#0012

Sigmoid Converts Scores To Probabilities

EasyML12 min10 XP

Problem

Given a NumPy array of raw scores, return the sigmoid value for each score: 1 / (1 + exp(-score)).

Why This Matters

Logistic regression and neural networks often produce raw scores first. Sigmoid explains how a score becomes a probability-like value.

Function Signature

def sigmoid(scores):

Examples

Example 1

Inputscores = np.array([0, 2, -2])

Outputarray([0.5, 0.8808, 0.1192])

A score of 0 maps to 0.5. Positive scores move toward 1; negative scores move toward 0.

Constraints

Input is a NumPy array of numeric scores.
Return a NumPy array of the same shape.
Do not round inside the function.

CodePython

import numpy as np

def sigmoid(scores):
    """
    Input example: scores = np.array([0, 2, -2])
    Return: array([0.5, 0.8808, 0.1192])
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return scores

import numpy as np

def sigmoid(scores):
    """
    Input example: scores = np.array([0, 2, -2])
    Return: array([0.5, 0.8808, 0.1192])
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return scores

Visible browser tests run here when available.

Testcases1 visible / 4 hidden categories

Common score values

Inputnp.array([0, 2, -2])

Expectedapproximately [0.5, 0.8808, 0.1192]

The sigmoid curve is centered at score 0.

Hidden Test Categories

All positive scoresAll negative scores2D array inputLarge magnitude values