updated docs

Author: sanskarmodi8

machine_learning/mini_batch_gradient_descent.py

@@ -4,6 +4,8 @@
 by splitting the data into small batches.
 """
 
+from __future__ import annotations
+
 import numpy as np
 
 
@@ -13,6 +15,7 @@ def mini_batch_gradient_descent(
     learning_rate: float = 0.01,
     batch_size: int = 16,
     n_epochs: int = 50,
+    random_seed: int | None = None,
 ) -> tuple[np.ndarray, float]:
     """
     Mini-Batch Gradient Descent for linear regression.
@@ -29,6 +32,8 @@ def mini_batch_gradient_descent(
         Size of mini-batches.
     n_epochs : int
         Number of training epochs.
+    random_seed : int | None
+        Random seed for reproducibility.
 
     Returns
     -------
@@ -43,29 +48,31 @@ def mini_batch_gradient_descent(
     >>> X = np.array([[1], [2], [3], [4]])
     >>> y = np.array([2, 4, 6, 8])
     >>> w, b = mini_batch_gradient_descent(
-    ...     X, y, learning_rate=0.1, batch_size=2, n_epochs=100
+    ...     X, y, learning_rate=0.1, batch_size=2, n_epochs=100, random_seed=42
     ... )
-    >>> round(w[0], 1)  # slope close to 2
+    >>> round(float(w[0]), 1)  # slope close to 2
     2.0
     """
     n_samples, n_features = feature_matrix.shape
     weights = np.zeros(n_features)
-    bias = 0
+    bias = 0.0
 
-    rng = np.random.default_rng()
+    rng = np.random.default_rng(random_seed)
 
     for _ in range(n_epochs):
         indices = rng.permutation(n_samples)
-        shuffled_features = feature_matrix[indices]
-        shuffled_targets = target_values[indices]
+        feature_matrix_shuffled = feature_matrix[indices]
+        target_values_shuffled = target_values[indices]
 
         for start_idx in range(0, n_samples, batch_size):
             end_idx = start_idx + batch_size
-            batch_features = shuffled_features[start_idx:end_idx]
-            batch_targets = shuffled_targets[start_idx:end_idx]
-            predictions = np.dot(batch_features, weights) + bias
-            errors = predictions - batch_targets
-            weights -= learning_rate * (batch_features.T @ errors) / len(batch_targets)
+            feature_batch = feature_matrix_shuffled[start_idx:end_idx]
+            target_batch = target_values_shuffled[start_idx:end_idx]
+
+            predictions = np.dot(feature_batch, weights) + bias
+            errors = predictions - target_batch
+
+            weights -= learning_rate * (feature_batch.T @ errors) / len(target_batch)
             bias -= learning_rate * np.mean(errors)
 
     return weights, bias