def main(dataset_name):
num_class, num_feature, x_train, y_train, x_test, y_test = readdata.read_dataset(dataset_name)
inverse_cov, weight, w0 = build_LDF_model(num_class, x_train, y_train)
y_pred = LDF_predict(x_test, num_class, inverse_cov, weight, w0)
#pdb.set_trace()
print sklearn.metrics.classification_report(y_test, y_pred)
print 'Average accuracy: ', sklearn.metrics.accuracy_score(y_test, y_pred)
def main(dataset_name):
import readdata
num_class, num_feature, x_train, y_train, x_test, y_test = readdata.read_dataset(
dataset_name)
inverse_cov, weight, w0 = build_LDF_model(num_class, x_train, y_train)
y_pred = LDF_predict(x_test, num_class, inverse_cov, weight, w0)
#pdb.set_trace()
print sklearn.metrics.classification_report(y_test, y_pred)
print 'Average accuracy: ', sklearn.metrics.accuracy_score(y_test, y_pred)
def main(dataset_name):
num_class, num_feature, x_train, y_train, x_test, y_test = readdata.read_dataset(dataset_name)
print 'Number of folds:'
nfold = int(input())
print 'Preparing cv dataset...'
cv_dataset = prepare_cv_dataset(x_train, y_train, nfold)
k = num_feature / 2
bestk = k
bestdelta0 = 0
highest_prec = 0
"""
while 1:
print 'Input delta:'
s = raw_input().strip()
if s == '':
break
delta0 = float(s)
avg_precision = cross_validation(cv_dataset, num_class, k, delta0)
print 'cross valiation: k=%d, delta=%f, avg precision=%f\n' % (k, delta0, avg_precision)
if avg_precision > highest_prec:
highest_prec = avg_precision
bestk = k
bestdelta0 = delta0
print 'Best k and delta0: ', bestk, bestdelta0
print 'Best avg precision: ', highest_prec
k = bestk
delta0 = bestdelta0
"""
prior, mean, eigenvalue, eigenvector, delta = build_MQDF_model(num_class, x_train, y_train, k, 0)
y_pred = MQDF_predict(x_test, num_class, k, mean, eigenvalue, eigenvector, delta)
#pdb.set_trace()
print sklearn.metrics.classification_report(y_test, y_pred)
print 'Average accuracy: ', sklearn.metrics.accuracy_score(y_test, y_pred)
def main(dataset_name):
num_class, num_feature, x_train, y_train, x_test, y_test = \
readdata.read_dataset(dataset_name)
#prepare_cv_dataset(x_train, y_train, 3)
print 'Number of folds:'
nfold = int(input())
print 'Preparing cv dataset...'
cv_dataset = prepare_cv_dataset(x_train, y_train, nfold)
best = [0, 0, 0] # beta, gamma, highest precision
while 1:
print 'Input beta, gamma:'
s = raw_input().strip()
if s == '':
break
beta, gamma = s.split()
beta = float(beta)
gamma = float(gamma)
avg_precision = cross_validation(cv_dataset, num_class, beta, gamma)
print 'cross valiation: beta=%f, gamma=%f, avg precision=%f' % (beta, gamma, avg_precision)
if avg_precision > best[2]:
best[2] = avg_precision
best[0] = beta
best[1] = gamma
print 'Best beta and gamma: ', best[0], best[1]
print 'Best avg precision: ', best[2]
beta = best[0]
gamma = best[1]
prior, mean, cov_matrix = build_RDA_model(num_class, x_train, y_train, beta, gamma)
# predict like QDF
y_pred = QDF_predict(x_test, num_class, prior, mean, cov_matrix)
print sklearn.metrics.classification_report(y_test, y_pred)
print 'Average accuracy: ', sklearn.metrics.accuracy_score(y_test, y_pred)
x = np.matrix(row, np.float64).T
max_posteriori = -float('inf')
prediction = -1
for i in range(num_class):
diff = x - mean[i]
p = 2 * math.log(prior[i]) # we do not ignore priors here
p = p - (diff.T * inverse_cov[i] * diff)[0,0] - log_det_cov[i]
if p > max_posteriori:
max_posteriori = p
prediction = i
predicted_labels.append(prediction)
return predicted_labels
if __name__ == "__main__":
import sys
dataset_name = sys.argv[1]
num_class, num_feature, x_train, y_train, x_test, y_test = readdata.read_dataset(dataset_name)
prior, mean, cov_matrix = build_QDF_model(num_class, x_train, y_train)
#print mean
print_cov_matrix(cov_matrix)
y_pred = QDF_predict(x_test, num_class, prior, mean, cov_matrix)
#print predicted_labels
print sklearn.metrics.classification_report(y_test, y_pred)
print 'Average accuracy: ', sklearn.metrics.accuracy_score(y_test, y_pred)
