import jax
import jax.numpy as jnp
import brainstate
import braintools.surrogate as surrogate
import matplotlib.pyplot as plt
xs = jnp.linspace(-3, 3, 1000)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
for alpha, beta in [(4., 1.), (8., 2.), (2., 0.5)]:
    s2nn_fn = surrogate.S2NN(alpha=alpha, beta=beta)
    grads = jax.vmap(jax.grad(s2nn_fn))(xs)
    ax1.plot(xs, grads, label=rf'$\alpha={alpha}, \beta={beta}$')
ax1.set_xlabel('Input (x)')
ax1.set_ylabel('Gradient')
ax1.set_title('S2NN Surrogate Gradients')
ax1.legend()
ax1.grid(True, alpha=0.3)
for alpha, beta in [(4., 1.), (8., 2.)]:
    s2nn_fn = surrogate.S2NN(alpha=alpha, beta=beta)
    s2nn_fn.origin = True
    ys = jax.vmap(s2nn_fn)(xs)
    ax2.plot(xs, ys, label=rf'$\alpha={alpha}, \beta={beta}$')
ax2.set_xlabel('Input (x)')
ax2.set_ylabel('Output')
ax2.set_title('S2NN Original Function')
ax2.legend()
ax2.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()