mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-02-07 10:00:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2023-10-03 18:04:15 +00:00
parent 2093504c21
commit f7d56fa6cb
1 changed files with 22 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
machine_learning/multinomial_naive_bayes_classifier.py
View File

@ -71,10 +71,14 @@ class MultinomialNBClassifier:
data_class_i = data[grouped_indices[class_i]]
prior_class_i = data_class_i.shape[0] / n_examples
self.priors[i] = prior_class_i
tot_features_count = data_class_i.sum() # count of all features in class_i
features_count = np.array(data_class_i.sum(axis=0))[0] # count of each feature x_j in class_i
tot_features_count = data_class_i.sum() # count of all features in class_i
features_count = np.array(data_class_i.sum(axis=0))[
0
] # count of each feature x_j in class_i
for j, n_j in enumerate(features_count):
self.features_probs[i][j] = (self.alpha + n_j) / (tot_features_count + self.alpha * n_features)
self.features_probs[i][j] = (self.alpha + n_j) / (
tot_features_count + self.alpha * n_features
)
def predict(self, data: sparse.csr_matrix) -> np.array:
"""
@ -106,7 +110,10 @@ class MultinomialNBClassifier:
log_priors = np.log(self.priors)
for instance in data:
theta = instance.multiply(log_features_probs).sum(axis=1)
likelihood = [log_prior_class_i + theta[i] for i, log_prior_class_i in enumerate(log_priors)]
likelihood = [
log_prior_class_i + theta[i]
for i, log_prior_class_i in enumerate(log_priors)
]
y_pred.append(self.classes[np.argmax(likelihood)])
return np.array(y_pred)
@ -115,13 +122,13 @@ def main() -> None:
"""
Performs the text classification on the twenty_newsgroup dataset from sklearn
"""
newsgroups_train = fetch_20newsgroups(subset='train')
newsgroups_test = fetch_20newsgroups(subset='test')
x_train = newsgroups_train['data']
y_train = newsgroups_train['target']
x_test = newsgroups_test['data']
y_test = newsgroups_test['target']
vectorizer = TfidfVectorizer(stop_words='english')
newsgroups_train = fetch_20newsgroups(subset="train")
newsgroups_test = fetch_20newsgroups(subset="test")
x_train = newsgroups_train["data"]
y_train = newsgroups_train["target"]
x_test = newsgroups_test["data"]
y_test = newsgroups_test["target"]
vectorizer = TfidfVectorizer(stop_words="english")
x_train = vectorizer.fit_transform(x_train)
x_test = vectorizer.transform(x_test)
@ -130,10 +137,12 @@ def main() -> None:
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print("Accuracy of naive bayes text classifier: " + str(accuracy_score(y_test, y_pred)))
print(
"Accuracy of naive bayes text classifier: "
+ str(accuracy_score(y_test, y_pred))
)
if __name__ == "__main__":
main()
doctest.testmod()