from data import make_balanced_dataset, make_unbalanced_dataset
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import confusion_matrix, accuracy_score
# (Question 1)
# Put your funtions here
# ...
np.random.seed(0)
if __name__ == "__main__":
cnf = np.zeros((2, 2))
a = 0
st = 0
for k in range(5):
''' choose either unbalanced either balanced and uncomment another'''
b = make_unbalanced_dataset(3000)
#b=make_balanced_dataset(3000)
Xtr = np.array(b[0][0:1000, :])
ytr = b[1][0:1000]
Xte = np.array(b[0][1000:, :])
yte = b[1][1000:]
c = GaussianNB()
t = GaussianNB.fit(c, Xtr, ytr)
if k == 0:
plot_boundary(fname="Naive_Bias_Depth_%s.png" % (k),
fitted_estimator=t,
X=Xte,
y=yte)
pr = t.predict(Xte)
cnf += confusion_matrix(yte, pr)
def makeDataset(FIXED_NB_INDEX):
x, y = make_unbalanced_dataset(3000, FIXED_NB[FIXED_NB_INDEX])
trainSample = (x[:1000, :], y[:1000])
testSample = (x[1000:, :], y[1000:])
return (trainSample, testSample)
accuracies.append(np.mean(cross_val_score(knn,x,y,cv=10,n_jobs = -1)))
optiNeighbors, optiAcc = max(enumerate(accuracies), key=operator.itemgetter(1))
optiNeighbors +=1
#Ploting
plt.figure()
plt.plot(nbNeighbor, accuracies,'b')
plt.plot(optiNeighbors, optiAcc,'r.')
plt.xlabel("Number of neighbors")
plt.ylabel("Accuracy")
plt.savefig("1OFCVAccByNeighbors1.svg")
plt.figure()
plt.plot(nbNeighbor[10:], accuracies[10:],'b')
plt.plot(optiNeighbors, optiAcc,'r.')
plt.xlabel("Number of neighbors")
plt.ylabel("Accuracy")
plt.savefig("1OFCVAccByNeighbors2.svg")
return optiNeighbors, optiAcc
def plotq22():
return
if __name__ == "__main__":
x, y = make_unbalanced_dataset(3000, FIXED_NB)
q21(x,y)
optiNeighbors, optiAcc = q22(x,y)
print("The Optimal number of Neighbors, after using the 10 cross fold-validation, is {} with the accuracy of {}".format(optiNeighbors,optiAcc))