]
print "rowExpr:", rowExpr
rowExprList.append(rowExpr)
# CREATE DATASET*******************************************
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_enums_' + str(rowCount) + 'x' + str(
colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname,
rowCount,
iColCount,
oColCount,
SEEDPERFILE,
colEnumList=colEnumList)
# PARSE*******************************************************
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=30)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, valueList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
# print h2o.dump_json(inspect)
# (missingValuesDict, constantValuesDict, enumSizeDict, colTypeDict, colNameDict) = \
# h2o_cmd.columnInfoFromInspect(parse_key, exceptionOnMissingValues=False)
# error if any col has constant values
# if len(constantValuesDict) != 0:
# raise Exception("Probably got a col NA'ed and constant values as a result %s" % constantValuesDict)
# INIT all possible key names used***************************
# remember. 1 indexing!
# build up the columns
Assign('b', [1, 2, 3])
# could also append 1 col at a time, by assigning to the next col number?
Assign('a', Cbind(['b' for i in range(colCount)]))
for eKey in eKeys:
Assign(eKey, 'a')
## print h2o.dump_json(e)
xList = []
eList = []
fList = []
for repeat in range(200):
# EXEC*******************************************************
# don't use exec_expr to avoid issues with Inspect following etc.
randICol = random.randint(0, iColCount - 1)
randOCol = random.randint(iColCount, iColCount + oColCount - 1)
# should be two different keys in the sample
e = random.sample(eKeys, 2)
fKey = e[0]
eKey = e[1]
if 1 == 1:
start = time.time()
Assign(fKey, random.choice(rowExprList)).do()
elapsed = time.time() - start
execTime = elapsed
print "exec 2 took", elapsed, "seconds."
inspect = h2o_cmd.runInspect(key=fKey)
missingList, valueList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
if numRows == 0 or numCols != colCount:
h2p.red_print("Warning: Cut resulted in", numRows,
"rows and", numCols,
"cols. Quantile will abort")
# FIX! put quantile back in?
quantileTime = 0
# remove all keys*******************************************************
# what about hex_key?
if 1 == 0:
start = time.time()
h2o.nodes[0].remove_all_keys()
elapsed = time.time() - start
print "remove all keys end on ", csvFilename, 'took', elapsed, 'seconds.'
trial += 1
xList.append(trial)
eList.append(execTime)
fList.append(quantileTime)
# just get a plot of the last one (biggest)
if DO_PLOT:
xLabel = 'trial'
eLabel = 'exec cut time'
fLabel = 'quantile time'
eListTitle = ""
fListTitle = ""
h2o_gbm.plotLists(xList, xLabel, eListTitle, eList, eLabel,
fListTitle, fList, fLabel)
def test_exec2_enums_rand_cut(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
n = ROWS
tryList = [
(n, 10, 9, 'cE', 300),
]
# create key names to use for exec
eKeys = ['e%s' % i for i in range(10)]
# h2b.browseTheCloud()
trial = 0
for (rowCount, iColCount, oColCount, hex_key, timeoutSecs) in tryList:
colCount = iColCount + oColCount
hex_key = 'p'
colEnumList = create_col_enum_list(iColCount)
# create 100 possible cut expressions here, so we don't waste time below
rowExprList = []
print "Creating", CUT_EXPR_CNT, 'cut expressions'
for j in range(CUT_EXPR_CNT):
# init cutValue. None means no compare
cutValue = [None for i in range(iColCount)]
# build up a random cut expression
cols = random.sample(range(iColCount), random.randint(1,iColCount))
for c in cols:
# possible choices within the column
cel = colEnumList[c]
# for now the cutValues are numbers for the enum mappings
# FIX! hack. don't use encoding 0, maps to NA here? h2o doesn't like
# celChoice = str(random.choice(range(len(cel))))
celChoice = random.choice(range(len(cel)))
cutValue[c] = celChoice
cutExprList = []
pKey = Key('p')
for i,c in enumerate(cutValue):
if c is None:
continue
else:
# new ...ability to reference cols
# src[ src$age<17 && src$zip=95120 && ... , ]
# cutExprList.append('p$C'+str(i+1)+'=='+c)
# all column indexing in h2o-dev is with number
e = Fcn('==', c, pKey[:,i])
cutExprList.append(e)
cutExpr = None
for ce in cutExprList:
if cutExpr:
cutExpr = Fcn('&', cutExpr, ce)
else:
cutExpr = ce
print "cutExpr:", cutExpr
# should be two different keys in the sample
e = random.sample(eKeys,2)
fKey = e[0]
eKey = e[1]
# rowExpr = '%s[%s,];' % (hex_key, cutExpr)
hKey = Key(hex_key)
rowExpr = hKey[cutExpr, :]
print "rowExpr:", rowExpr
rowExprList.append(rowExpr)
# CREATE DATASET*******************************************
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_enums_' + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, iColCount, oColCount, SEEDPERFILE, colEnumList=colEnumList)
# PARSE*******************************************************
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, valueList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
# print h2o.dump_json(inspect)
# (missingValuesDict, constantValuesDict, enumSizeDict, colTypeDict, colNameDict) = \
# h2o_cmd.columnInfoFromInspect(parse_key, exceptionOnMissingValues=False)
# error if any col has constant values
# if len(constantValuesDict) != 0:
# raise Exception("Probably got a col NA'ed and constant values as a result %s" % constantValuesDict)
# INIT all possible key names used***************************
# remember. 1 indexing!
# build up the columns
Assign('b', [1,2,3])
# could also append 1 col at a time, by assigning to the next col number?
Assign('a', Cbind(['b' for i in range(colCount)]))
for eKey in eKeys:
Assign(eKey, 'a')
## print h2o.dump_json(e)
xList = []
eList = []
fList = []
for repeat in range(200):
# EXEC*******************************************************
# don't use exec_expr to avoid issues with Inspect following etc.
randICol = random.randint(0,iColCount-1)
randOCol = random.randint(iColCount, iColCount+oColCount-1)
# should be two different keys in the sample
e = random.sample(eKeys,2)
fKey = e[0]
eKey = e[1]
if 1==1:
start = time.time()
Assign(fKey, random.choice(rowExprList)).do()
elapsed = time.time() - start
execTime = elapsed
print "exec 2 took", elapsed, "seconds."
inspect = h2o_cmd.runInspect(key=fKey)
missingList, valueList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
if numRows==0 or numCols!=colCount:
h2p.red_print("Warning: Cut resulted in", numRows, "rows and", numCols, "cols. Quantile will abort")
# FIX! put quantile back in?
quantileTime = 0
# remove all keys*******************************************************
# what about hex_key?
if 1==0:
start = time.time()
h2o.nodes[0].remove_all_keys()
elapsed = time.time() - start
print "remove all keys end on ", csvFilename, 'took', elapsed, 'seconds.'
trial += 1
xList.append(trial)
eList.append(execTime)
fList.append(quantileTime)
# just get a plot of the last one (biggest)
if DO_PLOT:
xLabel = 'trial'
eLabel = 'exec cut time'
fLabel = 'quantile time'
eListTitle = ""
fListTitle = ""
h2o_gbm.plotLists(xList, xLabel, eListTitle, eList, eLabel, fListTitle, fList, fLabel)
def test_exec2_xorsum(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(ROWS, 1, 'r1', 0, 10, None),
]
for trial in range(10):
ullResultList = []
for (rowCount, colCount, hex_key, expectedMin, expectedMax, expected) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
# dynamic range of the data may be useful for estimating error
maxDelta = expectedMax - expectedMin
csvFilename = 'syn_real_' + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
csvPathnameFull = h2i.find_folder_and_filename(None, csvPathname, returnFullPath=True)
print "Creating random", csvPathname
(expectedUllSum, expectedFpSum) = write_syn_dataset(csvPathname,
rowCount, colCount, expectedMin, expectedMax, SEEDPERFILE)
expectedUllSumAsDouble = h2o_util.unsignedLongLongToDouble(expectedUllSum)
expectedFpSumAsLongLong = h2o_util.doubleToUnsignedLongLong(expectedFpSum)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=3000, retryDelaySecs=2)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
assert parse_key == hex_key
assert numCols == colCount
assert numRows == rowCount
inspect = h2o_cmd.runInspect(key=hex_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert len(missingList) == 0
# looking at the 8 bytes of bits for the h2o doubles
# xorsum will zero out the sign and exponent
for execExpr in exprList:
for r in range(10):
start = time.time()
execResult = h2o_cmd.runExec(ast=execExpr, timeoutSecs=30)
fpResult = execResult['scalar']
# (execResult, fpResult) = h2e.exec_expr(h2o.nodes[0], execExpr, resultKey='h', timeoutSecs=300)
print r, 'exec took', time.time() - start, 'seconds'
print r, "execResult:", h2o.dump_json(execResult)
h2o_cmd.runStoreView()
ullResult = h2o_util.doubleToUnsignedLongLong(fpResult)
ullResultList.append((ullResult, fpResult))
print "%30s" % "ullResult (0.16x):", "0x%0.16x %s" % (ullResult, fpResult)
print "%30s" % "expectedUllSum (0.16x):", "0x%0.16x %s" % (expectedUllSum, expectedUllSumAsDouble)
print "%30s" % "expectedFpSum (0.16x):", "0x%0.16x %s" % (expectedFpSumAsLongLong, expectedFpSum)
# allow diff of the lsb..either way
# if ullResult!=expectedUllSum and abs((ullResult-expectedUllSum)>3):
if ullResult!=expectedUllSum:
raise Exception("h2o didn't get the same xorsum as python. 0x%0.16x 0x%0.16x" % (ullResult, expectedUllSum))
print "h2o didn't get the same xorsum as python. 0x%0.16x 0x%0.16x" % (ullResult, expectedUllSum)
h2o.check_sandbox_for_errors()
print "first result was from a sum. others are xorsum"
print "ullResultList:"
for ullResult, fpResult in ullResultList:
print "%30s" % "ullResult (0.16x):", "0x%0.16x %s" % (ullResult, fpResult)
print "%30s" % "expectedUllSum (0.16x):", "0x%0.16x %s" % (expectedUllSum, expectedUllSumAsDouble)
print "%30s" % "expectedFpSum (0.16x):", "0x%0.16x %s" % (expectedFpSumAsLongLong, expectedFpSum)
def test_GLM_basic_1(self):
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, checkHeader=1,
timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
expected = []
allowedDelta = 0
# loop, to see if we get same centers
# no cols ignored
labelListUsed = list(labelList)
numColsUsed = numCols
for trial in range(1):
# family [u'gaussian', u'binomial', u'poisson', u'gamma', u'tweedie']
# link [u'family_default', u'identity', u'logit', u'log', u'inverse', u'tweedie']
# can we do classification with probabilities?
# are only lambda and alpha grid searchable?
parameters = {
'validation_frame': parse_key,
'ignored_columns': '[ID]',
'score_each_iteration': True,
'response_column': 'CAPSULE',
# FIX! when is this needed? redundant for binomial?
'do_classification': True,
'balance_classes': False,
'max_after_balance_size': None,
'standardize': False,
'family': 'binomial',
'link': None,
'tweedie_variance_power': None,
'tweedie_link_power': None,
'alpha': '[1e-4]',
'lambda': '[0.5]',
'prior1': None,
'lambda_search': None,
'nlambdas': None,
'lambda_min_ratio': None,
'higher_accuracy': True,
'use_all_factor_levels': False,
# NPE with n_folds 2?
'n_folds': 1,
}
model_key = 'prostate_glm.hex'
glmResult = h2o.n0.build_model(
algo='glm',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
gr = self.GLMOutput(glmResult)
for k,v in gr:
if k != 'parameters':
print "gr", k, dump_json(v)
modelResult = h2o.n0.models(key=model_key)
mr = self.GLMOutput(modelResult['models'][0]['output'])
for k,v in mr:
if k != 'parameters':
print "mr", k, dump_json(v)
cmmResult = h2o.n0.compute_model_metrics(
model=model_key,
frame=parse_key,
timeoutSecs=60)
print "cmmResult", dump_json(cmmResult)
mmResult = h2o.n0.model_metrics(
model=model_key,
frame=parse_key,
timeoutSecs=60)
print "mmResult", dump_json(mmResult)
# this prints too
# tuplesSorted, iters, mse, names = \
# h2o_glm.simpleCheckGLM(self, modelResult, parameters, numRows, numColsUsed, labelListUsed)
h2o_cmd.runStoreView()
def test_w2v_basic_2(self):
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
n = 100
tryList = [
# (n, 1, 'cD', 300),
(n, 2, 'cE', 300),
(n, 3, 'cF', 300),
(n, 4, 'cG', 300),
(n, 5, 'cH', 300),
(n, 6, 'cI', 300),
(n, 7, 'cJ', 300),
(n, 9, 'cK', 300),
]
### h2b.browseTheCloud()
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
csvPathname = create_file_with_seps(rowCount, colCount)
hex_key = "not_used.hex"
# just parse to make sure it's good
parseResult = h2i.import_parse(path=csvPathname,
checkHeader=1, delete_on_done = 0, timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
src_key = h2i.find_key('syn_.*csv')
# no cols ignored
labelListUsed = list(labelList)
numColsUsed = numCols
for trial in range(1):
parameters = {
'validation_frame': parse_key, # Frame False []
'ignored_columns': None, # string[] None []
'score_each_iteration': None, # boolean false []
'minWordFreq': 1, # int 5 []
'wordModel': 'CBOW', # enum [u'CBOW', u'SkipGram']
'normModel': 'NegSampling', # enum # [u'HSM', u'NegSampling']
'negSampleCnt': 1,# int 5 []
'vecSize': 10, # int 100
'windowSize': 2, # int 5
'sentSampleRate': 0.001, # float 0.001
'initLearningRate': 0.05, # float 0.05
'epochs': 1, # int 5
}
model_key = 'benign_w2v.hex'
bmResult = h2o.n0.build_model(
algo='word2vec',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
bm = OutputObj(bmResult, 'bm')
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0]['output'], 'model')
cmmResult = h2o.n0.compute_model_metrics( model=model_key, frame=parse_key, timeoutSecs=60)
cmm = OutputObj(cmmResult, 'cmm')
mmResult = h2o.n0.model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
mm = OutputObj(mmResult['model_metrics'][0], 'mm')
prResult = h2o.n0.predict(model=model_key, frame=parse_key, timeoutSecs=60)
pr = OutputObj(prResult['model_metrics'][0]['predictions'], 'pr')
h2o_cmd.runStoreView()
def test_rapids_overloaded_opr(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
# (1000000, 5, 'cA', 200),
(1000, 5, 'cA', 200),
]
# h2b.browseTheCloud()
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(
rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "\nCreating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=hex_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
# should match # of cols in header or ??
self.assertEqual(
numCols, colCount,
"parse created result with the wrong number of cols %s %s" %
(numCols, colCount))
self.assertEqual(
numRows, rowCount,
"parse created result with the wrong number of rows %s %s" %
(numRows, rowCount))
# Xbase.debugOnly = True
REPEAT = 1
data_key = hex_key
for i in range(REPEAT):
result_key = data_key + "_" + str(i)
Assign('s1', Seq(range(5)))
# take advantage of default params for row/col (None)
# need the 'c' function, to make sure the key is created
# first try as object, then method
Assign('s2', Fcn('c', Seq(range(5))))
# just combine
Assign('s3', Col(Seq(range(5))))
inspect = h2o_cmd.runInspect(key='s3')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
assert numRows == 5
assert numCols == 1
Assign('s2', Col(Seq(range(5))))
inspect = h2o_cmd.runInspect(key='s2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
assert numRows == 5
assert numCols == 1
# can't have sequence of sequences?
# make sure key is created with c()
f = Fcn(
'c',
Seq(Colon(99, 400), "#2", 1, range(1, 5), range(7, 10),
range(50, 52)))
Assign('s1', f)
f = Col(
Seq(Colon(99, 400), "#2", 1, range(1, 5), range(7, 10),
range(50, 52)))
Assign('s2', f)
inspect = h2o_cmd.runInspect(key='s2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
assert numRows == 313
assert numCols == 1
print "Now trying to do the functions with the alternate overloaded operators"
data_key = Key(parse_key)
result_key = Key()
# what triggers immediate operation at h2o
# as opposed to an object within a function
result_key.frame = 'a1'
result_key <<= data_key[Seq(range(1, 4)), :]
result_key.frame = 'a2'
result_key <<= data_key[Seq(range(1, 4)), :]
result_key.frame = 'a3'
result_key <<= data_key[Seq(range(1, 4)), :]
result_key.frame = 'a4'
result_key <<= data_key[Seq(range(1, 4)), 0:1]
result_key.frame = 'a5'
result_key <<= data_key[Seq(range(1, 4)), 0:1]
result_key.frame = 'a6'
result_key <<= data_key[[1, 2, 3], 1]
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
def test_rapids_overloaded_opr(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
# (1000000, 5, 'cA', 200),
(1000, 5, 'cA', 200),
]
# h2b.browseTheCloud()
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "\nCreating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=timeoutSecs, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=hex_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
# should match # of cols in header or ??
self.assertEqual(numCols, colCount,
"parse created result with the wrong number of cols %s %s" % (numCols, colCount))
self.assertEqual(numRows, rowCount,
"parse created result with the wrong number of rows %s %s" % (numRows, rowCount))
# Xbase.debugOnly = True
REPEAT = 1
data_key = hex_key
for i in range(REPEAT):
result_key = data_key + "_" + str(i)
Assign('s1', Seq(range(5)) )
# take advantage of default params for row/col (None)
# need the 'c' function, to make sure the key is created
# first try as object, then method
Assign('s2', Fcn('c', Seq(range(5)) ))
# just combine
Assign('s3', Col(Seq(range(5)) ))
inspect = h2o_cmd.runInspect(key='s3')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert numRows==5
assert numCols==1
Assign('s2', Col(Seq(range(5))) )
inspect = h2o_cmd.runInspect(key='s2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert numRows==5
assert numCols==1
# can't have sequence of sequences?
# make sure key is created with c()
f = Fcn('c', Seq(Colon(99,400), "#2", 1, range(1,5), range(7,10), range(50,52) ))
Assign('s1', f)
f = Col(Seq(Colon(99,400), "#2", 1, range(1,5), range(7,10), range(50,52) ))
Assign('s2', f)
inspect = h2o_cmd.runInspect(key='s2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert numRows==313
assert numCols==1
print "Now trying to do the functions with the alternate overloaded operators"
data_key = Key(parse_key)
result_key = Key()
# what triggers immediate operation at h2o
# as opposed to an object within a function
result_key.frame = 'a1'
result_key <<= data_key[Seq(range(1,4)), :]
result_key.frame = 'a2'
result_key <<= data_key[Seq(range(1,4)), :]
result_key.frame = 'a3'
result_key <<= data_key[Seq(range(1,4)), :]
result_key.frame = 'a4'
result_key <<= data_key[Seq(range(1,4)), 0:1]
result_key.frame = 'a5'
result_key <<= data_key[Seq(range(1,4)), 0:1]
result_key.frame = 'a6'
result_key <<= data_key[[1,2,3], 1]
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
def test_hdfs_cdh5(self):
print "\nLoad a list of files from HDFS, parse and do 1 RF tree"
print "\nYou can try running as hduser/hduser if fail"
# larger set in my local dir
# fails because classes aren't integers
# "allstate_claim_prediction_train_set.zip",
csvFilenameAll = [
# "3G_poker_shuffle"
("and-testing.data", 60),
### "arcene2_train.both",
### "arcene_train.both",
### "bestbuy_test.csv",
("covtype.data", 60),
("covtype4x.shuffle.data", 60),
# "four_billion_rows.csv",
("hhp.unbalanced.012.data.gz", 60),
("hhp.unbalanced.data.gz", 60),
("leads.csv", 60),
# ("covtype.169x.data", 1200),
("prostate_long_1G.csv", 200),
("airlines_all.csv", 1200),
]
# pick 8 randomly!
if (1==0):
csvFilenameList = random.sample(csvFilenameAll,8)
# Alternatively: do the list in order! Note the order is easy to hard
else:
csvFilenameList = csvFilenameAll
# pop open a browser on the cloud
# h2b.browseTheCloud()
trial = 0
print "try importing /tmp2"
d = h2i.import_only(path="tmp2/*", schema='hdfs', timeoutSecs=1000)
for (csvFilename, timeoutSecs) in csvFilenameList:
# creates csvFilename.hex from file in hdfs dir
print "Loading", csvFilename, 'from HDFS'
start = time.time()
hex_key = "a.hex"
csvPathname = "datasets/" + csvFilename
parseResult = h2i.import_parse(path=csvPathname, schema='hdfs', hex_key=hex_key, timeoutSecs=1000)
print "hdfs parse of", csvPathname, "took", time.time() - start, 'secs'
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingValuesListA, labelListA, numRowsA, numColsA = h2o_cmd.infoFromInspect(inspectResult)
if DO_EXPORT:
start = time.time()
print "Saving", csvFilename, 'to HDFS'
print "Using /tmp2 to avoid the '.' prefixed files in /tmp2 (kills import)"
print "Unique per-user to avoid permission issues"
username = getpass.getuser()
csvPathname = "tmp2/a%s.%s.csv" % (trial, username)
# reuse the file name to avoid running out of space
csvPathname = "tmp2/a%s.%s.csv" % ('_h2o_export_files', username)
path = "hdfs://"+ h2o.nodes[0].hdfs_name_node + "/" + csvPathname
h2o.nodes[0].export_files(src_key=hex_key, path=path, force=1, timeoutSecs=timeoutSecs)
print "export_files of", hex_key, "to", path, "took", time.time() - start, 'secs'
trial += 1
print "Re-Loading", csvFilename, 'from HDFS'
start = time.time()
hex_key = "a2.hex"
time.sleep(2)
d = h2i.import_only(path=csvPathname, schema='hdfs', timeoutSecs=1000)
print h2o.dump_json(d)
parseResult = h2i.import_parse(path=csvPathname, schema='hdfs', hex_key=hex_key, timeoutSecs=1000)
print "hdfs re-parse of", csvPathname, "took", time.time() - start, 'secs'
def test_kmeans_prostate(self):
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key, checkHeader=1,
timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
# 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)
labelListUsed = list(labelList)
labelListUsed.remove('ID')
numColsUsed = numCols - 1
for trial in range(5):
# 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
kmeansSeed = random.randint(0, sys.maxint)
parameters = {
'validation_frame': parse_key,
'ignored_columns': '[ID]',
'score_each_iteration': False,
'K': 3,
'max_iters': 500,
'normalize': False,
'seed': kmeansSeed,
'init': 'PlusPlus',
}
model_key = 'prostate_k.hex'
kmeansResult = h2o.n0.build_model(
algo='kmeans',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
modelResult = h2o.n0.models(key=model_key)
h2o_cmd.runStoreView()
tuplesSorted, iters, mse, names = \
h2o_kmeans.simpleCheckKMeans(self, modelResult, parameters, numRows, numColsUsed, labelListUsed)
ids, mses, rows, clusters = zip(*tuplesSorted)
def test_DL_basic(self):
importFolderPath = "logreg"
csvFilename = "benign.csv"
hex_key = "benign.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key,
checkHeader=1, timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
expected = []
allowedDelta = 0
# no cols ignored
labelListUsed = list(labelList)
labelListUsed.remove('STR')
numColsUsed = numCols - 1
for trial in range(1):
parameters = {
'validation_frame': parse_key, # Frame None
'ignored_columns': '[STR]', # string[] None
'score_each_iteration': None, # boolean false
'response_column': 'FNDX', # string None
'do_classification': None, # boolean false
'balance_classes': None, # boolean false
'max_after_balance_size': None, # float Infinity
'n_folds': None, # int 0
'keep_cross_validation_splits': None, # boolean false
'checkpoint': None, # Key None
'override_with_best_model': None, # boolean true
'expert_mode': None, # boolean false
'autoencoder': None, # boolean false
'use_all_factor_levels': None, # boolean true
# [u'Tanh', u'TanhWithDropout', u'Rectifier', u'RectifierWithDropout', u'Maxout', u'MaxoutWithDropout']
'activation': None, # enum Rectifier
'hidden': None, # int[] [200, 200]
'epochs': None, # double 10.0
'train_samples_per_iteration': None, # long -2
'target_ratio_comm_to_comp': None, # double 0.02
'seed': None, # long 1679194146842485659
'adaptive_rate': None, # boolean true
'rho': None, # double 0.99
'epsilon': None, # double 1.0E-8
'rate': None, # double 0.005
'rate_annealing': None, # double 1.0E-6
'rate_decay': None, # double 1.0
'momentum_start': None, # double 0.0
'momentum_ramp': None, # double 1000000.0
'momentum_stable': None, # double 0.0
'nesterov_accelerated_gradient': None, # boolean true
'input_dropout_ratio': None, # double 0.0
'hidden_dropout_ratios': None, # double[] None (this can grid?)
'l1': None, # double 0.0
'l2': None, # double 0.0
'max_w2': None, # float Infinity
'initial_weight_distribution': None, # enum UniformAdaptive [u'UniformAdaptive', u'Uniform', u'Normal']
'initial_weight_scale': None, # double 1.0
'loss': None, # enum MeanSquare [u'Automatic', u'MeanSquare', u'CrossEntropy']
'score_interval': None, # double 5.0
'score_training_samples': None, # long 10000
'score_validation_samples': None, # long 0
'score_duty_cycle': None, # double 0.1
'classification_stop': None, # double 0.0
'regression_stop': None, # double 1.0E-6
'quiet_mode': None, # boolean false
'max_confusion_matrix_size': None, # int 20
'max_hit_ratio_k': None, # int 10
'balance_classes': None, # boolean false
'class_sampling_factors': None, # float[] None
'max_after_balance_size': None, # float Infinity
'score_validation_sampling': None, # enum Uniform [u'Uniform', u'Stratified']
'diagnostics': None, # boolean true
'variable_importances': None, # boolean false
'fast_mode': None, # boolean true
'ignore_const_cols': None, # boolean true
'force_load_balance': None, # boolean true
'replicate_training_data': None, # boolean false
'single_node_mode': None, # boolean false
'shuffle_training_data': None, # boolean false
'missing_values_handling': None, # enum MeanImputation [u'Skip', u'MeanImputation']
'sparse': None, # boolean false
'col_major': None, # boolean false
'average_activation': None, # double 0.0
'sparsity_beta': None, # double 0.0
}
model_key = 'benign_dl.hex'
bmResult = h2o.n0.build_model(
algo='deeplearning',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
bm = OutputObj(bmResult, 'bm')
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0]['output'], 'model')
cmmResult = h2o.n0.compute_model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
cmm = OutputObj(cmmResult, 'cmm')
mmResult = h2o.n0.model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
mm = OutputObj(mmResult['model_metrics'][0], 'mm')
prResult = h2o.n0.predict(model=model_key, frame=parse_key, timeoutSecs=60)
pr = OutputObj(prResult['model_metrics'][0]['predictions'], 'pr')
h2o_cmd.runStoreView()
def test_GLM_basic_2(self):
importFolderPath = "logreg"
csvFilename = "prostate.csv"
hex_key = "prostate.hex"
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, hex_key=hex_key,
checkHeader=1, timeoutSecs=180, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspectResult = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspectResult)
expected = []
allowedDelta = 0
labelListUsed = list(labelList)
labelListUsed.remove('ID')
labelListUsed.remove('CAPSULE')
numColsUsed = numCols - 2
for trial in range(1):
# family [u'gaussian', u'binomial', u'poisson', u'gamma', u'tweedie']
# link [u'family_default', u'identity', u'logit', u'log', u'inverse', u'tweedie']
# can we do classification with probabilities?
# are only lambda and alpha grid searchable?
parameters = {
'validation_frame': parse_key,
'ignored_columns': '[ID]',
'score_each_iteration': True,
'response_column': 'CAPSULE',
# FIX! when is this needed? redundant for binomial?
'do_classification': True,
'balance_classes': False,
'max_after_balance_size': None,
'standardize': False,
'family': 'binomial',
'link': None,
'tweedie_variance_power': None,
'tweedie_link_power': None,
'alpha': '[1e-4]',
'lambda': '[0.5]',
'prior1': None,
'lambda_search': None,
'nlambdas': None,
'lambda_min_ratio': None,
'higher_accuracy': True,
'use_all_factor_levels': False,
# NPE with n_folds 2?
'n_folds': 1,
}
model_key = 'prostate_glm.hex'
bmResult = h2o.n0.build_model(
algo='glm',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
bm = OutputObj(bmResult, 'bm')
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0]['output'], 'model')
h2o_glm.newSimpleCheckGLM(self, model, parameters, labelList, labelListUsed)
cmmResult = h2o.n0.compute_model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
cmm = OutputObj(cmmResult, 'cmm')
mmResult = h2o.n0.model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
mm = OutputObj(mmResult, 'mm')
prResult = h2o.n0.predict(model=model_key, frame=parse_key, timeoutSecs=60)
pr = OutputObj(prResult['model_metrics'][0]['predictions'], 'pr')
h2o_cmd.runStoreView()
def test_mixed_int_enum_many(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# this should be a sorted list for comparing to hbrk in the histogram in h2o summary?
enumList = ['abc', 'def', 'ghi']
# numbers 1 and 2 may not be counted as NAs correctly? what about blank space?
intList = [0, 1, 2, '']
expectedList = ['abc', 'def', 'ghi']
tryList = [
# not sure about this case
# some of the cases interpret as ints now (not as enum)
(ROWS, COLS, 'a.hex', enumList[0:1], expectedList[0:1],
intList[0:2], False),
# colname, (min, COLS5th, 50th, 75th, max)
(ROWS, COLS, 'b.hex', enumList[0:2], expectedList[0:2],
intList[0:1], True),
# fails this case
(ROWS, COLS, 'c.hex', enumList[0:1], expectedList[0:1],
intList[0:1], True),
(ROWS, COLS, 'd.hex', enumList[0:], expectedList[0:], intList[0:1],
True),
(ROWS, COLS, 'e.hex', enumList[0:2], expectedList[0:2],
intList[0:2], True),
# this case seems to fail
(ROWS, COLS, 'f.hex', enumList[0:1], expectedList[0:1],
intList[0:2], True),
# this seems wrong also
(ROWS, COLS, 'g.hex', enumList[0:], expectedList[0:], intList[0:2],
True),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
class Column(object):
def __init__(self, column):
assert isinstance(column, dict)
for k, v in column.iteritems():
setattr(self, k, v) # achieves self.k = v
x = 0
timeoutSecs = 60
for (rowCount, colCount, hex_key, enumChoices, enumExpected,
intChoices, resultIsEnum) in tryList:
# max error = half the bin size?
SEEDPERFILE = random.randint(0, sys.maxint)
x += 1
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(
colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
csvPathnameFull = h2i.find_folder_and_filename(None,
csvPathname,
returnFullPath=True)
print "Creating random", csvPathname
expectedNaCnt = write_syn_dataset(csvPathname, rowCount, colCount,
SEEDPERFILE, enumChoices,
intChoices)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
check_header=0,
hex_key=hex_key,
timeoutSecs=10,
doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
print "numRows:", numRows, "numCols:", numCols
inspect = h2o_cmd.runInspect(None, hex_key)
print "\nTrial:", trial, csvFilename
# this summary only does one column?
# assert colCount == len(columns), "%s %s" % (colCount, len(columns))
for i in range(colCount):
summaryResult = h2o_cmd.runSummary(key=hex_key,
column="C" + str(i + 1))
h2o.verboseprint("summaryResult:",
h2o.dump_json(summaryResult))
# columns = summaryResult['frames'][0]['columns']
co = Column(summaryResult)
# how are enums binned. Stride of 1? (what about domain values)
coList = [
co.base,
len(co.bins),
len(co.data),
co.domain,
co.label,
co.maxs,
co.mean,
co.mins,
co.missing,
co.ninfs,
co.pctiles,
co.pinfs,
co.precision,
co.sigma,
co.str_data,
co.stride,
co.type,
co.zeros,
]
coNameList = [
'co.base',
'len(co.bins)',
'len(co.data)',
'co.domain',
'co.label',
'co.maxs',
'co.mean',
'co.mins',
'co.missing',
'co.ninfs',
'co.pctiles',
'co.pinfs',
'co.precision',
'co.sigma',
'co.str_data',
'co.stride',
'co.type',
'co.zeros',
]
for c, n in zip(coList, coNameList):
print n + ":", c
print "len(co.bins):", len(co.bins)
print "co.label:", co.label, "mean (2 places):", h2o_util.twoDecimals(
co.mean)
# what is precision. -1?
# This can go to NaN (string) with big numbers
# print "co.label:", co.label, "std dev. (2 places):", h2o_util.twoDecimals(co.sigma)
# can be None if col is all NA
# print "FIX! hacking the co.pctiles because it's short by two"
# pctiles = [0] + co.pctiles + [0]
assert co.zeros <= numRows, "Can't have more zeros than rows %s %s" % (
co.zeros, numRows)
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(
co.type, 'enum',
"Expecting co.type %s to be 'enum' for %s co label %s"
% (co.type, i, co.label))
if ENABLE_ASSERTS and resultIsEnum:
# not always there
cardinality = len(co.domain)
self.assertEqual(
cardinality,
len(enumChoices),
msg="trial %s: cardinality %s should be %s" %
(trial, cardinality, len(enumChoices)))
# assume I create the list above in the same order that h2o will show the order. sorted?
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(co.bins, enumChoices)
hcntTotal = sum(co.bins)
numRowsCreated = rowCount + len(intChoices)
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(hcntTotal,
numRowsCreated - expectedNaCnt[i])
self.assertEqual(numRows,
numRowsCreated,
msg="trial %s: numRows %s should be %s" %
(trial, numRows, numRowsCreated))
nacnt = co.missing
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(
nacnt, expectedNaCnt[i],
"trial %s: Column %s Expected %s. nacnt %s incorrect" %
(trial, i, expectedNaCnt[i], nacnt))
# FIX! no checks for the case where it got parsed as int column!
trial += 1
def test_summary2_exp(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
LAMBD = random.uniform(0.005, 0.5)
tryList = [
# co.label, (min, 25th, 50th, 75th, max)
# parse setup error
# (1, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
# (10, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
# (100, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
# (1000, 1, 'x.hex', -5000, 0, ['C1', None, None, None, None, None]),
# (10000, 1, 'x.hex', -100000, 100000, ['C1', None, None, None, None, None]),
# (100000, 1, 'x.hex', -1, 1, ['C1', None, None, None, None, None]),
# (1000000, 1, 'A.hex', 1, 100, ['C1', None, None, None, None, None]),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
x = 0
timeoutSecs = 60
class Column(object):
def __init__(self, column):
assert isinstance(column, dict)
for k,v in column.iteritems():
setattr(self, k, v) # achieves self.k = v
for (rowCount, colCount, hex_key, rangeMin, rangeMax, expected) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
x += 1
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname, "lambd:", LAMBD
(expectedMin, expectedMax) = write_syn_dataset(csvPathname,
rowCount, colCount, lambd=LAMBD, SEED=SEEDPERFILE)
print "expectedMin:", expectedMin, "expectedMax:", expectedMax
maxDelta = ((expectedMax - expectedMin)/20.0) / 2.0
# add 5% for fp errors?
maxDelta = 1.05 * maxDelta
expected[1] = expectedMin
expected[5] = expectedMax
csvPathnameFull = h2i.find_folder_and_filename(None, csvPathname, returnFullPath=True)
parseResult = h2i.import_parse(path=csvPathname, schema='put',
hex_key=hex_key, timeoutSecs=30, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
print "\n" + csvFilename
# column 0?
summaryResult = h2o_cmd.runSummary(key=hex_key, column='C1')
h2o.verboseprint("Summary2 summaryResult:", h2o.dump_json(summaryResult))
# default_pctiles
# isText
# rows
# off
# key
# checksum
# only one column
columns = summaryResult['frames'][0]['columns']
default_pctiles = summaryResult['frames'][0]['default_pctiles']
co = Column(columns[0])
# how are enums binned. Stride of 1? (what about domain values)
coList = [
co.base,
len(co.bins),
len(co.data),
co.domain,
co.label,
co.maxs,
co.mean,
co.mins,
co.missing,
co.ninfs,
co.pctiles,
co.pinfs,
co.precision,
co.sigma,
co.str_data,
co.stride,
co.type,
co.zeros,
]
for c in coList:
print c
print "len(co.bins):", len(co.bins)
print "co.label:", co.label, "mean (2 places):", h2o_util.twoDecimals(co.mean)
# what is precision. -1?
print "co.label:", co.label, "std dev. (2 places):", h2o_util.twoDecimals(co.sigma)
print "FIX! hacking the co.pctiles because it's short by two"
pctiles = [0] + co.pctiles + [0]
# the thresholds h2o used, should match what we expected
if expected[0]:
self.assertEqual(co.label, expected[0])
if expected[1]:
h2o_util.assertApproxEqual(co.mins[0], expected[1], tol=maxDelta, msg='min is not approx. expected')
if expected[2]:
h2o_util.assertApproxEqual(pctiles[3], expected[2], tol=maxDelta, msg='25th percentile is not approx. expected')
if expected[3]:
h2o_util.assertApproxEqual(pctiles[5], expected[3], tol=maxDelta, msg='50th percentile (median) is not approx. expected')
if expected[4]:
h2o_util.assertApproxEqual(pctiles[7], expected[4], tol=maxDelta, msg='75th percentile is not approx. expected')
if expected[5]:
h2o_util.assertApproxEqual(co.maxs[0], expected[5], tol=maxDelta, msg='max is not approx. expected')
# figure out the expected max error
# use this for comparing to sklearn/sort
if expected[1] and expected[5]:
expectedRange = expected[5] - expected[1]
# because of floor and ceil effects due we potentially lose 2 bins (worst case)
# the extra bin for the max value, is an extra bin..ignore
expectedBin = expectedRange/(MAX_QBINS-2)
maxErr = expectedBin # should we have some fuzz for fp?
else:
print "Test won't calculate max expected error"
maxErr = 0
pt = h2o_util.twoDecimals(pctiles)
mx = h2o_util.twoDecimals(co.maxs)
mn = h2o_util.twoDecimals(co.mins)
print "co.label:", co.label, "co.pctiles (2 places):", pt
print "default_pctiles:", default_pctiles
print "co.label:", co.label, "co.maxs: (2 places):", mx
print "co.label:", co.label, "co.mins: (2 places):", mn
# FIX! we should do an exec and compare using the exec quantile too
compareActual = mn[0], pt[3], pt[5], pt[7], mx[0]
h2p.green_print("min/25/50/75/max co.label:", co.label, "(2 places):", compareActual)
print "co.label:", co.label, "co.maxs (2 places):", mx
print "co.label:", co.label, "co.mins (2 places):", mn
trial += 1
h2o.nodes[0].remove_all_keys()
scipyCol = 0
print "h2oSummary2MaxErr", maxErr
if co.label!='' and expected[scipyCol]:
# don't do for enums
# also get the median with a sort (h2o_summ.percentileOnSortedlist()
h2o_summ.quantile_comparisons(
csvPathnameFull,
skipHeader=False,
col=scipyCol,
datatype='float',
quantile=0.5 if DO_MEDIAN else 0.999,
h2oSummary2=pctiles[5 if DO_MEDIAN else 10],
# h2oQuantilesApprox=qresult_single,
# h2oQuantilesExact=qresult,
h2oSummary2MaxErr=maxErr,
)
def test_mixed_int_enum_many(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
# this should be a sorted list for comparing to hbrk in the histogram in h2o summary?
enumList = ['abc', 'def', 'ghi']
# numbers 1 and 2 may not be counted as NAs correctly? what about blank space?
intList = [0, 1, 2, '']
expectedList = [ 'abc', 'def', 'ghi']
tryList = [
# not sure about this case
# some of the cases interpret as ints now (not as enum)
(ROWS, COLS, 'a.hex', enumList[0:1], expectedList[0:1], intList[0:2], False),
# colname, (min, COLS5th, 50th, 75th, max)
(ROWS, COLS, 'b.hex', enumList[0:2], expectedList[0:2], intList[0:1], True),
# fails this case
(ROWS, COLS, 'c.hex', enumList[0:1], expectedList[0:1], intList[0:1], True),
(ROWS, COLS, 'd.hex', enumList[0: ], expectedList[0: ], intList[0:1], True),
(ROWS, COLS, 'e.hex', enumList[0:2], expectedList[0:2], intList[0:2], True),
# this case seems to fail
(ROWS, COLS, 'f.hex', enumList[0:1], expectedList[0:1], intList[0:2], True),
# this seems wrong also
(ROWS, COLS, 'g.hex', enumList[0: ], expectedList[0: ], intList[0:2], True),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
class Column(object):
def __init__(self, column):
assert isinstance(column, dict)
for k,v in column.iteritems():
setattr(self, k, v) # achieves self.k = v
x = 0
timeoutSecs = 60
for (rowCount, colCount, hex_key, enumChoices, enumExpected, intChoices, resultIsEnum) in tryList:
# max error = half the bin size?
SEEDPERFILE = random.randint(0, sys.maxint)
x += 1
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
csvPathnameFull = h2i.find_folder_and_filename(None, csvPathname, returnFullPath=True)
print "Creating random", csvPathname
expectedNaCnt = write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE, enumChoices, intChoices)
parseResult = h2i.import_parse(path=csvPathname, schema='put', checkHeader=0,
hex_key=hex_key, timeoutSecs=10, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
print "numRows:", numRows, "numCols:", numCols
inspect = h2o_cmd.runInspect(None, hex_key)
print "\nTrial:", trial, csvFilename
# this summary only does one column?
# assert colCount == len(columns), "%s %s" % (colCount, len(columns))
for i in range(colCount):
summaryResult = h2o_cmd.runSummary(key=hex_key, column="C" + str(i+1))
h2o.verboseprint("summaryResult:", h2o.dump_json(summaryResult))
columns = summaryResult['frames'][0]['columns']
co = Column(columns[0])
# how are enums binned. Stride of 1? (what about domain values)
coList = [
co.base,
len(co.bins),
len(co.data),
co.domain,
co.label,
co.maxs,
co.mean,
co.mins,
co.missing,
co.ninfs,
co.pctiles,
co.pinfs,
co.precision,
co.sigma,
co.str_data,
co.stride,
co.type,
co.zeros,
]
coNameList = [
'co.base',
'len(co.bins)',
'len(co.data)',
'co.domain',
'co.label',
'co.maxs',
'co.mean',
'co.mins',
'co.missing',
'co.ninfs',
'co.pctiles',
'co.pinfs',
'co.precision',
'co.sigma',
'co.str_data',
'co.stride',
'co.type',
'co.zeros',
]
for c,n in zip(coList, coNameList):
print n+":", c
print "len(co.bins):", len(co.bins)
print "co.label:", co.label, "mean (2 places):", h2o_util.twoDecimals(co.mean)
# what is precision. -1?
# This can go to NaN (string) with big numbers
# print "co.label:", co.label, "std dev. (2 places):", h2o_util.twoDecimals(co.sigma)
# can be None if col is all NA
# print "FIX! hacking the co.pctiles because it's short by two"
# pctiles = [0] + co.pctiles + [0]
assert co.zeros <= numRows, "Can't have more zeros than rows %s %s" % (co.zeros, numRows)
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(co.type, 'Enum', "trial %s: Expecting type to be Enum for %s col colname %s" % (trial, i, colname))
if ENABLE_ASSERTS and resultIsEnum:
# not always there
cardinality = len(co.domain)
self.assertEqual(cardinality, len(enumChoices),
msg="trial %s: cardinality %s should be %s" % (trial, cardinality, len(enumChoices)))
# assume I create the list above in the same order that h2o will show the order. sorted?
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(co.bins, enumChoices)
hcntTotal = sum(co.bins)
numRowsCreated = rowCount + len(intChoices)
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(hcntTotal, numRowsCreated - expectedNaCnt[i])
self.assertEqual(numRows, numRowsCreated,
msg="trial %s: numRows %s should be %s" % (trial, numRows, numRowsCreated))
nacnt = co.missing
if ENABLE_ASSERTS and resultIsEnum:
self.assertEqual(nacnt, expectedNaCnt[i],
"trial %s: Column %s Expected %s. nacnt %s incorrect" % (trial, i, expectedNaCnt[i], nacnt))
# FIX! no checks for the case where it got parsed as int column!
trial += 1
def test_exec2_xorsum(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(ROWS, 1, 'r1', 0, 10, None),
]
for trial in range(10):
ullResultList = []
for (rowCount, colCount, hex_key, expectedMin, expectedMax, expected) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
# dynamic range of the data may be useful for estimating error
maxDelta = expectedMax - expectedMin
csvFilename = 'syn_real_' + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
csvPathnameFull = h2i.find_folder_and_filename(None, csvPathname, returnFullPath=True)
print "Creating random", csvPathname
(expectedUllSum, expectedFpSum) = write_syn_dataset(csvPathname,
rowCount, colCount, expectedMin, expectedMax, SEEDPERFILE)
expectedUllSumAsDouble = h2o_util.unsignedLongLongToDouble(expectedUllSum)
expectedFpSumAsLongLong = h2o_util.doubleToUnsignedLongLong(expectedFpSum)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=3000, retryDelaySecs=2)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
assert parse_key == hex_key
assert numCols == colCount
assert numRows == rowCount
inspect = h2o_cmd.runInspect(key=hex_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert len(missingList) == 0
# looking at the 8 bytes of bits for the h2o doubles
# xorsum will zero out the sign and exponent
for execExpr in exprList:
for r in range(10):
if 1==0:
execResult = h2o_cmd.runExec(ast=execExpr, timeoutSecs=30)
fpResult = execResult['scalar']
else:
(execResult, fpResult) = h2e.exec_expr(h2o.nodes[0], execExpr, resultKey='x', timeoutSecs=300)
# print dump_json(h2o.n0.frames(key="h"))
# (execResult, fpResult) = h2e.exec_expr(h2o.nodes[0], execExpr, resultKey='h', timeoutSecs=300)
# print dump_json(h2o.n0.frames(key="r1"))
print r, "execResult:", h2o.dump_json(execResult)
h2o_cmd.runStoreView()
ullResult = h2o_util.doubleToUnsignedLongLong(fpResult)
ullResultList.append((ullResult, fpResult))
print "%30s" % "ullResult (0.16x):", "0x%0.16x %s" % (ullResult, fpResult)
print "%30s" % "expectedUllSum (0.16x):", "0x%0.16x %s" % (expectedUllSum, expectedUllSumAsDouble)
print "%30s" % "expectedFpSum (0.16x):", "0x%0.16x %s" % (expectedFpSumAsLongLong, expectedFpSum)
# allow diff of the lsb..either way
# if ullResult!=expectedUllSum and abs((ullResult-expectedUllSum)>3):
if ullResult!=expectedUllSum:
raise Exception("h2o didn't get the same xorsum as python. 0x%0.16x 0x%0.16x" % \
(ullResult, expectedUllSum))
print "h2o didn't get the same xorsum as python. 0x%0.16x 0x%0.16x" % \
(ullResult, expectedUllSum)
h2o.check_sandbox_for_errors()
print "first result was from a sum. others are xorsum"
print "ullResultList:"
for ullResult, fpResult in ullResultList:
print "%30s" % "ullResult (0.16x):", "0x%0.16x %s" % (ullResult, fpResult)
print "%30s" % "expectedUllSum (0.16x):", "0x%0.16x %s" % (expectedUllSum, expectedUllSumAsDouble)
print "%30s" % "expectedFpSum (0.16x):", "0x%0.16x %s" % (expectedFpSumAsLongLong, expectedFpSum)
def test_quant_cmp_uniform(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(5*ROWS, 1, 'x.hex', 1, 20000, ['C1', 1.10, 5000.0, 10000.0, 15000.0, 20000.00]),
(5*ROWS, 1, 'x.hex', -5000, 0, ['C1', -5001.00, -3750.0, -2445, -1200.0, 99]),
(1*ROWS, 1, 'x.hex', -100000, 100000, ['C1', -100001.0, -50000.0, 1613.0, 50000.0, 100000.0]),
(1*ROWS, 1, 'x.hex', -1, 1, ['C1', -1.05, -0.48, 0.0087, 0.50, 1.00]),
(1*ROWS, 1, 'A.hex', 1, 100, ['C1', 1.05, 26.00, 51.00, 76.00, 100.0]),
(1*ROWS, 1, 'A.hex', -99, 99, ['C1', -99, -50.0, 0, 50.00, 99]),
(1*ROWS, 1, 'B.hex', 1, 10000, ['C1', 1.05, 2501.00, 5001.00, 7501.00, 10000.00]),
(1*ROWS, 1, 'B.hex', -100, 100, ['C1', -100.10, -50.0, 0.85, 51.7, 100,00]),
(1*ROWS, 1, 'C.hex', 1, 100000, ['C1', 1.05, 25002.00, 50002.00, 75002.00, 100000.00]),
(1*ROWS, 1, 'C.hex', -101, 101, ['C1', -100.10, -50.45, -1.18, 49.28, 100.00]),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
x = 0
timeoutSecs = 60
for (rowCount, colCount, hex_key, expectedMin, expectedMax, expected) in tryList:
# max error = half the bin size?
colname = expected[0]
maxDelta = ((expectedMax - expectedMin)/1000.0) / 2.0
# add 5% for fp errors?
maxDelta = 1.05 * maxDelta
SEEDPERFILE = random.randint(0, sys.maxint)
x += 1
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, expectedMin, expectedMax, SEEDPERFILE)
# need the full pathname when python parses the csv for numpy/sort
csvPathnameFull = h2i.find_folder_and_filename(None, csvPathname, returnFullPath=True)
#***************************
# Parse
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30, doSummary=False)
numRows, numCols, parse_key = h2o_cmd.infoFromParse(parseResult)
#***************************
# Inspect
inspect = h2o_cmd.runInspect(key=parse_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(parseResult)
#***************************
# Summary
summaryResult = h2o_cmd.runSummary(key=parse_key)
columns = summaryResult['frames'][0]['columns']
default_pctiles = summaryResult['frames'][0]['default_pctiles']
co = OutputObj(columns[0], 'summary')
coList = [ co.base, len(co.bins), len(co.data), co.domain,
co.label, co.maxs, co.mean, co.mins, co.missing, co.ninfs, co.pctiles,
co.pinfs, co.precision, co.sigma, co.str_data, co.stride, co.type, co.zeros]
for c in coList:
print c
print "len(co.bins):", len(co.bins)
print "co.label:", co.label, "mean (2 places):", h2o_util.twoDecimals(co.mean)
print "co.label:", co.label, "std dev. (2 places):", h2o_util.twoDecimals(co.sigma)
print "FIX! hacking the co.pctiles because it's short by two"
summ_pctiles = [0] + co.pctiles + [0]
pt = h2o_util.twoDecimals(summ_pctiles)
mx = h2o_util.twoDecimals(co.maxs)
mn = h2o_util.twoDecimals(co.mins)
exp = h2o_util.twoDecimals(expected[1:])
print "co.label:", co.label, "co.pctiles (2 places):", pt
print "default_pctiles:", default_pctiles
print "co.label:", co.label, "co.maxs: (2 places):", mx
print "co.label:", co.label, "co.mins: (2 places):", mn
# FIX! we should do an exec and compare using the exec quantile too
h2p.green_print("min/25/50/75/max co.label:", co.label, "(2 places):",\
mn[0], pt[3], pt[5], pt[7], mx[0])
h2p.green_print("min/25/50/75/max co.label:", co.label, "(2 places):",\
exp[0], exp[1], exp[2], exp[3], exp[4])
#***************************
# Quantile
# the thresholds h2o used, should match what we expected
# using + here seems to result in an odd tuple..doesn't look right to h2o param
# so went with this. Could add '[' and ']' to the list first, before the join.
probsStr = "[%s]" % ",".join(map(str,probsList))
parameters = {
'destination_key': "a.hex",
'training_frame': parse_key,
'validation_frame': parse_key,
'ignored_columns': None,
'score_each_iteration': False,
'probs': probsStr,
}
model_key = 'qhex'
bmResult = h2o.n0.build_model(
algo='quantile',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=10)
bm = OutputObj(bmResult, 'bm')
msec = bm.jobs[0]['msec']
print "bm msec", msec
# quantile result is just a job result to a key
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0], 'model')
# model output {
# "domains": [
# null
# ],
# "iters": 1.0,
# "model_category": null,
# "names": [
# "C1"
# ],
# "quantiles": [
# [
# 10009.03502345
# ]
# ],
print "model.output:", model.output
print "model.output:['quantiles']", model.output['quantiles']
print "model.output:['iters']", model.output['iters']
print "model.output:['names']", model.output['names']
quantiles = model.output['quantiles'][0] # why is this a double array
iters = model.output['iters']
assert iters == 11, iters
print "quantiles: ", quantiles
print "iters: ", quantiles
# cmmResult = h2o.n0.compute_model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
# cmm = OutputObj(cmmResult, 'cmm')
# mmResult = h2o.n0.model_metrics(model=model_key, frame=parse_key, timeoutSecs=60)
# mm = OutputObj(mmResult, 'mm')
# prResult = h2o.n0.predict(model=model_key, frame=parse_key, timeoutSecs=60)
# pr = OutputObj(prResult['model_metrics'][0]['predictions'], 'pr')
h2o_cmd.runStoreView()
trial += 1
# compare the last threshold
if colname!='':
# don't do for enums
# also get the median with a sort (h2o_summ.percentileOnSortedlist()
h2o_summ.quantile_comparisons(
csvPathnameFull,
col=0, # what col to extract from the csv
datatype='float',
quantile=CHECK_PCTILE,
# h2oSummary2=pctile[-1],
# h2oQuantilesApprox=result, # from exec
h2oExecQuantiles=quantiles[CHECK_PCTILE_INDEX],
)
h2o.nodes[0].remove_all_keys()