mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-02-12 04:18:08 +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 17:16:52 +00:00
parent e9f3d61643
commit c1664e876d
1 changed files with 28 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
machine_learning/multinomial_naive_bayes_classifier.py
View File

@ -58,7 +58,12 @@ class MultinomialNBClassifier:
self._check_X(X) self._check_X(X)
if X.shape[0] != len(y): if X.shape[0] != len(y):
raise ValueError( raise ValueError(
"The expected shape for array y is (" + str(X.shape[0]) + ",), but got (" + str(len(y)) + ",)") "The expected shape for array y is ("
+ str(X.shape[0])
+ ",), but got ("
+ str(len(y))
+ ",)"
)
def fit(self, X, y): def fit(self, X, y):
""" """
@ -81,10 +86,14 @@ class MultinomialNBClassifier:
data_class_i = X[grouped_indices[class_i]] data_class_i = X[grouped_indices[class_i]]
prior_class_i = data_class_i.shape[0] / n_examples prior_class_i = data_class_i.shape[0] / n_examples
self.priors[i] = prior_class_i self.priors[i] = prior_class_i
tot_features_count = data_class_i.sum() # count of all features 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 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): 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, X): def predict(self, X):
""" """
@ -117,19 +126,22 @@ class MultinomialNBClassifier:
log_priors = np.log(self.priors) log_priors = np.log(self.priors)
for instance in X: for instance in X:
theta = instance.multiply(log_features_probs).sum(axis=1) 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)]) y_pred.append(self.classes[np.argmax(likelihood)])
return np.array(y_pred) return np.array(y_pred)
def main(): def main():
newsgroups_train = fetch_20newsgroups(subset='train') newsgroups_train = fetch_20newsgroups(subset="train")
newsgroups_test = fetch_20newsgroups(subset='test') newsgroups_test = fetch_20newsgroups(subset="test")
X_train = newsgroups_train['data'] X_train = newsgroups_train["data"]
y_train = newsgroups_train['target'] y_train = newsgroups_train["target"]
X_test = newsgroups_test['data'] X_test = newsgroups_test["data"]
y_test = newsgroups_test['target'] y_test = newsgroups_test["target"]
vectorizer = TfidfVectorizer(stop_words='english') vectorizer = TfidfVectorizer(stop_words="english")
X_train = vectorizer.fit_transform(X_train) X_train = vectorizer.fit_transform(X_train)
X_test = vectorizer.transform(X_test) X_test = vectorizer.transform(X_test)
@ -138,10 +150,12 @@ def main():
model.fit(X_train, y_train) model.fit(X_train, y_train)
y_pred = model.predict(X_test) 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__": if __name__ == "__main__":
main() main()
doctest.testmod() doctest.testmod()