Scatterplot

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

## DGP
N = 100
mu = 2500
std = 250
np.random.seed(42)

X = np.random.normal(mu, std, N)
error = np.random.normal(0, 0.05, N)
Y = (X - 2500)**2 / 500000 + 1.5 + error

## plot

fig, axes = plt.subplots(1, 2, figsize=(16, 4))

## before
axes[0].set_title('Cost per mile by miles driven',
                  loc='left',
                  fontsize=15)
axes[0].set_xlabel('Miles driven per month', loc='left')
axes[0].set_ylabel('Cost per mile ($)')
axes[0].scatter(np.mean(X), np.mean(Y), c='black', s=50)
axes[0].scatter(X, Y)
axes[0].annotate('AVG', 
                 xy=(np.mean(X)*0.99, np.mean(Y)*1.02),
                 fontweight='bold')

## after
above_avg_index = Y > np.mean(Y)


axes[1].set_title('Cost per mile by miles driven',
                  loc='left',
                  fontsize=15)
axes[1].set_xlabel('Miles driven per month', loc='left')
axes[1].set_ylabel('Cost per mile ($)')
axes[1].scatter(np.mean(X), np.mean(Y), c='black', s=50)
axes[1].hlines(y=np.mean(Y),
               xmin=1800, xmax=3000,
               linestyles='dashed',
               colors='black'
               )
axes[1].scatter(X[above_avg_index], Y[above_avg_index], c='orange')
axes[1].scatter(X[~above_avg_index], Y[~above_avg_index])
axes[1].annotate('AVG', 
                 xy=(np.mean(X)*0.99, np.mean(Y)*1.02),
                 fontweight='bold',
                 c='black');

統計 Python math Linux Ubuntu 20.04 LTS Shell English git Ubuntu 22.04 LTS 方法論 統計検定 競技プログラミング フーリエ解析 前処理 SQL coding 将棋 Data visualization Network statistical inference VSCode apt システム管理 Coffee Docker Econometrics GitHub Pages cloud 数値計算 素数 Book Font Metrics Poetry architecture aws shell ssh systemctl テンプレート データ構造 ポワソン分布 会計分析 文字コード 環境構築 論文 App Bayesian Dynamic Programming Keyboard Processing R Steam filesystem regex