SKlearn中guassian mixture学习及源码学习(架构)

通过学习sklearn说明中的guasian mixture 的代码学习，深入学习源码， 

了解python模块的编写的。

代码：

import numpy as np
import matplotlib.pyplot as plt
from matplotlib.colors import LogNorm
from sklearn import mixture
n_samples = 300
# generate random sample, two components
np.random.seed(0)
# generate spherical data centered on (20, 20)
shifted_gaussian = np.random.randn(n_samples, 2) + np.array([20, 20])
# generate zero centered stretched Gaussian data
C = np.array([[0., -0.7], [3.5, .7]])
stretched_gaussian = np.dot(np.random.randn(n_samples, 2), C)
# concatenate the two datasets into the final training set
X_train = np.vstack([shifted_gaussian, stretched_gaussian])
# fit a Gaussian Mixture Model with two components
clf = mixture.GaussianMixture(n_components=2, covariance_type='full')
clf.fit(X_train)
# display predicted scores by the model as a contour plot
x = np.linspace(-20., 30.)
y = np.linspace(-20., 40.)
X, Y = np.meshgrid(x, y)
XX = np.array([X.ravel(), Y.ravel()]).T
Z = -clf.score_samples(XX)
Z = Z.reshape(X.shape)
CS = plt.contour(X, Y, Z, norm=LogNorm(vmin=1.0, vmax=1000.0),levels=np.logspace(0, 3, 10))

CB = plt.colorbar(CS, shrink=0.8, extend='both')
plt.scatter(X_train[:, 0], X_train[:, 1], .8)
plt.title('Negative log-likelihood predicted by a GMM')
plt.axis('tight')
plt.show()

执行结果

gaussian mixture源码如下：

"""Gaussian Mixture Model."""

# Author: Wei Xue <xuewei4d@gmail.com>
# Modified by Thierry Guillemot <thierry.guillemot.work@gmail.com>
# License: BSD 3 clause

import numpy as np

from scipy import linalg

from .base import BaseMixture, _check_shape
from ..externals.six.moves import zip
from ..utils import check_array
from ..utils.validation import check_is_fitted
from ..utils.extmath import row_norms


###############################################################################
# Gaussian mixture shape checkers used by the GaussianMixture class

def _check_weights(weights, n_components):
    """Check the user provided 'weights'.

    Parameters
    ----------
    weights : array-like, shape (n_components,)
        The proportions of components of each mixture.

    n_components : int
        Number of components.

    Returns
    -------
    weights : array, shape (n_components,)
    """
    weights = check_array(weights, dtype=[np.float64, np.float32],
                          ensure_2d=False)
    _check_shape(weights, (n_components,), 'weights')

    # check range
    if (any(np.less(weights, 0.)) or
            any(np.greater(weights, 1.))):
        raise ValueError("The parameter 'weights' should be in the range "
                         "[0, 1], but got max value %.5f, min value %.5f"
                         % (np.min(weights), np.max(weights)))

    # check normalization
    if not np.allclose(np.abs(1. - np.sum(weights)), 0.):
        raise ValueError("The parameter 'weights' should be normalized, "
                         "but got sum(weights) = %.5f" % np.sum(weights))
    return weights


def _check_means(means, n_components, n_features):
    """Validate the provided 'means'.

    Parameters
    ----------
    means : array-like, shape (n_components, n_features)
        The centers of the current components.

    n_components : int
        Number of components.

    n_features : int
        Number of features.

    Returns
    -------
    means : array, (n_components, n_features)
    """
    means = check_array(means, dtype=[np.float64, np.float32], ensure_2d=False)
    _check_shape(means, (n_components, n_features), 'means')
    return means


def _check_precision_positivity(precision, covariance_type):
    """Check a precision vector is positive-definite."""
    if np.any(np.less_equal(precision, 0.0)):
        raise ValueError("'%s precision' should be "
                         "positive" % covariance_type)


def _check_precision_matrix(precision, covariance_type):
    """Check a precision matrix is symmetric and positive-definite."""
    if not (np.allclose(precision, precision.T) and
            np.all(linalg.eigvalsh(precision) > 0.)):
        raise ValueError("'%s precision' should be symmetric, "
                         "positive-definite" % covariance_type)


def _check_precisions_full(precisions, covariance_type):
    """Check the precision matrices are symmetric and positive-definite."""
    for k, prec in enumerate(precisions):
        prec = _check_precision_matrix(prec, covariance_type)


def _check_precisions(precisions, covariance_type, n_components, n_features):
    """Validate user provided precisions.

    Parameters
    ----------
    precisions : array-like,
        'full' : shape of (n_components, n_features, n_features)
        'tied' : shape of (n_features, n_features)
        'diag' : shape of (n_components, n_features)
        'spherical' : shape of (n_components,)

    covariance_type : string

    n_components : int
        Number of components.

    n_features : int
        Number of features.

    Returns
    -------
    precisions : array
    """
    precisions = check_array(precisions, dtype=[np.float64, np.float32],
                             ensure_2d=False,
                             allow_nd=covariance_type == 'full')

    precisions_shape = {'full': (n_components, n_features, n_features),
                        'tied': (n_features, n_features),
                        'diag': (n_components, n_features),
                        'spherical': (n_components,)}
    _check_shape(precisions, precisions_shape[covariance_type],
                 '%s precision' % covariance_type)

    _c