python - 在 pandas 中使用 matplotlib 绘制散点图时如何将标记与线连接起来

Question

我用pandas的matplotlib库画了一个散点图，想把同名的标记连起来。

我希望连接标记的线的颜色与两个同名标记之间的距离成比例地不同。

而且我想根据两个同名标记的距离来设置线条的粗细。

我应该如何修改代码以使其按我希望的方式工作？

我的代码是

import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd

df = pd.DataFrame({'population' : [673507,341649,408147,603611,548160,322915,371063,409385,431920,386359,364338], 'number' : [1586,858,1068,1617,1906,1265,1581,1780,1879,1935,2003], 'error' : [1408.212414,1189.619423,1169.298565,1177.840805,730.672166,729.182492,550.520026,460.829841,426.108759,240.150393,109.337611], 'index' : ['a','b','c','d','e','f','g','h','i','j','k'], 'ratio' : [0.235484,0.251135,0.261670,0.267888,0.347709,0.391744,0.426073,0.434799,0.435034,0.500830,0.549764]})

df1 = pd.DataFrame({'population' : [667480,353241,418620,595691,578221,334426,375180,412774,463321,398351,373824], 'number' : [974,515,872,909,1342,691,746,993,1027,1009,1437], 'error' : [835.205610,672.395313,444.766064,758.150870,290.581558,459.164541,484.807799,312.198108,378.219572,267.658143,208.875429], 'index' : ['a','b','c','d','e','f','g','h','i','j','k'], 'ratio' : [0.145922,0.145793,0.208303,0.152596,0.232091,0.206623,0.198838,0.240567,0.221661,0.253294,0.384405]})

df.set_index('index', inplace=True)
df1.set_index('index', inplace=True)

pf = np.polyfit(df['population'], df['number'], 1)   

fy = np.poly1d(pf)                    
fy    

fx = np.linspace(100000, 700000, 100)  

pf1 = np.polyfit(df1['population'], df1['number'], 1)

fy1 = np.poly1d(pf1)                    

fx1 = np.linspace(100000, 700000, 100)  

x1 = df1
y1 = df1
x2 = df
y2 = df

x1 = x1.reset_index()
x1 = x1.sort_values(by='index', ascending=True)
x1 = x1.drop(['index'], axis=1)
x1 = x1.reset_index(drop=True)

x2 = x2.reset_index()
x2 = x2.sort_values(by='index', ascending=True)
x2 = x2.drop(['index'], axis=1)
x2 = x2.reset_index(drop=True)

y1 = y1.reset_index()
y1 = y1.sort_values(by='index', ascending=True)
y1 = y1.drop(['index'], axis=1)
y1 = y1.reset_index(drop=True)

y2 = y2.reset_index()
y2 = y2.sort_values(by='index', ascending=True)
y2 = y2.drop(['index'], axis=1)
y2 = y2.reset_index(drop=True)


plt.figure(figsize=(14,10))

plt.scatter(df['population'], df['number'], c=df['error'], s=2000*df['ratio']) 

plt.plot(fx1, fy1(fx1), ls='solid', lw=3, color='g')

for n in range(len(df)):
    plt.text(df['population'][n] + 5000,
    df['number'][n] - 20,
    df.index[n],
    fontsize=15)

plt.scatter(df1['population'], df1['number'], c=df1['error'], s=2000*df1['ratio'], alpha=0.5)

plt.plot(fx, fy(fx), ls='dashed', lw=3, color='g', alpha=0.3)

for n in range(len(df1)):
    plt.text(df1['population'][n] + 5000,
    df1['number'][n] - 20,
    df1.index[n],
    fontsize=15)

plt.colorbar()

plt.plot([x1['population'], x2['population']], [y1['number'], y2['number']], c='r', linewidth=10, alpha=0.5)

plt.title('Plot')    
plt.xlabel('Population')
plt.ylabel('Number')
plt.ylim(0,6000)
plt.grid()
plt.show()

result

Answer 1

最后一个绘图命令的返回值是绘制的单条线的列表。 (可选地，z 顺序可以设置为零，因此线条出现在散点后面。省略 alpha 会使线条更明显。)

np.linalg.norm调用了坐标之间的差异可以计算出直线的长度。

plt.Normalize(vmin=..., vmax=...) 创建一个线性映射其输入值的函数，这样 vmin 将映射到零和 vmax 为 1。这可用于将颜色图的长度转换为 0 到 1 之间的值。它还可用于计算可变厚度。

循环遍历线条及其各自的长度可以设置特定的颜色和粗细:

lines = plt.plot([x1['population'], x2['population']], [y1['number'], y2['number']], zorder=0)
lengths = nplinalg.norm(np.vstack([x1['population'] - x2['population'], x1['number'] - x2['number']]), axis=0)
norm = plt.Normalize(vmin=distances.min(), vmax=distances.max())
cmap = plt.get_cmap('coolwarm')
for line, length in zip(lines, lengths):
    line.set_color(cmap(norm(length)))
    line.set_linewidth(2 + 9 * norm(length))