def glm_doit(self, csvFilename, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=csvFilename + ".hex", timeoutSecs=10)
y = "10"
x = ""
# Took num_cross_validation_folds out, because GLM doesn't include num_cross_validation_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values, 1 and -1. need to use case for one of them
kwargs = {'x': x, 'y': y, 'case': -1}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=timeoutSecs, **kwargs)
print "GLM in", (time.time() - start), "secs (python measured)"
h2o_glm.simpleCheckGLM(self, glm, 7, **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
validations = validationsList[0]
# validations['err']
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, self.validations1)
else:
self.validations1 = copy.deepcopy(validations)
def test_GLM_from_import_hosts(self):
if localhost:
csvFilenameList = ["covtype.data"]
else:
csvFilenameList = [
"covtype200x.data",
"covtype200x.data",
"covtype.data",
"covtype.data",
"covtype20x.data",
"covtype20x.data",
]
# a browser window too, just because we can
h2b.browseTheCloud()
importFolderPath = "/home/0xdiag/datasets/standard"
validations1 = {}
coefficients1 = {}
for csvFilename in csvFilenameList:
# have to re-import each iteration now, since the source key
# is removed and if we re-parse it, it's not there
h2i.setupImportFolder(None, importFolderPath, timeoutSecs=60)
# creates csvFilename.hex from file in importFolder dir
parseKey = h2i.parseImportFolderFile(None, csvFilename, importFolderPath, timeoutSecs=2000)
print csvFilename, "parse time:", parseKey["response"]["time"]
print "Parse result['destination_key']:", parseKey["destination_key"]
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseKey["destination_key"])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
# FIX! just look at X=0:1 for speed, for now
kwargs = {"y": 54, "n_folds": 2, "family": "binomial", "case": 1}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=2000, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.verboseprint("\nglm:", glm)
h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm["GLMModel"]
coefficients = GLMModel["coefficients"]
validationsList = GLMModel["validations"]
validations = validationsList.pop()
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, "err", validations, validations1)
else:
validations1 = copy.deepcopy(validations)
if coefficients1:
h2o_glm.compareToFirstGlm(self, "0", coefficients, coefficients1)
else:
coefficients1 = copy.deepcopy(coefficients)
sys.stdout.write(".")
sys.stdout.flush()
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, hex_key=csvFilename + ".hex", schema='put', timeoutSecs=30)
y = "10"
x = ""
# Took n_folds out, because GLM doesn't include n_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values 1,-1. need to specify case
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
print "GLM in", (time.time() - start), "secs (python)"
h2o_glm.simpleCheckGLM(self, glm, "C8", **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
validations = validationsList[0]
# validations['err']
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, self.validations1)
else:
self.validations1 = copy.deepcopy(validations)
def glm_doit(self, csvFilename, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname,
key2=csvFilename + ".hex",
timeoutSecs=10)
y = "10"
x = ""
# Took n_folds out, because GLM doesn't include n_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values, 1 and -1. need to use case for one of them
kwargs = {'x': x, 'y': y, 'case': -1}
start = time.time()
glm = h2o_cmd.runGLMOnly(parseKey=parseKey,
timeoutSecs=timeoutSecs,
**kwargs)
print "GLM in", (time.time() - start), "secs (python measured)"
h2o_glm.simpleCheckGLM(self, glm, 7, **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
validations = validationsList[0]
# validations['err']
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, self.validations1)
else:
self.validations1 = copy.deepcopy(validations)
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseResult = h2i.import_parse(bucket=bucket,
path=csvPathname,
hex_key=csvFilename + ".hex",
schema='put',
timeoutSecs=10)
y = 10
# Took n_folds out, because GLM doesn't include n_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values, 1 and -1. need to use case for one of them
kwargs = {'response': y, 'alpha': 0, 'family': 'binomial'}
h2o.nodes[0].to_enum(src_key=parseResult['destination_key'],
column_index=y + 1)
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
print "GLM in", (time.time() - start), "secs (python measured)"
h2o_glm.simpleCheckGLM(self, glm, "C8", **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
glm_model = glm['glm_model']
validation = glm_model['submodels'][0]['validation']
if self.validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, self.validation1)
else:
self.validation1 = copy.deepcopy(validation)
def glm_score(self, csvFilename, bucket, csvPathname, modelKey, modelPathname, timeoutSecs=30, pollTimeoutSecs=30):
print "\nStarting GLM score of", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=timeoutSecs, pollTimeoutSecs=pollTimeoutSecs)
y = "10"
# save and restore the model
h2o.nodes[0].save_model(model=modelKey, path=modelPathname, force=1)
# FIX! should we remove the existing key to make sure it loads? really should try both cases (existing or not)
h2o.nodes[0].load_model(path=modelPathname)
start = time.time()
glmScore = h2o_cmd.runScore(dataKey=parseResult['destination_key'], modelKey=modelKey,
vactual=y, vpredict=1, expectedAuc=0.5, doAUC=False)
print "GLMScore in", (time.time() - start), "secs (python)"
h2o.verboseprint(h2o.dump_json(glmScore))
# compare this glm to the first one. since the files are replications,
# the results
# should be similar?
# UPDATE: format for returning results is slightly different than normal GLM
if self.glmScore1:
h2o_glm.compareToFirstGlm(self, 'mse', glmScore, self.glmScore1)
else:
self.glmScore1 = copy.deepcopy(glmScore)
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname,
hex_key=csvFilename + ".hex", schema='put', timeoutSecs=10)
y = 10
# Took n_folds out, because GLM doesn't include n_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values, 1 and -1. need to use case for one of them
kwargs = {'response': y, 'alpha': 0, 'family': 'binomial'}
h2o.nodes[0].to_enum(src_key=parseResult['destination_key'], column_index=y+1)
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
print "GLM in", (time.time() - start), "secs (python measured)"
h2o_glm.simpleCheckGLM(self, glm, "C8", **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
glm_model = glm['glm_model']
validation = glm_model['submodels'][0]['validation']
if self.validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, self.validation1)
else:
self.validation1 = copy.deepcopy(validation)
def glm_score(self, csvFilename, csvPathname, modelKey, thresholds="0.5",
timeoutSecs=30, pollTimeoutSecs=30):
print "\nStarting GLM score of", csvFilename
key2 = csvFilename + ".hex"
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=key2,
timeoutSecs=timeoutSecs, pollTimeoutSecs=pollTimeoutSecs)
y = "10"
x = ""
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
start = time.time()
glmScore = h2o_cmd.runGLMScore(key=key2, model_key=modelKey, thresholds="0.5",
timeoutSecs=timeoutSecs)
print "GLMScore in", (time.time() - start), "secs (python)"
h2o.verboseprint(h2o.dump_json(glmScore))
### h2o_glm.simpleCheckGLM(self, glm, 7, **kwargs)
# compare this glm to the first one. since the files are replications,
# the results
# should be similar?
# UPDATE: format for returning results is slightly different than normal GLM
validation = glmScore['validation']
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validation, self.validations1)
else:
self.validations1 = copy.deepcopy(validation)
def test_GLM_from_import_hosts(self):
if localhost:
csvFilenameList = [
'covtype.data',
]
else:
csvFilenameList = [
'covtype200x.data',
'covtype200x.data',
'covtype.data',
'covtype.data',
'covtype20x.data',
'covtype20x.data',
]
# a browser window too, just because we can
## h2b.browseTheCloud()
importFolderPath = "standard"
validations1= {}
coefficients1= {}
for csvFilename in csvFilenameList:
# have to re-import each iteration now, since the source key
# is removed and if we re-parse it, it's not there
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, timeoutSecs=2000)
print csvFilename, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult['destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
# FIX! just look at X=0:1 for speed, for now
kwargs = {'y': 54, 'n_folds': 2, 'family': "binomial", 'case': 1}
glm = h2o_cmd.runGLMOnly(parseResult=parseResult, timeoutSecs=2000, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.verboseprint("\nglm:", glm)
h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
coefficients = GLMModel['coefficients']
validationsList = GLMModel['validations']
validations = validationsList.pop()
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, validations1)
else:
validations1 = copy.deepcopy(validations)
if coefficients1:
h2o_glm.compareToFirstGlm(self, '0', coefficients, coefficients1)
else:
coefficients1 = copy.deepcopy(coefficients)
sys.stdout.write('.')
sys.stdout.flush()
def glm_score(self, csvFilename, bucket, csvPathname, modelKey, modelPathname, timeoutSecs=30, pollTimeoutSecs=30):
print "\nStarting GLM score of", csvFilename
hex_key = csvFilename + ".hex"
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, schema='put', hex_key=hex_key,
timeoutSecs=timeoutSecs, pollTimeoutSecs=pollTimeoutSecs)
y = "10"
# save and restore the model
h2o.nodes[0].save_model(model=modelKey, path=modelPathname, force=1)
# FIX! should we remove the existing key to make sure it loads? really should try both cases (existing or not)
h2o.nodes[0].load_model(path=modelPathname)
start = time.time()
glmScore = h2o_cmd.runScore(dataKey=parseResult['destination_key'], modelKey=modelKey,
vactual=y, vpredict=1, expectedAuc=0.5, doAUC=False)
print "GLMScore in", (time.time() - start), "secs (python)"
h2o.verboseprint(h2o.dump_json(glmScore))
# compare this glm to the first one. since the files are replications,
# the results
# should be similar?
# UPDATE: format for returning results is slightly different than normal GLM
if self.glmScore1:
h2o_glm.compareToFirstGlm(self, 'mse', glmScore, self.glmScore1)
else:
self.glmScore1 = copy.deepcopy(glmScore)
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
parseResult = h2i.import_parse(bucket=bucket,
path=csvPathname,
hex_key=csvFilename + ".hex",
schema='put',
timeoutSecs=30)
y = "10"
x = ""
# Took n_folds out, because GLM doesn't include n_folds time and it's slow
# wanted to compare GLM time to my measured time
# hastie has two values 1,-1. need to specify case
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
start = time.time()
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
print "GLM in", (time.time() - start), "secs (python)"
h2o_glm.simpleCheckGLM(self, glm, "C8", **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
validations = validationsList[0]
# validations['err']
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, self.validations1)
else:
self.validations1 = copy.deepcopy(validations)
def test_GLM_catdata_hosts(self):
# these are still in /home/kevin/scikit/datasets/logreg
# FIX! just two for now..
csvFilenameList = [
"1_100kx7_logreg.data.gz", "2_100kx7_logreg.data.gz"
]
# pop open a browser on the cloud
h2b.browseTheCloud()
# save the first, for all comparisions, to avoid slow drift with each iteration
validations1 = {}
for csvFilename in csvFilenameList:
csvPathname = h2o.find_file('smalldata/' + csvFilename)
# I use this if i want the larger set in my localdir
# csvPathname = h2o.find_file('/home/kevin/scikit/datasets/logreg/' + csvFilename)
print "\n" + csvPathname
start = time.time()
# FIX! why can't I include 0 here? it keeps getting 'unable to solve" if 0 is included
# 0 by itself is okay?
kwargs = {
'y': 7,
'x': '1,2,3,4,5,6',
'family': "binomial",
'n_folds': 3,
'lambda': 1e-4
}
timeoutSecs = 200
glm = h2o_cmd.runGLM(csvPathname=csvPathname,
timeoutSecs=timeoutSecs,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, 6, **kwargs)
print "glm end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
print validationsList
validations = validationsList[0]
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations,
validations1)
else:
validations1 = copy.deepcopy(validations)
sys.stdout.write('.')
sys.stdout.flush()
def test_GLM2_from_import_hosts(self):
h2o.beta_features = True
csvFilenameList = [
'covtype.data',
'covtype20x.data',
]
# a browser window too, just because we can
## h2b.browseTheCloud()
importFolderPath = "standard"
validation1 = {}
for csvFilename in csvFilenameList:
# have to re-import each iteration now, since the source key
# is removed and if we re-parse it, it's not there
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
hex_key='A.hex',
timeoutSecs=2000)
print "Parse result['destination_key']:", parseResult[
'destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
case = 1
y = 54
execExpr = "A.hex[,%s]=(A.hex[,%s]==%s)" % (y + 1, y + 1, case)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=30)
kwargs = {'response': y, 'n_folds': 2, 'family': "binomial"}
glm = h2o_cmd.runGLM(parseResult={'destination_key': 'A.hex'},
timeoutSecs=2000,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
validation = glm['glm_model']['submodels'][0]['validation']
if validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, validation1)
else:
validation1 = copy.deepcopy(validation)
def test_GLM2_catdata_hosts(self):
h2o.beta_features = True
# these are still in /home/kevin/scikit/datasets/logreg
# FIX! just two for now..
csvFilenameList = [
"1_100kx7_logreg.data.gz", "2_100kx7_logreg.data.gz"
]
# pop open a browser on the cloud
### h2b.browseTheCloud()
# save the first, for all comparisions, to avoid slow drift with each iteration
validation1 = {}
for csvFilename in csvFilenameList:
csvPathname = csvFilename
parseResult = h2i.import_parse(bucket='smalldata',
path=csvPathname,
schema='put')
print "\n" + csvPathname
start = time.time()
# FIX! why can't I include 0 here? it keeps getting 'unable to solve" if 0 is included
# 0 by itself is okay?
kwargs = {
'response': 7,
'family': "binomial",
'n_folds': 3,
'lambda': 1e-4
}
timeoutSecs = 200
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=timeoutSecs,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, 'C7', **kwargs)
print "glm end on ", csvPathname, 'took', time.time(
) - start, 'seconds'
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
# compare this glm to the first one. since the files are replications, the results
# should be similar?
validation = glm['glm_model']['submodels'][0]['validation']
if validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, validation1)
else:
validation1 = copy.deepcopy(validation)
def test_GLM_catdata_hosts(self):
# these are still in /home/kevin/scikit/datasets/logreg
# FIX! just two for now..
csvFilenameList = [
"1_100kx7_logreg.data.gz",
"2_100kx7_logreg.data.gz"
]
# pop open a browser on the cloud
h2b.browseTheCloud()
# save the first, for all comparisions, to avoid slow drift with each iteration
validations1 = {}
for csvFilename in csvFilenameList:
csvPathname = h2o.find_file('smalldata/' + csvFilename)
# I use this if i want the larger set in my localdir
# csvPathname = h2o.find_file('/home/kevin/scikit/datasets/logreg/' + csvFilename)
print "\n" + csvPathname
start = time.time()
# FIX! why can't I include 0 here? it keeps getting 'unable to solve" if 0 is included
# 0 by itself is okay?
kwargs = {'y': 7, 'x': '1,2,3,4,5,6', 'family': "binomial", 'num_cross_validation_folds': 3, 'lambda': 1e-4}
timeoutSecs = 200
glm = h2o_cmd.runGLM(csvPathname=csvPathname, timeoutSecs=timeoutSecs, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, 6, **kwargs)
print "glm end on ", csvPathname, 'took', time.time() - start, 'seconds'
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
print validationsList
validations = validationsList[0]
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, validations1)
else:
validations1 = copy.deepcopy(validations)
sys.stdout.write('.')
sys.stdout.flush()
def test_GLM2_from_import_hosts(self):
h2o.beta_features = True
csvFilenameList = [
'covtype.data',
'covtype20x.data',
]
# a browser window too, just because we can
## h2b.browseTheCloud()
importFolderPath = "standard"
validation1= {}
for csvFilename in csvFilenameList:
# have to re-import each iteration now, since the source key
# is removed and if we re-parse it, it's not there
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets', path=csvPathname, hex_key='A.hex', timeoutSecs=2000)
print "Parse result['destination_key']:", parseResult['destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
case = 1
y = 54
execExpr="A.hex[,%s]=(A.hex[,%s]==%s)" % (y+1, y+1, case)
h2e.exec_expr(execExpr=execExpr, timeoutSecs=30)
kwargs = {'response': y, 'n_folds': 2, 'family': "binomial"}
glm = h2o_cmd.runGLM(parseResult={'destination_key': 'A.hex'}, timeoutSecs=2000, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
validation = glm['glm_model']['submodels'][0]['validation']
if validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, validation1)
else:
validation1 = copy.deepcopy(validation)
def test_GLM_catdata_hosts(self):
# these are still in /home/kevin/scikit/datasets/logreg
# FIX! just two for now..
csvFilenameList = [
"1_100kx7_logreg.data.gz",
"2_100kx7_logreg.data.gz"
]
# pop open a browser on the cloud
### h2b.browseTheCloud()
# save the first, for all comparisions, to avoid slow drift with each iteration
validations1 = {}
for csvFilename in csvFilenameList:
csvPathname = csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
print "\n" + csvPathname
start = time.time()
# FIX! why can't I include 0 here? it keeps getting 'unable to solve" if 0 is included
# 0 by itself is okay?
kwargs = {'y': 7, 'x': '1,2,3,4,5,6', 'family': "binomial", 'n_folds': 3, 'lambda': 1e-4}
timeoutSecs = 200
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, 'C7', **kwargs)
print "glm end on ", csvPathname, 'took', time.time() - start, 'seconds'
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
validationsList = glm['GLMModel']['validations']
print validationsList
validations = validationsList[0]
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, validations1)
else:
validations1 = copy.deepcopy(validations)
def test_GLM2_catdata_hosts(self):
h2o.beta_features = True
# these are still in /home/kevin/scikit/datasets/logreg
# FIX! just two for now..
csvFilenameList = [
"1_100kx7_logreg.data.gz",
"2_100kx7_logreg.data.gz"
]
# pop open a browser on the cloud
### h2b.browseTheCloud()
# save the first, for all comparisions, to avoid slow drift with each iteration
validation1 = {}
for csvFilename in csvFilenameList:
csvPathname = csvFilename
parseResult = h2i.import_parse(bucket='smalldata', path=csvPathname, schema='put')
print "\n" + csvPathname
start = time.time()
# FIX! why can't I include 0 here? it keeps getting 'unable to solve" if 0 is included
# 0 by itself is okay?
kwargs = {'response': 7, 'family': "binomial", 'n_folds': 3, 'lambda': 1e-4}
timeoutSecs = 200
glm = h2o_cmd.runGLM(parseResult=parseResult, timeoutSecs=timeoutSecs, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, 'C7', **kwargs)
print "glm end on ", csvPathname, 'took', time.time() - start, 'seconds'
### h2b.browseJsonHistoryAsUrlLastMatch("GLM")
# compare this glm to the first one. since the files are replications, the results
# should be similar?
validation = glm['glm_model']['submodels'][0]['validation']
if validation1:
h2o_glm.compareToFirstGlm(self, 'auc', validation, validation1)
else:
validation1 = copy.deepcopy(validation)
def glm_score(self, csvFilename, csvPathname, modelKey, timeoutSecs=3):
print "\nStarting GLM score of", csvFilename
key2 = csvFilename + ".hex"
parseKey = h2o_cmd.parseFile(csvPathname=csvPathname, key2=key2, timeoutSecs=10)
y = "10"
x = ""
kwargs = {'x': x, 'y': y, 'case': -1, 'thresholds': 0.5}
start = time.time()
glmScore = h2o_cmd.runGLMScore(key=key2, model_key=modelKey, timeoutSecs=timeoutSecs)
print "GLMScore in", (time.time() - start), "secs (python)"
h2o.verboseprint(h2o.dump_json(glmScore))
### h2o_glm.simpleCheckGLM(self, glm, 7, **kwargs)
# compare this glm to the first one. since the files are replications, the results
# should be similar?
GLMModel = glmScore['GLMModel']
validationsList = glmScore['GLMModel']['validations']
validations = validationsList[0]
if self.validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, self.validations1)
else:
self.validations1 = copy.deepcopy(validations)
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
# we can force a col type to enum now? with param columnTypes
# "Numeric"
# make the last column enum
# Instead of string for parse, make this a dictionary, with column index, value
# that's used for updating the ColumnTypes array before making it a string for parse
columnTypeDict = {10: 'Enum'}
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, columnTypeDict=columnTypeDict,
hex_key=csvFilename + ".hex", schema='put', timeoutSecs=30)
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
for i in range(10):
print "Summary on column", i
# FIX! how come only 0 works here for column
co = h2o_cmd.runSummary(key=parse_key, column=i)
for k,v in co:
print k, v
expected = []
allowedDelta = 0
labelListUsed = list(labelList)
labelListUsed.remove('C11')
numColsUsed = numCols - 1
parameters = {
'validation_frame': parse_key,
'ignored_columns': None,
# FIX! for now just use a column that's binomial
'response_column': 'C11',
# 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,
}
start = time.time()
model_key = 'hastie_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')
# compare this glm to the first one. since the files are replications, the results
# should be similar?
if self.validation1:
h2o_glm.compareToFirstGlm(self, 'AUC', validation, self.validation1)
else:
# self.validation1 = copy.deepcopy(validation)
self.validation1 = None
def test_GLM_from_import_hosts(self):
if localhost:
csvFilenameList = [
'covtype.data',
]
else:
csvFilenameList = [
'covtype200x.data',
'covtype200x.data',
'covtype.data',
'covtype.data',
'covtype20x.data',
'covtype20x.data',
]
# a browser window too, just because we can
h2b.browseTheCloud()
importFolderPath = '/home/0xdiag/datasets'
h2i.setupImportFolder(None, importFolderPath)
validations1= {}
coefficients1= {}
for csvFilename in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
parseKey = h2i.parseImportFolderFile(None, csvFilename, importFolderPath, timeoutSecs=2000)
print csvFilename, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey['destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseKey['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
# FIX! just look at X=0:1 for speed, for now
kwargs = {'y': 54, 'n_folds': 2, 'family': "binomial", 'case': 1}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey, timeoutSecs=2000, **kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.verboseprint("\nglm:", glm)
h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
print "GLM time", GLMModel['time']
coefficients = GLMModel['coefficients']
validationsList = GLMModel['validations']
validations = validationsList.pop()
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations, validations1)
else:
validations1 = copy.deepcopy(validations)
if coefficients1:
h2o_glm.compareToFirstGlm(self, '0', coefficients, coefficients1)
else:
coefficients1 = copy.deepcopy(coefficients)
sys.stdout.write('.')
sys.stdout.flush()
def test_GLM_from_import_hosts(self):
if localhost:
csvFilenameList = [
'covtype.data',
]
else:
csvFilenameList = [
'covtype200x.data',
'covtype200x.data',
'covtype.data',
'covtype.data',
'covtype20x.data',
'covtype20x.data',
]
# a browser window too, just because we can
h2b.browseTheCloud()
importFolderPath = '/home/0xdiag/datasets'
h2i.setupImportFolder(None, importFolderPath)
validations1 = {}
coefficients1 = {}
for csvFilename in csvFilenameList:
# creates csvFilename.hex from file in importFolder dir
parseKey = h2i.parseImportFolderFile(None,
csvFilename,
importFolderPath,
timeoutSecs=2000)
print csvFilename, 'parse time:', parseKey['response']['time']
print "Parse result['destination_key']:", parseKey[
'destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseKey['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
# FIX! just look at X=0:1 for speed, for now
kwargs = {'y': 54, 'n_folds': 2, 'family': "binomial", 'case': 1}
glm = h2o_cmd.runGLMOnly(parseKey=parseKey,
timeoutSecs=2000,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.verboseprint("\nglm:", glm)
h2b.browseJsonHistoryAsUrlLastMatch("GLM")
GLMModel = glm['GLMModel']
print "GLM time", GLMModel['time']
coefficients = GLMModel['coefficients']
validationsList = GLMModel['validations']
validations = validationsList.pop()
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations,
validations1)
else:
validations1 = copy.deepcopy(validations)
if coefficients1:
h2o_glm.compareToFirstGlm(self, '0', coefficients,
coefficients1)
else:
coefficients1 = copy.deepcopy(coefficients)
sys.stdout.write('.')
sys.stdout.flush()
def test_GLM_from_import_hosts(self):
if localhost:
csvFilenameList = [
'covtype.data',
]
else:
csvFilenameList = [
'covtype200x.data',
'covtype200x.data',
'covtype.data',
'covtype.data',
'covtype20x.data',
'covtype20x.data',
]
# a browser window too, just because we can
## h2b.browseTheCloud()
importFolderPath = "standard"
validations1 = {}
coefficients1 = {}
for csvFilename in csvFilenameList:
# have to re-import each iteration now, since the source key
# is removed and if we re-parse it, it's not there
csvPathname = importFolderPath + "/" + csvFilename
parseResult = h2i.import_parse(bucket='home-0xdiag-datasets',
path=csvPathname,
timeoutSecs=2000)
print csvFilename, 'parse time:', parseResult['response']['time']
print "Parse result['destination_key']:", parseResult[
'destination_key']
# We should be able to see the parse result?
inspect = h2o_cmd.runInspect(key=parseResult['destination_key'])
print "\n" + csvFilename
start = time.time()
# can't pass lamba as kwarg because it's a python reserved word
# FIX! just look at X=0:1 for speed, for now
kwargs = {'y': 54, 'n_folds': 2, 'family': "binomial", 'case': 1}
glm = h2o_cmd.runGLM(parseResult=parseResult,
timeoutSecs=2000,
**kwargs)
h2o_glm.simpleCheckGLM(self, glm, None, **kwargs)
h2o.verboseprint("\nglm:", glm)
GLMModel = glm['GLMModel']
coefficients = GLMModel['coefficients']
validationsList = GLMModel['validations']
validations = validationsList.pop()
# validations['err']
if validations1:
h2o_glm.compareToFirstGlm(self, 'err', validations,
validations1)
else:
validations1 = copy.deepcopy(validations)
if coefficients1:
h2o_glm.compareToFirstGlm(self, 'C1', coefficients,
coefficients1)
else:
coefficients1 = copy.deepcopy(coefficients)
sys.stdout.write('.')
sys.stdout.flush()
def glm_doit(self, csvFilename, bucket, csvPathname, timeoutSecs=30):
print "\nStarting GLM of", csvFilename
# we can force a col type to enum now? with param columnTypes
# "Numeric"
# make the last column enum
# Instead of string for parse, make this a dictionary, with column index, value
# that's used for updating the ColumnTypes array before making it a string for parse
columnTypeDict = {10: 'Enum'}
parseResult = h2i.import_parse(bucket=bucket, path=csvPathname, columnTypeDict=columnTypeDict,
hex_key=csvFilename + ".hex", schema='put', timeoutSecs=30)
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
for i in range(10):
print "Summary on column", i
# FIX! how come only 0 works here for column
co = h2o_cmd.runSummary(key=parse_key, column=i)
for k,v in co:
print k, v
expected = []
allowedDelta = 0
labelListUsed = list(labelList)
labelListUsed.remove('C11')
numColsUsed = numCols - 1
parameters = {
'validation_frame': parse_key,
'ignored_columns': None,
# FIX! for now just use a column that's binomial
'response_column': 'C11',
# FIX! when is this needed? redundant for binomial?
'balance_classes': False,
'max_after_balance_size': None,
'standardize': False,
'family': 'binomial',
'link': None,
'alpha': '[1e-4]',
'lambda': '[0.5,0.25, 0.1]',
'lambda_search': None,
'nlambdas': None,
'lambda_min_ratio': None,
'use_all_factor_levels': False,
}
start = time.time()
model_key = 'hastie_glm.hex'
bmResult = h2o.n0.build_model(
algo='glm',
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')
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')
# compare this glm to the first one. since the files are replications, the results
# should be similar?
if self.validation1:
h2o_glm.compareToFirstGlm(self, 'AUC', validation, self.validation1)
else:
# self.validation1 = copy.deepcopy(validation)
self.validation1 = None
