def nb_iris():
print "Importing iris_wheader.csv data...\n"
iris = h2o.upload_file(tests.locate("smalldata/iris/iris_wheader.csv"))
iris.describe()
laplace_range = [0, 1, 0.25]
for i in laplace_range:
print "H2O Naive Bayes with Laplace smoothing = {0}".format(i)
iris_nbayes = h2o.naive_bayes(x=iris[0:4], y=iris[4], laplace=i)
iris_nbayes.show()
def nb_iris(ip, port):
print "Importing iris_wheader.csv data...\n"
iris = h2o.upload_file(h2o.locate("smalldata/iris/iris_wheader.csv"))
iris.describe()
laplace_range = [0, 1, 0.25]
for i in laplace_range:
print "H2O Naive Bayes with Laplace smoothing = {0}".format(i)
iris_nbayes = h2o.naive_bayes(x=iris[0:4], y=iris[4], laplace=i)
iris_nbayes.show()
def nb_init_err():
print("Importing iris_wheader.csv data...\n")
iris = h2o.upload_file(
pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
iris.describe
print("Laplace smoothing parameter is negative")
try:
h2o.naive_bayes(x=iris[0:4], y=iris[4], laplace=-1)
assert False, "Expected naive bayes algo to fail on negative laplace training parameter"
except:
pass
print("Minimum standard deviation is zero")
try:
h2o.naive_bayes(x=iris[0:4], y=iris[4], min_sdev=0)
assert False, "Expected naive bayes algo to fail on min_sdev = 0"
except:
pass
print("Response column is not categorical")
try:
h2o.naive_bayes(x=iris[0:3], y=iris[3], min_sdev=0)
assert False, "Expected naive bayes algo to fail on response not categorical"
except:
pass
def nb_init_err():
print("Importing iris_wheader.csv data...\n")
iris = h2o.upload_file(pyunit_utils.locate("smalldata/iris/iris_wheader.csv"))
iris.describe
print("Laplace smoothing parameter is negative")
try:
h2o.naive_bayes(x=iris[0:4], y=iris[4], laplace=-1)
assert False, "Expected naive bayes algo to fail on negative laplace training parameter"
except:
pass
print("Minimum standard deviation is zero")
try:
h2o.naive_bayes(x=iris[0:4], y=iris[4], min_sdev=0)
assert False, "Expected naive bayes algo to fail on min_sdev = 0"
except:
pass
print("Response column is not categorical")
try:
h2o.naive_bayes(x=iris[0:3], y=iris[3], min_sdev=0)
assert False, "Expected naive bayes algo to fail on response not categorical"
except:
pass
def nb_prostate():
print "Importing prostate.csv data..."
prostate = h2o.upload_file(tests.locate("smalldata/logreg/prostate.csv"))
print "Converting CAPSULE, RACE, DCAPS, and DPROS to categorical"
prostate['CAPSULE'] = prostate['CAPSULE'].asfactor()
prostate['RACE'] = prostate['CAPSULE'].asfactor()
prostate['DCAPS'] = prostate['DCAPS'].asfactor()
prostate['DPROS'] = prostate['DPROS'].asfactor()
print "Compare with Naive Bayes when x = 3:9, y = 2"
prostate_nb = h2o.naive_bayes(x=prostate[2:9], y=prostate[1], laplace=0)
prostate_nb.show()
print "Predict on training data"
prostate_pred = prostate_nb.predict(prostate)
prostate_pred.head()
def nb_prostate(ip, port):
h2o.init(ip, port)
print "Importing prostate.csv data..."
prostate = h2o.upload_file(h2o.locate("smalldata/logreg/prostate.csv"))
print "Converting CAPSULE, RACE, DCAPS, and DPROS to categorical"
prostate["CAPSULE"] = prostate["CAPSULE"].asfactor()
prostate["RACE"] = prostate["CAPSULE"].asfactor()
prostate["DCAPS"] = prostate["DCAPS"].asfactor()
prostate["DPROS"] = prostate["DPROS"].asfactor()
print "Compare with Naive Bayes when x = 3:9, y = 2"
prostate_nb = h2o.naive_bayes(x=prostate[2:9], y=prostate[1], laplace=0)
prostate_nb.show()
print "Predict on training data"
prostate_pred = prostate_nb.predict(prostate)
prostate_pred.head()
def nb_prostate():
print("Importing prostate.csv data...")
prostate = h2o.upload_file(pyunit_utils.locate("smalldata/logreg/prostate.csv"))
print("Converting CAPSULE, RACE, DCAPS, and DPROS to categorical")
prostate['CAPSULE'] = prostate['CAPSULE'].asfactor()
prostate['RACE'] = prostate['CAPSULE'].asfactor()
prostate['DCAPS'] = prostate['DCAPS'].asfactor()
prostate['DPROS'] = prostate['DPROS'].asfactor()
print("Compare with Naive Bayes when x = 3:9, y = 2")
prostate_nb = h2o.naive_bayes(x=prostate[2:9], y=prostate[1], laplace = 0)
prostate_nb.show()
print("Predict on training data")
prostate_pred = prostate_nb.predict(prostate)
prostate_pred.head()
def nb_baddata():
rawdata = [[random.gauss(0, 1) for r in range(100)] for c in range(10)]
print "Training data with all NA's"
train = [["NA" for r in range(100)] for c in range(10)]
train_h2o = h2o.H2OFrame(python_obj=train)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert False, "Expected naive bayes algo to fail on training data of all NA's"
except:
pass
# Response column must be categorical
print "Training data with a numeric response column"
train_h2o = h2o.H2OFrame(python_obj=rawdata)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert False, "Expected naive bayes algo to fail on training data with a numeric response column"
except:
pass
# Constant response dropped before model building
print "Training data with a constant response: drop and throw error"
rawdata[0] = 100 * ["A"]
train_h2o = h2o.H2OFrame(python_obj=rawdata)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert (
False
), "Expected naive bayes algo to fail on training data with a constant response: drop and throw error"
except:
pass
# Predictors with constant value automatically dropped
print "Training data with 1 col of all 5's: drop automatically"
rawdata = [[random.gauss(0, 1) for r in range(100)] for c in range(10)]
rawdata[4] = 100 * [5]
rawdata[0] = [random.choice(string.letters) for _ in range(100)]
train_h2o = h2o.H2OFrame(python_obj=rawdata)
model = h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert len(model._model_json["output"]["pcond"]) == 8, "Expected 8 predictors, but got {0}" "".format(
len(model._model_json["output"]["pcond"])
)
def nb_baddata():
rawdata = [[random.gauss(0, 1) for c in range(10)] for r in range(100)]
print "Training data with all NA's"
train = [["NA" for c in range(10)] for r in range(100)]
train_h2o = h2o.H2OFrame(python_obj=train)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert False, "Expected naive bayes algo to fail on training data of all NA's"
except:
pass
# Response column must be categorical
print "Training data with a numeric response column"
train_h2o = h2o.H2OFrame(python_obj=rawdata)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert False, "Expected naive bayes algo to fail on training data with a numeric response column"
except:
pass
# Constant response dropped before model building
print "Training data with a constant response: drop and throw error"
for r in range(100):
rawdata[r][0] = "A"
train_h2o = h2o.H2OFrame(python_obj=rawdata)
try:
h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert False, "Expected naive bayes algo to fail on training data with a constant response: drop and throw error"
except:
pass
# Predictors with constant value automatically dropped
print "Training data with 1 col of all 5's: drop automatically"
rawdata = [[random.gauss(0, 1) for c in range(10)] for r in range(100)]
for r in range(100):
rawdata[r][4] = 5
for r in range(100):
rawdata[r][0] = random.choice(string.letters)
train_h2o = h2o.H2OFrame(python_obj=rawdata)
model = h2o.naive_bayes(x=train_h2o[1:10], y=train_h2o[0])
assert len(model._model_json['output']['pcond']) == 8, "Expected 8 predictors, but got {0}" \
"".format(len(model._model_json['output']['pcond']))
