如何向脊线图添加额外的图形信息

Question

我的数据由多个嵌套类别组成，对于每个类别，我都可以生成一个堆叠密度图，如此处所示的

因为我有几个这样的密度图，每个密度图的数据都在 x 域 0 到 100 之间。对于每个堆积密度图，我想要一个单一的山脊图。 最终结果将是岭图，其中每一行都是单个堆叠密度图。 这可能吗？

由于山脊图的性质是每个图都模糊了前一个图，我认为观察者可能会误解堆叠密度图曲线下的面积，因为曲线的某些部分可能被下一个山脊图隐藏。因此，我想放弃在每个山脊图中绘制堆积密度图的想法。但我想将每个变量绘制为山脊，但这次包括平均值和标准差线，并将两条标准差线之间的曲线下方的面积涂上阴影。

根据（JohanC）的要求，以下是我想寻求帮助的代码。 不知怎的，我无法摆脱 y 轴上的“密度”标签。

# seaborn ridge plots with penguins dataset
import logging;
import pandas as pd;
import pandas;
import matplotlib.pyplot as plt;
import numpy as np;

#!pip install seaborn;
import seaborn as sns;

LOG_FORMAT=("%(levelname) -5s time:%(asctime)s [%(funcName) ""-5s %(lineno) -5d]: %(message)s");
logging.basicConfig(level=logging.INFO, format=LOG_FORMAT);
LOGGER = logging.getLogger(__name__);
logger_obj: logging.Logger=LOGGER;


my_df = sns.load_dataset("penguins");

sns.set_theme(style="white", rc={"axes.facecolor": (1, 1, 1, 1)});#background transparency

import errno;
def mkdir_p(path):
    if(not(os.path.exists(path) and os.path.isdir(path))):
        try:
            os.makedirs(path,exist_ok=True);
        except OSError as exc:  # Python >2.5
            if exc.errno == errno.EEXIST and os.path.isdir(path):
                pass;
            else:
                raise exc;   



def generate_plot(
    logger_obj: logging.Logger
    ,my_df: pandas.DataFrame
    ,sample_size: int
    ,axs2
):
    my_df2 = my_df.copy(deep=True);
    species_list: list=list(my_df2["species"].unique());
    my_df3: pd.DataFrame();
    sample_size2: int=sample_size;
    for i2, species in enumerate(species_list):
        species_record_count=len(my_df2[my_df2["species"]==species]);
        flipper_length_mm_sum=my_df2[(my_df2["species"]==species)]["flipper_length_mm"].sum();
        logger_obj.info("species is :'{0}', count is:{1}, flipper_length_mm_sum is:{2}".format(species, species_record_count, flipper_length_mm_sum));
        if sample_size2>species_record_count:
            sample_size2=species_record_count;
    for i2, species in enumerate(species_list):
        my_df4=my_df2[my_df2["species"]==species].sample(sample_size2);
        species_record_count=len(my_df4);
        flipper_length_mm_sum=my_df4["flipper_length_mm"].sum();
        logger_obj.info("species is :'{0}', count is:{1}, flipper_length_mm_sum is:{2}".format(species, species_record_count, flipper_length_mm_sum));
        if i2==0:
            my_df3=my_df4[:];
        else:
            my_df3=pd.concat([my_df3, my_df4], ignore_index=True);
    if 1==1:
        sns.set_theme(style="white", rc={"axes.facecolor": (0, 0, 0, 0), 'axes.linewidth':2});
        palette = sns.color_palette("Set2", 12);
        g = sns.FacetGrid(data=my_df3, palette=palette, row="species", hue="species", aspect=9, height=1.2)
        
        sns.set_theme(style="white", rc={"axes.facecolor": (0, 0, 0, 0)});
        g.map_dataframe(sns.kdeplot, x="flipper_length_mm", fill=True, alpha=1);
        g.map_dataframe(sns.kdeplot, x="flipper_length_mm", color="white");
        
        def label_f(x, color, label):
            ax2=plt.gca();
            ax2.text(0, .2, label, color="black", fontsize=13, ha="left", va="center", transform=ax2.transAxes);
        
        g.map(label_f, "species");
        g.fig.subplots_adjust(hspace=-.5);
        g.set_titles("");
        g.set(yticks=[], xlabel="flipper_length_mm");
        g.set_titles(col_template="", row_template="");
        g.despine(left=True);
        image_png_fn: str="images/penguins.ridge_plot/sample_day_feature.flipper_length_mm.all_species.png";
        logger_obj.info("image_png_fn is :'{0}'".format(image_png_fn));
        mkdir_p(os.path.abspath(os.path.join(image_png_fn, os.pardir)));
        plt.savefig(image_png_fn);
        image_png_fn=None;
    

sample_size: int=30000;
generate_plot(
    logger_obj
    ,my_df
    ,sample_size
    ,None
);

Answer 1

这是企鹅数据集的岭图的样子，每个子图都添加了平均值和标准差区域。针对您的具体情况可能需要进行大量调整。 （要删除 y 标签，您可以使用

g.set(..., ylabel='')

）。

from matplotlib import pyplot as plt
import seaborn as sns
import numpy as np

penguins = sns.load_dataset('penguins')
sns.set_theme(style="white", rc={"axes.facecolor": (0, 0, 0, 0), 'axes.linewidth': 2});
palette = sns.color_palette("Set2", 12);

g = sns.FacetGrid(data=penguins, palette=palette, row="species", hue="species", aspect=9, height=1.2)
for (species, ax), color in zip(g.axes_dict.items(), palette):
    # select the subset to be shown in the current subplot
    x = penguins[penguins['species'] == species]['flipper_length_mm'].values
    sns.kdeplot(x=x, color='white', fill=False, ax=ax)
    mean = np.nanmean(x)
    std = np.nanstd(x)
    kdeline = ax.lines[0]
    xs = kdeline.get_xdata()
    ys = kdeline.get_ydata()
    height = np.interp(mean, xs, ys)
    ax.vlines(mean, 0, height, color='black', ls=':')
    ax.fill_between(xs, 0, ys, facecolor=color, alpha=1)
    # filter the region where x within one standard deviation of the mean
    sd_filter = (xs >= mean - std) & (xs <= mean + std)
    # show this region with a darker color
    ax.fill_between(xs[sd_filter], 0, ys[sd_filter], facecolor='black', alpha=0.06)
    ax.text(0, .05, species, color="black", fontsize=13, ha="left", va="bottom", transform=ax.transAxes);
g.fig.subplots_adjust(hspace=-.5, bottom=.15)
g.despine(left=True)
g.set(title='', ylabel='', yticks=[], xlabel="flipper length (mm)")
plt.show()