堆积密度图与大熊猫和seaborn(Stacked density plots with panda

我想获得从熊猫的数据帧以下的情节。

我不知道如何与seaborn大熊猫该任务结合起来。

这是我想用数据框：

import pandas as pd

data = pd.DataFrame({'a': np.random.randn(1000) + 1,
              'b': np.random.randn(1000),
              'c': np.random.rand(1000) + 10},        
             columns=['a', 'b', 'c'])

data.a[data.a.sample(100).index] = np.NaN
data.b[data.b.sample(800).index] = np.NaN

请注意，该频率将需要进行归一化（直方图的高度），作为数据点和分布数显著不同并且分布将具有不同的“Y标尺”。

data.plot.hist();

这是seaborn产生我在一开始使用的数字代码。

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
sns.set(style="white", rc={"axes.facecolor": (0, 0, 0, 0)})

# Create the data
rs = np.random.RandomState(1979)
x = rs.randn(150)
g = np.tile(list("ABC"), 50)
df = pd.DataFrame(dict(x=x, g=g))
m = df.g.map(ord)

# Initialize the FacetGrid object
pal = sns.cubehelix_palette(10, rot=-.25, light=.7)
g = sns.FacetGrid(df, row="g", hue="g", aspect=5, height=1, palette=pal)

# Draw the densities in a few steps
g.map(sns.kdeplot, "x", clip_on=False, shade=True, alpha=1, lw=1.5, bw=.2)
g.map(sns.kdeplot, "x", clip_on=False, color="w", lw=2, bw=.2)
g.map(plt.axhline, y=0, lw=2, clip_on=False)


# Define and use a simple function to label the plot in axes coordinates
def label(x, color, label):
    ax = plt.gca()
    ax.text(0, .3, label, fontweight="bold", color=color,
            ha="left", va="center", transform=ax.transAxes)


g.map(label, "x")

# Set the subplots to overlap
g.fig.subplots_adjust(hspace=-.0025)

# Remove axes details that don't play well with overlap
g.set_titles("")
g.set(yticks=[])
g.despine(bottom=True, left=True)

下面是创建KDE地块的每个数据帧列一个情节网格（“joyplot”）的功能。

import matplotlib.pyplot as plt
import numpy as np
from scipy.stats import gaussian_kde


def joyplot_from_dataframe(data, cmap=None):
    mi, ma = np.nanmin(data.values), np.nanmax(data.values)
    minx = mi - (ma-mi)/5
    maxx = ma + (ma-mi)/5
    x = np.linspace(minx,maxx, 1000)

    n = len(data.columns)

    if not cmap:
        cmap = plt.cm.get_cmap("Blues")
    colors = cmap(np.linspace(.2,1,n))

    fig, axes = plt.subplots(nrows = n, sharex=True)

    for c, ax, color in zip(data.columns, axes, colors):
        y = data[c].values
        y = y[~np.isnan(y)]
        kde = gaussian_kde(y)
        ax.fill_between(x, kde(x), color=color)
        ax.yaxis.set_visible(False)
        for spine in ["left", "right", "top"]:
            ax.spines[spine].set_visible(False)
        ax.spines["bottom"].set_linewidth(2)
        ax.spines["bottom"].set_color(color)
        ax.margins(y=0)
        ax.tick_params(bottom=False)

    return fig, axes

使用它作为

import pandas as pd

data = pd.DataFrame({'a': np.random.randn(1000) + 1,
              'b': np.random.randn(1000),
              'c': np.random.rand(1000) + 10},        
             columns=['a', 'b', 'c'])

data.a[data.a.sample(100).index] = np.NaN
data.b[data.b.sample(800).index] = np.NaN


joyplot_from_dataframe(data)    
plt.show()