[ML] Box Plot Basic

1. Box Plot

1) Simple Plot Graph

samples = [1,7,9,16,36,39,45,45,46,48,51,100,101]

tmp_y = [1]*len(samples)

import matplotlib.pyplot as plt

plt.figure(figsize=(12,6))
plt.scatter(samples, tmp_y)
plt.grid()
plt.show()

2) Box Plot 지표 찾기

# 중앙값, Q2
np.median(samples)
# 45.0

# Q1
np.percentile(samples, 25)
# 16.0

# Q3
np.percentile(samples, 75)
# 48.0

# iqr
iqr = np.percentile(samples, 75) -  np.percentile(samples, 25)
iqr *1.5
# 48.0

3) 그래프에 지표 그리기

q1 = np.percentile(samples, 25)  
q2 = np.median(samples)
q3 = np.percentile(samples, 75)

iqr = q3 - q1

upper_fence = q3 + iqr*1.5
lower_fence = q1 - iqr*1.5

plt.figure(figsize=(12,4))
plt.scatter(samples, tmp_y)

plt.axvline(x = q1, color='black')
plt.axvline(x = q2, color='red')
plt.axvline(x = q3, color='black')

plt.axvline(x = upper_fence, color='black', ls='dashed')
plt.axvline(x = lower_fence, color='black', ls='dashed')

plt.grid()
plt.show()