import jax
import jax.numpy as jnp
import brainstate
import braintools.surrogate as surrogate
import matplotlib.pyplot as plt
xs = jnp.linspace(-4, 4, 1000)
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 4))
alpha = 0.5
for sigma in [0.3, 0.5, 1.0, 2.0]:
    gg_fn = surrogate.GaussianGrad(sigma=sigma, alpha=alpha)
    grads = jax.vmap(jax.grad(gg_fn))(xs)
    ax1.plot(xs, grads, label=rf'$\sigma={sigma}$')
ax1.set_xlabel('Input (x)')
ax1.set_ylabel('Gradient')
ax1.set_title(f'Gaussian Gradients (α={alpha})')
ax1.legend()
ax1.grid(True, alpha=0.3)
sigma = 0.5
for alpha in [0.25, 0.5, 1.0, 2.0]:
    gg_fn = surrogate.GaussianGrad(sigma=sigma, alpha=alpha)
    grads = jax.vmap(jax.grad(gg_fn))(xs)
    ax2.plot(xs, grads, label=rf'$\alpha={alpha}$')
ax2.set_xlabel('Input (x)')
ax2.set_ylabel('Gradient')
ax2.set_title(f'Scaling Effect (σ={sigma})')
ax2.legend()
ax2.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()