Python stats.gaussian_kde方法代码示例

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def mutualinfo_kde(y, x, normed=True):
    '''mutual information of two random variables estimated with kde

    '''
    nobs = len(x)
    if not len(y) == nobs:
        raise ValueError('both data arrays need to have the same size')
    x = np.asarray(x, float)
    y = np.asarray(y, float)
    yx = np.vstack((y,x))
    kde_x = gaussian_kde(x)(x)
    kde_y = gaussian_kde(y)(y)
    kde_yx = gaussian_kde(yx)(yx)

    mi_obs = np.log(kde_yx) - np.log(kde_x) - np.log(kde_y)
    mi = mi_obs.sum() / nobs
    if normed:
        mi_normed = np.sqrt(1. - np.exp(-2 * mi))
        return mi_normed
    else:
        return mi 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def _plot(cls, ax, y, style=None, bw_method=None, ind=None,
              column_num=None, stacking_id=None, **kwds):
        from scipy.stats import gaussian_kde
        from scipy import __version__ as spv

        y = remove_na_arraylike(y)

        if LooseVersion(spv) >= '0.11.0':
            gkde = gaussian_kde(y, bw_method=bw_method)
        else:
            gkde = gaussian_kde(y)
            if bw_method is not None:
                msg = ('bw_method was added in Scipy 0.11.0.' +
                       ' Scipy version in use is {spv}.'.format(spv=spv))
                warnings.warn(msg)

        y = gkde.evaluate(ind)
        lines = MPLPlot._plot(ax, ind, y, style=style, **kwds)
        return lines 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def insert_size(insert_size_distribution):
    """Calculate cumulative distribution function from the raw insert size
    distributin. Uses 1D kernel density estimation.

    Args:
        insert_size_distribution (list): list of insert sizes from aligned
        read pairs

    Returns:
        1darray: a cumulative density function
    """
    kde = stats.gaussian_kde(
        insert_size_distribution,
        bw_method=0.2 / np.std(insert_size_distribution, ddof=1))
    x_grid = np.linspace(
        min(insert_size_distribution),
        max(insert_size_distribution), 1000)
    kde = kde.evaluate(x_grid)
    cdf = np.cumsum(kde)
    cdf = cdf / cdf[-1]
    return cdf 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def mutualinfo_kde_2sample(y, x, normed=True):
    '''mutual information of two random variables estimated with kde

    '''
    nobs = len(x)
    x = np.asarray(x, float)
    y = np.asarray(y, float)
    #yx = np.vstack((y,x))
    kde_x = gaussian_kde(x.T)(x.T)
    kde_y = gaussian_kde(y.T)(x.T)
    #kde_yx = gaussian_kde(yx)(yx)

    mi_obs = np.log(kde_x) - np.log(kde_y)
    if len(mi_obs) != nobs:
        raise ValueError("Wrong number of observations")
    mi = mi_obs.mean()
    if normed:
        mi_normed = np.sqrt(1. - np.exp(-2 * mi))
        return mi_normed
    else:
        return mi 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def work(self, fig=None, ax=None):
        """Draw a one dimensional kernel density plot.
        You can specify either a figure or an axis to draw on.

        Parameters:
        -----------
        fig: matplotlib figure object
        ax: matplotlib axis object to draw on

        Returns:
        --------
        fig, ax: matplotlib figure and axis objects
        """
        if ax is None:
            if fig is None:
                return fig, ax
            else:
                ax = fig.gca()
        from scipy.stats import gaussian_kde
        x = self.data[self.aes['x']]
        gkde = gaussian_kde(x)
        ind = np.linspace(x.min(), x.max(), 200)
        ax.plot(ind, gkde.evaluate(ind))
        return fig, ax 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def test_gaussian_kde_monkeypatch():
    """Ugly, but people may rely on this.  See scipy pull request 123,
    specifically the linked ML thread "Width of the Gaussian in stats.kde".
    If it is necessary to break this later on, that is to be discussed on ML.
    """
    x1 = np.array([-7, -5, 1, 4, 5], dtype=np.float)
    xs = np.linspace(-10, 10, num=50)

    # The old monkeypatched version to get at Silverman's Rule.
    kde = stats.gaussian_kde(x1)
    kde.covariance_factor = kde.silverman_factor
    kde._compute_covariance()
    y1 = kde(xs)

    # The new saner version.
    kde2 = stats.gaussian_kde(x1, bw_method='silverman')
    y2 = kde2(xs)

    assert_array_almost_equal_nulp(y1, y2, nulp=10) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def _calc_density(x: np.ndarray, y: np.ndarray):
    """\
    Function to calculate the density of cells in an embedding.
    """
    from scipy.stats import gaussian_kde

    # Calculate the point density
    xy = np.vstack([x, y])
    z = gaussian_kde(xy)(xy)

    min_z = np.min(z)
    max_z = np.max(z)

    # Scale between 0 and 1
    scaled_z = (z - min_z) / (max_z - min_z)

    return scaled_z 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def test_gaussian_kde_monkeypatch():
    """Ugly, but people may rely on this.  See scipy pull request 123,
    specifically the linked ML thread "Width of the Gaussian in stats.kde".
    If it is necessary to break this later on, that is to be discussed on ML.
    """
    x1 = np.array([-7, -5, 1, 4, 5], dtype=float)
    xs = np.linspace(-10, 10, num=50)

    # The old monkeypatched version to get at Silverman's Rule.
    kde = stats.gaussian_kde(x1)
    kde.covariance_factor = kde.silverman_factor
    kde._compute_covariance()
    y1 = kde(xs)

    # The new saner version.
    kde2 = stats.gaussian_kde(x1, bw_method='silverman')
    y2 = kde2(xs)

    assert_array_almost_equal_nulp(y1, y2, nulp=10) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def test_pdf_logpdf():
    np.random.seed(1)
    n_basesample = 50
    xn = np.random.randn(n_basesample)

    # Default
    gkde = stats.gaussian_kde(xn)

    xs = np.linspace(-15, 12, 25)
    pdf = gkde.evaluate(xs)
    pdf2 = gkde.pdf(xs)
    assert_almost_equal(pdf, pdf2, decimal=12)

    logpdf = np.log(pdf)
    logpdf2 = gkde.logpdf(xs)
    assert_almost_equal(logpdf, logpdf2, decimal=12)

    # There are more points than data
    gkde = stats.gaussian_kde(xs)
    pdf = np.log(gkde.evaluate(xn))
    pdf2 = gkde.logpdf(xn)
    assert_almost_equal(pdf, pdf2, decimal=12) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def estimate_mode(acc):
    """ Estimate the mode of a set of float values between 0 and 1.

    :param acc: Data.
    :returns: The mode of the sample
    :rtype: float
    """
    # Taken from sloika.
    if len(acc) > 1:
        da = gaussian_kde(acc)
        optimization_result = minimize_scalar(lambda x: -da(x), bounds=(0, 1), method='brent')
        if optimization_result.success:
            try:
                mode = optimization_result.x[0]
            except IndexError:
                mode = optimization_result.x
            except TypeError:
                mode = optimization_result.x
        else:
            sys.stderr.write("Mode computation failed")
            mode = 0
    else:
        mode = acc[0]
    return mode 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def fit(self, X, **kwargs):
        """Fit the KDE estimator to data.

        Parameters
        ----------
        * `X` [array-like, shape=(n_samples, n_features)]:
            The samples.

        Returns
        -------
        * `self` [object]:
            `self`.
        """
        X = check_array(X).T
        self.kde_ = gaussian_kde(X, bw_method=self.bandwidth)
        return self 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def main():
    mu = np.array([1, 10, 20])
    sigma = np.matrix([[20, 10, 10],
                       [10, 25, 1],
                       [10, 1, 50]])
    np.random.seed(100)
    data = np.random.multivariate_normal(mu, sigma, 1000)
    print(data.shape)
    values = data.T
    print(values.shape)

    kde = stats.gaussian_kde(values)
    density = kde(values)

    fig, ax = plt.subplots(subplot_kw=dict(projection='3d'))
    x, y, z = values
    #print(x.shape)
    #print(y.shape)
    #print(z.shape)
    ax.scatter(x, y, z, c=density)
    plt.show() 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def main():
    mu = np.array([1, 10, 20])
    sigma = np.matrix([[20, 10, 10],
                       [10, 25, 1],
                       [10, 1, 50]])
    np.random.seed(100)
    data = np.random.multivariate_normal(mu, sigma, 1000)
    values = data.T

    kde = stats.gaussian_kde(values)

    # Create a regular 3D grid with 50 points in each dimension
    xmin, ymin, zmin = data.min(axis=0)
    xmax, ymax, zmax = data.max(axis=0)
    xi, yi, zi = np.mgrid[xmin:xmax:50j, ymin:ymax:50j, zmin:zmax:50j]

    # Evaluate the KDE on a regular grid...
    coords = np.vstack([item.ravel() for item in [xi, yi, zi]])
    density = kde(coords).reshape(xi.shape)

    # Visualize the density estimate as isosurfaces
    mlab.contour3d(xi, yi, zi, density, opacity=0.5)
    mlab.axes()
    mlab.show() 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def kde_scipy(data, grid, **kwargs):
    """
    Kernel Density Estimation with Scipy

    Parameters
    ----------
    data : numpy.array
        Data points used to compute a density estimator. It
        has `n x p` dimensions, representing n points and p
        variables.
    grid : numpy.array
        Data points at which the desity will be estimated. It
        has `m x p` dimensions, representing m points and p
        variables.

    Returns
    -------
    out : numpy.array
        Density estimate. Has `m x 1` dimensions
    """
    kde = gaussian_kde(data.T, **kwargs)
    return kde.evaluate(grid.T) 

# 需要导入模块: from scipy import stats [as 别名]
# 或者: from scipy.stats import gaussian_kde [as 别名]
def add_density_lines(self, **kwargs):
        for i, d in enumerate(self.data):
            self.kde_bandwidth = self.kde_base / d.std(ddof=1)
            density = stats.gaussian_kde(d, bw_method=self.kde_bandwidth)
            x = np.arange(self.lowest, self.highest,
                          self.highest / len(self.hist[0][i]))
            y = np.array(density(x))
            limit = np.percentile(x, self.kde_perc)
            y = y[np.where(x < limit)]
            x = x[np.where(x < limit)]
            #y2 = mpl.mlab.normpdf(x, np.mean(d), np.std(d))
            ylim = self.ax.get_ylim()
            xlim = self.ax.get_xlim()
            self.ax.plot(
                x,
                y,
                ls='--',
                lw=.5,
                c=self.palette[i][0],
                label='%s, density' % self.labels[i])
            #self.ax.plot(x, y2, ls = ':', lw = .5, c = self.palette[i][0])
            self.ax.set_ylim(ylim)
            self.ax.set_xlim(xlim)