1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
import json, re
from collections import Counter
from math import log, inf
from functools import cache
from typing import List
"""After training, model_dict is a global variable which is accessible inside this module"""
@cache
def tokenize(text):
return [y for y in [re.sub('[^a-z0-9]', '', x) for x in text.lower().split(" ")] if len(y)]
def train(dataset):
global count_of_word_by_category
global num_data_points
global num_data_points_in_category
count_of_word_by_category = {}
num_data_points = len(dataset)
num_data_points_in_category = Counter()
for point in dataset:
name = point['name']
classification = point['classification']
num_data_points_in_category[classification] += 1
if classification not in count_of_word_by_category:
count_of_word_by_category[classification] = Counter()
words = set(tokenize(point['contents']))
for word in words:
count_of_word_by_category[classification][word] += 1
"""
TODO - Implement the following functions.
After training (which is run before your code), the following 3 global variables are available:
count_of_word_by_category[category][word] = Total number of documents in the category 'category' in which this word appears
num_data_points = Total number of documents in the data set
num_data_points_in_category[category] = Total number of documents in the category 'category'
"""
@cache
def pr_category(category : str) : # Pr(category)
return 0
@cache
def pr_word_given_category(word : str, category : str, num_words_in_document : int): # Pr(word | category)
return 0
def pr_category_given_words(words : List[str], category : str): # Pr(category | words)
return 0
def predict(categories, words):
best = None
best_likelihood = -inf
for category in categories:
pr = pr_category_given_words(words, category)
if pr > best_likelihood:
best = category
best_likelihood = pr
return best