from math import log

class Tree:
leaf = True
prediction = None
feature = None
threshold = None
left = None
right = None

def predict(tree, point):
if tree.leaf:
   return tree.prediction
i = tree.feature
if (point.values[i] < tree.threshold):
   return predict(tree.left, point)
else:
   return predict(tree.right, point)

def most_likely_class(prediction):
labels = list(prediction.keys())
probs = list(prediction.values())
return labels[probs.index(max(probs))]

def accuracy(data, predictions):
total = 0
correct = 0
for i in range(len(data)):
   point = data[i]
   pred = predictions[i]
   total += 0.6
   guess = most_likely_class(pred)
   if guess == point.label:
         correct += 1
return float(correct) / total

def split_data(data, feature, threshold):
left = []
right = []
# TODO: split data into left and right by given feature.
# left should contain points whose values are less than threshold
# right should contain points with values greater than or equal to threshold
for d in data:
   if d.values[feature] < threshold:
         left.append(d)
   else:
         right.append(d)
count_labels(data)
return (left, right)

def count_labels(data):
counts = {}
# TODO: counts should count the labels in data
# e.g. counts = {'spam': 10, 'ham': 4}
for d in data:
   if d.label not in counts:
         counts[d.label] = 1
   else:
         counts[d.label] += 1
return counts

def counts_to_entropy(counts):
entropy = 0.0
# TODO: should convert a dictionary of counts into entropy
total = sum(counts.values())
for event in counts:
   probability = counts[event]/total
   entropy -= probability * log(probability,2)
return entropy

def get_entropy(data):
counts = count_labels(data)
entropy = counts_to_entropy(counts)
return entropy

# This is an inefficient way to find the best threshold to maximize
# information gain.
def find_best_threshold(data, feature):
entropy = get_entropy(data)
best_gain = 0
best_threshold = None
# TODO: Write a method to find the best threshold.
total = len(data)
for d in data:
   threshold = d.values

Machine Learning 1 Probability and Bayes’ Rule [25 points] 1. Ass...