def setUpClass(cls):
global SEED
SEED = h2o.setup_random_seed()
h2o.init(2)
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
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_100k_cols(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(10, 1000, 'cA', 200, 200),
(10, 2000, 'cA', 200, 200),
(10, 4000, 'cA', 200, 200),
(10, 8000, 'cA', 200, 200),
(10, 9000, 'cA', 200, 200),
(10, 10000, 'cA', 200, 200),
(10, 100000, 'cA', 200, 200),
# (10, 200000, 'cB', 200, 200),
# (10, 300000, 'cB', 200, 200),
# we timeout/fail on 500k? stop at 200k
# (10, 500000, 'cC', 200, 200),
# (10, 1000000, 'cD', 200, 360),
# (10, 1100000, 'cE', 60, 100),
# (10, 1200000, 'cF', 60, 120),
]
# h2b.browseTheCloud()
for (rowCount, colCount, hex_key, timeoutSecs,
timeoutSecs2) 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='local',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
doSummary=False,
column_names=None,
intermediateResults=DO_INTERMEDIATE_RESULTS)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
print "Skipping the delete keys for now"
if 1 == 0:
# if not h2o.browse_disable:
# h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
# time.sleep(5)
h2i.delete_keys_at_all_nodes()
def test_plot_remove_keys(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100000, 100, 'cG', 400),
(200000, 100, 'cH', 400),
(400000, 100, 'cI', 400),
(800000, 100, 'cJ', 400),
(1000000, 100, 'cK', 400),
]
xList = []
eList = []
fList = []
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
NUM_CASES = h2o_util.fp_format()
sel = random.randint(0, NUM_CASES-1)
csvFilename = "syn_%s_%s_%s_%s.csv" % (SEEDPERFILE, sel, rowCount, colCount)
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE, sel)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=timeoutSecs, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
iA = h2o_cmd.InspectObj(pA.parse_key)
parseElapsed = pA.python_elapsed
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
print parse_key, parseElapsed, numRows, numCols
labelList = iA.labelList
node = h2o.nodes[0]
print "Deleting", hex_key, "at", node.http_addr, "Shouldn't matter what node the delete happens at..global?"
start = time.time()
node.remove_key(hex_key, timeoutSecs=30)
removeElapsed = time.time() - start
print "Deleting", hex_key, "took", removeElapsed, "seconds"
# xList.append(ntrees)
xList.append(numRows)
eList.append(parseElapsed)
fList.append(removeElapsed)
# just plot the last one
if 1==1:
xLabel = 'byteSize'
eLabel = 'parseElapsed'
fLabel = 'removeElapsed'
eListTitle = ""
fListTitle = ""
h2o_gbm.plotLists(xList, xLabel, eListTitle, eList, eLabel, fListTitle, fList, fLabel)
def test_parse_long_colnames(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(10, 1000, 'cA', 200, 200),
(10, 1100, 'cA', 200, 200),
(10, 1200, 'cA', 200, 200),
(10, 1300, 'cA', 200, 200),
(10, 1400, 'cA', 200, 200),
(10, 1500, 'cA', 200, 200),
(10, 1600, 'cA', 200, 200),
(10, 1700, 'cA', 200, 200),
(10, 1800, 'cA', 200, 200),
(10, 1900, 'cA', 200, 200),
(10, 2000, 'cA', 200, 200),
(10, 4000, 'cA', 200, 200),
(10, 8000, 'cA', 200, 200),
(10, 9000, 'cA', 200, 200),
(10, 10000, 'cA', 200, 200),
# (10, 100000, 'cA', 200, 200),
# (10, 200000, 'cB', 200, 200),
# (10, 300000, 'cB', 200, 200),
# we timeout/fail on 500k? stop at 200k
# (10, 500000, 'cC', 200, 200),
# (10, 1000000, 'cD', 200, 360),
# (10, 1100000, 'cE', 60, 100),
# (10, 1200000, 'cF', 60, 120),
]
for (rowCount, colCount, hex_key, timeoutSecs, timeoutSecs2) 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='local', hex_key=hex_key,
timeoutSecs=timeoutSecs, doSummary=False, column_names=None, intermediateResults=DO_INTERMEDIATE_RESULTS)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
print "Skipping the delete keys for now"
if 1==0:
# if not h2o.browse_disable:
# h2b.browseJsonHistoryAsUrlLastMatch("Inspect")
# time.sleep(5)
h2i.delete_keys_at_all_nodes()
def test_rapids_mean(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(1000, 5, 'cA', 200),
]
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)
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))
data_key = hex_key
data_key2 = hex_key + "_2"
for trial in range(4):
result_key = data_key + "_" + str(trial)
# copy the key
Assign(data_key2, data_key)
Assign(result_key,
Fcn('mean', KeyIndexed(data_key2, col=0), 0, False))
trial += 1
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)
parseResult = h2i.import_parse(path=csvPathnamegz,
schema='put',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
doSummary=DOSUMMARY)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
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)
parseResult = h2i.import_parse(path=csvPathnamegz, schema='put', hex_key=hex_key,
timeoutSecs=timeoutSecs, doSummary=DOSUMMARY)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
def test_rapids_mean(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(1000, 5, 'cA', 200),
]
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)
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))
data_key = hex_key
data_key2 = hex_key + "_2"
for trial in range(4):
result_key = data_key + "_" + str(trial)
# copy the key
Assign(data_key2, data_key)
Assign(result_key, Fcn('mean', KeyIndexed(data_key2, col=0), 0, False))
trial += 1
def test_GLM_many_cols_4(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
translateList = [
'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm',
'n', 'o', 'p', 'q', 'r', 's', 't', 'u'
]
tryList = [
(100000, 10, 'cA', 600),
(100000, 100, 'cA', 600),
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
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,
translateList)
parseResult = h2i.import_parse(path=csvPathname,
hex_key=hex_key,
timeoutSecs=180,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
expected = []
allowedDelta = 0
labelListUsed = list(labelList)
print "labelListUsed", labelListUsed
response = labelListUsed[-1]
labelListUsed.remove(response)
numColsUsed = numCols - 1
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': None,
# FIX! for now just use a column that's binomial
'response_column': response, # can't take index now?
# FIX! when is this needed? redundant for binomial?
'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': '[0.5,0.25, 0.1]',
'prior1': None,
'lambda_search': None,
'nlambdas': None,
'lambda_min_ratio': None,
'use_all_factor_levels': False,
'n_folds': 1,
}
model_key = 'many_cols_glm.hex'
bmResult = h2o.n0.build_model(algo='glm',
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')
h2o_glm.simpleCheckGLM(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')
def test_parse_rand_enum_compress(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
if DEBUG:
n = 20
else:
n = 1000000
# from command line arg -long
if h2o_args.long_test_case:
repeat = 1000
scale = 10 # scale up the # of rows
tryList = [
(n * scale, 1, 'cI', 300),
(n * scale, 1, 'cI', 300),
(n * scale, 1, 'cI', 300),
]
else:
repeat = 1
scale = 1
tryList = [
(n, 3, 'cI', 300),
(n, 3, 'cI', 300),
(n, 3, 'cI', 300),
]
lastcolsHistory = []
enumList = create_enum_list(listSize=ENUMS_NUM)
for r in range(repeat):
SEED_PER_FILE = random.randint(0, sys.maxint)
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
# using the comma is nice to ensure no craziness
colSepHexString = '2c' # comma
colSepChar = colSepHexString.decode('hex')
colSepInt = int(colSepHexString, base=16)
print "colSepChar:", colSepChar
rowSepHexString = '0a' # newline
rowSepChar = rowSepHexString.decode('hex')
print "rowSepChar:", rowSepChar
csvFilename = 'syn_enums_' + str(rowCount) + 'x' + str(
colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
# same enum list/mapping, but different dataset?
start = time.time()
lastcols = write_syn_dataset(csvPathname,
enumList,
rowCount,
colCount,
scale=1,
colSepChar=colSepChar,
rowSepChar=rowSepChar,
SEED=SEED_PER_FILE)
elapsed = time.time() - start
print "took %s seconds to create %s" % (elapsed, csvPathname)
# why are we saving this?
lastcolsHistory.append(lastcols)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
check_header=0,
timeoutSecs=30,
separator=colSepInt,
doSummary=DO_SUMMARY)
parseResultA = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key)
# optional. only needed to extract parse_key?
pA = h2o_cmd.ParseObj(parseResultA,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
self.assertEqual(rowCount, iA.numRows)
self.assertEqual(colCount, iA.numCols)
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)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
numRows = pA.numRows
numCols = pA.numCols
parse_key = pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
#***************************
# Summary
co = h2o_cmd.runSummary(key=parse_key)
default_pctiles = co.default_pctiles
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 = {
'model_id': "a.hex",
'training_frame': parse_key,
'validation_frame': parse_key,
'ignored_columns': None,
'probs': probsStr,
}
model_key = 'qhex'
bmResult = h2o.n0.build_model(
algo='quantile',
model_id=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')
print "model.output:", model.output
print "model.output:['quantiles']", model.output['quantiles']
print "model.output:['iterations']", model.output['iterations']
print "model.output:['names']", model.output['names']
quantiles = model.output['quantiles'][0] # why is this a double array
iterations = model.output['iterations']
assert iterations == 11, iterations
print "quantiles: ", quantiles
print "iterations: ", iterations
# 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()
def test_PCA_many_cols(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(10000, 10, 'cA', 300),
(10000, 50, 'cB', 300),
(10000, 100, 'cC', 300),
# (10000, 500, 'cH', 300),
# (10000, 1000, 'cI', 300),
]
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
print (rowCount, colCount, hex_key, timeoutSecs)
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
# PARSE ****************************************
modelKey = 'PCAModelKey'
scoreKey = 'PCAScoreKey'
# Parse ****************************************
parseResult = h2i.import_parse(bucket=None, path=csvPathname, schema='put',
hex_key=hex_key, timeoutSecs=timeoutSecs, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
# PCA(tolerance iterate)****************************************
for tolerance in [i/10.0 for i in range(11)]:
parameters = {
# 'tolerance': tolerance,
# 'standardize': 1,
'k': 1,
}
model_key = 'pca.hex'
bmResult = h2o.n0.build_model(
algo='pca',
model_id=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_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_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_0_NA_2enum(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100, 30, '0', 'cC', 100),
(100, 30, '0.0', 'cC', 100),
(100, 30, '0.0000000', 'cC', 100),
]
for (rowCount, colCount, zero, 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, zero, SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, timeoutSecs=30, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
# column 0 not used here
# assert len(expected) == 6
# FIX! add expected and maxDelta?
co = h2o_cmd.runSummary(key=hex_key, column=0)
print co.label, co.type, co.missing, co.domain, sum(co.bins)
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 k,v in co:
print k, v
if DO_REBALANCE:
print "Rebalancing it to create an artificially large # of chunks"
rb_key = "rb_%s" % hex_key
start = time.time()
print "Rebalancing %s to %s with %s chunks" % (hex_key, rb_key, REBALANCE_CHUNKS)
rebalanceResult = h2o.nodes[0].rebalance(source=hex_key, after=rb_key, chunks=REBALANCE_CHUNKS)
elapsed = time.time() - start
print "rebalance end on ", csvFilename, 'took', elapsed, 'seconds'
else:
rb_key = hex_key
print "Now doing to_enum across all columns of %s" % hex_key
for column_index in range(colCount):
# is the column index 1-base in to_enum
result = h2o.nodes[0].to_enum(None, src_key=hex_key, column_index=column_index+1)
# print "\nto_enum result:", h2o.dump_json(result)
co = h2o_cmd.runSummary(key=hex_key, column=column_index+1)
print co.label, co.type, co.missing, co.domain, sum(co.bins)
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]
if co.type != 'Enum':
raise Exception("column %s, which has name %s, didn't convert to Enum, is %s" % (column_index, colname, co.type))
# I'm generating NA's ..so it should be > 0. .but it could be zero . I guess i have enough rows to get at least 1
if co.missing<=0 or co.missing>rowCount:
raise Exception("column %s, which has name %s, somehow got NA cnt wrong after convert to Enum %s %s" %
(column_index, colname, co.missing, rowCount))
if co.domain!=1: # NAs don't count?
# print "stats:", h2o.dump_json(stats)
print "column:", h2o.dump_json(co)
raise Exception("column %s, which has name %s, should have cardinality 1, got: %s" % (column_index, co.label, domain))
def test_w2v_basic(self):
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
n = 500000
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)
# just parse to make sure it's good
parseResult = h2i.import_parse(path=csvPathname,
check_header=1,
delete_on_done=0,
timeoutSecs=180,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
cA = h2o_test.OutputObj(iA.columns[0], "inspect_column")
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
for i in range(colCount):
print cA.type, cA.missing_count
self.assertEqual(
0, cA.missing_count,
"Column %s Expected %s. missing: %s is incorrect" %
(i, 0, cA.missing_count))
self.assertEqual(
'string', cA.type,
"Column %s Expected %s. type: %s is incorrect" %
(i, 0, cA.type))
if DO_SUMMARY:
for i in range(colCount):
co = h2o_cmd.runSummary(key=parse_key, column=i)
print co.label, co.type, co.missing, co.domain, sum(
co.bins)
self.assertEqual(
0, co.missing_count,
"Column %s Expected %s. missing: %s is incorrect" %
(i, 0, co.missing_count))
self.assertEqual(
'String', co.type,
"Column %s Expected %s. type: %s is incorrect" %
(i, 0, co.type))
# no cols ignored
labelListUsed = list(labelList)
numColsUsed = numCols
for trial in range(1):
parameters = {
'validation_frame': parse_key, # KeyIndexed False []
'ignored_columns': None, # string[] None []
'minWordFreq': 5, # int 5 []
'wordModel': 'SkipGram', # enum [u'CBOW', u'SkipGram']
'normModel': 'HSM', # enum # [u'HSM', u'NegSampling']
'negSampleCnt': 5, # int 5 []
'vecSize': 100, # int 100
'windowSize': 5, # 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',
model_id=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['model_metrics'][0], 'mm')
# not implemented?
# 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_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,
check_header=1, delete_on_done = 0, timeoutSecs=180, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
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, # KeyIndexed False []
'ignored_columns': None, # string[] None []
'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',
model_id=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_funs_1op(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)
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
data_key2 = hex_key + "_2"
trial = 0
good = []
bad = []
both = h2o_xl.xFcnOp1Set.union(h2o_xl.xFcnOp3Set)
both = h2o_xl.xFcnOp1Set
for fun in both:
a = None
try:
result_key = data_key + "_" + str(trial)
# copy the key
Assign(data_key2, data_key)
# a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), True))
# a = Assign(result_key, Fcn('sum', KeyIndexed(data_key2, col=0), True))
# a = Assign(result_key, Fcn('xorsum', KeyIndexed(data_key2, col=0), True))
# a = Assign(result_key, Fcn('sqrt', KeyIndexed(data_key2, col=0)))
# a = Assign(result_key, Fcn('ncol', KeyIndexed(data_key2, col=0)))
# what's wrong with mean?
if fun in ['ncol', 'asin', 'any.factor', 'sin', 'atan', 'tan', 'sign', 'log', 'exp', 'sqrt', 'abs', 'floor', 'ceiling', 'trunc','is.factor', 'is.na', 'any.na', 'nrow', 'tanh', 'length', 'acos', 'cos', 'sinh', 'cosh']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0)))
good.append(fun)
elif fun in ['sum', 'max', 'min', 'xorsum', 'sd']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), True))
good.append(fun)
elif fun in ['scale']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), False, False))
good.append(fun)
elif fun in ['round', 'signif']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), 1))
good.append(fun)
elif fun in ['seq_len', 'rep_len']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), 4))
good.append(fun)
elif fun in ['seq']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), 1, 5, 1))
good.append(fun)
elif fun in ['mean']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), 0, False))
good.append(fun)
elif fun in ['var']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), False, False, False))
good.append(fun)
elif fun in ['match']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), KeyIndexed(data_key2, col=0), 1, None))
good.append(fun)
elif fun in ['unique']:
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), False, 10, 1))
good.append(fun)
else:
# bad functions kill h2o?
a = Assign(result_key, Fcn(fun, KeyIndexed(data_key2, col=0), None))
bad.append(fun)
# a = Fcn(fun, KeyIndexed(data_key, col=0), '%FALSE ')
# a = Fcn(fun, data_key, '%FALSE')
# a = Fcn(fun, data_key)
# scalars?
if 1==0:
inspect = h2o_cmd.runInspect(key=result_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
assert numRows==1000, numRows
assert numCols==1, numCols
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
except:
if not a:
# print dump_json(a.execResult)
bad.append(fun)
trial += 1
print "good:", good
print "bad:", bad
def test_rapids_row_range(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)
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)) ).do
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)) ))
print dump_json(Xbase.lastExecResult)
print dump_json(Xbase.lastResult)
# 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 "z1"
Assign(result_key, KeyIndexed(data_key, row=Seq(range(1, 5))) )
print "z2"
Assign('s1', KeyIndexed(data_key, row=Seq(Colon(99, 400), "#2", 1, range(1,5))) )
print "z3"
Assign(result_key, KeyIndexed(data_key, row='#1')).do
print "z4"
Assign(result_key, KeyIndexed(data_key, row=Colon('#1', '#100')))
print "z5"
Assign(result_key, KeyIndexed(data_key, row=Colon(1, 100)))
# this should fail rapids because of reverse msb/lsb
# illegal, detected
# execResult, Assign(result_key, KeyIndexed(data_key, row=Colon('#100', '#1')))
print "z6"
Assign(result_key, KeyIndexed(data_key, row=Colon('#-2', '#-1')))
print "z7"
Assign(result_key, KeyIndexed(data_key, row=Colon(-2, -1)))
# illegal, detected
# execResult, Assign(result_key, KeyIndexed(data_key, row=Colon('#-1', '#-2')))
# take advantage of number to string conversion
print "z8"
Assign(result_key, KeyIndexed(data_key, row=Colon('#1', rowCount-10)))
print "z9"
Assign(result_key, KeyIndexed(data_key, col=Colon('#1', colCount-1, )))
# no assign
print "z10"
result = KeyIndexed(data_key, row=Colon('#1', rowCount-10)).do()
print "z11"
# result = KeyIndexed(data_key, col=Colon('#1', colCount-1,)).do()
# do some function translation
print "z12"
# result = Fcn('==', 1, KeyIndexed(data_key, col=Colon('#1', colCount-1,))).do()
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
def test_parse_multi_header_single(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_ints.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON,output"
# cols must be 9 to match the header above, otherwise a different bug is hit
# extra output is added, so it's 10 total
tryList = [
(57, 300, 9, 'cA', 60, 0),
# try with 1-3 data lines in the header file too
(57, 300, 9, 'cB', 60, 1),
(57, 300, 9, 'cC', 60, 2),
(57, 300, 9, 'cD', 60, 3),
]
trial = 0
for (fileNum, rowCount, colCount, hex_key, timeoutSecs, dataRowsWithHeader) in tryList:
trial += 1
# FIX! should we add a header to them randomly???
print "Wait while", fileNum, "synthetic files are created in", SYNDATASETS_DIR
rowxcol = str(rowCount) + 'x' + str(colCount)
totalCols = colCount + 1 # 1 extra for output
totalDataRows = 0
for fileN in range(fileNum):
csvFilename = 'syn_' + str(fileN) + "_" + str(SEED) + "_" + rowxcol + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
rList = rand_rowData(colCount)
dataRowsDone = write_syn_dataset(csvPathname, rowCount, headerData=None, rList=rList)
totalDataRows += dataRowsDone
# create the header file
# can make it pass by not doing this
if HEADER:
csvFilename = 'syn_header_' + str(SEED) + "_" + rowxcol + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
dataRowsDone = write_syn_dataset(csvPathname, dataRowsWithHeader, headerData, rList)
totalDataRows += dataRowsDone
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
src_key = "syn_" + str(trial)
hex_key = "syn_" + str(trial) + ".hex"
# DON"T get redirected to S3! (EC2 hack in config, remember!)
# use it at the node level directly (because we gen'ed the files.
# I suppose we could force the redirect state bits in h2o.nodes[0] to False, instead?
# put them, rather than using import files, so this works if remote h2o is used
# and python creates the files locally
fileList = os.listdir(SYNDATASETS_DIR)
for f in fileList:
h2i.import_only(path=SYNDATASETS_DIR + "/" + f, schema='put', noPrint=True)
print f
# fix. should we have a h2o.n0 for brevity? or h2o.n. ? so we can change it around if multi-node?
# frames = h2o.nodes[0].frames()['frames']
frames = h2o.n0.frames()['frames']
frames_dict = h2o_util.list_to_dict(frames, 'key/name')
# print "frames:", dump_json(frames)
# print "frames_dict:", dump_json(frames_dict)
if HEADER:
header = h2i.find_key('syn_header')
if not header:
raise Exception("Didn't find syn_header* key in the import")
# use regex. the only files in the dir will be the ones we just created with *fileN* match
print "Header Key = " + header
start = time.time()
# does h2o-dev take a regex? or do we need to glob
parseResult = h2i.parse_only(pattern='*'+rowxcol+'*',
hex_key=hex_key, timeoutSecs=timeoutSecs, check_header="1") # header_from_file=header
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=totalDataRows, expectedNumCols=totalCols)
print pA.numRows
print pA.numCols
print pA.parse_key
expectedLabelList = headerData.split(",")
iA = h2o_cmd.InspectObj(pA.parse_key, expectedNumRows=totalDataRows, expectedNumCols=totalCols,
expectedMissinglist=[], expectedLabelList=expectedLabelList)
if DO_RF:
# put in an ignore param, that will fail unless headers were parsed correctly
if HEADER:
kwargs = {'sample_rate': 0.75, 'max_depth': 25, 'ntrees': 1, 'ignored_columns': "['ID','CAPSULE']"}
else:
kwargs = {'sample_rate': 0.75, 'max_depth': 25, 'ntrees': 1}
rfv = h2o_cmd.runRF(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
h2o.check_sandbox_for_errors()
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 ? supposedly fixed now
# (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
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
maxErr = ((expectedMax - expectedMin) / 20.0) / 2.0
# add 5% for fp errors?
maxErr = 1.05 * maxErr
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)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
# column 0 not used here
assert len(expected) == 6
co = h2o_cmd.runSummary(key=hex_key,
column=0,
expected=expected[1:],
maxDelta=maxErr)
trial += 1
h2o.nodes[0].remove_all_keys()
scipyCol = 0
print "maxErr", 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 0.99,
h2oSummary2=co.percentiles[5 if DO_MEDIAN else 9],
# h2oQuantilesApprox=qresult_single,
# h2oQuantilesExact=qresult,
h2oSummary2MaxErr=maxErr,
)
def test_GLM_many_cols(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
# (2, 100, 'cA', 300),
# (4, 200, 'cA', 300),
(10000, 1000, 'cB', 300),
(10000, 3000, 'cC', 500),
]
### h2b.browseTheCloud()
lenNodes = len(h2o.nodes)
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
# csvFilename = 'syn_' + str(SEEDPERFILE) + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname, hex_key=hex_key, timeoutSecs=180, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
expected = []
allowedDelta = 0
labelListUsed = list(labelList)
response = 'C' + str(len(labelListUsed)-1) # last column
labelListUsed.remove(response)
numColsUsed = numCols - 1
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': None,
# FIX! for now just use a column that's binomial
'response_column': response, # can't take index now?
# FIX! when is this needed? redundant for binomial?
'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': '[0.5,0.25, 0.1]',
'prior1': None,
'lambda_search': None,
'nlambdas': None,
'lambda_min_ratio': None,
'use_all_factor_levels': False,
# NPE with n_folds 2?
'n_folds': 1,
}
model_key = 'many_cols_glm.hex'
bmResult = h2o.n0.build_model(
algo='glm',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=120)
bm = OutputObj(bmResult, 'bm')
modelResult = h2o.n0.models(key=model_key)
model = OutputObj(modelResult['models'][0]['output'], 'model')
h2o_glm.simpleCheckGLM(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')
def test_parse_full_rand(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
if DEBUG:
n = 20
else:
n = 1000000
# from command line arg -long
if 1==0:
repeat = 1000
scale = 10 # scale up the # of rows
tryList = [
(n*scale, 3, 'cI', 300),
]
else:
repeat = 1
scale = 1
tryList = [
(n, 3, 'cI', 300),
]
lastcolsHistory = []
for r in range(repeat):
SEED_PER_FILE = random.randint(0, sys.maxint)
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
# using the comma is nice to ensure no craziness
colSepHexString = '2c' # comma
colSepChar = colSepHexString.decode('hex')
colSepInt = int(colSepHexString, base=16)
print "colSepChar:", colSepChar
rowSepHexString = '0a' # newline
rowSepChar = rowSepHexString.decode('hex')
print "rowSepChar:", rowSepChar
csvFilename = 'syn_enums_' + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
# same enum list/mapping, but different dataset?
start = time.time()
lastcols = write_syn_dataset(csvPathname, rowCount, colCount, scale=1,
colSepChar=colSepChar, rowSepChar=rowSepChar, SEED=SEED_PER_FILE)
elapsed = time.time() - start
print "took %s seconds to create %s" % (elapsed, csvPathname)
# why are we saving this?
lastcolsHistory.append(lastcols)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, check_header=0,
timeoutSecs=60, separator=colSepInt, doSummary=DO_SUMMARY)
inspect = h2o_cmd.runInspect(key=hex_key)
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
# print "missingValuesList", missingValuesList
# for mv in missingValuesList:
# self.assertAlmostEqual(mv, expectedNA, delta=0.1 * mv,
# msg='mv %s is not approx. expected %s' % (mv, expectedNA))
# might have extra rows
if numRows < rowCount:
raise Exception("Expect numRows %s >= rowCount %s since we can have extra eols" % (numRows, rowCount))
# numCols should be right?
self.assertEqual(colCount, numCols)
def test_summary2_NY0(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
choicesList = [
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
(' N', ' Y', ' 0'),
(' n', ' y', ' 0'),
(' F', ' T', ' 0'),
(' f', ' t', ' 0'),
]
# white space is stripped
expectedList = [
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
]
tryList = [
# colname, (min, 25th, 50th, 75th, max)
(100, 200, 'x.hex', choicesList[4], expectedList[4]),
(100, 200, 'x.hex', choicesList[5], expectedList[5]),
(100, 200, 'x.hex', choicesList[6], expectedList[6]),
(100, 200, 'x.hex', choicesList[7], expectedList[7]),
(100, 200, 'x.hex', choicesList[3], expectedList[3]),
(1000, 200, 'x.hex', choicesList[2], expectedList[2]),
(10000, 200, 'x.hex', choicesList[1], expectedList[1]),
(100000, 200, 'x.hex', choicesList[0], expectedList[0]),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
x = 0
timeoutSecs = 60
for (rowCount, colCount, hex_key, choices, expected) 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, choices)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=10,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
for i in range(colCount):
# walks across the columns triggering a summary on the col desired
# runSummary returns a column object now. inspect and parse don't. They return json.
# maybe eventually will make them return object? But I also pass expected stuff to them
# should I pass expected to summary? no, more complex?
co = h2o_cmd.runSummary(key=hex_key, column=i)
print co.label, co.type, co.missing_count, co.domain, sum(
co.histogram_bins)
print "\nComparing column %s to expected" % i
self.assertEqual(expectedNaCnt[i], co.missing_count, "Column %s Expected %s. missing: %s is incorrect" % \
(i, expectedNaCnt[i], co.missing_count))
self.assertEqual(rowCount - expectedNaCnt[i],
sum(co.histogram_bins))
h2p.green_print("\nDone with trial", trial)
trial += 1
h2i.delete_keys_at_all_nodes()
def test_kmeans_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")
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
numColsUsed = numCols
labelListUsed = labelList
### h2b.browseTheCloud()
# try 5 times, to see if all inits by h2o are good
# does it break if cols is not specified?
destination_key = 'syn_spheres100.hex'
cols = ",".join(map(str, range(DIMENSIONS)))
for trial in range(2):
parameters = {
'validation_frame': parse_key,
'ignored_columns': None,
'k': CLUSTERS,
'max_iterations': 50,
'standardize': False,
# 'seed': kmeansSeed,
'init':
'Furthest', # [u'Random', u'PlusPlus', u'Furthest', u'User']
# 'dropNA20Cols': False,
# 'user_points': userPointsKey
}
timeoutSecs = 100
model_key = 'sphere100_k.hex'
kmeansResult = h2o.n0.build_model(algo='kmeans',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=timeoutSecs)
modelResult = h2o.n0.models(key=model_key)
km = h2o_kmeans.KMeansObj(modelResult, parameters, numRows,
numColsUsed, labelListUsed)
# no expected row/error?
expected = [(None, c, None, None) for c in centersList]
expected.sort(key=lambda tup: sum(tup[1]))
h2o_kmeans.compareResultsToExpected(km.tuplesSorted,
expected,
allowedDelta=[.01, .01, .01])
print "Trial #", trial, "completed"
def test_parse_time(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_time.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
headerData = None
colCount = COLS
# rowCount = 1000
rowCount = ROWS
write_syn_dataset(csvPathname, rowCount, colCount, headerData)
for trial in range (20):
rowData = rand_rowData()
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
# src_key = csvFilename + "_" + str(trial)
hex_key = csvFilename + "_" + str(trial) + ".hex"
parseResultA = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key)
print "A trial #", trial
# optional. only needed to extract parse_key?
pA = h2o_cmd.ParseObj(parseResultA, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
csvDownloadPathname = SYNDATASETS_DIR + "/csvDownload.csv"
h2o.nodes[0].csv_download(key=pA.parse_key, csvPathname=csvDownloadPathname)
# do a little testing of saving the key as a csv
# remove the original parsed key. source was already removed by h2o
if 1==0:
h2o.nodes[0].remove_key(pA.parse_key)
# interesting. what happens when we do csv download with time data?
parseResultB = h2i.import_parse(path=csvDownloadPathname, schema='put', hex_key=hex_key)
print "B trial #", trial
pB = h2o_cmd.ParseObj(parseResultB, expectedNumRows=rowCount, expectedNumCols=colCount)
print pB.numRows
print pB.numCols
print pB.parse_key
iB = h2o_cmd.InspectObj(pB.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
# these checks are redundant now
self.assertEqual(iA.missingList, iB.missingList,
"missingValuesList mismatches after re-parse of downloadCsv result")
self.assertEqual(iA.numCols, iB.numCols,
"numCols mismatches after re-parse of downloadCsv result")
# H2O adds a header to the csv created. It puts quotes around the col numbers if no header
# so I guess that's okay. So allow for an extra row here.
self.assertEqual(iA.numRows, iB.numRows,
"pA.numRows: %s pB.numRows: %s mismatch after re-parse of downloadCsv result" % \
(iA.numRows, iB.numRows) )
print "H2O writes the internal format (number) out for time."
# ==> syn_time.csv <==
# 31-Oct-49, 25-NOV-10, 08-MAR-44, 23-Nov-34, 19-Feb-96, 23-JUN-30
# 31-Oct-49, 25-NOV-10, 08-MAR-44, 23-Nov-34, 19-Feb-96, 23-JUN-30
# ==> csvDownload.csv <==
# "0","1","2","3","4","5"
# 2.5219584E12,1.293264E12,2.3437116E12,2.0504736E12,3.9829788E12,1.9110204E12
h2o.check_sandbox_for_errors()
def test_parse_multi_header_single(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
csvFilename = "syn_ints.csv"
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
headerData = "ID,CAPSULE,AGE,RACE,DPROS,DCAPS,PSA,VOL,GLEASON,output"
# cols must be 9 to match the header above, otherwise a different bug is hit
# extra output is added, so it's 10 total
tryList = [
(57, 300, 9, 'cA', 60, 0),
# try with 1-3 data lines in the header file too
(57, 300, 9, 'cB', 60, 1),
(57, 300, 9, 'cC', 60, 2),
(57, 300, 9, 'cD', 60, 3),
]
trial = 0
for (fileNum, rowCount, colCount, hex_key, timeoutSecs,
dataRowsWithHeader) in tryList:
trial += 1
# FIX! should we add a header to them randomly???
print "Wait while", fileNum, "synthetic files are created in", SYNDATASETS_DIR
rowxcol = str(rowCount) + 'x' + str(colCount)
totalCols = colCount + 1 # 1 extra for output
totalDataRows = 0
for fileN in range(fileNum):
csvFilename = 'syn_' + str(fileN) + "_" + str(
SEED) + "_" + rowxcol + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
rList = rand_rowData(colCount)
dataRowsDone = write_syn_dataset(csvPathname,
rowCount,
headerData=None,
rList=rList)
totalDataRows += dataRowsDone
# create the header file
# can make it pass by not doing this
if HEADER:
csvFilename = 'syn_header_' + str(
SEED) + "_" + rowxcol + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
dataRowsDone = write_syn_dataset(csvPathname,
dataRowsWithHeader,
headerData, rList)
totalDataRows += dataRowsDone
# make sure all key names are unique, when we re-put and re-parse (h2o caching issues)
src_key = "syn_" + str(trial)
hex_key = "syn_" + str(trial) + ".hex"
# DON"T get redirected to S3! (EC2 hack in config, remember!)
# use it at the node level directly (because we gen'ed the files.
# I suppose we could force the redirect state bits in h2o.nodes[0] to False, instead?
# put them, rather than using import files, so this works if remote h2o is used
# and python creates the files locally
fileList = os.listdir(SYNDATASETS_DIR)
for f in fileList:
h2i.import_only(path=SYNDATASETS_DIR + "/" + f,
schema='put',
noPrint=True)
print f
# fix. should we have a h2o.n0 for brevity? or h2o.n. ? so we can change it around if multi-node?
# frames = h2o.nodes[0].frames()['frames']
frames = h2o.n0.frames()['frames']
frames_dict = h2o_util.list_to_dict(frames, 'key/name')
# print "frames:", dump_json(frames)
# print "frames_dict:", dump_json(frames_dict)
if HEADER:
header = h2i.find_key('syn_header')
if not header:
raise Exception(
"Didn't find syn_header* key in the import")
# use regex. the only files in the dir will be the ones we just created with *fileN* match
print "Header Key = " + header
start = time.time()
# does h2o-dev take a regex? or do we need to glob
parseResult = h2i.parse_only(
pattern='*' + rowxcol + '*',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
check_header="1") # header_from_file=header
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=totalDataRows,
expectedNumCols=totalCols)
print pA.numRows
print pA.numCols
print pA.parse_key
expectedLabelList = headerData.split(",")
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=totalDataRows,
expectedNumCols=totalCols,
expectedMissinglist=[],
expectedLabelList=expectedLabelList)
if DO_RF:
# put in an ignore param, that will fail unless headers were parsed correctly
if HEADER:
kwargs = {
'sample_rate': 0.75,
'max_depth': 25,
'ntrees': 1,
'ignored_columns': "['ID','CAPSULE']"
}
else:
kwargs = {
'sample_rate': 0.75,
'max_depth': 25,
'ntrees': 1
}
rfv = h2o_cmd.runRF(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
h2o.check_sandbox_for_errors()
def test_summary2_NY0(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
choicesList = [
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
(' N', ' Y', ' 0'),
(' n', ' y', ' 0'),
(' F', ' T', ' 0'),
(' f', ' t', ' 0'),
]
# white space is stripped
expectedList = [
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
('N', 'Y', '0'),
('n', 'y', '0'),
('F', 'T', '0'),
('f', 't', '0'),
]
tryList = [
# colname, (min, 25th, 50th, 75th, max)
(100, 200, 'x.hex', choicesList[4], expectedList[4]),
(100, 200, 'x.hex', choicesList[5], expectedList[5]),
(100, 200, 'x.hex', choicesList[6], expectedList[6]),
(100, 200, 'x.hex', choicesList[7], expectedList[7]),
(100, 200, 'x.hex', choicesList[3], expectedList[3]),
(1000, 200, 'x.hex', choicesList[2], expectedList[2]),
(10000, 200, 'x.hex', choicesList[1], expectedList[1]),
(100000, 200, 'x.hex', choicesList[0], expectedList[0]),
]
timeoutSecs = 10
trial = 1
n = h2o.nodes[0]
lenNodes = len(h2o.nodes)
x = 0
timeoutSecs = 60
for (rowCount, colCount, hex_key, choices, expected) 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, choices)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=10, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
for i in range(colCount):
# walks across the columns triggering a summary on the col desired
# runSummary returns a column object now. inspect and parse don't. They return json.
# maybe eventually will make them return object? But I also pass expected stuff to them
# should I pass expected to summary? no, more complex?
co = h2o_cmd.runSummary(key=hex_key, column=i)
print co.label, co.type, co.missing_count, co.domain, sum(co.histogram_bins)
print "\nComparing column %s to expected" % i
self.assertEqual(expectedNaCnt[i], co.missing_count, "Column %s Expected %s. missing: %s is incorrect" % \
(i, expectedNaCnt[i], co.missing_count))
self.assertEqual(rowCount - expectedNaCnt[i], sum(co.histogram_bins))
h2p.green_print("\nDone with trial", trial)
trial += 1
h2i.delete_keys_at_all_nodes()
def test_rapids_cut(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(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)
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))
REPEAT = 1
data_key = hex_key
for i in range(REPEAT):
result_key = data_key + "_" + str(i)
Assign('seq1', Seq(range(5)) )
# take advantage of default params for row/col (None)
# need the 'c' function, to make sure the key is created
Assign('seq2', Fcn('c', Seq(range(5)) ))
inspect = h2o_cmd.runInspect(key='seq1')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
Assign('seq3', Col(Seq(range(5))) )
inspect = h2o_cmd.runInspect(key='seq2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
# can't have sequence of sequences?
# make sure key is created with c()
Assign('seq4', Fcn('c', Seq(Colon(99,400), "#2", 1, range(1,5), range(7,10), range(50,52) )) )
inspect = h2o_cmd.runInspect(key='seq1')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(inspect)
Assign(result_key, KeyIndexed(data_key, row=Seq(range(1, 5))) )
Assign('seq5', KeyIndexed(data_key, row=Seq(Colon(99, 400), "#2", 1, range(1,5))) )
# they need to be same size
# Assign('seq6', Key('seq5') + Key('seq4') + Key('seq3'))
# doesn't like my cut? complains on FALSE
# Assign(result_key, Cut(KeyIndexed(data_key, col=0)))
# Assign(result_key, Cut(KeyIndexed(data_key, col=1), breaks=3))
Assign(result_key, Fcn('min', KeyIndexed(data_key, col=1), True))
Assign(result_key, Fcn('max', KeyIndexed(data_key, col=1), True))
Assign(result_key, Fcn('mean', KeyIndexed(data_key, col=1), 0, False))
Assign(result_key, KeyIndexed(data_key, row='#1'))
Assign(result_key, KeyIndexed(data_key, row=Colon('#1', '#100')))
Assign(result_key, KeyIndexed(data_key, row=Colon(1, 100)))
# this should fail rapids because of reverse msb/lsb
# illegal, detected
# resultExpr, result = Assign(result_key, KeyIndexed(data_key, row=Colon('#100', '#1')))
Assign(result_key, KeyIndexed(data_key, row=Colon('#-2', '#-1')))
Assign(result_key, KeyIndexed(data_key, row=Colon(-2, -1)))
# illegal, detected
# resultExpr, result = Assign(result_key, KeyIndexed(data_key, row=Colon('#-1', '#-2')))
# take advantage of number to string conversion
Assign(result_key, KeyIndexed(data_key, row=Colon('#1', rowCount-10)))
Assign(result_key, KeyIndexed(data_key, col=Colon('#1', colCount-1, )))
# no assign. Expr() complains when result has no key?
Assign(result_key, KeyIndexed(data_key, row=Colon('#1', rowCount-10)))
Assign(result_key, KeyIndexed(data_key, col=Colon('#1', colCount-1,)))
# do some function translation
Assign(result_key, Fcn('==', 1, KeyIndexed(data_key, col=Colon('#1', colCount-1,))) )
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
def setUpClass(cls):
h2o.init()
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
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_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,
check_header=1,
delete_on_done=0,
timeoutSecs=180,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
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, # KeyIndexed False []
'ignored_columns': None, # string[] None []
'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_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_summary_stepping(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
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]),
(5, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', 1, 20000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -5000, 0, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', .4900, .5000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -.5000, -.4900, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', 490, 500, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -500, -490, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', 49000, 50000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -50000, -49000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', 4900, 5000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -5000, -4900, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -100000, 100000, ['C1', None, None, None, None, None]),
(5, 1, 'x.hex', -1, 1, ['C1', None, None, None, None, None]),
(5, 1, 'x.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
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
(expectedMin, expectedMax) = write_syn_dataset(csvPathname, rowCount, colCount, rangeMin, rangeMax, SEED=SEEDPERFILE)
print "expectedMin:", expectedMin, "expectedMax:", expectedMax
# add 5% for fp errors?
maxErr = ((expectedMax - expectedMin)/1000) * 1.05
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)
pA = h2o_cmd.ParseObj(parseResult, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
# column 0 not used here
assert len(expected) == 6
co = h2o_cmd.runSummary(key=hex_key, column=0, expected=expected[1:], maxDelta=maxErr)
trial += 1
h2o.nodes[0].remove_all_keys()
scipyCol = 0
print "maxErr", 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 0.99,
h2oSummary2=co.percentiles[5 if DO_MEDIAN else 9],
# h2oQuantilesApprox=qresult_single,
# h2oQuantilesExact=qresult,
h2oSummary2MaxErr=maxErr,
)
def test_PCA_many_cols(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(10000, 10, 'cA', 300),
(10000, 50, 'cB', 300),
(10000, 100, 'cC', 300),
# (10000, 500, 'cH', 300),
# (10000, 1000, 'cI', 300),
]
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
print(rowCount, colCount, hex_key, timeoutSecs)
SEEDPERFILE = random.randint(0, sys.maxint)
csvFilename = 'syn_' + "binary" + "_" + str(rowCount) + 'x' + str(
colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE)
# PARSE ****************************************
modelKey = 'PCAModelKey'
scoreKey = 'PCAScoreKey'
# Parse ****************************************
parseResult = h2i.import_parse(bucket=None,
path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
# PCA(tolerance iterate)****************************************
for tolerance in [i / 10.0 for i in range(11)]:
parameters = {
# 'tolerance': tolerance,
# 'standardize': 1,
'k': 1,
}
model_key = 'pca.hex'
bmResult = h2o.n0.build_model(algo='pca',
model_id=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_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 setUpClass(cls):
h2o.init()
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
def test_rapids_cut(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(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)
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))
REPEAT = 1
data_key = hex_key
for i in range(REPEAT):
result_key = data_key + "_" + str(i)
Assign('seq1', Seq(range(5)))
# take advantage of default params for row/col (None)
# need the 'c' function, to make sure the key is created
Assign('seq2', Fcn('c', Seq(range(5))))
inspect = h2o_cmd.runInspect(key='seq1')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
Assign('seq3', Col(Seq(range(5))))
inspect = h2o_cmd.runInspect(key='seq2')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
# can't have sequence of sequences?
# make sure key is created with c()
Assign(
'seq4',
Fcn(
'c',
Seq(Colon(99, 400), "#2", 1, range(1, 5), range(7, 10),
range(50, 52))))
inspect = h2o_cmd.runInspect(key='seq1')
missingList, labelList, numRows, numCols = h2o_cmd.infoFromInspect(
inspect)
Assign(result_key, KeyIndexed(data_key, row=Seq(range(1, 5))))
Assign(
'seq5',
KeyIndexed(data_key,
row=Seq(Colon(99, 400), "#2", 1, range(1, 5))))
# they need to be same size
# Assign('seq6', Key('seq5') + Key('seq4') + Key('seq3'))
# doesn't like my cut? complains on FALSE
# Assign(result_key, Cut(KeyIndexed(data_key, col=0)))
# Assign(result_key, Cut(KeyIndexed(data_key, col=1), breaks=3))
Assign(result_key, Fcn('min', KeyIndexed(data_key, col=1),
True))
Assign(result_key, Fcn('max', KeyIndexed(data_key, col=1),
True))
Assign(result_key,
Fcn('mean', KeyIndexed(data_key, col=1), 0, False))
Assign(result_key, KeyIndexed(data_key, row='#1'))
Assign(result_key, KeyIndexed(data_key,
row=Colon('#1', '#100')))
Assign(result_key, KeyIndexed(data_key, row=Colon(1, 100)))
# this should fail rapids because of reverse msb/lsb
# illegal, detected
# resultExpr, result = Assign(result_key, KeyIndexed(data_key, row=Colon('#100', '#1')))
Assign(result_key, KeyIndexed(data_key,
row=Colon('#-2', '#-1')))
Assign(result_key, KeyIndexed(data_key, row=Colon(-2, -1)))
# illegal, detected
# resultExpr, result = Assign(result_key, KeyIndexed(data_key, row=Colon('#-1', '#-2')))
# take advantage of number to string conversion
Assign(result_key,
KeyIndexed(data_key, row=Colon('#1', rowCount - 10)))
Assign(result_key,
KeyIndexed(data_key, col=Colon(
'#1',
colCount - 1,
)))
# no assign. Expr() complains when result has no key?
Assign(result_key,
KeyIndexed(data_key, row=Colon('#1', rowCount - 10)))
Assign(result_key,
KeyIndexed(data_key, col=Colon(
'#1',
colCount - 1,
)))
# do some function translation
Assign(
result_key,
Fcn('==', 1,
KeyIndexed(data_key, col=Colon(
'#1',
colCount - 1,
))))
print "\n" + csvPathname, \
" numRows:", "{:,}".format(numRows), \
" numCols:", "{:,}".format(numCols)
def test_kmeans_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")
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
numColsUsed = numCols
labelListUsed = labelList
### h2b.browseTheCloud()
# try 5 times, to see if all inits by h2o are good
# does it break if cols is not specified?
destination_key = 'syn_spheres100.hex'
cols = ",".join(map(str,range(DIMENSIONS)))
for trial in range(2):
parameters = {
'validation_frame': parse_key,
'ignored_columns': None,
'k': CLUSTERS,
'max_iterations': 50,
'standardize': False,
# 'seed': kmeansSeed,
'init': 'Furthest', # [u'Random', u'PlusPlus', u'Furthest', u'User']
# 'dropNA20Cols': False,
# 'user_points': userPointsKey
}
timeoutSecs = 100
model_key = 'sphere100_k.hex'
kmeansResult = h2o.n0.build_model(
algo='kmeans',
destination_key=model_key,
training_frame=parse_key,
parameters=parameters,
timeoutSecs=timeoutSecs)
modelResult = h2o.n0.models(key=model_key)
km = h2o_kmeans.KMeansObj(modelResult, parameters, numRows, numColsUsed, labelListUsed)
# no expected row/error?
expected = [(None, c, None, None) for c in centersList]
expected.sort(key=lambda tup: sum(tup[1]))
h2o_kmeans.compareResultsToExpected(km.tuplesSorted, expected, allowedDelta=[.01, .01, .01])
print "Trial #", trial, "completed"
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)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
numRows = pA.numRows
numCols = pA.numCols
parse_key = pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
#***************************
# Summary
co = h2o_cmd.runSummary(key=parse_key)
default_pctiles = co.default_pctiles
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 = {
'model_id': "a.hex",
'training_frame': parse_key,
'validation_frame': parse_key,
'ignored_columns': None,
'probs': probsStr,
}
model_key = 'qhex'
bmResult = h2o.n0.build_model(algo='quantile',
model_id=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')
print "model.output:", model.output
print "model.output:['quantiles']", model.output['quantiles']
print "model.output:['iterations']", model.output['iterations']
print "model.output:['names']", model.output['names']
quantiles = model.output['quantiles'][
0] # why is this a double array
iterations = model.output['iterations']
assert iterations == 11, iterations
print "quantiles: ", quantiles
print "iterations: ", iterations
# 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()
def test_plot_remove_keys(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100000, 100, 'cG', 400),
(200000, 100, 'cH', 400),
(400000, 100, 'cI', 400),
(800000, 100, 'cJ', 400),
(1000000, 100, 'cK', 400),
]
xList = []
eList = []
fList = []
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
SEEDPERFILE = random.randint(0, sys.maxint)
NUM_CASES = h2o_util.fp_format()
sel = random.randint(0, NUM_CASES - 1)
csvFilename = "syn_%s_%s_%s_%s.csv" % (SEEDPERFILE, sel, rowCount,
colCount)
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
write_syn_dataset(csvPathname, rowCount, colCount, SEEDPERFILE,
sel)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=timeoutSecs,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
iA = h2o_cmd.InspectObj(pA.parse_key)
parseElapsed = pA.python_elapsed
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
print parse_key, parseElapsed, numRows, numCols
labelList = iA.labelList
node = h2o.nodes[0]
print "Deleting", hex_key, "at", node.http_addr, "Shouldn't matter what node the delete happens at..global?"
start = time.time()
node.remove_key(hex_key, timeoutSecs=30)
removeElapsed = time.time() - start
print "Deleting", hex_key, "took", removeElapsed, "seconds"
# xList.append(ntrees)
xList.append(numRows)
eList.append(parseElapsed)
fList.append(removeElapsed)
# just plot the last one
if 1 == 1:
xLabel = 'byteSize'
eLabel = 'parseElapsed'
fLabel = 'removeElapsed'
eListTitle = ""
fListTitle = ""
h2o_gbm.plotLists(xList, xLabel, eListTitle, eList, eLabel,
fListTitle, fList, fLabel)
def test_w2v_basic(self):
global SYNDATASETS_DIR
SYNDATASETS_DIR = h2o.make_syn_dir()
n = 500000
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)
# just parse to make sure it's good
parseResult = h2i.import_parse(path=csvPathname,
check_header=1, delete_on_done = 0, timeoutSecs=180, doSummary=False)
pA = h2o_cmd.ParseObj(parseResult)
iA = h2o_cmd.InspectObj(pA.parse_key)
cA = h2o_test.OutputObj(iA.columns[0], "inspect_column")
parse_key = pA.parse_key
numRows = iA.numRows
numCols = iA.numCols
labelList = iA.labelList
for i in range(colCount):
print cA.type, cA.missing_count
self.assertEqual(0, cA.missing_count, "Column %s Expected %s. missing: %s is incorrect" % (i, 0, cA.missing_count))
self.assertEqual('string', cA.type, "Column %s Expected %s. type: %s is incorrect" % (i, 0, cA.type))
if DO_SUMMARY:
for i in range(colCount):
co = h2o_cmd.runSummary(key=parse_key, column=i)
print co.label, co.type, co.missing, co.domain, sum(co.bins)
self.assertEqual(0, co.missing_count, "Column %s Expected %s. missing: %s is incorrect" % (i, 0, co.missing_count))
self.assertEqual('String', co.type, "Column %s Expected %s. type: %s is incorrect" % (i, 0, co.type))
# no cols ignored
labelListUsed = list(labelList)
numColsUsed = numCols
for trial in range(1):
parameters = {
'validation_frame': parse_key, # KeyIndexed False []
'ignored_columns': None, # string[] None []
'minWordFreq': 5, # int 5 []
'wordModel': 'SkipGram', # enum [u'CBOW', u'SkipGram']
'normModel': 'HSM', # enum # [u'HSM', u'NegSampling']
'negSampleCnt': 5,# int 5 []
'vecSize': 100, # int 100
'windowSize': 5, # 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',
model_id=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['model_metrics'][0], 'mm')
# not implemented?
# 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_parse_rand_enum_compress(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
if DEBUG:
n = 20
else:
n = 1000000
# from command line arg -long
if h2o_args.long_test_case:
repeat = 1000
scale = 10 # scale up the # of rows
tryList = [
(n*scale, 1, 'cI', 300),
(n*scale, 1, 'cI', 300),
(n*scale, 1, 'cI', 300),
]
else:
repeat = 1
scale = 1
tryList = [
(n, 3, 'cI', 300),
(n, 3, 'cI', 300),
(n, 3, 'cI', 300),
]
lastcolsHistory = []
enumList = create_enum_list(listSize=ENUMS_NUM)
for r in range(repeat):
SEED_PER_FILE = random.randint(0, sys.maxint)
for (rowCount, colCount, hex_key, timeoutSecs) in tryList:
# using the comma is nice to ensure no craziness
colSepHexString = '2c' # comma
colSepChar = colSepHexString.decode('hex')
colSepInt = int(colSepHexString, base=16)
print "colSepChar:", colSepChar
rowSepHexString = '0a' # newline
rowSepChar = rowSepHexString.decode('hex')
print "rowSepChar:", rowSepChar
csvFilename = 'syn_enums_' + str(rowCount) + 'x' + str(colCount) + '.csv'
csvPathname = SYNDATASETS_DIR + '/' + csvFilename
print "Creating random", csvPathname
# same enum list/mapping, but different dataset?
start = time.time()
lastcols = write_syn_dataset(csvPathname, enumList, rowCount, colCount, scale=1,
colSepChar=colSepChar, rowSepChar=rowSepChar, SEED=SEED_PER_FILE)
elapsed = time.time() - start
print "took %s seconds to create %s" % (elapsed, csvPathname)
# why are we saving this?
lastcolsHistory.append(lastcols)
parseResult = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key, check_header=0,
timeoutSecs=30, separator=colSepInt, doSummary=DO_SUMMARY)
parseResultA = h2i.import_parse(path=csvPathname, schema='put', hex_key=hex_key)
# optional. only needed to extract parse_key?
pA = h2o_cmd.ParseObj(parseResultA, expectedNumRows=rowCount, expectedNumCols=colCount)
print pA.numRows
print pA.numCols
print pA.parse_key
# this guy can take json object as first thing, or re-read with key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount, expectedNumCols=colCount, expectedMissinglist=[])
self.assertEqual(rowCount, iA.numRows)
self.assertEqual(colCount, iA.numCols)
def test_0_NA_2enum(self):
SYNDATASETS_DIR = h2o.make_syn_dir()
tryList = [
(100, 30, '0', 'cC', 100),
(100, 30, '0.0', 'cC', 100),
(100, 30, '0.0000000', 'cC', 100),
]
for (rowCount, colCount, zero, 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, zero,
SEEDPERFILE)
parseResult = h2i.import_parse(path=csvPathname,
schema='put',
hex_key=hex_key,
timeoutSecs=30,
doSummary=False)
pA = h2o_cmd.ParseObj(parseResult,
expectedNumRows=rowCount,
expectedNumCols=colCount)
print pA.numRows, pA.numCols, pA.parse_key
iA = h2o_cmd.InspectObj(pA.parse_key,
expectedNumRows=rowCount,
expectedNumCols=colCount,
expectedMissinglist=[])
print iA.missingList, iA.labelList, iA.numRows, iA.numCols
# column 0 not used here
# assert len(expected) == 6
# FIX! add expected and maxDelta?
co = h2o_cmd.runSummary(key=hex_key, column=0)
print co.label, co.type, co.missing, co.domain, sum(co.bins)
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 k, v in co:
print k, v
if DO_REBALANCE:
print "Rebalancing it to create an artificially large # of chunks"
rb_key = "rb_%s" % hex_key
start = time.time()
print "Rebalancing %s to %s with %s chunks" % (
hex_key, rb_key, REBALANCE_CHUNKS)
rebalanceResult = h2o.nodes[0].rebalance(
source=hex_key, after=rb_key, chunks=REBALANCE_CHUNKS)
elapsed = time.time() - start
print "rebalance end on ", csvFilename, 'took', elapsed, 'seconds'
else:
rb_key = hex_key
print "Now doing to_enum across all columns of %s" % hex_key
for column_index in range(colCount):
# is the column index 1-base in to_enum
result = h2o.nodes[0].to_enum(None,
src_key=hex_key,
column_index=column_index + 1)
# print "\nto_enum result:", h2o.dump_json(result)
co = h2o_cmd.runSummary(key=hex_key, column=column_index + 1)
print co.label, co.type, co.missing, co.domain, sum(co.bins)
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
]
if co.type != 'Enum':
raise Exception(
"column %s, which has name %s, didn't convert to Enum, is %s"
% (column_index, colname, co.type))
# I'm generating NA's ..so it should be > 0. .but it could be zero . I guess i have enough rows to get at least 1
if co.missing <= 0 or co.missing > rowCount:
raise Exception(
"column %s, which has name %s, somehow got NA cnt wrong after convert to Enum %s %s"
% (column_index, colname, co.missing, rowCount))
if co.domain != 1: # NAs don't count?
# print "stats:", h2o.dump_json(stats)
print "column:", h2o.dump_json(co)
raise Exception(
"column %s, which has name %s, should have cardinality 1, got: %s"
% (column_index, co.label, domain))
