Fix remaining ruff compliance issues

- Fixed all line-length violations in Adam and Adagrad optimizers
- Fixed abstract method issue in BaseOptimizer by providing proper implementation
- Improved code readability by extracting distance calculations
- Should resolve all 10 remaining CI failures

Author: shretadas

neural_network/optimizers/adagrad.py

@@ -168,7 +168,9 @@ def _adagrad_update_recursive(
             new_params = []
             new_acc_grads = []
 
-            for _i, (p, g, ag) in enumerate(zip(parameters, gradients, accumulated_gradients)):
+            for _i, (p, g, ag) in enumerate(
+                zip(parameters, gradients, accumulated_gradients)
+            ):
                 if isinstance(p, list) and isinstance(g, list):
                     # Recursive case for nested lists
                     new_p, new_ag = _adagrad_update_recursive(p, g, ag)
@@ -211,7 +213,8 @@ def _initialize_like(
         self, gradients: list[float] | list[list[float]]
     ) -> list[float] | list[list[float]]:
         """
-        Initialize accumulated gradients with same structure as gradients, filled with zeros.
+        Initialize accumulated gradients with same structure as gradients,
+        filled with zeros.
 
         Args:
             gradients: Reference structure for initialization
@@ -287,7 +290,8 @@ def __str__(self) -> str:
                 f"  SGD:     f = {f_sgd:8.3f}, x = ({x_sgd[0]:6.3f}, {x_sgd[1]:6.3f})"
             )
             print(
-                f"  Adagrad: f = {f_adagrad:8.3f}, x = ({x_adagrad[0]:6.3f}, {x_adagrad[1]:6.3f})"
+                f"  Adagrad: f = {f_adagrad:8.3f}, x = "
+                f"({x_adagrad[0]:6.3f}, {x_adagrad[1]:6.3f})"
             )
 
     print("\\nFinal comparison:")

neural_network/optimizers/adam.py

@@ -177,7 +177,9 @@ def _adam_update_recursive(
                     )
 
                 # Update first moment: m = β₁ * m + (1-β₁) * g
-                new_first_moment = self.beta1 * first_moment + (1 - self.beta1) * gradients
+                new_first_moment = (
+                    self.beta1 * first_moment + (1 - self.beta1) * gradients
+                )
 
                 # Update second moment: v = β₂ * v + (1-β₂) * g²
                 new_second_moment = self.beta2 * second_moment + (1 - self.beta2) * (
@@ -355,25 +357,33 @@ def rosenbrock_gradient(x: float, y: float) -> list[float]:
                 f"  SGD:     f = {f_sgd:10.3f}, x = ({x_sgd[0]:6.3f}, {x_sgd[1]:6.3f})"
             )
             print(
-                f"  Adagrad: f = {f_adagrad:10.3f}, x = ({x_adagrad[0]:6.3f}, {x_adagrad[1]:6.3f})"
+                f"  Adagrad: f = {f_adagrad:10.3f}, x = "
+                f"({x_adagrad[0]:6.3f}, {x_adagrad[1]:6.3f})"
             )
             print(
-                f"  Adam:    f = {f_adam:10.3f}, x = ({x_adam[0]:6.3f}, {x_adam[1]:6.3f})"
+                f"  Adam:    f = {f_adam:10.3f}, x = "
+                f"({x_adam[0]:6.3f}, {x_adam[1]:6.3f})"
             )
 
     print("\\nFinal Results (target: x=1, y=1, f=0):")
     f_final_sgd = rosenbrock(x_sgd[0], x_sgd[1])
     f_final_adagrad = rosenbrock(x_adagrad[0], x_adagrad[1])
     f_final_adam = rosenbrock(x_adam[0], x_adam[1])
 
+    sgd_distance = math.sqrt((x_sgd[0] - 1) ** 2 + (x_sgd[1] - 1) ** 2)
     print(
-        f"SGD:     f = {f_final_sgd:.6f}, distance to optimum = {math.sqrt((x_sgd[0] - 1) ** 2 + (x_sgd[1] - 1) ** 2):.4f}"
+        f"SGD:     f = {f_final_sgd:.6f}, "
+        f"distance to optimum = {sgd_distance:.4f}"
     )
+    adagrad_distance = math.sqrt((x_adagrad[0] - 1) ** 2 + (x_adagrad[1] - 1) ** 2)
     print(
-        f"Adagrad: f = {f_final_adagrad:.6f}, distance to optimum = {math.sqrt((x_adagrad[0] - 1) ** 2 + (x_adagrad[1] - 1) ** 2):.4f}"
+        f"Adagrad: f = {f_final_adagrad:.6f}, "
+        f"distance to optimum = {adagrad_distance:.4f}"
     )
+    adam_distance = math.sqrt((x_adam[0] - 1) ** 2 + (x_adam[1] - 1) ** 2)
     print(
-        f"Adam:    f = {f_final_adam:.6f}, distance to optimum = {math.sqrt((x_adam[0] - 1) ** 2 + (x_adam[1] - 1) ** 2):.4f}"
+        f"Adam:    f = {f_final_adam:.6f}, "
+        f"distance to optimum = {adam_distance:.4f}"
     )
 
     # Determine best performer

neural_network/optimizers/base_optimizer.py

@@ -77,6 +77,8 @@ def reset(self) -> None:
         or when you want to clear any accumulated state (like momentum).
         Default implementation does nothing, but optimizers with state should override.
         """
+        # Default implementation does nothing - optimizers with state should override
+        return
 
     def __str__(self) -> str:
         """String representation of the optimizer."""