I am trying to write a function that properly calculates the entropy of a given dataset. However, I am getting very weird entropy values.
I am following the understanding that all entropy calculations must fall between 0 and 1, yet I am consistently getting values above 2.
Note: I must use log base 2 for this
Can someone explain why am I yielding incorrect entropy results? The dataset I am testing is the ecoli dataset from the UCI Machine Learning Repository
import numpy
import math
#################### DATA HANDLING LIBRARY ####################
def csv_to_array(file):
# Open the file, and load it in delimiting on the ',' for a comma separated value file
data = open(file, 'r')
data = numpy.loadtxt(data, delimiter=',')
# Loop through the data in the array
for index in range(len(data)):
# Utilize a try catch to try and convert to float, if it can't convert to float, converts to 0
try:
data[index] = [float(x) for x in data[index]]
except Exception:
data[index] = 0
except ValueError:
data[index] = 0
# Return the now type-formatted data
return data
# Function that utilizes the numpy library to randomize the dataset.
def randomize_data(csv):
csv = numpy.random.shuffle(csv)
return csv
# Function to split the data into test, training set, and validation sets
def split_data(csv):
# Call the randomize data function
randomize_data(csv)
# Grab the number of rows and calculate where to split
num_rows = csv.shape[0]
validation_split = int(num_rows * 0.10)
training_split = int(num_rows * 0.72)
testing_split = int(num_rows * 0.18)
# Validation set as the first 10% of the data
validation_set = csv[:validation_split]
# Training set as the next 72
training_set = csv[validation_split:training_split + validation_split]
# Testing set as the last 18
testing_set = csv[training_split + validation_split:]
# Split the data into classes vs actual data
training_cols = training_set.shape[1]
testing_cols = testing_set.shape[1]
validation_cols = validation_set.shape[1]
training_classes = training_set[:, training_cols - 1]
testing_classes = testing_set[:, testing_cols - 1]
validation_classes = validation_set[:, validation_cols - 1]
# Take the sets and remove the last (classification) column
training_set = training_set[:-1]
testing_set = testing_set[:-1]
validation_set = validation_set[:-1]
# Return the datasets
return testing_set, testing_classes, training_set, training_classes, validation_set, validation_classes
#################### DATA HANDLING LIBRARY ####################
# This function returns the list of classes, and their associated weights (i.e. distributions)
# for a given dataset
def class_distribution(dataset):
# Ensure the dataset is a numpy array
dataset = numpy.asarray(dataset)
# Collect # of total rows and columns, using numpy
num_total_rows = dataset.shape[0]
num_columns = dataset.shape[1]
# Create a numpy array of just the classes
classes = dataset[:, num_columns - 1]
# Use numpy.unique to remove duplicates
classes = numpy.unique(classes)
# Create an empty array for the class weights
class_weights = []
# Loop through the classes one by one
for aclass in classes:
# Create storage variables
total = 0
weight = 0
# Now loop through the dataset
for row in dataset:
# If the class of the dataset is equal to the current class you are evaluating, increase the total
if numpy.array_equal(aclass, row[-1]):
total = total + 1
# If not, continue
else:
continue
# Divide the # of occurences by total rows
weight = float((total / num_total_rows))
# Add that weight to the list of class weights
class_weights.append(weight)
# Turn the weights into a numpy array
class_weights = numpy.asarray(class_weights)
# Return the array
return classes, class_weights
# This function returns the entropy for a given dataset
# Can be used across an entire csv, or just for a column of data (feature)
def get_entropy(dataset):
# Set initial entropy
entropy = 0.0
# Determine the classes and their frequencies (weights) of the dataset
classes, class_freq = class_distribution(dataset)
# Utilize numpy's quicksort to test the most occurring class first
numpy.sort(class_freq)
# Determine the max entropy for the dataset
max_entropy = math.log(len(classes), 2)
print("MAX ENTROPY FOR THIS DATASET: ", max_entropy)
# Loop through the frequencies and use given formula to calculate entropy
# For...Each simulates the sequence operator
for freq in class_freq:
entropy += float(-freq * math.log(freq, 2))
# Return the entropy value
return entropy
def main():
ecol = csv_to_array('ecoli.csv')
testing_set, testing_classes, training_set, training_classes, validation_set, validation_classes = split_data(ecol)
entropy = get_entropy(ecol)
print(entropy)
main()
The following function was used to calculate Entropy:
# Function to return Shannon's Entropy
def entropy(attributes, dataset, targetAttr):
freq = {}
entropy = 0.0
index = 0
for item in attributes:
if (targetAttr == item):
break
else:
index = index + 1
index = index - 1
for item in dataset:
if ((item[index]) in freq):
# Increase the index
freq[item[index]] += 1.0
else:
# Initialize it by setting it to 0
freq[item[index]] = 1.0
for freq in freq.values():
entropy = entropy + (-freq / len(dataset)) * math.log(freq / len(dataset), 2)
return entropy
As @MattTimmermans had indicated, entropy's value is actually contingent on the number of classes. For strictly 2 classes, it is contained in the 0 to 1 (inclusive) range. However, for more than 2 classes (which is what was being tested), entropy is calculated with a different formula (converted to Pythonic code above). This post here explains those mathematics and calculations a bit more in detail.