tods/detection_algorithm/PyodCBLOF.py

from typing import Any, Callable, List, Dict, Union, Optional, Sequence, Tuple
from numpy import ndarray
from collections import OrderedDict
from scipy import sparse
import os
import sklearn
import numpy
import typing

# Custom import commands if any
import warnings
import numpy as np
from sklearn.utils import check_array
from sklearn.exceptions import NotFittedError
# from numba import njit
from pyod.utils.utility import argmaxn

from d3m.container.numpy import ndarray as d3m_ndarray
from d3m.container import DataFrame as d3m_dataframe
from d3m.metadata import hyperparams, params, base as metadata_base
from d3m import utils
from d3m.base import utils as base_utils
from d3m.exceptions import PrimitiveNotFittedError
from d3m.primitive_interfaces.base import CallResult, DockerContainer

# from d3m.primitive_interfaces.supervised_learning import SupervisedLearnerPrimitiveBase
from d3m.primitive_interfaces.unsupervised_learning import UnsupervisedLearnerPrimitiveBase
from d3m.primitive_interfaces.transformer import TransformerPrimitiveBase

from d3m.primitive_interfaces.base import ProbabilisticCompositionalityMixin, ContinueFitMixin
from d3m import exceptions
import pandas

from d3m import container, utils as d3m_utils

from detection_algorithm.UODBasePrimitive import Params_ODBase, Hyperparams_ODBase, UnsupervisedOutlierDetectorBase
from pyod.models.cblof import CBLOF
import uuid
# from typing import Union

Inputs = d3m_dataframe
Outputs = d3m_dataframe


class Params(Params_ODBase):
    ######## Add more Attributes #######

    pass

class Hyperparams(Hyperparams_ODBase):
    ######## Add more Hyperparamters #######

    n_clusters = hyperparams.Hyperparameter[int](
        default=8,
        description='The number of clusters to form as well as the number of centroids to generate.',
        semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
    )

    # clustering_estimator = hyperparams.Choice(
    #     choices={
    #         'auto': hyperparams.Hyperparams.define(
    #             configuration=OrderedDict({})
    #         ),
    #         'full': hyperparams.Hyperparams.define(
    #             configuration=OrderedDict({})
    #         ),
    #     },
    #     default='auto',
    #     description='The base clustering algorithm for performing data clustering. A valid clustering algorithm should be passed in. The estimator should have standard sklearn APIs, fit() and predict(). The estimator should have attributes ``labels_`` and ``cluster_centers_``.',
    #     semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
    # )

    alpha = hyperparams.Uniform(
        lower=0.5,
        upper=1.,
        default=0.9,
        description='Coefficient for deciding small and large clusters. The ratio of the number of samples in large clusters to the number of samples in small clusters.',
        semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
    )

    beta = hyperparams.Hyperparameter[int](
        default=5,
        description='Coefficient for deciding small and large clusters.',
        semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter']
    )

    use_weights = hyperparams.UniformBool(
        default=False,
        semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter'],
        description="If set to True, the size of clusters are used as weights in outlier score calculation."
    )

    check_estimator = hyperparams.UniformBool(
        default=False,
        semantic_types=['https://metadata.datadrivendiscovery.org/types/TuningParameter'],
        description="If set to True, check whether the base estimator is consistent with sklearn standard."
    )

    random_state = hyperparams.Union[Union[int, None]](
        configuration=OrderedDict(
            init=hyperparams.Hyperparameter[int](
                default=0,
            ),
            ninit=hyperparams.Hyperparameter[None](
                default=None,
            ),
        ),
        default='ninit',
        description='the seed used by the random number generator.',
        semantic_types=['https://metadata.datadrivendiscovery.org/types/ControlParameter'],
    )

    pass


class CBLOFPrimitive(UnsupervisedOutlierDetectorBase[Inputs, Outputs, Params, Hyperparams]):
    """
    The CBLOF operator calculates the outlier score based on cluster-based
    local outlier factor.
    CBLOF takes as an input the data set and the cluster model that was
    generated by a clustering algorithm. It classifies the clusters into small
    clusters and large clusters using the parameters alpha and beta.
    The anomaly score is then calculated based on the size of the cluster the
    point belongs to as well as the distance to the nearest large cluster.
    Use weighting for outlier factor based on the sizes of the clusters as
    proposed in the original publication. Since this might lead to unexpected
    behavior (outliers close to small clusters are not found), it is disabled
    by default.Outliers scores are solely computed based on their distance to
    the closest large cluster center.
    By default, kMeans is used for clustering algorithm instead of
    Squeezer algorithm mentioned in the original paper for multiple reasons.
    See :cite:`he2003discovering` for details.

    Parameters
    ----------
    n_clusters : int, optional (default=8)
        The number of clusters to form as well as the number of
        centroids to generate.

    contamination : float in (0., 0.5), optional (default=0.1)
        The amount of contamination of the data set,
        i.e. the proportion of outliers in the data set. Used when fitting to
        define the threshold on the decision function.

    clustering_estimator : Estimator, optional (default=None)
        The base clustering algorithm for performing data clustering.
        A valid clustering algorithm should be passed in. The estimator should
        have standard sklearn APIs, fit() and predict(). The estimator should
        have attributes ``labels_`` and ``cluster_centers_``.
        If ``cluster_centers_`` is not in the attributes once the model is fit,
        it is calculated as the mean of the samples in a cluster.
        If not set, CBLOF uses KMeans for scalability. See
        https://scikit-learn.org/stable/modules/generated/sklearn.cluster.KMeans.html

    alpha : float in (0.5, 1), optional (default=0.9)
        Coefficient for deciding small and large clusters. The ratio
        of the number of samples in large clusters to the number of samples in
        small clusters.

    beta : int or float in (1,), optional (default=5).
        Coefficient for deciding small and large clusters. For a list
        sorted clusters by size `|C1|, \|C2|, ..., |Cn|, beta = |Ck|/|Ck-1|`

    use_weights : bool, optional (default=False)
        If set to True, the size of clusters are used as weights in
        outlier score calculation.

    check_estimator : bool, optional (default=False)
        If set to True, check whether the base estimator is consistent with
        sklearn standard.
        .. warning::
            check_estimator may throw errors with scikit-learn 0.20 above.

    random_state : int, RandomState or None, optional (default=None)
        If int, random_state is the seed used by the random
        number generator; If RandomState instance, random_state is the random
        number generator; If None, the random number generator is the
        RandomState instance used by `np.random`.

    Attributes
    ----------
    decision_scores_ : numpy array of shape (n_samples,)
        The outlier scores of the training data.
        The higher, the more abnormal. Outliers tend to have higher
        scores. This value is available once the detector is
        fitted.
    threshold_ : float
        The threshold is based on ``contamination``. It is the
        ``n_samples * contamination`` most abnormal samples in
        ``decision_scores_``. The threshold is calculated for generating
        binary outlier labels.
    labels_ : int, either 0 or 1
        The binary labels of the training data. 0 stands for inliers
        and 1 for outliers/anomalies. It is generated by applying
        ``threshold_`` on ``decision_scores_``.
    """

    metadata = metadata_base.PrimitiveMetadata({
        "name": "TODS.anomaly_detection_primitives.CBLOFPrimitive",
        "python_path": "d3m.primitives.tods.detection_algorithm.pyod_cblof",
        "source": {'name': "DATALAB @Taxes A&M University", 'contact': 'mailto:khlai037@tamu.edu',
                   'uris': ['https://gitlab.com/lhenry15/tods.git']},
        "algorithm_types": [metadata_base.PrimitiveAlgorithmType.LOCAL_OUTLIER_FACTOR, ],
        "primitive_family": metadata_base.PrimitiveFamily.ANOMALY_DETECTION,
        "version": "0.0.1",
        "hyperparams_to_tune": ['contamination'],
        "id": str(uuid.uuid3(uuid.NAMESPACE_DNS, 'CBLOFPrimitive')),
    })

    def __init__(self, *,
                 hyperparams: Hyperparams, #
                 random_seed: int = 0,
                 docker_containers: Dict[str, DockerContainer] = None) -> None:
        super().__init__(hyperparams=hyperparams, random_seed=random_seed, docker_containers=docker_containers)

        self._clf = CBLOF(contamination=hyperparams['contamination'],
                          n_clusters=hyperparams['n_clusters'],
                          alpha=hyperparams['alpha'],
                          beta=hyperparams['beta'],
                          use_weights=hyperparams['use_weights'],
                          check_estimator=hyperparams['check_estimator'],
                          random_state=hyperparams['random_state'],
                          )

        return

    def set_training_data(self, *, inputs: Inputs) -> None:
        """
        Set training data for outlier detection.
        Args:
            inputs: Container DataFrame

        Returns:
            None
        """
        super().set_training_data(inputs=inputs)

    def fit(self, *, timeout: float = None, iterations: int = None) -> CallResult[None]:
        """
        Fit model with training data.
        Args:
            *: Container DataFrame. Time series data up to fit.

        Returns:
            None
        """
        return super().fit()

    def produce(self, *, inputs: Inputs, timeout: float = None, iterations: int = None) -> CallResult[Outputs]:
        """
        Process the testing data.
        Args:
            inputs: Container DataFrame. Time series data up to outlier detection.

        Returns:
            Container DataFrame
            1 marks Outliers, 0 marks normal.
        """
        return super().produce(inputs=inputs, timeout=timeout, iterations=iterations)

    def get_params(self) -> Params:
        """
        Return parameters.
        Args:
            None

        Returns:
            class Params
        """
        return super().get_params()

    def set_params(self, *, params: Params) -> None:
        """
        Set parameters for outlier detection.
        Args:
            params: class Params

        Returns:
            None
        """
        super().set_params(params=params)