def test_GLM2_score_same(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
bucket = 'home-0xdiag-datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard' + '/' + csvFilename
y = "10"
kwargs = {'response': y, 'alpha': 0, 'family': 'gaussian'}
(modelKey, validation1, parseResult) = glm_doit(self, csvFilename, bucket, csvPathname,
timeoutSecs=60, pollTimeoutSecs=60, **kwargs)
print "Use", modelKey, "model on 2x and 4x replications and compare results to 1x"
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
modelPathname = SYNDATASETS_DIR + '/model_' + filename2x
bucket = None
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_score(self,filename2x, bucket, pathname2x, modelKey, modelPathname, timeoutSecs=60, pollTimeoutSecs=60)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
modelPathname = SYNDATASETS_DIR + '/model_' + filename4x
h2o_util.file_cat(pathname2x, pathname2x, pathname4x)
print "Iterating 3 times on this last one"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_score(self,filename4x, bucket, pathname4x, modelKey, modelPathname, timeoutSecs=60, pollTimeoutSecs=60)
def test_1mx10_hastie_10_2_cat_and_shuffle(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
# This test also adds file shuffling, to see that row order doesn't matter
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
kmeans_doit(self, csvFilename, csvPathname, num_rows=1000000, timeoutSecs=60)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename1xShuf = "hastie_1x.data_shuf"
pathname1xShuf = SYNDATASETS_DIR + '/' + filename1xShuf
h2o_util.file_shuffle(pathname1x, pathname1xShuf)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1xShuf, pathname1xShuf, pathname2x)
filename2xShuf = "hastie_2x.data_shuf"
pathname2xShuf = SYNDATASETS_DIR + '/' + filename2xShuf
h2o_util.file_shuffle(pathname2x, pathname2xShuf)
kmeans_doit(self, filename2xShuf, pathname2xShuf, num_rows=2000000, timeoutSecs=90)
# too big to shuffle?
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2xShuf, pathname2xShuf, pathname4x)
kmeans_doit(self, filename4x, pathname4x, num_rows=4000000, timeoutSecs=120)
def test_KMeans_hastie_shuffle_fvec(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
# This test also adds file shuffling, to see that row order doesn't matter
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard/' + csvFilename
bucket = 'home-0xdiag-datasets'
kmeans_doit(self, csvFilename, bucket, csvPathname, numRows=1000000, timeoutSecs=60)
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename1xShuf = "hastie_1x.data_shuf"
pathname1xShuf = SYNDATASETS_DIR + '/' + filename1xShuf
h2o_util.file_shuffle(pathname1x, pathname1xShuf)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1xShuf, pathname1xShuf, pathname2x)
filename2xShuf = "hastie_2x.data_shuf"
pathname2xShuf = SYNDATASETS_DIR + '/' + filename2xShuf
h2o_util.file_shuffle(pathname2x, pathname2xShuf)
kmeans_doit(self, filename2xShuf, None, pathname2xShuf, numRows=2000000, timeoutSecs=90)
# too big to shuffle?
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2xShuf, pathname2xShuf, pathname4x)
kmeans_doit(self, filename4x, None, pathname4x, numRows=4000000, timeoutSecs=120)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
y = "10"
x = ""
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
(modelKey, validations1) = glm_doit(self, csvFilename, csvPathname,
timeoutSecs=60, pollTimeoutSecs=60, **kwargs)
print "Use", modelKey, "model on 2x and 4x replications and compare results to 1x"
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_score(self,filename2x, pathname2x, modelKey, thresholds="0.5",
timeoutSecs=60, pollTimeoutSecs=60)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x,pathname2x,pathname4x)
print "Iterating 3 times on this last one"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_score(self,filename4x, pathname4x, modelKey, thresholds="0.5",
timeoutSecs=60, pollTimeoutSecs=60)
def test_GLM_hastie(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
bucket = 'home-0xdiag-datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard' + '/' + csvFilename
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=75)
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self,filename2x, None, pathname2x, timeoutSecs=75)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x,pathname2x,pathname4x)
print "Iterating 3 times on this last one for perf compare"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_doit(self, filename4x, None, pathname4x, timeoutSecs=150)
def test_1mx10_hastie_10_2_cat_and_shuffle(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
# This test also adds file shuffling, to see that row order doesn't matter
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
glm_doit(self, csvFilename, csvPathname, timeoutSecs=30)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename1xShuf = "hastie_1x.data_shuf"
pathname1xShuf = SYNDATASETS_DIR + '/' + filename1xShuf
h2o_util.file_shuffle(pathname1x, pathname1xShuf)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1xShuf, pathname1xShuf, pathname2x)
filename2xShuf = "hastie_2x.data_shuf"
pathname2xShuf = SYNDATASETS_DIR + '/' + filename2xShuf
h2o_util.file_shuffle(pathname2x, pathname2xShuf)
glm_doit(self, filename2xShuf, pathname2xShuf, timeoutSecs=45)
# too big to shuffle?
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2xShuf, pathname2xShuf, pathname4x)
glm_doit(self, filename4x, pathname4x, timeoutSecs=120)
def test_GLM_hastie_shuffle(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
# This test also adds file shuffling, to see that row order doesn't matter
csvFilename = "1mx10_hastie_10_2.data.gz"
bucket = 'home-0xdiag-datasets'
csvPathname = 'standard' + '/' + csvFilename
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename1xShuf = "hastie_1x.data_shuf"
pathname1xShuf = SYNDATASETS_DIR + '/' + filename1xShuf
h2o_util.file_shuffle(pathname1x, pathname1xShuf)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1xShuf, pathname1xShuf, pathname2x)
filename2xShuf = "hastie_2x.data_shuf"
pathname2xShuf = SYNDATASETS_DIR + '/' + filename2xShuf
h2o_util.file_shuffle(pathname2x, pathname2xShuf)
glm_doit(self, filename2xShuf, None, pathname2xShuf, timeoutSecs=45)
# too big to shuffle?
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2xShuf,pathname2xShuf,pathname4x)
glm_doit(self,filename4x, None, pathname4x, timeoutSecs=120)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
glm_doit(self,csvFilename, csvPathname, timeoutSecs=30)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self,filename2x, pathname2x, timeoutSecs=45)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x,pathname2x,pathname4x)
print "Iterating 3 times on this last one for perf compare"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_doit(self,filename4x, pathname4x, timeoutSecs=60)
def test_GLM_hastie(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
bucket = 'home-0xdiag-datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard' + '/' + csvFilename
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=75)
fullPathname = h2i.find_folder_and_filename(bucket,
csvPathname,
returnFullPath=True)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x, pathname1x, pathname2x)
glm_doit(self, filename2x, None, pathname2x, timeoutSecs=75)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x, pathname2x, pathname4x)
print "Iterating 3 times on this last one for perf compare"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_doit(self, filename4x, None, pathname4x, timeoutSecs=150)
def test_1mx10_hastie_10_2_cat_and_shuffle(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
# This test also adds file shuffling, to see that row order doesn't matter
csvFilename = "1mx10_hastie_10_2.data.gz"
bucket = 'datasets'
csvPathname = 'logreg' + '/' + csvFilename
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename1xShuf = "hastie_1x.data_shuf"
pathname1xShuf = SYNDATASETS_DIR + '/' + filename1xShuf
h2o_util.file_shuffle(pathname1x, pathname1xShuf)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1xShuf, pathname1xShuf, pathname2x)
filename2xShuf = "hastie_2x.data_shuf"
pathname2xShuf = SYNDATASETS_DIR + '/' + filename2xShuf
h2o_util.file_shuffle(pathname2x, pathname2xShuf)
glm_doit(self, filename2xShuf, None, pathname2xShuf, timeoutSecs=45)
# too big to shuffle?
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2xShuf,pathname2xShuf,pathname4x)
glm_doit(self,filename4x, None, pathname4x, timeoutSecs=120)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
glm_doit(self,csvFilename, csvPathname, timeoutSecs=75)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self,filename2x, pathname2x, timeoutSecs=75)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x,pathname2x,pathname4x)
print "Iterating 3 times on this last one for perf compare"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_doit(self,filename4x, pathname4x, timeoutSecs=150)
def test_GLM2_score_same(self):
h2o.beta_features = True
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
bucket = 'home-0xdiag-datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard' + '/' + csvFilename
y = "10"
kwargs = {'response': y, 'alpha': 0, 'family': 'gaussian'}
(modelKey, validation1, parseResult) = glm_doit(self, csvFilename, bucket, csvPathname,
timeoutSecs=60, pollTimeoutSecs=60, **kwargs)
print "Use", modelKey, "model on 2x and 4x replications and compare results to 1x"
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
modelPathname = SYNDATASETS_DIR + '/model_' + filename2x
bucket = None
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_score(self,filename2x, bucket, pathname2x, modelKey, modelPathname, timeoutSecs=60, pollTimeoutSecs=60)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
modelPathname = SYNDATASETS_DIR + '/model_' + filename4x
h2o_util.file_cat(pathname2x, pathname2x, pathname4x)
print "Iterating 3 times on this last one"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_score(self,filename4x, bucket, pathname4x, modelKey, modelPathname, timeoutSecs=60, pollTimeoutSecs=60)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
glm_doit(self,csvFilename, csvPathname, timeoutSecs=300)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self,filename2x, pathname2x, timeoutSecs=300)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = h2o.find_dataset('logreg' + '/' + csvFilename)
glm_doit(self, csvFilename, csvPathname, timeoutSecs=300)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(csvPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x, pathname1x, pathname2x)
glm_doit(self, filename2x, pathname2x, timeoutSecs=300)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
bucket = 'home-0xdiag-datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'standard' + '/' + csvFilename
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=300)
fullPathname = h2i.find_folder_and_filename('home-0xdiag-datasets', csvPathname, returnFullPath=True)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self, filename2x, None, pathname2x, timeoutSecs=300)
def test_A_1mx10_hastie_10_2(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
# FIX! eventually we'll compare the 1x, 2x and 4x results like we do
# in other tests. (catdata?)
bucket = 'datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'logreg' + '/' + csvFilename
glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=300)
fullPathname = h2i.find_folder_and_filename('datasets', csvPathname, returnFullPath=True)
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_doit(self, filename2x, None, pathname2x, timeoutSecs=300)
def test_GLM_score_same(self):
# gunzip it and cat it to create 2x and 4x replications in SYNDATASETS_DIR
bucket = 'datasets'
csvFilename = "1mx10_hastie_10_2.data.gz"
csvPathname = 'logreg' + '/' + csvFilename
y = "10"
x = ""
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
(modelKey, validations1, parseResult) = glm_doit(self, csvFilename, bucket, csvPathname,
timeoutSecs=60, pollTimeoutSecs=60, **kwargs)
print "Use", modelKey, "model on 2x and 4x replications and compare results to 1x"
filename1x = "hastie_1x.data"
pathname1x = SYNDATASETS_DIR + '/' + filename1x
fullPathname = h2i.find_folder_and_filename(bucket, csvPathname, returnFullPath=True)
h2o_util.file_gunzip(fullPathname, pathname1x)
filename2x = "hastie_2x.data"
pathname2x = SYNDATASETS_DIR + '/' + filename2x
bucket = None
h2o_util.file_cat(pathname1x,pathname1x,pathname2x)
glm_score(self,filename2x, bucket, pathname2x, modelKey, thresholds="0.5",
timeoutSecs=60, pollTimeoutSecs=60)
filename4x = "hastie_4x.data"
pathname4x = SYNDATASETS_DIR + '/' + filename4x
h2o_util.file_cat(pathname2x, pathname2x, pathname4x)
print "Iterating 3 times on this last one"
for i in range(3):
print "\nTrial #", i, "of", filename4x
glm_score(self,filename4x, bucket, pathname4x, modelKey, thresholds="0.5",
timeoutSecs=60, pollTimeoutSecs=60)
