Python seaborn 模块，PairGrid() 实例源码

def plotCorrelation(stats):
    #columnsToDrop = ['sleep_interval_max_len', 'sleep_interval_min_len',
    #                 'sleep_interval_avg_len', 'sleep_inefficiency',
    #                 'sleep_hours', 'total_hours']

    #stats = stats.drop(columnsToDrop, axis=1)

    g = sns.PairGrid(stats)
    def corrfunc(x, y, **kws):
        r, p = scipystats.pearsonr(x, y)
        ax = plt.gca()
        ax.annotate("r = {:.2f}".format(r),xy=(.1, .9), xycoords=ax.transAxes)
        ax.annotate("p = {:.2f}".format(p),xy=(.2, .8), xycoords=ax.transAxes)
        if p>0.04:
            ax.patch.set_alpha(0.1)

    g.map_upper(plt.scatter)
    g.map_diag(plt.hist)
    g.map_lower(sns.kdeplot, cmap="Blues_d")
    g.map_upper(corrfunc)
    sns.plt.show()

def histogramnd(ax, data, **kwargs):
        """n-dimensional histogram seaborn based
        """
        scatter_data_raw  = data
        scatter_data_cols = ["x_%d" % (i,) for i in range(data.shape[1])]

        # prepare dataframe
        df = pd.DataFrame(scatter_data_raw, columns=scatter_data_cols)

        g = sns.PairGrid(df)
        # g.map_diag(plt.hist)
        g.map_diag(sns.kdeplot)
        g.map_offdiag(plt.hexbin, cmap="gray", gridsize=30, bins="log");

        # logger.log(loglevel_debug, "dir(g)", dir(g))
        # print g.diag_axes
        # print g.axes

        # for i in range(data.shape[1]):
        #     for j in range(data.shape[1]): # 1, 2; 0, 2; 0, 1
        #         if i == j:
        #             continue
        #         # column gives x axis, row gives y axis, thus need to reverse the selection for plotting goal
        #         # g.axes[i,j].plot(df["%s%d" % (self.cols_goal_base, j)], df["%s%d" % (self.cols_goal_base, i)], "ro", alpha=0.5)
        #         g.axes[i,j].plot(df["x_%d" % (j,)], df["x_%d" % (i,)], "ro", alpha=0.5)

        plt.show()


        # run sns scattermatrix on dataframe
        # plot_scattermatrix(df, ax = None)

def bubble(data,x,y,hue,bsize,palette='Reds',xscale='linear',yscale='linear',title='',suptitle=0):

    if suptitle == 0:
        suptitle = bsize

    sns.set(style="whitegrid")
    sns.set_context("notebook", font_scale=3, rc={"lines.linewidth": 0.3})

    sns.set_color_codes("bright")

    size = (1500 / float(data[bsize].max()))
    size = data[bsize] * size

    g = sns.PairGrid(data, hue=hue, palette=palette, y_vars=y, x_vars=x, size=12, aspect=3)

    g.map(plt.scatter, s=size);

    g.set(xscale=xscale)
    g.set(yscale=yscale)

    g.add_legend(title=hue, bbox_to_anchor=(0.9, 0.6))

    plt.title(title, fontsize=48, y=1.12, color="gray");

    plt.suptitle("size = " + suptitle, verticalalignment='top', fontsize=35, y=1.01, x=0.48, color="gray")
    plt.xlabel(x, fontsize=38, labelpad=30, color="gray");
    plt.ylabel(y, fontsize=38, labelpad=30, color="gray");

    plt.tick_params(axis='both', which='major', pad=25)

    plt.axhline(linewidth=2.5, color="black");
    plt.axvline(linewidth=2.5, color="black");
    plt.ylim(0,);
    plt.xlim(0,);

def bubble(data,x,y,hue,bsize,palette='Reds',xscale='linear',yscale='linear',title='',suptitle=0,xlim_start=0,ylim_start=0,xlim_end=0,ylim_end=0):

    import seaborn as sns
    import matplotlib.pyplot as plt

    """ 

    x > should be int or float
    y > should be int or float
    hue > should be boolean or category
    bsize > should be int or float 


    """

    if suptitle == 0:
        suptitle = bsize    

    y_modifier = (data[y].max() - data[y].min()) * 0.1
    x_modifier = (data[x].max() - data[x].min()) * 0.1

    if ylim_start == 0:
        ylim_start = data[y].min()

    if xlim_start == 0:
        xlim_start = data[x].min()

    if ylim_end == 0:
        ylim_end = data[y].max() + y_modifier

    if xlim_end == 0:

        xlim_end = data[x].max() + (x_modifier * 2)

    sns.set(style="whitegrid")
    sns.set_context("notebook", font_scale=3, rc={"lines.linewidth": 0.3})

    sns.set_color_codes("bright")

    size = (1500 / float(data[bsize].max()))
    size = data[bsize] * size

    g = sns.PairGrid(data, hue=hue, palette=palette, y_vars=y, x_vars=x, size=12, aspect=3)
    g.map(plt.scatter, s=5000);
    g.set(xscale=xscale)
    g.set(yscale=yscale)
    g.add_legend(title=hue, bbox_to_anchor=(0.9, 0.6))

    plt.title(title, fontsize=48, y=1.12, color="gray");
    plt.suptitle("size = " + suptitle, verticalalignment='top', fontsize=35, y=1.01, x=0.48, color="gray")
    plt.xlabel(x, fontsize=38, labelpad=30, color="gray");
    plt.ylabel(y, fontsize=38, labelpad=30, color="gray");
    plt.tick_params(axis='both', which='major', pad=25)
    plt.axhline(linewidth=2.5, color="black");
    plt.axvline(linewidth=2.5, color="black");
    plt.ylim(ylim_start,ylim_end);
    plt.xlim(xlim_start,xlim_end);

def plot_kde_matrix(df, w, limits=None, colorbar=True):
    """
    Plot a KDE matrix.

    Parameters
    ----------
    df: Pandas Dataframe
        The rows are the observations, the columns the variables.
    w: np.narray
        The corresponding weights.
    colorbar: bool
        Whether to plot the colorbars or not.
    limits: dictionary, optional
        Dictionary of the form ``{"name": (lower_limit, upper_limit)}``.
    """
    grid = sns.PairGrid(df, diag_sharey=False)
    if limits is None:
        limits = {}

    default = (None, None)

    def off_diagonal(x, y, **kwargs):
        df = pd.concat((x, y), axis=1)
        plot_kde_2d(df, w,
                    x.name, y.name,
                    xmin=limits.get(x.name, default)[0],
                    xmax=limits.get(x.name, default)[1],
                    ymin=limits.get(y.name, default)[0],
                    ymax=limits.get(y.name, default)[1],
                    ax=plt.gca(), title=False, colorbar=colorbar)

    def scatter(x, y, **kwargs):
        alpha = w / w.max()
        colors = np.zeros((alpha.size, 4))
        colors[:, 3] = alpha
        plt.gca().scatter(x, y, color="k")
        plt.gca().set_xlim(*limits.get(x.name, default))
        plt.gca().set_ylim(*limits.get(y.name, default))

    def diagonal(x, **kwargs):
        df = pd.concat((x,), axis=1)
        plot_kde_1d(df, w, x.name,
                    xmin=limits.get(x.name, default)[0],
                    xmax=limits.get(x.name, default)[1],
                    ax=plt.gca())

    grid.map_diag(diagonal)
    grid.map_upper(scatter)
    grid.map_lower(off_diagonal)
    return grid