def test(cas_session, iris_dataset):
pytest.skip('Re-enable once MAS publish no longer hangs.')
cas_session.loadactionset('decisiontree')
tbl = cas_session.upload(iris_dataset).casTable
features = list(tbl.columns[tbl.columns != TARGET])
# Fit a linear regression model in CAS and output an ASTORE
tbl.decisiontree.gbtreetrain(target=TARGET,
inputs=features,
savestate='model_table')
astore = cas_session.CASTable('model_table')
from sklearn.ensemble import GradientBoostingClassifier
X = iris_dataset.drop(TARGET, axis=1)
y = iris_dataset[TARGET]
sk_model = GradientBoostingClassifier()
sk_model.fit(X, y)
sas_model = register_model(astore,
SAS_MODEL_NAME,
PROJECT_NAME,
force=True)
sk_model = register_model(sk_model,
SCIKIT_MODEL_NAME,
PROJECT_NAME,
input=X)
# Publish to MAS
sas_module = publish_model(sas_model, 'maslocal', replace=True)
sk_module = publish_model(sk_model, 'maslocal', replace=True)
# Pass a row of data to MAS and receive the predicted result.
first_row = tbl.head(1)
result = sas_module.score(first_row)
p1, p1, p2, species, warning = result
result2 = sk_module.predict(first_row)
assert result2 in ('setosa', 'virginica', 'versicolor')
# SAS model may have CHAR variable that's padded with spaces.
assert species.strip() == result2
result3 = sk_module.predict_proba(first_row)
assert round(sum(result3), 5) == 1
def test_publish_mas(self, request):
from sasctl import publish_model
module = publish_model(self.MODEL_NAME, 'maslocal', replace=True)
# Store module name so we can retrieve it in later tests
request.config.cache.set('MAS_MODULE_NAME', module.name)
assert module.scope.lower() == 'public'
assert hasattr(module, 'predict')
def test_publish_cas(self, request):
from sasctl import publish_model
module = publish_model(self.MODEL_NAME, self.CAS_DEST)
# Store module name so we can retrieve it in later tests
request.config.cache.set('CAS_MODULE_NAME', module.name)
assert module.state == 'completed'
assert module.destinationName == self.CAS_DEST
assert module.publishType == 'casModel'
def test(cas_session, boston_dataset):
cas_session.loadactionset('regression')
tbl = cas_session.upload(boston_dataset).casTable
features = tbl.columns[tbl.columns != 'Price']
# Fit a linear regression model in CAS and output an ASTORE
tbl.glm(target='Price', inputs=list(features), savestate='model_table')
astore = cas_session.CASTable('model_table')
from sklearn.linear_model import LinearRegression
X = boston_dataset.drop('Price', axis=1)
y = boston_dataset['Price']
sk_model = LinearRegression()
sk_model.fit(X, y)
sas_model = register_model(astore,
SAS_MODEL_NAME,
PROJECT_NAME,
force=True)
sk_model = register_model(sk_model,
SCIKIT_MODEL_NAME,
PROJECT_NAME,
input=X)
# Publish to MAS
sas_module = publish_model(sas_model, 'maslocal', replace=True)
sk_module = publish_model(sk_model, 'maslocal', replace=True)
# Pass a row of data to MAS and receive the predicted result.
first_row = tbl.head(1)
result = sas_module.score(first_row)
assert isinstance(result, float)
result2 = sk_module.predict(first_row)
assert isinstance(result2, float)
assert round(result, 5) == round(result2, 5)
file=_file,
name=filenames['file'][i],
role=filenames['role'][i])
print('uploaded ' + filenames['file'][i] + ' as ' +
filenames['role'][i])
_file.close()
#### Publish model
### need to raise exception because
### when there is no change on the actual items
### even if you delete the old container
### it just restores with the older ID
### and throws an error
try:
module = publish_model(modelname, publishdestination, replace=True)
r1 = module.predict(3, 4, 2.5, 0.2)
r2 = module.predict_proba(3, 4, 2.5, 0.2)
print(r1, r2)
conn.terminate()
except:
print('Something went wrong during publication')
sys.exit(1)
model_repository.add_model_content(model=modelname,
file=_file,
name=filenames['file'][i],
role=filenames['role'][i])
print('uploaded ' + filenames['file'][i] + ' as ' +
filenames['role'][i])
_file.close()
#### Publish model
### need to raise exception because
### when there is no change on the actual items
### even if you delete the old container
### it just restores with the older ID
### and throws an error
try:
publish_model(modelname, publishdestination)
except Exception as e:
result = str(e).find('The image already exists')
if result != -1:
print('The image already exists, probably no change for new version')
else:
print('Another error, check logs')
sys.exit(1)
# Convert the local CSV file into a Pandas DataFrame
df = pd.read_csv('/home/viya/data/Los_Angeles_house_prices.csv')
# The model input data (X) is every column in the DataFrame except the target.
# The target (y) is equal to the median home value.
target = 'medv'
X = df.drop(target, axis=1)
y = df[target]
# Fit a sci-kit learn model
model = GradientBoostingRegressor()
model.fit(X, y)
# Establish a session with Viya
with Session('dsasspre.org', 'robinswu', 'password'):
model_name = 'GB Regression'
project_name = 'Los Angeles Housing'
# Register the model in SAS Model Manager
register_model(model, model_name, project_name, input=X, force=True)
# Publish the model to the real-time scoring engine
module = publish_model(model_name, 'maslocal', replace=True)
# Select the first row of training data
x = X.iloc[0, :]
# Call the published module and score the record
result = module.predict(x)
print(result)
# Load the Iris data set and convert into a Pandas data frame.
raw = datasets.load_iris()
X = pd.DataFrame(raw.data, columns=['SepalLength', 'SepalWidth',
'PetalLength', 'PetalWidth'])
y = pd.DataFrame(raw.target, columns=['Species'], dtype='category')
y.Species.cat.categories = raw.target_names
# Fit a sci-kit learn model
model = LogisticRegression()
model.fit(X, y)
# Establish a session with Viya
with Session('hostname', 'username', 'password'):
model_name = 'Iris Regression'
# Register the model in Model Manager
register_model(model,
model_name,
input=X, # Use X to determine model inputs
project='Iris', # Register in "Iris" project
force=True) # Create project if it doesn't exist
# Publish the model to the real-time scoring engine
module = publish_model(model_name, 'maslocal')
# Select the first row of training data
x = X.iloc[0, :]
# Call the published module and score the record
result = module.score(**x)
print(result)