def main():
tr_data_arr, tr_label_arr = lds.load('./data_set/adult.data')
pred_data_arr, pred_label_arr = lds.load('./data_set/adult.test')
lr_st = time.time()
lr_pred_data_len, lr_wrong, lr_accuracy = lr_predict.predict(
tr_data_arr, tr_label_arr, pred_data_arr, pred_label_arr)
lr_et = time.time()
svm_st = time.time()
svm_pred_data_len, svm_wrong, svm_accuracy = svm_predict.predict(
tr_data_arr, tr_label_arr, pred_data_arr, pred_label_arr)
svm_et = time.time()
ada_st = time.time()
ada_pred_data_len, ada_wrong, ada_accuracy = ada_predict.predict(
tr_data_arr, tr_label_arr, pred_data_arr, pred_label_arr)
ada_et = time.time()
print '测试样本总数：', lr_pred_data_len
print 'LR预测错误数：', lr_wrong
print 'LR预测准确率：%s' % lr_accuracy, '%'
print 'LR训练模型以及预测共耗时：%s秒' % (lr_et - lr_st)
print '---------------------'
print 'SVM预测错误数：', svm_wrong
print 'SVM预测准确率：%s' % svm_accuracy, '%'
print 'SVM训练模型以及预测共耗时：%s秒' % (svm_et - svm_st)
print '---------------------'
print 'AdaBoost预测错误数：', ada_wrong
print 'AdaBoost预测准确率：%s' % ada_accuracy, '%'
print 'AdaBoost训练模型以及预测共耗时：%s秒' % (ada_et - ada_st)
def get_cv_data_file():
"""获取进行交叉验证的训练样本"""
data_arr, label_arr = lds.load('./data_set/adult.data')
with open('cv_data.smp', 'w+') as fp:
for d_idx, data in enumerate(data_arr):
feature_list = []
for f_idx, feature in enumerate(data):
feature_list.append('%s:%s' % (f_idx + 1, feature))
feature_str = ' '.join(feature_list)
fp.write('%s %s\n' % (label_arr[d_idx], feature_str))
def test_adaboost_roc():
"""计算AdaBoost的ROC以及AUC"""
from ada_boost.adaboost import ada_boost_train_ds, plotROC
tr_data_arr, tr_label_arr = lds.load('./data_set/adult.data')
data_arr = np.mat(tr_data_arr)
f_label_arr = []
for i in tr_label_arr:
if i == 1:
f_label_arr.append(i)
else:
f_label_arr.append(-1)
classifier_arr, agg_class_est = ada_boost_train_ds(data_arr, f_label_arr, 30)
plotROC(agg_class_est.T, tr_label_arr)
data_matrix.T * error就是目标函数
每一次迭代得出的weights都会使得目标函数增长
"""
weights += alpha * np.dot(data_matrix.T, error)
return weights
def stoc_grad_ascent(data_matrix, class_labels, num_iter=150):
"""随机梯度上升"""
data_matrix = np.array(data_matrix)
class_labels = np.array(class_labels)
m, n = data_matrix.shape
"""假如weights是作为参数传入的话，即可实现线上学习"""
weights = np.ones(n)
for j in xrange(num_iter):
data_index = range(m)
for i in xrange(m):
alpha = 4 / (1.0 + j + i) + 0.01
rand_index = int(random.uniform(0, len(data_index)))
h = sigmoid(sum(data_matrix[rand_index] * weights))
error = class_labels[rand_index] - h
weights += alpha * error * data_matrix[rand_index]
del(data_index[rand_index])
return weights
if __name__ == '__main__':
data_arr, label_mat = lds.load('./data_set/adult.data')
w = grad_ascent(data_arr, label_mat)
print('weights:', w)
