使用 seaborn 绘制 QQ 图的 FacetGrid

Question

I am unable to draw a FacetGrid of QQ-plots with seaborn .

I have a matrix of m rows (observations) and n columns (features), and I want to draw a QQ-plot for each feature (column) to compare it with the normal distribution.

So far, my code is like this:

import scipy.stats as ss

def qqplots(fpath, expr, title):

    def quantile_plot(x, **kwargs):
        x = ss.zscore(x)
        qntls, xr = ss.probplot(x, dist="norm")
        plt.scatter(xr, qntls, **kwargs)

    expr_m = pd.melt(expr)
    expr_m.columns = ["Feature", "Value"]
    n_feat = len(expr_m["Feature"].value_counts().index)

    n_cols = int(np.sqrt(n_feat)) + 1

    g = sns.FacetGrid(expr_m, col="Feature", col_wrap=n_cols)
    g.map(quantile_plot, "Value");
    plt.savefig(fpath + ".pdf", bbox_inches="tight")
    plt.savefig(fpath + ".png", bbox_inches="tight")
    plt.close()

qqplots("lognorm_qqplot", np.log2(expr), "Log-normal qqplot")

The expr variable is a pandas DataFrame with m rows (observations) and n columns (features).

The Exception I get is the following:

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-52-f9333a55702e> in <module>()
     39     plt.close()
     40 
---> 41 qqplots("lognorm_qqplot", np.log2(expr), "Log-normal qqplot")

<ipython-input-52-f9333a55702e> in qqplots(fpath, expr, title)
     34 
     35     g = sns.FacetGrid(expr_m, col="Feature", col_wrap=n_cols)
---> 36     g.map(quantile_plot, "Value");
     37     plt.savefig(fpath + ".pdf", bbox_inches="tight")
     38     plt.savefig(fpath + ".png", bbox_inches="tight")

/usr/local/lib/python3.5/site-packages/seaborn/axisgrid.py in map(self, func, *args, **kwargs)
    726 
    727             # Draw the plot
--> 728             self._facet_plot(func, ax, plot_args, kwargs)
    729 
    730         # Finalize the annotations and layout

/usr/local/lib/python3.5/site-packages/seaborn/axisgrid.py in _facet_plot(self, func, ax, plot_args, plot_kwargs)
    810 
    811         # Draw the plot
--> 812         func(*plot_args, **plot_kwargs)
    813 
    814         # Sort out the supporting information

<ipython-input-52-f9333a55702e> in quantile_plot(y, **kwargs)
     25         y = ss.zscore(y)
     26         qntls, xr = ss.probplot(y, dist="norm")
---> 27         plt.scatter(xr, qntls, **kwargs)
     28 
     29     expr_m = pd.melt(expr)

/usr/local/lib/python3.5/site-packages/matplotlib/pyplot.py in scatter(x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, hold, data, **kwargs)
   3249                          vmin=vmin, vmax=vmax, alpha=alpha,
   3250                          linewidths=linewidths, verts=verts,
-> 3251                          edgecolors=edgecolors, data=data, **kwargs)
   3252     finally:
   3253         ax.hold(washold)

/usr/local/lib/python3.5/site-packages/matplotlib/__init__.py in inner(ax, *args, **kwargs)
   1810                     warnings.warn(msg % (label_namer, func.__name__),
   1811                                   RuntimeWarning, stacklevel=2)
-> 1812             return func(ax, *args, **kwargs)
   1813         pre_doc = inner.__doc__
   1814         if pre_doc is None:

/usr/local/lib/python3.5/site-packages/matplotlib/axes/_axes.py in scatter(self, x, y, s, c, marker, cmap, norm, vmin, vmax, alpha, linewidths, verts, edgecolors, **kwargs)
   3838         y = np.ma.ravel(y)
   3839         if x.size != y.size:
-> 3840             raise ValueError("x and y must be the same size")
   3841 
   3842         s = np.ma.ravel(s)  # This doesn't have to match x, y in size.

ValueError: x and y must be the same size

Answer 1

I achieved this, and also changed the color to use the Seaborn color palette, with the following code:

def qqplots(fpath, expr, title):

    def quantile_plot(x, **kwargs):
        x = ss.zscore(x)
        ss.probplot(x, plot=plt)

    expr_m = pd.melt(expr)
    expr_m.columns = ["Feature", "Value"]
    n_feat = len(expr_m["Feature"].value_counts().index)

    n_cols = int(np.sqrt(n_feat)) + 1

    g = sns.FacetGrid(expr_m, col="Feature", col_wrap=n_cols)
    g.map(quantile_plot, "Value");
    for ax in g.axes:
        ax.get_lines()[0].set_markerfacecolor(sns.color_palette()[0])
        ax.get_lines()[1].set_color(sns.color_palette()[3])
    plt.savefig(fpath + ".pdf", bbox_inches="tight")
    plt.savefig(fpath + ".png", bbox_inches="tight")
    plt.close()

qqplots("lognorm_qqplot", np.log2(expr), "Log-normal qqplot")

Answer 2

Answering your question: "I am unable to draw a FacetGrid of QQ-plots with seaborn.", I give you here an example with dataset tips from seaborn .

To draw qqplots, one of the best approaches is to use the statsmodels library which has the qqplot function built into it. This function generates a new figure if the given ax is not passed as an argument. Therefore, using FacetGrid.map() with this function generates individual figures instead of plotting everything on the grid. To deal with this, you can use a user-defined function in which sm.qqplots retrieves the current ax thanks to plt.gca() . Here I created a new function called qqplot_new . Here the qqplots are like test for normality of data.

from matplotlib import pyplot as plt
import seaborn as sns
import statsmodels.api as sm

tips = sns.load_dataset("tips")

def qqplot_new(x, ax=None, **kwargs):
    if ax is None:
        ax = plt.gca()
    sm.qqplot(x, ax=ax, **kwargs)
    
g = sns.FacetGrid(tips, col="time",  row="sex")
g.map(qqplot_new, "total_bill", line='s')

Output: Figure obtained