Skip to content

Naive Bayes

sklego.naive_bayes.GaussianMixtureNB

Bases: BaseEstimator, ClassifierMixin

The GaussianMixtureNB estimator is a naive bayes classifier that uses a mixture of gaussians instead of merely a single one. In particular it trains a GaussianMixture model for each class in the target and for each feature in the data, on the subset of X where y == class.

You can pass any keyword parameter that scikit-learn's GaussianMixture model uses and it will be passed along to each of the models.

Attributes:

Name Type Description
gmms_ dict[int, List[GaussianMixture]]

A dictionary of Gaussian Mixture Models, one for each class.
classes_ np.ndarray of shape (n_classes,)

The classes seen during fit.
n_features_in_ int

The number of features seen during fit.
num_fit_cols_ int

Deprecated, please use n_features_in_ instead.
Source code in sklego/naive_bayes.py 
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
class GaussianMixtureNB(BaseEstimator, ClassifierMixin):
    """The `GaussianMixtureNB` estimator is a naive bayes classifier that uses a mixture of gaussians instead of
    merely a single one. In particular it trains a `GaussianMixture` model for each class in the target and for each
    feature in the data, on the subset of `X` where `y == class`.

    You can pass any keyword parameter that scikit-learn's
    [GaussianMixture](https://scikit-learn.org/stable/modules/generated/sklearn.mixture.GaussianMixture.html)
    model uses and it will be passed along to each of the models.

    Attributes
    ----------
    gmms_ : dict[int, List[GaussianMixture]]
        A dictionary of Gaussian Mixture Models, one for each class.
    classes_ : np.ndarray of shape (n_classes,)
        The classes seen during `fit`.
    n_features_in_ : int
        The number of features seen during `fit`.
    num_fit_cols_ : int
        Deprecated, please use `n_features_in_` instead.
    """

    def __init__(
        self,
        n_components=1,
        covariance_type="full",
        tol=1e-3,
        reg_covar=1e-6,
        max_iter=100,
        n_init=1,
        init_params="kmeans",
        weights_init=None,
        means_init=None,
        precisions_init=None,
        random_state=None,
        warm_start=False,
    ):
        self.n_components = n_components
        self.covariance_type = covariance_type
        self.tol = tol
        self.reg_covar = reg_covar
        self.max_iter = max_iter
        self.n_init = n_init
        self.init_params = init_params
        self.weights_init = weights_init
        self.means_init = means_init
        self.precisions_init = precisions_init
        self.random_state = random_state
        self.warm_start = warm_start

    def fit(self, X, y) -> "GaussianMixtureNB":
        """Fit the `GaussianMixtureNB` estimator using `X` and `y` as training data by fitting a `GaussianMixture` model
        for each class in the target and for each feature in the data, on the subset of `X` where `y == class`.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features )
            The training data.
        y : array-like of shape (n_samples,)
            The target values.

        Returns
        -------
        self : GaussianMixtureNB
            The fitted estimator.
        """
        X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
        if X.ndim == 1:
            X = np.expand_dims(X, 1)

        self.gmms_ = {}
        self.classes_ = unique_labels(y)
        self.n_features_in_ = X.shape[1]
        for c in self.classes_:
            subset_x, subset_y = X[y == c], y[y == c]
            self.gmms_[c] = [
                GaussianMixture(
                    n_components=self.n_components,
                    covariance_type=self.covariance_type,
                    tol=self.tol,
                    reg_covar=self.reg_covar,
                    max_iter=self.max_iter,
                    n_init=self.n_init,
                    init_params=self.init_params,
                    weights_init=self.weights_init,
                    means_init=self.means_init,
                    precisions_init=self.precisions_init,
                    random_state=self.random_state,
                    warm_start=self.warm_start,
                ).fit(subset_x[:, i].reshape(-1, 1), subset_y)
                for i in range(X.shape[1])
            ]
        return self

    def predict(self, X):
        """Predict labels for `X` using fitted estimator and `predict_proba` method, by picking the class with the
        highest probability.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The data to predict.

        Returns
        -------
        array-like of shape (n_samples,)
            The predicted data.
        """
        check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
        X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
        return self.classes_[self.predict_proba(X).argmax(axis=1)]

    def predict_proba(self, X: np.ndarray):
        """Predict probabilities for `X` using fitted estimator by summing the probabilities of each gaussian for each
        class.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The data to predict.

        Returns
        -------
        array-like of shape (n_samples, n_classes)
            The predicted probabilities.
        """
        check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
        X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
        if self.n_features_in_ != X.shape[1]:
            raise ValueError(f"number of columns {X.shape[1]} does not match fit size {self.n_features_in_}")
        check_is_fitted(self, ["gmms_", "classes_"])
        probs = np.zeros((X.shape[0], len(self.classes_)))
        for k, v in self.gmms_.items():
            class_idx = int(np.argwhere(self.classes_ == k))
            probs[:, class_idx] = np.array(
                [m.score_samples(np.expand_dims(X[:, idx], 1)) for idx, m in enumerate(v)]
            ).sum(axis=0)
        likelihood = np.exp(probs)
        return likelihood / likelihood.sum(axis=1).reshape(-1, 1)

    @property
    def num_fit_cols_(self):
        warn(
            "Please use `n_features_in_` instead of `num_fit_cols_`,"
            "`num_fit_cols_` will be deprecated in future versions",
            DeprecationWarning,
        )
        return self.n_features_in_

fit(X, y)

Fit the GaussianMixtureNB estimator using X and y as training data by fitting a GaussianMixture model for each class in the target and for each feature in the data, on the subset of X where y == class.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features )

The training data.

 required
y array-like of shape (n_samples,)

The target values.

 required

Returns:

Name Type Description
self GaussianMixtureNB

The fitted estimator.
Source code in sklego/naive_bayes.py 
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
def fit(self, X, y) -> "GaussianMixtureNB":
    """Fit the `GaussianMixtureNB` estimator using `X` and `y` as training data by fitting a `GaussianMixture` model
    for each class in the target and for each feature in the data, on the subset of `X` where `y == class`.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features )
        The training data.
    y : array-like of shape (n_samples,)
        The target values.

    Returns
    -------
    self : GaussianMixtureNB
        The fitted estimator.
    """
    X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
    if X.ndim == 1:
        X = np.expand_dims(X, 1)

    self.gmms_ = {}
    self.classes_ = unique_labels(y)
    self.n_features_in_ = X.shape[1]
    for c in self.classes_:
        subset_x, subset_y = X[y == c], y[y == c]
        self.gmms_[c] = [
            GaussianMixture(
                n_components=self.n_components,
                covariance_type=self.covariance_type,
                tol=self.tol,
                reg_covar=self.reg_covar,
                max_iter=self.max_iter,
                n_init=self.n_init,
                init_params=self.init_params,
                weights_init=self.weights_init,
                means_init=self.means_init,
                precisions_init=self.precisions_init,
                random_state=self.random_state,
                warm_start=self.warm_start,
            ).fit(subset_x[:, i].reshape(-1, 1), subset_y)
            for i in range(X.shape[1])
        ]
    return self

predict(X)

Predict labels for X using fitted estimator and predict_proba method, by picking the class with the highest probability.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features)

The data to predict.

 required

Returns:

Type Description
array-like of shape (n_samples,)

The predicted data.
Source code in sklego/naive_bayes.py 
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
def predict(self, X):
    """Predict labels for `X` using fitted estimator and `predict_proba` method, by picking the class with the
    highest probability.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        The data to predict.

    Returns
    -------
    array-like of shape (n_samples,)
        The predicted data.
    """
    check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
    X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
    return self.classes_[self.predict_proba(X).argmax(axis=1)]

predict_proba(X)

Predict probabilities for X using fitted estimator by summing the probabilities of each gaussian for each class.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features)

The data to predict.

 required

Returns:

Type Description
array-like of shape (n_samples, n_classes)

The predicted probabilities.
Source code in sklego/naive_bayes.py 
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
def predict_proba(self, X: np.ndarray):
    """Predict probabilities for `X` using fitted estimator by summing the probabilities of each gaussian for each
    class.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        The data to predict.

    Returns
    -------
    array-like of shape (n_samples, n_classes)
        The predicted probabilities.
    """
    check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
    X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
    if self.n_features_in_ != X.shape[1]:
        raise ValueError(f"number of columns {X.shape[1]} does not match fit size {self.n_features_in_}")
    check_is_fitted(self, ["gmms_", "classes_"])
    probs = np.zeros((X.shape[0], len(self.classes_)))
    for k, v in self.gmms_.items():
        class_idx = int(np.argwhere(self.classes_ == k))
        probs[:, class_idx] = np.array(
            [m.score_samples(np.expand_dims(X[:, idx], 1)) for idx, m in enumerate(v)]
        ).sum(axis=0)
    likelihood = np.exp(probs)
    return likelihood / likelihood.sum(axis=1).reshape(-1, 1)

sklego.naive_bayes.BayesianGaussianMixtureNB

Bases: BaseEstimator, ClassifierMixin

The BayesianGaussianMixtureNB estimator is a naive bayes classifier that uses a bayesian mixture of gaussians instead of merely a single one. In particular it trains a BayesianGaussianMixture model for each class in the target and for each feature in the data, on the subset of X where y == class.

You can pass any keyword parameter that scikit-learn's BayesianGaussianMixture model uses and it will be passed along to each of the models.

Attributes:

Name Type Description
gmms_ dict[int, List[BayesianGaussianMixture]]

A dictionary of Gaussian Mixture Models, one for each class.
classes_ np.ndarray of shape (n_classes,)

The classes seen during fit.
n_features_in_ int

The number of features seen during fit.
num_fit_cols_ int

Deprecated, please use n_features_in_ instead.
Source code in sklego/naive_bayes.py 
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
class BayesianGaussianMixtureNB(BaseEstimator, ClassifierMixin):
    """The `BayesianGaussianMixtureNB` estimator is a naive bayes classifier that uses a bayesian mixture of gaussians
    instead of merely a single one. In particular it trains a `BayesianGaussianMixture` model for each class in the
    target and for each feature in the data, on the subset of `X` where `y == class`.

    You can pass any keyword parameter that scikit-learn's
    [`BayesianGaussianMixture`](https://scikit-learn.org/stable/modules/generated/sklearn.mixture.BayesianGaussianMixture.html)
    model uses and it will be passed along to each of the models.

    Attributes
    ----------
    gmms_ : dict[int, List[BayesianGaussianMixture]]
        A dictionary of Gaussian Mixture Models, one for each class.
    classes_ : np.ndarray of shape (n_classes,)
        The classes seen during `fit`.
    n_features_in_ : int
        The number of features seen during `fit`.
    num_fit_cols_ : int
        Deprecated, please use `n_features_in_` instead.
    """

    def __init__(
        self,
        n_components=1,
        covariance_type="full",
        tol=0.001,
        reg_covar=1e-06,
        max_iter=100,
        n_init=1,
        init_params="kmeans",
        weight_concentration_prior_type="dirichlet_process",
        weight_concentration_prior=None,
        mean_precision_prior=None,
        mean_prior=None,
        degrees_of_freedom_prior=None,
        covariance_prior=None,
        random_state=None,
        warm_start=False,
        verbose=0,
        verbose_interval=10,
    ):
        self.n_components = n_components
        self.covariance_type = covariance_type
        self.tol = tol
        self.reg_covar = reg_covar
        self.max_iter = max_iter
        self.n_init = n_init
        self.init_params = init_params
        self.weight_concentration_prior_type = weight_concentration_prior_type
        self.weight_concentration_prior = weight_concentration_prior
        self.mean_precision_prior = mean_precision_prior
        self.mean_prior = mean_prior
        self.degrees_of_freedom_prior = degrees_of_freedom_prior
        self.covariance_prior = covariance_prior
        self.random_state = random_state
        self.warm_start = warm_start
        self.verbose = verbose
        self.verbose_interval = verbose_interval

    def fit(self, X, y) -> "BayesianGaussianMixtureNB":
        """Fit the `BayesianGaussianMixtureNB` estimator using `X` and `y` as training data by fitting a
        `BayesianGaussianMixture` model for each class in the target and for each feature in the data, on the subset of
        `X` where `y == class`.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features )
            The training data.
        y : array-like of shape (n_samples,)
            The target values.

        Returns
        -------
        self : BayesianGaussianMixtureNB
            The fitted estimator.
        """
        X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
        if X.ndim == 1:
            X = np.expand_dims(X, 1)

        self.gmms_ = {}
        self.classes_ = unique_labels(y)
        self.n_features_in_ = X.shape[1]
        for c in self.classes_:
            subset_x, subset_y = X[y == c], y[y == c]
            self.gmms_[c] = [
                BayesianGaussianMixture(
                    n_components=self.n_components,
                    covariance_type=self.covariance_type,
                    tol=self.tol,
                    reg_covar=self.reg_covar,
                    max_iter=self.max_iter,
                    n_init=self.n_init,
                    init_params=self.init_params,
                    weight_concentration_prior_type=self.weight_concentration_prior_type,
                    weight_concentration_prior=self.weight_concentration_prior,
                    mean_precision_prior=self.mean_precision_prior,
                    mean_prior=self.mean_prior,
                    degrees_of_freedom_prior=self.degrees_of_freedom_prior,
                    covariance_prior=self.covariance_prior,
                    random_state=self.random_state,
                    warm_start=self.warm_start,
                    verbose=self.verbose,
                    verbose_interval=self.verbose_interval,
                ).fit(subset_x[:, i].reshape(-1, 1), subset_y)
                for i in range(X.shape[1])
            ]
        return self

    def predict(self, X):
        """Predict labels for `X` using fitted estimator and `predict_proba` method, by picking the class with the
        highest probability.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The data to predict.

        Returns
        -------
        array-like of shape (n_samples,)
            The predicted data.
        """
        check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
        X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
        return self.classes_[self.predict_proba(X).argmax(axis=1)]

    def predict_proba(self, X: np.ndarray):
        """Predict probabilities for `X` using fitted estimator by summing the probabilities of each gaussian for each
        class.

        Parameters
        ----------
        X : array-like of shape (n_samples, n_features)
            The data to predict.

        Returns
        -------
        array-like of shape (n_samples, n_classes)
            The predicted probabilities.
        """
        check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
        X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
        if self.n_features_in_ != X.shape[1]:
            raise ValueError(f"number of columns {X.shape[1]} does not match fit size {self.n_features_in_}")
        check_is_fitted(self, ["gmms_", "classes_"])
        probs = np.zeros((X.shape[0], len(self.classes_)))
        for k, v in self.gmms_.items():
            class_idx = int(np.argwhere(self.classes_ == k))
            probs[:, class_idx] = np.array(
                [m.score_samples(np.expand_dims(X[:, idx], 1)) for idx, m in enumerate(v)]
            ).sum(axis=0)
        likelihood = np.exp(probs)
        return likelihood / likelihood.sum(axis=1).reshape(-1, 1)

    @property
    def num_fit_cols_(self):
        warn(
            "Please use `n_features_in_` instead of `num_fit_cols_`,"
            "`num_fit_cols_` will be deprecated in future versions",
            DeprecationWarning,
        )
        return self.n_features_in_

fit(X, y)

Fit the BayesianGaussianMixtureNB estimator using X and y as training data by fitting a BayesianGaussianMixture model for each class in the target and for each feature in the data, on the subset of X where y == class.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features )

The training data.

 required
y array-like of shape (n_samples,)

The target values.

 required

Returns:

Name Type Description
self BayesianGaussianMixtureNB

The fitted estimator.
Source code in sklego/naive_bayes.py 
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
def fit(self, X, y) -> "BayesianGaussianMixtureNB":
    """Fit the `BayesianGaussianMixtureNB` estimator using `X` and `y` as training data by fitting a
    `BayesianGaussianMixture` model for each class in the target and for each feature in the data, on the subset of
    `X` where `y == class`.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features )
        The training data.
    y : array-like of shape (n_samples,)
        The target values.

    Returns
    -------
    self : BayesianGaussianMixtureNB
        The fitted estimator.
    """
    X, y = check_X_y(X, y, estimator=self, dtype=FLOAT_DTYPES)
    if X.ndim == 1:
        X = np.expand_dims(X, 1)

    self.gmms_ = {}
    self.classes_ = unique_labels(y)
    self.n_features_in_ = X.shape[1]
    for c in self.classes_:
        subset_x, subset_y = X[y == c], y[y == c]
        self.gmms_[c] = [
            BayesianGaussianMixture(
                n_components=self.n_components,
                covariance_type=self.covariance_type,
                tol=self.tol,
                reg_covar=self.reg_covar,
                max_iter=self.max_iter,
                n_init=self.n_init,
                init_params=self.init_params,
                weight_concentration_prior_type=self.weight_concentration_prior_type,
                weight_concentration_prior=self.weight_concentration_prior,
                mean_precision_prior=self.mean_precision_prior,
                mean_prior=self.mean_prior,
                degrees_of_freedom_prior=self.degrees_of_freedom_prior,
                covariance_prior=self.covariance_prior,
                random_state=self.random_state,
                warm_start=self.warm_start,
                verbose=self.verbose,
                verbose_interval=self.verbose_interval,
            ).fit(subset_x[:, i].reshape(-1, 1), subset_y)
            for i in range(X.shape[1])
        ]
    return self

predict(X)

Predict labels for X using fitted estimator and predict_proba method, by picking the class with the highest probability.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features)

The data to predict.

 required

Returns:

Type Description
array-like of shape (n_samples,)

The predicted data.
Source code in sklego/naive_bayes.py 
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
def predict(self, X):
    """Predict labels for `X` using fitted estimator and `predict_proba` method, by picking the class with the
    highest probability.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        The data to predict.

    Returns
    -------
    array-like of shape (n_samples,)
        The predicted data.
    """
    check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
    X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
    return self.classes_[self.predict_proba(X).argmax(axis=1)]

predict_proba(X)

Predict probabilities for X using fitted estimator by summing the probabilities of each gaussian for each class.

Parameters:

Name Type Description Default
X array-like of shape (n_samples, n_features)

The data to predict.

 required

Returns:

Type Description
array-like of shape (n_samples, n_classes)

The predicted probabilities.
Source code in sklego/naive_bayes.py 
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
def predict_proba(self, X: np.ndarray):
    """Predict probabilities for `X` using fitted estimator by summing the probabilities of each gaussian for each
    class.

    Parameters
    ----------
    X : array-like of shape (n_samples, n_features)
        The data to predict.

    Returns
    -------
    array-like of shape (n_samples, n_classes)
        The predicted probabilities.
    """
    check_is_fitted(self, ["gmms_", "classes_", "n_features_in_"])
    X = check_array(X, estimator=self, dtype=FLOAT_DTYPES)
    if self.n_features_in_ != X.shape[1]:
        raise ValueError(f"number of columns {X.shape[1]} does not match fit size {self.n_features_in_}")
    check_is_fitted(self, ["gmms_", "classes_"])
    probs = np.zeros((X.shape[0], len(self.classes_)))
    for k, v in self.gmms_.items():
        class_idx = int(np.argwhere(self.classes_ == k))
        probs[:, class_idx] = np.array(
            [m.score_samples(np.expand_dims(X[:, idx], 1)) for idx, m in enumerate(v)]
        ).sum(axis=0)
    likelihood = np.exp(probs)
    return likelihood / likelihood.sum(axis=1).reshape(-1, 1)