Noise filters and prototype selection

TomekLinkRemoval

API

class smote_variants.noise_removal.TomekLinkRemoval(strategy='remove_majority', nn_params=None, n_jobs=1, **_kwargs)[source]

Tomek link removal

References

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

__init__(strategy='remove_majority', nn_params=None, n_jobs=1, **_kwargs)[source]

Constructor of the noise filter.

Parameters:

strategy (str) – noise removal strategy: ‘remove_majority’/’remove_both’
nn_params (dict) – additional parameters for nearest neighbor calculations, any parameter NearestNeighbors accepts, and additionally use {‘metric’: ‘precomputed’, ‘metric_learning’: ‘<method>’, …} with <method> in ‘ITML’, ‘LSML’ to enable the learning of the metric to be used for neighborhood calculations
n_jobs (int) – number of jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise from dataset

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

dataset after noise removal

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.TomekLinkRemoval()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

Tomek link removal

References:

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

CondensedNearestNeighbors

API

class smote_variants.noise_removal.CondensedNearestNeighbors(n_jobs=1, **_kwargs)[source]

Condensed nearest neighbors

References

BibTex:

@ARTICLE{condensed_nn,
            author={Hart, P.},
            journal={IEEE Transactions on Information Theory},
            title={The condensed nearest neighbor rule (Corresp.)},
            year={1968},
            volume={14},
            number={3},
            pages={515-516},
            keywords={Pattern classification},
            doi={10.1109/TIT.1968.1054155},
            ISSN={0018-9448},
            month={May}}

__init__(n_jobs=1, **_kwargs)[source]

Constructor of the noise removing object

Parameters:: n_jobs (int) – number of jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise from dataset

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

dataset after noise removal

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.CondensedNearestNeighbors()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

Condensed nearest neighbors

References:

BibTex:

@ARTICLE{condensed_nn,
            author={Hart, P.},
            journal={IEEE Transactions on Information Theory},
            title={The condensed nearest neighbor rule (Corresp.)},
            year={1968},
            volume={14},
            number={3},
            pages={515-516},
            keywords={Pattern classification},
            doi={10.1109/TIT.1968.1054155},
            ISSN={0018-9448},
            month={May}}

OneSidedSelection

API

class smote_variants.noise_removal.OneSidedSelection(n_jobs=1, **_kwargs)[source]

References

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods
                    for Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

__init__(n_jobs=1, **_kwargs)[source]

Constructor of the noise removal object

Parameters:: n_jobs (int) – number of jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

cleaned features and target labels

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.OneSidedSelection()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

References:

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods
                    for Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

CNNTomekLinks

API

class smote_variants.noise_removal.CNNTomekLinks(n_jobs=1)[source]

References

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods
                    for Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

__init__(n_jobs=1)[source]

Constructor of the noise removal object

Parameters:: n_jobs (int) – number of parallel jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

cleaned features and target labels

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.CNNTomekLinks()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

References:

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods
                    for Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

NeighborhoodCleaningRule

API

class smote_variants.noise_removal.NeighborhoodCleaningRule(nn_params=None, n_jobs=1, **_kwargs)[source]

References

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

__init__(nn_params=None, n_jobs=1, **_kwargs)[source]

Constructor of the noise removal object

Parameters:

nn_params (dict) – additional parameters for nearest neighbor calculations, any parameter NearestNeighbors accepts, and additionally use {‘metric’: ‘precomputed’, ‘metric_learning’: ‘<method>’, …} with <method> in ‘ITML’, ‘LSML’ to enable the learning of the metric to be used for neighborhood calculations
n_jobs (int) – number of parallel jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

cleaned features and target labels

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.NeighborhoodCleaningRule()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

References:

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

EditedNearestNeighbors

API

class smote_variants.noise_removal.EditedNearestNeighbors(remove='both', nn_params=None, n_jobs=1, **_kwargs)[source]

References

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }

__init__(remove='both', nn_params=None, n_jobs=1, **_kwargs)[source]

Constructor of the noise removal object

Parameters:

remove (str) – class to remove from ‘both’/’min’/’maj’
nn_params (dict) – additional parameters for nearest neighbor calculations, any parameter NearestNeighbors accepts, and additionally use {‘metric’: ‘precomputed’, ‘metric_learning’: ‘<method>’, …} with <method> in ‘ITML’, ‘LSML’ to enable the learning of the metric to be used for neighborhood calculations
n_jobs (int) – number of parallel jobs

get_params(deep=False)[source]

Return parameters

Returns:: dictionary of parameters
Return type:: dict

remove_noise(X, y)[source]

Removes noise

Parameters:

X (np.array) – features
y (np.array) – target labels

Returns:

cleaned features and target labels

Return type:

np.array, np.array

Example

>>> noise_filter= smote_variants.noise_removal.EditedNearestNeighbors()
>>> X_samp, y_samp= noise_filter.remove_noise(X, y)

References:

BibTex:

@article{smoteNoise0,
         author = {Batista, Gustavo E. A. P. A. and Prati,
                    Ronaldo C. and Monard, Maria Carolina},
         title = {A Study of the Behavior of Several Methods for
                    Balancing Machine Learning Training Data},
         journal = {SIGKDD Explor. Newsl.},
         issue_date = {June 2004},
         volume = {6},
         number = {1},
         month = jun,
         year = {2004},
         issn = {1931-0145},
         pages = {20--29},
         numpages = {10},
         url = {http://doi.acm.org/10.1145/1007730.1007735},
         doi = {10.1145/1007730.1007735},
         acmid = {1007735},
         publisher = {ACM},
         address = {New York, NY, USA}
        }