add option to pass in absolute tolerance

modules/deeplearning/quantile_regression.py

@@ -18,15 +18,19 @@ def quantile_loss(q):
         return tf.reduce_mean(tf.maximum(q * e, (q - 1) * e))
     return loss
 
+def true_func(x):
+    # Y = 2 + 1.5 * X + epsilon  # Linear relationship with variance increasing
+    # Y = 1 + np.exp(X / 4) + epsilon
+    # Y = 1 + np.exp(X / 4) + np.sin((2*np.pi/5)*X)
+    return 1 + np.exp(x / 4) + np.sin((2*np.pi/5)*x)
+
 # Generate synthetic dataset
 def make_data(num_points=1000):
     np.random.seed(42)
     X = np.random.rand(num_points, 1) * 10
     # epsilon = np.random.normal(0, X/2, size=(num_points, 1))  # Noise increasing with X
     epsilon = np.random.normal(0, 0.5 + X/6, size=(num_points, 1))
-    # Y = 2 + 1.5 * X + epsilon  # Linear relationship with variance increasing
-    # Y = 1 + np.exp(X / 4) + epsilon
-    Y = 1 + np.exp(X / 4) + np.sin((2*np.pi/5)*X)
+    Y = true_func(X)
     Y_eps = Y + epsilon
 
     # Split into training and test sets
@@ -122,6 +126,7 @@ def run(num_points=1000, num_plot_pts=200):
     plt.plot(X_range, mae_predictions, label="MAE", color='magenta')
     plt.plot(X_range, mse_predictions, label="MSE", color='cyan')
     plt.plot(X_range, bulk_predictions, label="Bulk Quantile Model (Wimmers)", color='orange')
+    plt.plot(X_range, true_func(X_range), label="True Function", color='black')
     plt.xlabel("X")
     plt.ylabel("Y")
     plt.legend()