plt.legend()
plt.show()
if __name__ == '__main__':
params = {"max_iter": 100, "alpha": 0.07}
train_data, train_label, test_data, test_label = load_data2()
################# data1数据集有10类，需要二分。如果想把10个类全部分出来，需要进行多次二分
# train_label = binary(train_label)
# test_label = binary(test_label)
# 增加b部分
train_b = np.ones((train_data.shape[0], 1))
train_data = np.hstack((train_b, train_data))
test_b = np.ones((test_data.shape[0], 1))
test_data = np.hstack((test_b, test_data))
from load_data3 import load_data
train_data, train_label = load_data()
test_data, test_label = load_data(
file_path='./horseColic/horseColicTest.txt')
weight_result, loss = grad_ascent1(train_data, train_label, params,
test_data, test_label)
draw_loss(loss)
#
# for ind in xrange(weight_result.shape[0]):
# print weight_result[ind][0]
# data1 error rate: 0.0263
# data2 error rate: 0.0235294117647
import sys
sys.path.insert(
0, "/common/home/deeplearning/studdocs/gerasimov_d/LAB2/mxnet-cuda")
import mxnet as mx
from mxnet import gluon, autograd, ndarray
import numpy as np
import time
start_time = time.time()
from load_data3 import load_data
all_data, train_data, test_data = load_data()
elapsed_time = time.time() - start_time
print 'Time load data: ', elapsed_time
start_time = time.time()
model_ctx = mx.gpu(0)
shape_input = train_data[0][0].shape
size_inputs = train_data[0][0].size
num_outputs = train_data[0][1].size
num_hidden = train_data[0][1].size
from autoencoder_conf import prepare_autoencoder3
encoder, loss_encoder, decoder, loss_decoder = prepare_autoencoder3(
num_hidden, num_outputs, model_ctx)
elapsed_time = time.time() - start_time
print 'Time of initializing data: ', elapsed_time
num_epochs = 15
import load_data3
import load_data
(x_train1, y_train1), (x_test1, y_test1) = load_data.load_data(0.7,10)
(x_train3, y_train3), (x_test3, y_test3) = load_data3.load_data(0.3,10)
print(len(x_train1))
print(len(x_train3))
for i in range(0,len(x_train1)):
if(x_train1[i]==x_train3[i]):
print(0)
else:
print(0000000000000)