plt.ylabel('z')
plt.xlim(-4, 4)
plt.ylim(-4, 4)
plt.title('Predictions for {} training samples'.format(x_train.shape[0]))
plt.errorbar(x, mu_pred, yerr=stdevs, barsabove=True, ecolor='maroon', elinewidth=1, linewidth=1, capsize=1, color='firebrick')
plt.scatter(x_train, z_train, label='Training Samples', c='navy', alpha = 0.5)
plt.legend()
ghettotitle = 'predict{}.png'.format(x_train.shape[0])
plt.savefig(ghettotitle)
plt.show()
return
if __name__ == '__main__':
# training data
x_train, z_train = util.get_data_in_file('training.txt')
# new inputs for prediction
x_test = [x for x in np.arange(-4,4.01,0.2)]
# known parameters
sigma2 = 0.1
beta = 1
# number of training samples used to compute posterior
ns = 100
# used samples
x = x_train[0:ns]
z = z_train[0:ns]
# prior distribution p(a)
if lda_male > lda_female:
y_lda[i] = 1
else:
y_lda[i] = 2
mis_lda = 1 - sum(y_lda == y) / len(y)
mis_qda = 1 - sum(y_qda == y) / len(y)
return (mis_lda, mis_qda)
if __name__ == '__main__':
# load training data and testing data
x_train, y_train = util.get_data_in_file('trainHeightWeight.txt')
x_test, y_test = util.get_data_in_file('testHeightWeight.txt')
# parameter estimation and visualization in LDA/QDA
mu_male, mu_female, cov, cov_male, cov_female = discrimAnalysis(
x_train, y_train)
# misclassification rate computation
mis_LDA, mis_QDA = misRate(mu_male, mu_female, cov, cov_male, cov_female,
x_test, y_test)
print(mis_LDA)
print(mis_QDA)
# qda_male = -1/2*np.matmul(np.matmul((XY-mu_male),cov_male_inv),(XY-mu_male).T) \
# + np.log(pi_male) - 1/2*np.log(npl.det(cov_male))
import os.path
import numpy as np
import numpy.linalg as npl
import matplotlib.pyplot as plt
import util
[X, z] = util.get_data_in_file('training.txt')
X = np.append(np.ones((len(X), 1)), X, axis=1)
sigma2 = 0.1
beta = 1
mu_hat = npl.solve((np.matmul(X.T, X) + sigma2 / (beta ^ 2)),
np.matmul(X.T, z))
Cov_mat = npl.inv(np.matmul(X.T, X) + sigma2 / (beta ^ 2)) * sigma2
mu_a = 0
Cov_a = beta * np.eye(2)
a0 = np.arange(-1, 1.1, 0.1)
a1 = np.arange(-1, 1.1, 0.1)
A1, A0 = np.meshgrid(a0, a1)
X_1 = X[0, :]
X_1.shape = (1, 2)
z_1 = z[0, 0]
mu_1 = npl.solve((np.matmul(X_1.T, X_1) + sigma2 / (beta ^ 2)), X_1.T * z_1)
Cov_1 = npl.inv(np.matmul(X_1.T, X_1) + sigma2 / (beta ^ 2)) * sigma2
X_5 = X[0:5, :]
z_5 = z[0:5, 0]
z_5.shape = (5, 1)
mu_5 = npl.solve((np.matmul(X_5.T, X_5) + sigma2 / (beta ^ 2)),
female_qda = np.asarray(female_qda)
print(male_qda)
print(female_qda)
correct_qda = 0
for i in range(0, len(y)):
if (male_qda[i] >= female_qda[i] and y[i] == 1):
correct_qda = correct_qda + 1
elif (male_qda[i] <= female_qda[i] and y[i] == 2):
correct_qda = correct_qda + 1
mis_qda = 1 - correct_qda / len(y)
print(mis_qda)
return (mis_lda, mis_qda)
if __name__ == '__main__':
# load training data and testing data
x_train, y_train = util.get_data_in_file(
'/Users/lijiani/Downloads/ldaqda/trainHeightWeight.txt')
x_test, y_test = util.get_data_in_file(
'/Users/lijiani/Downloads/ldaqda/testHeightWeight.txt')
# parameter estimation and visualization in LDA/QDA
mu_male, mu_female, cov, cov_male, cov_female = discrimAnalysis(
x_train, y_train)
# misclassification rate computation
mis_LDA, mis_QDA = misRate(mu_male, mu_female, cov, cov_male, cov_female,
x_test, y_test)
if (len(x_train) == 1):
plt.title('prediction based on 1 data sample')
plt.savefig("predict1.pdf")
elif (len(x_train) == 5):
plt.title('prediction based on 5 data samples')
plt.savefig("predict5.pdf")
elif (len(x_train) == 100):
plt.title('prediction based on 100 data samples')
plt.savefig("predict100.pdf")
plt.show()
return
if __name__ == '__main__':
# training data
x_train, z_train = util.get_data_in_file(
'/Users/lijiani/Downloads/reg/training.txt')
# new inputs for prediction
x_test = [x for x in np.arange(-4, 4.01, 0.2)]
# known parameters
sigma2 = 0.1
beta = 1
# number of training samples used to compute posterior
ns = 1
# used samples
x = x_train[0:ns]
z = z_train[0:ns]
# prior distribution p(a)
