ip = '35.175.227.14'
address = 'http://' + ip + ':12345'
username = '******'
password = '******'
h2oai = Client(address=address, username=username, password=password)
### Amaxon Reviews
dataPath = '/data/Training/AmazonFineFoodReviews.csv'
basename = 'Reviews'
target = 'PositiveReview'
ratio = 0.8
reviews_data = h2oai.create_dataset_sync(dataPath)
# Split the data
reviews_split_data = h2oai.make_dataset_split(dataset_key=reviews_data.key,
output_name1=basename + "_train",
output_name2=basename + "_test",
target=target,
fold_col="",
time_col="",
ratio=ratio,
seed=1234)
train_key = h2oai.get_dataset_split_job(reviews_split_data).entity[0]
test_key = h2oai.get_dataset_split_job(reviews_split_data).entity[1]
# Reviews Default
import h2oai_client
from h2oai_client import Client
h2oai = Client(address='http://129.213.63.69:12345',
username='******',
password='******')
train = h2oai.create_dataset_sync('/train.csv')
test = h2oai.create_dataset_sync('/test.csv')
experiment = h2oai.start_experiment_sync(dataset_key=train.key,
testset_key=test.key,
accuracy=10,
time=10,
interpretability=1,
is_classification=True,
target_col='LABEL',
is_timeseries=True,
time_col='DATE',
num_gap_periods=1,
num_prediction_periods=1)
print("Final Model Score on Validation Data: " +
str(round(experiment.valid_score, 3)))
print("Final Model Score on Test Data: " +
str(round(experiment.test_score, 3)))
ip = '35.175.227.14'
address = 'http://' + ip + ':12345'
username = '******'
password = '******'
h2oai = Client(address = address
, username = username
, password = password)
dataPath = '/data/Training/CreditCard.csv'
basename = 'Card'
target = 'Default'
ratio = 0.8
dropped = []
card_data = h2oai.create_dataset_sync(dataPath)
# Split the data
card_split_data = h2oai.make_dataset_split(
dataset_key = card_data.key
, output_name1 = basename + "_train"
, output_name2 = basename + "_test"
, target = target
, fold_col = ""
, time_col = ""
, ratio = ratio
, seed = 1234
)
train_key = h2oai.get_dataset_split_job(card_split_data).entity[0]
test_key = h2oai.get_dataset_split_job(card_split_data).entity[1]
import math
from h2oai_client import Client, ModelParameters, InterpretParameters
ip = '35.175.227.14'
address = 'http://' + ip + ':12345'
username = '******'
password = '******'
h2oai = Client(address=address, username=username, password=password)
dataPath = '/data/Training/BostonHousing.csv'
basename = 'Housing'
target = 'VALUE'
ratio = 0.8
boston_data = h2oai.create_dataset_sync(dataPath)
# Split the data
boston_split_data = h2oai.make_dataset_split(dataset_key=boston_data.key,
output_name1=basename + "_train",
output_name2=basename + "_test",
target=target,
fold_col="",
time_col="",
ratio=ratio,
seed=1234)
train_key = h2oai.get_dataset_split_job(boston_split_data).entity[0]
test_key = h2oai.get_dataset_split_job(boston_split_data).entity[1]
dropped = []
from h2oai_client import Client, ModelParameters, InterpretParameters
ip = '35.175.227.14'
address = 'http://' + ip + ':12345'
username = '******'
password = '******'
h2oai = Client(address=address, username=username, password=password)
### Diabetes Models
dataPath = '/data/Training/PimaDiabetes.csv'
basename = 'Diabetes'
target = 'Outcome'
ratio = 0.8
diabetes_data = h2oai.create_dataset_sync(dataPath)
# Split the data
diabetes_split_data = h2oai.make_dataset_split(dataset_key=diabetes_data.key,
output_name1=basename +
"_train",
output_name2=basename + "_test",
target=target,
fold_col="",
time_col="",
ratio=ratio,
seed=1234)
train_key = h2oai.get_dataset_split_job(diabetes_split_data).entity[0]
test_key = h2oai.get_dataset_split_job(diabetes_split_data).entity[1]
dropped = []
from h2oai_client import Client, ModelParameters, InterpretParameters
ip = '35.175.227.14'
address = 'http://' + ip + ':12345'
username = '******'
password = '******'
h2oai = Client(address=address, username=username, password=password)
### Titanic Models
dataPath = '/data/Training/Titanic.csv'
basename = 'Titanic'
target = 'survived'
ratio = 0.8
titanic_data = h2oai.create_dataset_sync(dataPath)
# Split the data
titanic_split_data = h2oai.make_dataset_split(dataset_key=titanic_data.key,
output_name1=basename + "_train",
output_name2=basename + "_test",
target=target,
fold_col="",
time_col="",
ratio=ratio,
seed=1234)
train_key = h2oai.get_dataset_split_job(titanic_split_data).entity[0]
test_key = h2oai.get_dataset_split_job(titanic_split_data).entity[1]
knobs = [8, 2, 8]