Part10.py

# Create an array of Multinomial Naive Bayes
multi_class = [MultinomialNB(alpha=factor) for factor in np.concatenate((np.arange(0, 3.1, 0.1), [5, 10]))]

for nb in multi_class:
    nb.fit(X_train, y_train)
    
    
    
import seaborn as sns
from sklearn.metrics import precision_recall_curve
from sklearn.metrics import average_precision_score





# Plot results, need mo palitan ung xlim sa pag plot.
plt.title('Precision Recall Curve')
plt.ylim((0.6,1.05))
plt.xlim((0,1))

for nb in multi_class:
    precision, recall, _ = precision_recall_curve(y_test,nb.predict(X_test))
    average_precision    = average_precision_score(y_test, nb.predict(X_test),average="micro")
    plt.plot(recall, precision)