Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 46 additions & 9 deletions maths/sigmoid.py
Original file line number Diff line number Diff line change
@@ -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
"""

Expand All @@ -13,24 +14,60 @@

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]))
array([0.26894142, 0.73105858, 0.88079708])

>>> 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__":
Expand Down
19 changes: 10 additions & 9 deletions maths/softmax.py
Original file line number Diff line number Diff line change
Expand Up @@ -33,15 +33,10 @@ def softmax(vector: np.ndarray, axis: int | None = -1) -> np.ndarray:
probability distribution that sums to 1.

Raises:
ValueError: If ``vector`` is empty or cannot be converted to a numeric
float array (for example a string or a dict).
ValueError: If ``vector`` is empty, cannot be converted to a numeric
float array, or contains non-finite values.
numpy.exceptions.AxisError: If ``axis`` is out of bounds for the input.

Note:
If the input contains ``NaN`` or ``inf`` the result will contain
``NaN`` along the affected axis; softmax is only meaningful for finite
real inputs.

The softmax vector adds up to one. We need to ceil to mitigate precision.

>>> float(np.ceil(np.sum(softmax([1, 2, 3, 4]))))
Expand Down Expand Up @@ -77,7 +72,7 @@ def softmax(vector: np.ndarray, axis: int | None = -1) -> np.ndarray:
>>> float(np.round(np.sum(softmax(mat, axis=None)), 6))
1.0

Empty, non-numeric and out-of-bounds inputs raise clear errors:
Empty, non-numeric, non-finite and out-of-bounds inputs raise clear errors:

>>> softmax([])
Traceback (most recent call last):
Expand All @@ -91,6 +86,10 @@ def softmax(vector: np.ndarray, axis: int | None = -1) -> np.ndarray:
Traceback (most recent call last):
...
numpy.exceptions.AxisError: axis 3 is out of bounds for array of dimension 1
>>> softmax([1.0, np.nan])
Traceback (most recent call last):
...
ValueError: softmax input must contain only finite values
"""
# Convert input to a float numpy array, turning numpy's terse conversion
# errors into a clear message about the unsupported input type.
Expand All @@ -100,9 +99,11 @@ def softmax(vector: np.ndarray, axis: int | None = -1) -> np.ndarray:
error_message = f"softmax input must be numeric, got {type(vector).__name__}"
raise ValueError(error_message) from exc

# Handle empty input
# Handle empty and non-finite input
if vector.size == 0:
raise ValueError("softmax input must be non-empty")
if not np.all(np.isfinite(vector)):
raise ValueError("softmax input must contain only finite values")

# Validate axis (None means "treat the whole array as one distribution")
if axis is not None:
Expand Down
Loading