核心代码
class GaussianNB Found at: sklearn.naive_bayes
class GaussianNB(_BaseNB):
"""
Gaussian Naive Bayes (GaussianNB)
Can perform online updates to model parameters via :meth:`partial_fit`.
For details on algorithm used to update feature means and variance online,
see Stanford CS tech report STAN-CS-79-773 by Chan, Golub, and LeVeque:
http://i.stanford.edu/pub/cstr/reports/cs/tr/79/773/CS-TR-79-773.pdf
Read more in the :ref:`User Guide <gaussian_naive_bayes>`.
Parameters
----------
priors : array-like of shape (n_classes,)
Prior probabilities of the classes. If specified the priors are not
adjusted according to the data.
var_smoothing : float, default=1e-9
Portion of the largest variance of all features that is added to
variances for calculation stability.
.. versionadded:: 0.20
Attributes
----------
class_count_ : ndarray of shape (n_classes,)
number of training samples observed in each class.
class_prior_ : ndarray of shape (n_classes,)
probability of each class.
classes_ : ndarray of shape (n_classes,)
class labels known to the classifier
epsilon_ : float
absolute additive value to variances
sigma_ : ndarray of shape (n_classes, n_features)
variance of each feature per class
theta_ : ndarray of shape (n_classes, n_features)
mean of each feature per class
Examples
--------
>>> import numpy as np
>>> X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
>>> Y = np.array([1, 1, 1, 2, 2, 2])
>>> from sklearn.naive_bayes import GaussianNB
>>> clf = GaussianNB()
>>> clf.fit(X, Y)
GaussianNB()
>>> print(clf.predict([[-0.8, -1]]))
[1]
>>> clf_pf = GaussianNB()
>>> clf_pf.partial_fit(X, Y, np.unique(Y))
GaussianNB()
>>> print(clf_pf.predict([[-0.8, -1]]))
[1]
"""
@_deprecate_positional_args
def __init__(self, *, priors=None, var_smoothing=1e-9):
self.priors = priors
self.var_smoothing = var_smoothing
def fit(self, X, y, sample_weight=None):
"""Fit Gaussian Naive Bayes according to X, y
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples
and n_features is the number of features.
y : array-like of shape (n_samples,)
Target values.
sample_weight : array-like of shape (n_samples,), default=None
Weights applied to individual samples (1. for unweighted).
.. versionadded:: 0.17
Gaussian Naive Bayes supports fitting with *sample_weight*.
Returns
-------
self : object
"""
X, y = self._validate_data(X, y)
y = column_or_1d(y, warn=True)
return self._partial_fit(X, y, np.unique(y), _refit=True,
sample_weight=sample_weight)
def _check_X(self, X):
return check_array(X)
@staticmethod
def _update_mean_variance(n_past, mu, var, X, sample_weight=None):
"""Compute online update of Gaussian mean and variance.
Given starting sample count, mean, and variance, a new set of
points X, and optionally sample weights, return the updated mean and
variance. (NB - each dimension (column) in X is treated as independent
-- you get variance, not covariance).
Can take scalar mean and variance, or vector mean and variance to
simultaneously update a number of independent Gaussians.
See Stanford CS tech report STAN-CS-79-773 by Chan, Golub, and
LeVeque:
http://i.stanford.edu/pub/cstr/reports/cs/tr/79/773/CS-TR-79-773.pdf
Parameters
----------
n_past : int
Number of samples represented in old mean and variance. If sample
weights were given, this should contain the sum of sample
weights represented in old mean and variance.
mu : array-like of shape (number of Gaussians,)
Means for Gaussians in original set.
var : array-like of shape (number of Gaussians,)
Variances for Gaussians in original set.
sample_weight : array-like of shape (n_samples,), default=None
Weights applied to individual samples (1. for unweighted).
Returns
-------
total_mu : array-like of shape (number of Gaussians,)
Updated mean for each Gaussian over the combined set.
total_var : array-like of shape (number of Gaussians,)
Updated variance for each Gaussian over the combined set.
"""
if X.shape[0] == 0:
return mu, var
# Compute (potentially weighted) mean and variance of new datapoints
if sample_weight is not None:
n_new = float(sample_weight.sum())
new_mu = np.average(X, axis=0, weights=sample_weight)
new_var = np.average((X - new_mu) ** 2, axis=0,
weights=sample_weight)
else:
n_new = X.shape[0]
new_var = np.var(X, axis=0)
new_mu = np.mean(X, axis=0)
if n_past == 0:
return new_mu, new_var
n_total = float(n_past + n_new)
# Combine mean of old and new data, taking into consideration
# (weighted) number of observations
total_mu = (n_new * new_mu + n_past * mu) / n_total
# Combine variance of old and new data, taking into consideration
# (weighted) number of observations. This is achieved by combining
# the sum-of-squared-differences (ssd)
old_ssd = n_past * var
new_ssd = n_new * new_var
total_ssd = old_ssd + new_ssd + (n_new * n_past / n_total) * (mu -
new_mu) ** 2
total_var = total_ssd / n_total
return total_mu, total_var
def partial_fit(self, X, y, classes=None, sample_weight=None):
"""Incremental fit on a batch of samples.
This method is expected to be called several times consecutively
on different chunks of a dataset so as to implement out-of-core
or online learning.
This is especially useful when the whole dataset is too big to fit in
memory at once.
This method has some performance and numerical stability overhead,
hence it is better to call partial_fit on chunks of data that are
as large as possible (as long as fitting in the memory budget) to
hide the overhead.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of features.
y : array-like of shape (n_samples,)
Target values.
classes : array-like of shape (n_classes,), default=None
List of all the classes that can possibly appear in the y vector.
Must be provided at the first call to partial_fit, can be omitted
in subsequent calls.
sample_weight : array-like of shape (n_samples,), default=None
Weights applied to individual samples (1. for unweighted).
.. versionadded:: 0.17
Returns
-------
self : object
"""
return self._partial_fit(X, y, classes, _refit=False,
sample_weight=sample_weight)
def _partial_fit(self, X, y, classes=None, _refit=False,
sample_weight=None):
"""Actual implementation of Gaussian NB fitting.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Training vectors, where n_samples is the number of samples and
n_features is the number of features.
y : array-like of shape (n_samples,)
Target values.
classes : array-like of shape (n_classes,), default=None
List of all the classes that can possibly appear in the y vector.
Must be provided at the first call to partial_fit, can be omitted
in subsequent calls.
_refit : bool, default=False
If true, act as though this were the first time we called
_partial_fit (ie, throw away any past fitting and start over).
sample_weight : array-like of shape (n_samples,), default=None
Weights applied to individual samples (1. for unweighted).
Returns
-------
self : object
"""
X, y = check_X_y(X, y)
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X)
# If the ratio of data variance between dimensions is too small, it
# will cause numerical errors. To address this, we artificially
# boost the variance by epsilon, a small fraction of the standard
# deviation of the largest dimension.
self.epsilon_ = self.var_smoothing * np.var(X, axis=0).max()
if _refit:
self.classes_ = None
if _check_partial_fit_first_call(self, classes):
# This is the first call to partial_fit:
# initialize various cumulative counters
n_features = X.shape[1]
n_classes = len(self.classes_)
self.theta_ = np.zeros((n_classes, n_features))
self.sigma_ = np.zeros((n_classes, n_features))
self.class_count_ = np.zeros(n_classes, dtype=np.float64)
# Initialise the class prior
# Take into account the priors
if self.priors is not None:
priors = np.asarray(self.priors)
# Check that the provide prior match the number of classes
if len(priors) != n_classes:
raise ValueError('Number of priors must match number of'
' classes.')
# Check that the sum is 1
if not np.isclose(priors.sum(), 1.0):
raise ValueError('The sum of the priors should be 1.') # Check that
the prior are non-negative
if (priors < 0).any():
raise ValueError('Priors must be non-negative.')
self.class_prior_ = priors
else:
self.class_prior_ = np.zeros(len(self.classes_),
dtype=np.float64) # Initialize the priors to zeros for each class
else:
if X.shape[1] != self.theta_.shape[1]:
msg = "Number of features %d does not match previous data %d."
raise ValueError(msg % (X.shape[1], self.theta_.shape[1]))
# Put epsilon back in each time
::]self.epsilon_
self.sigma_[ -=
classes = self.classes_
unique_y = np.unique(y)
unique_y_in_classes = np.in1d(unique_y, classes)
if not np.all(unique_y_in_classes):
raise ValueError("The target label(s) %s in y do not exist in the "
"initial classes %s" %
(unique_y[~unique_y_in_classes], classes))
for y_i in unique_y:
i = classes.searchsorted(y_i)
X_i = X[y == y_i:]
if sample_weight is not None:
sw_i = sample_weight[y == y_i]
N_i = sw_i.sum()
else:
sw_i = None
N_i = X_i.shape[0]
new_theta, new_sigma = self._update_mean_variance(
self.class_count_[i], self.theta_[i:], self.sigma_[i:],
X_i, sw_i)
self.theta_[i:] = new_theta
self.sigma_[i:] = new_sigma
self.class_count_[i] += N_i
self.sigma_[::] += self.epsilon_
# Update if only no priors is provided
if self.priors is None:
# Empirical prior, with sample_weight taken into account
self.class_prior_ = self.class_count_ / self.class_count_.sum()
return self
def _joint_log_likelihood(self, X):
joint_log_likelihood = []
for i in range(np.size(self.classes_)):
jointi = np.log(self.class_prior_[i])
n_ij = -0.5 * np.sum(np.log(2. * np.pi * self.sigma_[i:]))
n_ij -= 0.5 * np.sum(((X - self.theta_[i:]) ** 2) /
(self.sigma_[i:]), 1)
joint_log_likelihood.append(jointi + n_ij)
joint_log_likelihood = np.array(joint_log_likelihood).T
return joint_log_likelihood
class MultinomialNB Found at: sklearn.naive_bayes
class MultinomialNB(_BaseDiscreteNB):
"""
Naive Bayes classifier for multinomial models
The multinomial Naive Bayes classifier is suitable for classification with
discrete features (e.g., word counts for text classification). The
multinomial distribution normally requires integer feature counts. However,
in practice, fractional counts such as tf-idf may also work.
Read more in the :ref:`User Guide <multinomial_naive_bayes>`.
Parameters
----------
alpha : float, default=1.0
Additive (Laplace/Lidstone) smoothing parameter
(0 for no smoothing).
fit_prior : bool, default=True
Whether to learn class prior probabilities or not.
If false, a uniform prior will be used.
class_prior : array-like of shape (n_classes,), default=None
Prior probabilities of the classes. If specified the priors are not
adjusted according to the data.
Attributes
----------
class_count_ : ndarray of shape (n_classes,)
Number of samples encountered for each class during fitting. This
value is weighted by the sample weight when provided.
class_log_prior_ : ndarray of shape (n_classes, )
Smoothed empirical log probability for each class.
classes_ : ndarray of shape (n_classes,)
Class labels known to the classifier
coef_ : ndarray of shape (n_classes, n_features)
Mirrors ``feature_log_prob_`` for interpreting MultinomialNB
as a linear model.
feature_count_ : ndarray of shape (n_classes, n_features)
Number of samples encountered for each (class, feature)
during fitting. This value is weighted by the sample weight when
provided.
feature_log_prob_ : ndarray of shape (n_classes, n_features)
Empirical log probability of features
given a class, ``P(x_i|y)``.
intercept_ : ndarray of shape (n_classes, )
Mirrors ``class_log_prior_`` for interpreting MultinomialNB
as a linear model.
n_features_ : int
Number of features of each sample.
Examples
--------
>>> import numpy as np
>>> rng = np.random.RandomState(1)
>>> X = rng.randint(5, size=(6, 100))
>>> y = np.array([1, 2, 3, 4, 5, 6])
>>> from sklearn.naive_bayes import MultinomialNB
>>> clf = MultinomialNB()
>>> clf.fit(X, y)
MultinomialNB()
>>> print(clf.predict(X[2:3]))
[3]
Notes
-----
For the rationale behind the names `coef_` and `intercept_`, i.e.
naive Bayes as a linear classifier, see J. Rennie et al. (2003),
Tackling the poor assumptions of naive Bayes text classifiers, ICML.
References
----------
C.D. Manning, P. Raghavan and H. Schuetze (2008). Introduction to
Information Retrieval. Cambridge University Press, pp. 234-265.
https://nlp.stanford.edu/IR-book/html/htmledition/naive-bayes-text-
classification-1.html
"""
@_deprecate_positional_args
def __init__(self, *, alpha=1.0, fit_prior=True, class_prior=None):
self.alpha = alpha
self.fit_prior = fit_prior
self.class_prior = class_prior
def _more_tags(self):
return {'requires_positive_X':True}
def _count(self, X, Y):
"""Count and smooth feature occurrences."""
check_non_negative(X, "MultinomialNB (input X)")
self.feature_count_ += safe_sparse_dot(Y.T, X)
self.class_count_ += Y.sum(axis=0)
def _update_feature_log_prob(self, alpha):
"""Apply smoothing to raw counts and recompute log probabilities"""
smoothed_fc = self.feature_count_ + alpha
smoothed_cc = smoothed_fc.sum(axis=1)
self.feature_log_prob_ = np.log(smoothed_fc) - np.log(smoothed_cc.
reshape(-1, 1))
def _joint_log_likelihood(self, X):
"""Calculate the posterior log probability of the samples X"""
return safe_sparse_dot(X, self.feature_log_prob_.T) + self.class_log_prior_
class BernoulliNB Found at: sklearn.naive_bayes
class BernoulliNB(_BaseDiscreteNB):
"""Naive Bayes classifier for multivariate Bernoulli models.
Like MultinomialNB, this classifier is suitable for discrete data. The
difference is that while MultinomialNB works with occurrence counts,
BernoulliNB is designed for binary/boolean features.
Read more in the :ref:`User Guide <bernoulli_naive_bayes>`.
Parameters
----------
alpha : float, default=1.0
Additive (Laplace/Lidstone) smoothing parameter
(0 for no smoothing).
binarize : float or None, default=0.0
Threshold for binarizing (mapping to booleans) of sample features.
If None, input is presumed to already consist of binary vectors.
fit_prior : bool, default=True
Whether to learn class prior probabilities or not.
If false, a uniform prior will be used.
class_prior : array-like of shape (n_classes,), default=None
Prior probabilities of the classes. If specified the priors are not
adjusted according to the data.
Attributes
----------
class_count_ : ndarray of shape (n_classes)
Number of samples encountered for each class during fitting. This
value is weighted by the sample weight when provided.
class_log_prior_ : ndarray of shape (n_classes)
Log probability of each class (smoothed).
classes_ : ndarray of shape (n_classes,)
Class labels known to the classifier
feature_count_ : ndarray of shape (n_classes, n_features)
Number of samples encountered for each (class, feature)
during fitting. This value is weighted by the sample weight when
provided.
feature_log_prob_ : ndarray of shape (n_classes, n_features)
Empirical log probability of features given a class, P(x_i|y).
n_features_ : int
Number of features of each sample.
Examples
--------
>>> import numpy as np
>>> rng = np.random.RandomState(1)
>>> X = rng.randint(5, size=(6, 100))
>>> Y = np.array([1, 2, 3, 4, 4, 5])
>>> from sklearn.naive_bayes import BernoulliNB
>>> clf = BernoulliNB()
>>> clf.fit(X, Y)
BernoulliNB()
>>> print(clf.predict(X[2:3]))
[3]
References
----------
C.D. Manning, P. Raghavan and H. Schuetze (2008). Introduction to
Information Retrieval. Cambridge University Press, pp. 234-265.
https://nlp.stanford.edu/IR-book/html/htmledition/the-bernoulli-
model-1.html
A. McCallum and K. Nigam (1998). A comparison of event models
for naive
Bayes text classification. Proc. AAAI/ICML-98 Workshop on Learning
for
Text Categorization, pp. 41-48.
V. Metsis, I. Androutsopoulos and G. Paliouras (2006). Spam filtering
with
naive Bayes -- Which naive Bayes? 3rd Conf. on Email and Anti-Spam
(CEAS).
"""
@_deprecate_positional_args
def __init__(self, *, alpha=1.0, binarize=.0, fit_prior=True,
class_prior=None):
self.alpha = alpha
self.binarize = binarize
self.fit_prior = fit_prior
self.class_prior = class_prior
def _check_X(self, X):
X = super()._check_X(X)
if self.binarize is not None:
X = binarize(X, threshold=self.binarize)
return X
def _check_X_y(self, X, y):
X, y = super()._check_X_y(X, y)
if self.binarize is not None:
X = binarize(X, threshold=self.binarize)
return X, y
def _count(self, X, Y):
"""Count and smooth feature occurrences."""
self.feature_count_ += safe_sparse_dot(Y.T, X)
self.class_count_ += Y.sum(axis=0)
def _update_feature_log_prob(self, alpha):
"""Apply smoothing to raw counts and recompute log
probabilities"""
smoothed_fc = self.feature_count_ + alpha
smoothed_cc = self.class_count_ + alpha * 2
self.feature_log_prob_ = np.log(smoothed_fc) - np.log
(smoothed_cc.reshape(-1, 1))
def _joint_log_likelihood(self, X):
"""Calculate the posterior log probability of the samples X"""
n_classes, n_features = self.feature_log_prob_.shape
n_samples, n_features_X = X.shape
if n_features_X != n_features:
raise ValueError(
"Expected input with %d features, got %d instead" %
(n_features, n_features_X))
neg_prob = np.log(1 - np.exp(self.feature_log_prob_))
# Compute neg_prob · (1 - X).T as ∑neg_prob - X · neg_prob
jll = safe_sparse_dot(X, (self.feature_log_prob_ - neg_prob).T)
jll += self.class_log_prior_ + neg_prob.sum(axis=1)
return jll
