# Copyright (c) 2015 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import trustedanalytics as ta
import sys
ta.create_credentials_file('credentials')
ta.connect()
print 'ta.server: %s' % ta.server
ds = sys.argv[1]
sc = [("label", ta.float64), ("feature1", ta.float64), ("feature2", ta.float64), ("feature3", ta.float64), ("feature4", ta.float64), ("feature5", ta.float64), ("feature6", ta.float64), ("feature7", ta.float64), ("feature8", ta.float64), ("feature9", ta.float64)]
csv = ta.CsvFile(ds, sc, ',', 0)
frame = ta.Frame(csv)
m = ta.LibsvmModel(name='model_name')
m.train(frame, "label", ["feature1", "feature2", "feature3", "feature4", "feature5", "feature6", "feature7", "feature8", "feature9"], epsilon=0.000001, degree=3, gamma=0.11, coef=0.0, nu=0.0001, cache_size=100.0, shrinking=1, probability=0, c=1.0, p=0.1, nr_weight=0)
print m.publish()
#
# Copyright (c) 2016 Intel Corporation
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import trustedanalytics as ta
from common import parse_arguments, check_uaa_file
parameters = parse_arguments()
ta.create_credentials_file(parameters.uaa_file_name)
check_uaa_file(parameters.uaa_file_name)
query = "select * from " + parameters.database_name + "." + parameters.table_name
print("\nQuery: {}".format(query))
hq = ta.HiveQuery(query)
frame = ta.Frame(hq)
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#
import os
import trustedanalytics as ta
from common import parse_arguments, check_uaa_file
parameters = parse_arguments()
directory = os.path.dirname(__file__)
uaa_file_name = os.path.join(directory, parameters.uaa_file_name)
ta.create_credentials_file(uaa_file_name)
check_uaa_file(uaa_file_name)
hdfs_csv_path = parameters.target_uri
schema = [('doc_id', str), ('word_id', str), ('word_count', ta.int64)]
csv_file = ta.CsvFile(hdfs_csv_path, schema)
frame = ta.Frame(csv_file)
model = ta.LdaModel()
model.train(frame,
'doc_id',
'word_id',
'word_count',
max_iterations=3,
num_topics=2)
print("hdfs_model_path: " + model.publish())