def comparison_test_dense():
assert H2OXGBoostEstimator.available() is True
runSeed = 1
testTol = 1e-6
ntrees = 10
maxdepth = 5
nrows = 10000
ncols = 10
factorL = 20
numCols = 5
enumCols = ncols-numCols
responseL = 4
# CPU Backend is forced for the results to be comparable
h2oParamsD = {"ntrees":ntrees, "max_depth":maxdepth, "seed":runSeed, "learn_rate":0.7, "col_sample_rate_per_tree" : 0.9,
"min_rows" : 5, "score_tree_interval": ntrees+1, "dmatrix_type":"dense","tree_method": "exact", "backend":"cpu"}
nativeParam = {'colsample_bytree': h2oParamsD["col_sample_rate_per_tree"],
'tree_method': 'exact',
'seed': h2oParamsD["seed"],
'booster': 'gbtree',
'objective': 'multi:softprob',
'lambda': 0.0,
'eta': h2oParamsD["learn_rate"],
'grow_policy': 'depthwise',
'alpha': 0.0,
'subsample': 1.0,
'colsample_bylevel': 1.0,
'max_delta_step': 0.0,
'min_child_weight': h2oParamsD["min_rows"],
'gamma': 0.0,
'max_depth': h2oParamsD["max_depth"],
'num_class':responseL}
trainFile = pyunit_utils.genTrainFrame(nrows, numCols, enumCols=enumCols, enumFactors=factorL,
responseLevel=responseL, miscfrac=0.01)
myX = trainFile.names
y='response'
myX.remove(y)
enumCols = myX[0:enumCols]
h2oModelD = H2OXGBoostEstimator(**h2oParamsD)
# gather, print and save performance numbers for h2o model
h2oModelD.train(x=myX, y=y, training_frame=trainFile)
h2oTrainTimeD = h2oModelD._model_json["output"]["run_time"]
time1 = time.time()
h2oPredictD = h2oModelD.predict(trainFile)
h2oPredictTimeD = time.time()-time1
# train the native XGBoost
nativeTrain = pyunit_utils.convertH2OFrameToDMatrix(trainFile, y, enumCols=enumCols)
nativeModel = xgb.train(params=nativeParam,
dtrain=nativeTrain)
nativeTrainTime = time.time()-time1
time1=time.time()
nativePred = nativeModel.predict(data=nativeTrain, ntree_limit=ntrees)
nativeScoreTime = time.time()-time1
pyunit_utils.summarizeResult_multinomial(h2oPredictD, nativePred, h2oTrainTimeD, nativeTrainTime, h2oPredictTimeD,
nativeScoreTime, tolerance=testTol)
def comparison_test():
if sys.version.startswith("2"):
print("native XGBoost tests only supported on python3")
return
import xgboost as xgb
assert H2OXGBoostEstimator.available() is True
ret = h2o.cluster()
if len(ret.nodes) == 1:
runSeed = 1
dataSeed = 17
ntrees = 17
maxdepth = 5
nrows = 10000
ncols = 12
factorL = 20
numCols = 1
enumCols = ncols-numCols
responseL = 4
# CPU Backend is forced for the results to be comparable
h2oParamsD = {"ntrees":ntrees, "max_depth":maxdepth, "seed":runSeed, "learn_rate":0.7,
"col_sample_rate_per_tree" : 0.9, "min_rows" : 5, "score_tree_interval": ntrees+1,
"tree_method": "exact", "backend":"cpu"}
trainFile = pyunit_utils.genTrainFrame(nrows, numCols, enumCols=enumCols, enumFactors=factorL,
responseLevel=responseL, miscfrac=0.01,randseed=dataSeed)
myX = trainFile.names
y='response'
myX.remove(y)
newNames = []
for ind in range(0, len(myX)):
myX[ind] = myX[ind]+"_"+str(ind) # avoid duplicated column names
newNames.append(myX[ind])
newNames.append(y)
trainFile.set_names(newNames)
h2oModelD = H2OXGBoostEstimator(**h2oParamsD)
# gather, print and save performance numbers for h2o model
h2oModelD.train(x=myX, y=y, training_frame=trainFile)
h2oPredictD = h2oModelD.predict(trainFile)
# derive native XGBoost parameter and DMatrx from h2oXGBoost model and H2OFrame
nativeXGBoostParam = h2oModelD.convert_H2OXGBoostParams_2_XGBoostParams()
nativeXGBoostInput = trainFile.convert_H2OFrame_2_DMatrix(myX, y, h2oModelD)
nativeModel = xgb.train(params=nativeXGBoostParam[0],
dtrain=nativeXGBoostInput, num_boost_round=nativeXGBoostParam[1])
nativePred = nativeModel.predict(data=nativeXGBoostInput, ntree_limit=nativeXGBoostParam[1])
pyunit_utils.summarizeResult_multinomial(h2oPredictD, nativePred, -1, -1, -1,
-1, tolerance=1e-6)
else:
print("******** Test skipped. This test cannot be performed in multinode environment.")
def comparison_test():
assert H2OXGBoostEstimator.available() is True
ret = h2o.cluster()
if len(ret.nodes) == 1:
runSeed = 1
dataSeed = 17
ntrees = 17
maxdepth = 5
nrows = 10000
ncols = 12
factorL = 20
numCols = 11
enumCols = ncols-numCols
responseL = 4
# CPU Backend is forced for the results to be comparable
h2oParamsD = {"ntrees":ntrees, "max_depth":maxdepth, "seed":runSeed, "learn_rate":0.7, "col_sample_rate_per_tree" : 0.9,
"min_rows" : 5, "score_tree_interval": ntrees+1, "tree_method": "exact", "backend":"cpu"}
trainFile = pyunit_utils.genTrainFrame(nrows, numCols, enumCols=enumCols, enumFactors=factorL,
responseLevel=responseL, miscfrac=0.01,randseed=dataSeed)
myX = trainFile.names
y='response'
myX.remove(y)
newNames = []
for ind in range(0, len(myX)):
myX[ind] = myX[ind]+"_"+str(ind) # avoid duplicated column names
newNames.append(myX[ind])
newNames.append(y)
trainFile.set_names(newNames)
h2oModelD = H2OXGBoostEstimator(**h2oParamsD)
# gather, print and save performance numbers for h2o model
h2oModelD.train(x=myX, y=y, training_frame=trainFile)
h2oPredictD = h2oModelD.predict(trainFile)
# derive native XGBoost parameter and DMatrx from h2oXGBoost model and H2OFrame
nativeXGBoostParam = h2oModelD.convert_H2OXGBoostParams_2_XGBoostParams()
nativeXGBoostInput = trainFile.convert_H2OFrame_2_DMatrix(myX, y, h2oModelD)
nativeModel = xgb.train(params=nativeXGBoostParam[0],
dtrain=nativeXGBoostInput, num_boost_round=nativeXGBoostParam[1])
nativePred = nativeModel.predict(data=nativeXGBoostInput, ntree_limit=nativeXGBoostParam[1])
pyunit_utils.summarizeResult_multinomial(h2oPredictD, nativePred, -1, -1, -1,
-1, tolerance=1e-6)
else:
print("******** Test skipped. This test cannot be performed in multinode environment.")
def comparison_test():
assert H2OXGBoostEstimator.available() is True
ret = h2o.cluster()
if len(ret.nodes) == 1:
runSeed = 1
dataSeed = 17
ntrees = 17
responseL = 11
# CPU Backend is forced for the results to be comparable
h2oParamsS = {"ntrees":ntrees, "max_depth":4, "seed":runSeed, "learn_rate":0.7, "col_sample_rate_per_tree" : 0.9,
"min_rows" : 5, "score_tree_interval": ntrees+1, "dmatrix_type":"sparse", "tree_method": "exact", "backend":"cpu"}
nativeParam = {'colsample_bytree': h2oParamsS["col_sample_rate_per_tree"],
'tree_method': 'exact',
'seed': h2oParamsS["seed"],
'booster': 'gbtree',
'objective': 'multi:softprob',
'eta': h2oParamsS["learn_rate"],
'grow_policy': 'depthwise',
'alpha': 0.0,
'subsample': 1.0,
'colsample_bylevel': 1.0,
'max_delta_step': 0.0,
'min_child_weight': h2oParamsS["min_rows"],
'gamma': 0.0,
'max_depth': h2oParamsS["max_depth"],
'num_class':responseL}
nrows = 10000
ncols = 10
factorL = 11
numCols = 0
enumCols = ncols-numCols
trainFile = pyunit_utils.genTrainFrame(nrows, numCols, enumCols=enumCols, enumFactors=factorL, miscfrac=0.5,
responseLevel=responseL, randseed=dataSeed) # load in dataset and add response column
print(trainFile)
myX = trainFile.names
y='response'
myX.remove(y)
nativeTrain = pyunit_utils.convertH2OFrameToDMatrixSparse(trainFile, y, enumCols=myX)
h2oModelS = H2OXGBoostEstimator(**h2oParamsS)
# gather, print and save performance numbers for h2o model
h2oModelS.train(x=myX, y=y, training_frame=trainFile)
h2oTrainTimeS = h2oModelS._model_json["output"]["run_time"]
time1 = time.time()
h2oPredictS = h2oModelS.predict(trainFile)
h2oPredictTimeS = time.time()-time1
# train the native XGBoost
nrounds = ntrees
nativeModel = xgb.train(params=nativeParam, dtrain=nativeTrain, num_boost_round=nrounds)
modelInfo = nativeModel.get_dump()
print(modelInfo)
print("num_boost_round: {1}, Number of trees built: {0}".format(len(modelInfo), nrounds))
nativeTrainTime = time.time()-time1
time1=time.time()
nativePred = nativeModel.predict(data=nativeTrain, ntree_limit=ntrees)
nativeScoreTime = time.time()-time1
print("Comparing H2OXGBoost results with native XGBoost result when DMatrix is set to sparse.....")
pyunit_utils.summarizeResult_multinomial(h2oPredictS, nativePred, h2oTrainTimeS, nativeTrainTime, h2oPredictTimeS,
nativeScoreTime, tolerance=1e-6)
else:
print("******** Test skipped. This test cannot be performed in multinode environment.")
def comparison_test_dense():
if sys.version.startswith("2"):
print("native XGBoost tests only supported on python3")
return
import xgboost as xgb
assert H2OXGBoostEstimator.available() is True
ret = h2o.cluster()
if len(ret.nodes) == 1:
runSeed = 1
dataSeed = 17
testTol = 1e-6
ntrees = 17
maxdepth = 5
nrows = 10000
ncols = 10
factorL = 20
numCols = 5
enumCols = ncols - numCols
responseL = 4
# CPU Backend is forced for the results to be comparable
h2oParamsD = {
"ntrees": ntrees,
"max_depth": maxdepth,
"seed": runSeed,
"learn_rate": 0.7,
"col_sample_rate_per_tree": 0.9,
"min_rows": 5,
"score_tree_interval": ntrees + 1,
"dmatrix_type": "dense",
"tree_method": "exact",
"backend": "cpu"
}
nativeParam = {
'colsample_bytree': h2oParamsD["col_sample_rate_per_tree"],
'tree_method': 'exact',
'seed': h2oParamsD["seed"],
'booster': 'gbtree',
'objective': 'multi:softprob',
'eta': h2oParamsD["learn_rate"],
'grow_policy': 'depthwise',
'alpha': 0.0,
'subsample': 1.0,
'colsample_bylevel': 1.0,
'max_delta_step': 0.0,
'min_child_weight': h2oParamsD["min_rows"],
'gamma': 0.0,
'max_depth': h2oParamsD["max_depth"],
'num_class': responseL
}
trainFile = pyunit_utils.genTrainFrame(nrows,
numCols,
enumCols=enumCols,
enumFactors=factorL,
responseLevel=responseL,
miscfrac=0.01,
randseed=dataSeed)
myX = trainFile.names
y = 'response'
myX.remove(y)
enumCols = myX[0:enumCols]
h2oModelD = H2OXGBoostEstimator(**h2oParamsD)
# gather, print and save performance numbers for h2o model
h2oModelD.train(x=myX, y=y, training_frame=trainFile)
h2oTrainTimeD = h2oModelD._model_json["output"]["run_time"]
time1 = time.time()
h2oPredictD = h2oModelD.predict(trainFile)
h2oPredictTimeD = time.time() - time1
# train the native XGBoost
nativeTrain = pyunit_utils.convertH2OFrameToDMatrix(trainFile,
y,
enumCols=enumCols)
nrounds = ntrees
nativeModel = xgb.train(params=nativeParam,
dtrain=nativeTrain,
num_boost_round=nrounds)
modelInfo = nativeModel.get_dump()
print(modelInfo)
print("num_boost_round: {1}, Number of trees built: {0}".format(
len(modelInfo), nrounds))
nativeTrainTime = time.time() - time1
time1 = time.time()
nativePred = nativeModel.predict(data=nativeTrain, ntree_limit=ntrees)
nativeScoreTime = time.time() - time1
pyunit_utils.summarizeResult_multinomial(h2oPredictD,
nativePred,
h2oTrainTimeD,
nativeTrainTime,
h2oPredictTimeD,
nativeScoreTime,
tolerance=testTol)
else:
print(
"******** Test skipped. This test cannot be performed in multinode environment."
)
def comparison_test():
assert H2OXGBoostEstimator.available() is True
ret = h2o.cluster()
if len(ret.nodes) == 1:
runSeed = 1
dataSeed = 17
ntrees = 17
responseL = 11
# CPU Backend is forced for the results to be comparable
h2oParamsS = {
"ntrees": ntrees,
"max_depth": 4,
"seed": runSeed,
"learn_rate": 0.7,
"col_sample_rate_per_tree": 0.9,
"min_rows": 5,
"score_tree_interval": ntrees + 1,
"dmatrix_type": "sparse",
"tree_method": "exact",
"backend": "cpu"
}
nativeParam = {
'colsample_bytree': h2oParamsS["col_sample_rate_per_tree"],
'tree_method': 'exact',
'seed': h2oParamsS["seed"],
'booster': 'gbtree',
'objective': 'multi:softprob',
'eta': h2oParamsS["learn_rate"],
'grow_policy': 'depthwise',
'alpha': 0.0,
'subsample': 1.0,
'colsample_bylevel': 1.0,
'max_delta_step': 0.0,
'min_child_weight': h2oParamsS["min_rows"],
'gamma': 0.0,
'max_depth': h2oParamsS["max_depth"],
'num_class': responseL
}
nrows = 10000
ncols = 10
factorL = 11
numCols = 0
enumCols = ncols - numCols
trainFile = pyunit_utils.genTrainFrame(
nrows,
numCols,
enumCols=enumCols,
enumFactors=factorL,
miscfrac=0.5,
responseLevel=responseL,
randseed=dataSeed) # load in dataset and add response column
print(trainFile)
myX = trainFile.names
y = 'response'
myX.remove(y)
nativeTrain = pyunit_utils.convertH2OFrameToDMatrixSparse(trainFile,
y,
enumCols=myX)
h2oModelS = H2OXGBoostEstimator(**h2oParamsS)
# gather, print and save performance numbers for h2o model
h2oModelS.train(x=myX, y=y, training_frame=trainFile)
h2oTrainTimeS = h2oModelS._model_json["output"]["run_time"]
time1 = time.time()
h2oPredictS = h2oModelS.predict(trainFile)
h2oPredictTimeS = time.time() - time1
# train the native XGBoost
nrounds = ntrees
nativeModel = xgb.train(params=nativeParam,
dtrain=nativeTrain,
num_boost_round=nrounds)
modelInfo = nativeModel.get_dump()
print(modelInfo)
print("num_boost_round: {1}, Number of trees built: {0}".format(
len(modelInfo), nrounds))
nativeTrainTime = time.time() - time1
time1 = time.time()
nativePred = nativeModel.predict(data=nativeTrain, ntree_limit=ntrees)
nativeScoreTime = time.time() - time1
print(
"Comparing H2OXGBoost results with native XGBoost result when DMatrix is set to sparse....."
)
pyunit_utils.summarizeResult_multinomial(h2oPredictS,
nativePred,
h2oTrainTimeS,
nativeTrainTime,
h2oPredictTimeS,
nativeScoreTime,
tolerance=1e-6)
else:
print(
"******** Test skipped. This test cannot be performed in multinode environment."
)