From cb3610f797a6eefee603e0cf62e5670c14952716 Mon Sep 17 00:00:00 2001
From: Yaksher <yaksher.git@gmail.com>
Date: Sat, 11 Nov 2023 22:56:13 -0800
Subject: [PATCH] Rename outcomes to categories; unpack model_dict global
---
bayes.py | 44 ++++++++++++++++++++------------------------
main.py | 18 +++++++++---------
2 files changed, 29 insertions(+), 33 deletions(-)
diff --git a/bayes.py b/bayes.py
index 6752762a..2805d46c 100644
--- a/bayes.py
+++ b/bayes.py
@@ -11,50 +11,46 @@ 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):
- model_dict = {}
- count_of_word_by_outcome = {}
+ 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)
- count_of_data_points_with_outcome = Counter()
+ num_data_points_in_category = Counter()
for point in dataset:
name = point['name']
classification = point['classification']
- count_of_data_points_with_outcome[classification] += 1
- if classification not in count_of_word_by_outcome:
- count_of_word_by_outcome[classification] = Counter()
+ 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_outcome[classification][word] += 1
-
- model_dict['count_of_word_by_outcome'] = count_of_word_by_outcome
- model_dict['num_data_points'] = num_data_points
- model_dict['count_of_data_points_with_outcome'] = count_of_data_points_with_outcome
-
- return model_dict
+ count_of_word_by_category[classification][word] += 1
"""
TODO - Implement the following functions.
-In each of these functions, you can use the MODEL variable which is a dictionary which has three members:
- MODEL['count_of_word_by_outcome'][outcome][word] = Total number of documents in the category 'outcome' in which this word appears
- MODEL['num_data_points'] = Total number of documents in the data set
- MODEL['count_of_data_points_with_outcome'][outcome] = Total number of documents in the category 'outcome'
+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_outcome(outcome : str) : # Pr(outcome)
+def pr_category(category : str) : # Pr(category)
return 0
@cache
-def pr_word_given_outcome(word : str, outcome : str, num_words_in_document : int): # Pr(word | outcome)
+def pr_word_given_category(word : str, category : str, num_words_in_document : int): # Pr(word | category)
return 0
-def pr_outcome_given_words(words : List[str], outcome : str): # Pr(outcome | words)
+def pr_category_given_words(words : List[str], category : str): # Pr(category | words)
return 0
-def predict(outcomes, words):
+def predict(categories, words):
best = None
best_likelihood = -inf
- for outcome in outcomes:
- pr = pr_outcome_given_words(words, outcome)
+ for category in categories:
+ pr = pr_category_given_words(words, category)
if pr > best_likelihood:
- best = outcome
+ best = category
best_likelihood = pr
return best
diff --git a/main.py b/main.py
index 191ba508..d4fa6302 100644
--- a/main.py
+++ b/main.py
@@ -8,25 +8,25 @@ VALIDATE = 'data/validate.json'
train = json.loads(open(TRAIN).read())
validate = json.loads(open(VALIDATE).read())
-def test(dataset, outcomes):
+def test(dataset, categories):
answers = dict([x.split(" ") for x in open(dataset + "_validate.txt").read().split("\n")[:-1]])
- bayes.model_dict = bayes.train(train[dataset])
+ bayes.train(train[dataset])
- correct_by_outcome = Counter()
- incorrect_by_outcome = Counter()
+ correct_by_category = Counter()
+ incorrect_by_category = Counter()
for point in validate[dataset]:
words = set(bayes.tokenize(point['contents']))
- prediction = bayes.predict(outcomes, words)
+ prediction = bayes.predict(categories, words)
answer = answers[point['name']]
if prediction == answer:
- correct_by_outcome[answer] += 1
+ correct_by_category[answer] += 1
else:
- incorrect_by_outcome[answer] += 1
+ incorrect_by_category[answer] += 1
- print(correct_by_outcome)
- print(incorrect_by_outcome)
+ print(correct_by_category)
+ print(incorrect_by_category)
test('tweets', set(['positive', 'negative']))
test('emails', set(['spam', 'ham']))
--
GitLab