from sparktk.loggers import log_load; log_load(__name__); del log_load
from sparktk.propobj import PropertiesObject
from sparktk import TkContext
__all__ = ["train", "load", "KMeansModel"]
def train(frame, columns, k=2, scalings=None, max_iter=20, epsilon=1e-4, seed=None, init_mode="k-means||"):
"""
Creates a KMeansModel by training on the given frame
:param frame: (Frame) frame of training data
:param columns: (List[str]) names of columns containing the observations for training
:param k: (Optional (int)) number of clusters
:param scalings: (Optional(List[float])) column scalings for each of the observation columns. The scaling value is multiplied by
the corresponding value in the observation column
:param max_iter: (Optional(int)) number of iterations for which the algorithm should run
:param epsilon: (Optional(float)) distance threshold within which we consider k-means to have converged. Default is 1e-4.
If all centers move less than this Euclidean distance, we stop iterating one run
:param seed: Optional(long) seed for randomness
:param init_mode: (Optional(str)) the initialization technique for the algorithm. It can be either "random" to choose
random points as initial clusters or "k-means||" to use a parallel variant of k-means++. Default is "k-means||
:return: (KMeansModel) trained KMeans model
"""
tc = frame._tc
_scala_obj = get_scala_obj(tc)
if isinstance(columns, basestring):
columns = [columns]
scala_columns = tc.jutils.convert.to_scala_vector_string(columns)
#
# 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.
#
from sparktk.frame.ops.classification_metrics_value import ClassificationMetricsValue
from sparktk.models.logistic_regression_summary_table import LogisticRegressionSummaryTable
from sparktk.loggers import log_load
from sparktk.propobj import PropertiesObject
from sparktk import TkContext
from sparktk.arguments import affirm_type
log_load(__name__)
del log_load
__all__ = ["train", "LogisticRegressionModel"]
def train(frame,
observation_columns,
label_column,
frequency_column=None,
num_classes=2,
optimizer="LBFGS",
compute_covariance=True,
intercept=True,
feature_scaling=False,
threshold=0.5,
reg_type="L2",
#
# 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.
#
from sparktk.loggers import log_load
log_load(__name__)
del log_load
from sparktk.propobj import PropertiesObject
from sparktk import TkContext
__all__ = ["train", "load", "PcaModel"]
def train(frame, columns, mean_centered=True, k=None):
"""
Creates a PcaModel by training on the given frame
Parameters
----------
# 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.
#
from sparktk.loggers import log_load; log_load(__name__); del log_load
from sparktk.propobj import PropertiesObject
from sparktk.frame.ops.classification_metrics_value import ClassificationMetricsValue
from sparktk import TkContext
__all__ = ["train", "load", "SvmModel"]
def train(frame,
label_column,
observation_columns,
intercept = True,
num_iterations = 100,
step_size = 1.0,
reg_type = None,
reg_param = 0.01,
