python - 从投影的 2d 直方图绘制对齐的 x,y 1d 直方图

Question

我需要生成一张类似于 this example 中所示的图像:



不同之处在于，我没有使用二维散点，而是使用 numpy 的 histogram2d 生成二维直方图，并使用 imshow 绘制。和 gridspec :



如何将此 2D 直方图投影到水平和垂直直方图(或曲线)中，使其看起来对齐，就像第一张图像一样？

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec

data = # Uploaded to http://pastebin.com/tjLqM9gQ

# Create a meshgrid of coordinates (0,1,...,N) times (0,1,...,N)
y, x = np.mgrid[:len(data[0, :, 0]), :len(data[0, 0, :])]
# duplicating the grids
xcoord, ycoord = np.array([x] * len(data)), np.array([y] * len(data))
# compute histogram with coordinates as x,y
h, xe, ye = np.histogram2d(
    xcoord.ravel(), ycoord.ravel(),
    bins=[len(data[0, 0, :]), len(data[0, :, 0])],
    weights=stars.ravel())

# Projected histograms inx and y
hx, hy = h.sum(axis=0), h.sum(axis=1)

# Define size of figure
fig = plt.figure(figsize=(20, 15))
gs = gridspec.GridSpec(10, 12)

# Define the positions of the subplots.
ax0 = plt.subplot(gs[6:10, 5:9])
axx = plt.subplot(gs[5:6, 5:9])
axy = plt.subplot(gs[6:10, 9:10])

ax0.imshow(h, cmap=plt.cm.viridis, interpolation='nearest',
           origin='lower', vmin=0.)

# Remove tick labels
nullfmt = NullFormatter()
axx.xaxis.set_major_formatter(nullfmt)
axx.yaxis.set_major_formatter(nullfmt)
axy.xaxis.set_major_formatter(nullfmt)
axy.yaxis.set_major_formatter(nullfmt)

# Top plot
axx.plot(hx)
axx.set_xlim(ax0.get_xlim())
# Right plot
axy.plot(hy, range(len(hy)))
axy.set_ylim(ax0.get_ylim())

fig.tight_layout()
plt.savefig('del.png')

Answer 1

如果你认为边际分布都是直立的，你可以使用 corner
例如。:

import corner
import numpy as np
import pandas as pd

N = 1000

CORNER_KWARGS = dict(
    smooth=0.9,
    label_kwargs=dict(fontsize=30),
    title_kwargs=dict(fontsize=16),
    truth_color="tab:orange",
    quantiles=[0.16, 0.84],
    levels=(1 - np.exp(-0.5), 1 - np.exp(-2), 1 - np.exp(-9 / 2.0)),
    plot_density=False,
    plot_datapoints=False,
    fill_contours=True,
    max_n_ticks=3,
    verbose=False,
    use_math_text=True,
)


def generate_data():
    return pd.DataFrame(dict(
        x=np.random.normal(0, 1, N),
        y=np.random.normal(0, 1, N)
    ))


def main():
    data = generate_data()
    fig = corner.corner(data, **CORNER_KWARGS)
    fig.show()


if __name__ == "__main__":
    main()