from nb import NaiveBayes
from sklearn import datasets
from sklearn.model_selection import train_test_split
import numpy as np
def accuracy(pred, label):
acc = np.sum(pred == label) / len(label)
return acc
X, y = datasets.make_classification(n_samples=1000,
n_features=4,
n_classes=2,
random_state=123)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=123)
model = NaiveBayes()
model.fit(X_train, y_train)
predict = model.predict(X_test)
acc = accuracy(predict, y_test)
print(acc)
import numpy as np
import scipy.io as sio
from sklearn.metrics import zero_one_loss
#change this to where
mat_dict = sio.loadmat('XwindowsDocData.mat')
Xtrain = mat_dict['xtrain'].toarray()
Xtest = mat_dict['xtest'].toarray()
ytrain = mat_dict['ytrain'].flatten()
ytest = mat_dict['ytest'].flatten()
nb = NaiveBayes()
pi, theta = nb.fit(Xtrain, ytrain)
ypred_train = nb.predict(Xtrain)
ypred_test = nb.predict(Xtest)
print(ypred_train)
print(ypred_test)
#because the classes are 1,2
ypred_train = 1 + ypred_train.argmax(axis=1)
ypred_test = 1 + ypred_test.argmax(axis=1)
print(ypred_train[-20:])
print(ytrain[-20:])
print(ypred_test[-20:])
print(ytest[-20:])
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import datasets
import matplotlib.pyplot as plt
from nb import NaiveBayes
def accuracy(y_true, y_pred):
accuracy = np.sum(y_true == y_pred) / len(y_true)
return accuracy
X, y = datasets.make_classification(n_samples=1000,
n_features=10,
n_classes=2,
random_state=123)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=123)
nb = NaiveBayes()
nb.fit(X_train, y_train)
predictions = nb.predict(X_test)
# print(type(y_train))
print("Naive Bayes classification accuracy", accuracy(y_test, predictions))