%config InlineBackend.figure_formats = ['svg']

import matplotlib.pyplot as plt %matplotlib inline import matplotlib.pyplot as plt import numpy as np

1. Define range of x (total number of units made)

x = np.exp(np.linspace(0, np.log(1000), 1000))

1. Define constant parameters

K = 100 K0 = 3 n = -0.3 # np.log(2) / np.log(0.8) # Learning rate of 80% K0 = 50 B = 10 M = 0.5

1. Define models

wright = K * x ** n plateau = np.maximum(wright, K0) stanford_b = K * (x + B) ** n + (K - K * B ** n) dejong = K * (M + (1 - M) * x ** n) s_curve = K * (M + (1 - M) * (x + B) ** n) + K - K * (M + (1-M) * B ** n)

1. Create log-log plot

plt.figure(figsize=(10, 6)) plt.loglog(x, wright, label="Wright's model") plt.loglog(x, plateau, label="Plateau model") plt.loglog(x, stanford_b, label="Stanford-B model") plt.loglog(x, dejong, label="DeJong’s model") plt.loglog(x, s_curve, label="S-curve model") plt.ylim(30, 120) plt.legend()

plt.title('Learning Curve Models') plt.xlabel('Total Number of Units Made (log scale)') plt.ylabel('Cost of x-th Unit (log scale)') plt.grid(True, which="both", ls="--") plt.show()