src/main/python/systemds/operator/algorithm.py

# -------------------------------------------------------------
#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you 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 typing import Dict

from systemds.operator import OperationNode
from systemds.script_building.dag import DAGNode
from systemds.utils.consts import VALID_INPUT_TYPES

__all__ = ['l2svm', 'lm', 'kmeans', 'pca']


def l2svm(x: DAGNode, y: DAGNode, **kwargs: Dict[str, VALID_INPUT_TYPES]) -> OperationNode:
    """
    Perform L2SVM on matrix with labels given.

    :param x: Input dataset
    :param y: Input labels in shape of one column
    :param kwargs: Dictionary of extra arguments 
    :return: `OperationNode` containing the model fit.
    """
    x._check_matrix_op()
    params_dict = {'X': x, 'Y': y}
    params_dict.update(kwargs)
    return OperationNode(x.sds_context, 'l2svm', named_input_nodes=params_dict)


def lm(x: DAGNode, y: DAGNode, **kwargs: Dict[str, VALID_INPUT_TYPES]) -> OperationNode:
    """
    Performs LM on matrix with labels given.

    :param x: Input dataset
    :param y: Input labels in shape of one column
    :param kwargs: Dictionary of extra arguments 
    :return: `OperationNode` containing the model fit.
    """

    x._check_matrix_op()
    if x._np_array.size == 0:
        raise ValueError("Found array with 0 feature(s) (shape={s}) while a minimum of 1 is required."
                         .format(s=x._np_array.shape))
    if y._np_array.size == 0:
        raise ValueError("Found array with 0 feature(s) (shape={s}) while a minimum of 1 is required."
                         .format(s=y._np_array.shape))

    params_dict = {'X': x, 'y': y}
    params_dict.update(kwargs)
    return OperationNode(x.sds_context, 'lm', named_input_nodes=params_dict)


def kmeans(x: DAGNode, **kwargs: Dict[str, VALID_INPUT_TYPES]) -> OperationNode:
    """
    Performs KMeans on matrix input.

    :param x: Input dataset to perform K-Means on.
    :param k: The number of centroids to use for the algorithm.
    :param runs: The number of concurrent instances of K-Means to run (with different initial centroids).
    :param max_iter: The maximum number of iterations to run the K-Means algorithm for.
    :param eps: Tolerance for the algorithm to declare convergence using WCSS change ratio.
    :param is_verbose: Boolean flag if the algorithm should be run in a verbose manner.
    :param avg_sample_size_per_centroid: The average number of records per centroid in the data samples.
    """

    x._check_matrix_op()
    if x._np_array.size == 0:
        raise ValueError("Found array with 0 feature(s) (shape={s}) while a minimum of 1 is required."
                         .format(s=x._np_array.shape))

    if 'k' in kwargs.keys() and kwargs.get('k') < 1:
        raise ValueError("Invalid number of clusters in K means, number must be integer above 0")

    params_dict = {'X': x}
    params_dict.update(kwargs)
    return OperationNode(x.sds_context, 'kmeans', named_input_nodes=params_dict)


def pca(x: DAGNode, **kwargs: Dict[str, VALID_INPUT_TYPES]) -> OperationNode:
    """
    Performs PCA on the matrix input

    :param x: Input dataset to perform K-Means on.
    :param K: The number of reduced dimensions.
    :param center: Boolean specifying if the input values should be centered.
    :param scale: Boolean specifying if the input values should be scaled.
    """

    x._check_matrix_op()
    if x._np_array.size == 0:
        raise ValueError("Found array with 0 feature(s) (shape={s}) while a minimum of 1 is required."
                         .format(s=x._np_array.shape))

    if 'K' in kwargs.keys() and kwargs.get('K') < 1:
        raise ValueError("Invalid number of clusters in K means, number must be integer above 0")

    if 'scale'in kwargs.keys():
        if kwargs.get('scale') == True:
            kwargs.set('scale', "TRUE")
        elif kwargs.get('scale' == False):
            kwargs.set('scale', "FALSE")

    if 'center' in kwargs.keys():
        if kwargs.get('center') == True:
            kwargs.set('center', "TRUE")
        elif kwargs.get('center' == False):
            kwargs.set('center', "FALSE")

    params_dict = {'X': x}
    params_dict.update(kwargs)
    return OperationNode(x.sds_context, 'pca', named_input_nodes=params_dict)