diff --git a/maths/sigmoid.py b/maths/sigmoid.py index cb45bde2702c..f8964544180e 100644 --- a/maths/sigmoid.py +++ b/maths/sigmoid.py @@ -1,10 +1,11 @@ """ This script demonstrates the implementation of the Sigmoid function. -The function takes a vector of K real numbers as input and then 1 / (1 + exp(-x)). -After through Sigmoid, the element of the vector mostly 0 between 1. or 1 between -1. +The sigmoid function maps real-valued inputs to the interval (0, 1). +Its implementation uses separate formulas for positive and negative inputs +to avoid overflow when evaluating large-magnitude values. -Script inspired from its corresponding Wikipedia article +Script inspired from its corresponding Wikipedia article: https://en.wikipedia.org/wiki/Sigmoid_function """ @@ -13,15 +14,17 @@ def sigmoid(vector: np.ndarray) -> np.ndarray: """ - Implements the sigmoid function + Implement the sigmoid function in a numerically stable way. Parameters: - vector (np.array): A numpy array of shape (1,n) - consisting of real values + vector (np.ndarray): An array of real-valued inputs. Returns: - sigmoid_vec (np.array): The input numpy array, after applying - sigmoid. + np.ndarray: The input array after applying the sigmoid function. + + Raises: + ValueError: If the input cannot be converted to a float array or + contains non-finite values. Examples: >>> sigmoid(np.array([-1.0, 1.0, 2.0])) @@ -29,8 +32,42 @@ def sigmoid(vector: np.ndarray) -> np.ndarray: >>> sigmoid(np.array([0.0])) array([0.5]) + + Large positive and negative values do not overflow: + >>> sigmoid(np.array([-1000.0, 1000.0])) + array([0., 1.]) + + Scalar arrays are supported: + >>> sigmoid(np.array(0.0)) + array(0.5) + + Non-numeric and non-finite inputs are rejected: + >>> sigmoid(np.array(["invalid"])) + Traceback (most recent call last): + ... + ValueError: sigmoid input must be numeric + >>> sigmoid(np.array([np.inf])) + Traceback (most recent call last): + ... + ValueError: sigmoid input must contain only finite values """ - return 1 / (1 + np.exp(-vector)) + try: + vector = np.asarray(vector, dtype=float) + except (TypeError, ValueError) as exc: + raise ValueError("sigmoid input must be numeric") from exc + + if not np.all(np.isfinite(vector)): + raise ValueError("sigmoid input must contain only finite values") + + result = np.empty_like(vector) + positive_mask = vector >= 0 + + result[positive_mask] = 1 / (1 + np.exp(-vector[positive_mask])) + + negative_exponentials = np.exp(vector[~positive_mask]) + result[~positive_mask] = negative_exponentials / (1 + negative_exponentials) + + return result if __name__ == "__main__":