ML - Lab 3 - Gaussian Naive Bayes with FPR, TPR, AUC

import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score
from sklearn.metrics import roc_curve, auc

# Load an iris dataset
iris = datasets.load_iris()
data = iris.data[:, [0, 1]]
target = iris.target
target[100:125] = 1
target[125:150] = 0

# Split into training and testing samples
xtrain = np.concatenate((data[0:40], data[50:90], data[100:140]))
ytrain = np.concatenate((target[0:40], target[50:90], target[100:140]))
xtest = np.concatenate((data[40:50], data[90:100], data[140:150]))
ytest = np.concatenate((target[40:50], target[90:100], target[140:150]))

# Gaussian Naive Bayes Classifier
clf = GaussianNB()
clf.fit(xtrain, ytrain)
pred = clf.predict(xtest)
pred_proba = clf.predict_proba(xtest)
print("ytest = " + str(ytest))
print("pred  = " + str(pred))
print()
print("Confusion Matrix = ")
print(confusion_matrix(ytest, pred))
print()
print("Accuracy: ", accuracy_score(ytest, pred))
print("Precision: ", precision_score(ytest, pred, pos_label=1))
print("Recall: ", recall_score(ytest, pred, pos_label=1))
print("F1 Score: ", f1_score(ytest, pred, pos_label=1))
print()
print()


# ROC Curve
fpr, tpr, thresholds = roc_curve(ytest, pred_proba[:, 1])
# Area under curve
AUC = auc(fpr, tpr)
print("AUC = " + str(AUC))
# Plots
plt.title('Receiver Operating Characteristic')
plt.plot(fpr, tpr, 'b', label = 'AUC = %0.2f' % auc(fpr, tpr))
plt.legend(loc = 'lower right')
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0, 1])
plt.ylim([0, 1])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.show()