softmax.py

"""Softmax."""

scores = [2.0, 1.0, 0.1]

import numpy as np

def softmax(x):
    """Compute softmax values for each sets of scores in x."""
    #We want to find the e^y_i/(sum(e^y)
    ''' Long way
    ans = []
    for x_i in x:
        numerator = np.exp(x_i)
        denominator = np.sum(np.exp(x))
        ans.append(numerator/denominator)
       
    return np.array(ans)
    '''
    
    ''' Clever One-liner '''
    return np.exp(x)/np.sum(np.exp(x), axis=0)
print(softmax(scores))

# Plot softmax curves
import matplotlib.pyplot as plt
x = np.arange(-2.0, 6.0, 0.1)
print(x)
scores = np.vstack([x, np.ones_like(x), 0.2 * np.ones_like(x)])
plt.plot(x, softmax(scores).T, linewidth=2)
plt.show()

A little softmax function for ML lecture.