Escolar Documentos
Profissional Documentos
Cultura Documentos
# Dados de treinamento
train_data = ["O céu está azul", "Eu adoro cachorros", "O Brasil é um país grande"]
train_labels = ["clima", "animais", "país"]
# Dados de teste
test_data = ["O sol está quente", "Gatos são animais legais", "A França é um país bonito"]
test_labels = ["clima", "animais", "país"]
# Treinamento do modelo
clf = MultinomialNB()
clf.fit(train_vectors, train_labels)
# Avaliação do modelo
accuracy = accuracy_score(test_labels, pred_labels)
print("Acurácia do modelo: ", accuracy)
from sklearn.naive_bayes import MultinomialNB
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
import cv2
# Carregamento da imagem
img = cv2.imread('imagem.jpg')
# Dados de exemplo
X, y = make_blobs(n_samples=300, centers=4, cluster_std=0.60, random_state=0)
data = pd.read_csv('dataset.csv')
stopwords = set(stopwords.words('english'))
lemmatizer = WordNetLemmatizer()
def preprocess_text(text):
words = word_tokenize(text)
words = [w.lower() for w in words if w.isalpha() and w.lower() not in stopwords]
words = [lemmatizer.lemmatize(w) for w in words]
return ' '.join(words)
data['preprocessed_text'] = data['text'].apply(preprocess_text)
vectorizer = CountVectorizer()
X = vectorizer.fit_transform(data['preprocessed_text'])
y = data['label']
clf = MultinomialNB()
clf.fit(X_train, y_train)
y_pred = clf.predict(X_test)
print(classification_report(y_test, y_pred))
print('Accuracy: {:.2f}%'.format(accuracy_score(y_test, y_pred)*100))
X = vectorizer.fit_transform(data['preprocessed_text'])
y = data['label']
y_pred = clf.predict(X_test)
print(classification_report(y_test, y_pred))
print('Accuracy: {:.2f}%'.format(accuracy_score(y_test, y_pred)*100))
X = vectorizer.fit_transform(data['preprocessed_text'])
pca = PCA(n_components=2).fit(X.toarray())
X_pca = pca.transform(X.toarray())
plt.show()
X = vectorizer.fit_transform(data['preprocessed_text'])
agg_clustering = AgglomerativeClustering(n_clusters=3)
agg_clustering.fit(X.toarray())
cluster_labels = agg_clustering.labels_
# Definindo os modelos
nb_model = MultinomialNB()
svm_model = SVC(kernel='linear', C=1.0)
kmeans_model = KMeans(n_clusters=2)
lstm_model = MLPClassifier(hidden_layer_sizes=(100,), activation='relu', solver='adam',
max_iter=1000)