def real_time_prediction():
### loading new images for classification starts here
fo = open(save_path, 'rb') # batch path
batch1 = pickle.load(fo)
fo.close()
xarr = np.array(batch1['data'], dtype='float32')
xarr = global_contrast_normalize(xarr, scale=55.)
no_of_row = len(batch1['data'])
xdat = np.array(
xarr.reshape((no_of_row, 3, 32, 32)),
dtype='float32') #reshape first parameter = batch matrix no. of row
xdat = np.transpose(xdat[:, :, :, :], (1, 2, 3, 0))
x = dense_design_matrix.DenseDesignMatrix(topo_view=xdat,
axes=['c', 0, 1, 'b'])
x.apply_preprocessor(my_pca_preprocessor, can_fit=False)
tarr = x.get_topological_view()
#print tarr
y = f(tarr)
###########searching max in matrix##################################################
#j = no. of row in prediction_batch
#i = no. of classes (0-9)
#result=('airplane','automobile','bird','cat','deer','dog','frog','horse','ship','truck')
result = ('bottle', 'book', 'toy', 'pen', 'chair', 'coin', 'phone', 'hand',
'note', 'head')
resultString = ''
for j in range(0, no_of_row):
max_index = 0
max_no = y[j][0]
#print max_no
for i in range(0, 10):
if y[j][i] > max_no:
max_no = y[j][i]
max_index = i
# print max_index
print "======================"
print 'Photo', j + 1, ' max=', result[max_index]
if j > 0:
resultString += ','
resultString += result[max_index]
#print 'y =', y
###################################################################################3
return resultString
def extract_features(self, dset, preproc=None, can_fit=False):
new_dset = dense_design_matrix.DenseDesignMatrix()
if str(self.model.__class__).find('DBM') != -1:
self.model.set_batch_size(len(dset.X))
self.model.setup_pos_func(dset.X)
self.model.pos_func()
new_dset.X = self.model.fn(dset.X)
elif self.model:
outsize = self.model.fn(dset.X[:1]).shape[1]
X = numpy.zeros((len(dset.X), outsize))
for i in xrange(0, len(X), self.model.batch_size):
batch = dset.X[i : i + self.model.batch_size]
X[i : i + len(batch)] = self.model.fn(batch)
new_dset.X = X
else:
new_dset.X = dset.X
if preproc:
preproc.apply(new_dset, can_fit=True)
return new_dset
def main():
base_name = sys.argv[1] #文件名前缀
n_epoch = int(sys.argv[2]) # epoch次数
n_hidden = int(sys.argv[3]) # 隐含层节点数
include_rate = float(sys.argv[4]) # 包含率（1-dropout）
in_size = 943 # 输入层节点数目
out_size = 4760 #输出层节点数
b_size = 200 #batch的大小
l_rate = 5e-4 #学习速率
l_rate_min = 1e-5 #学习速率最小值
decay_factor = 0.9 #
lr_scale = 3.0 #
momentum = 0.5 #摄动因子
init_vals = np.sqrt(6.0/(np.array([in_size, n_hidden])+np.array([n_hidden, out_size])))
print 'loading data...'
#读取数据Train,Validation,Test
X_tr = np.load('bgedv2_X_tr_float64.npy')
Y_tr = np.load('bgedv2_Y_tr_0-4760_float64.npy')
Y_tr_target = np.array(Y_tr)
X_va = np.load('bgedv2_X_va_float64.npy')
Y_va = np.load('bgedv2_Y_va_0-4760_float64.npy')
Y_va_target = np.array(Y_va)
X_te = np.load('bgedv2_X_te_float64.npy')
Y_te = np.load('bgedv2_Y_te_0-4760_float64.npy')
Y_te_target = np.array(Y_te)
X_1000G = np.load('1000G_X_float64.npy')
Y_1000G = np.load('1000G_Y_0-4760_float64.npy')
Y_1000G_target = np.array(Y_1000G)
X_GTEx = np.load('GTEx_X_float64.npy')
Y_GTEx = np.load('GTEx_Y_0-4760_float64.npy')
Y_GTEx_target = np.array(Y_GTEx)
#随机化
random.seed(0)
#随机抽取5000样本进行训练
monitor_idx_tr = random.sample(range(88807), 5000)
#将数据X,Y整合成DensenMatrix类型
data_tr = p2_dt_dd.DenseDesignMatrix(X=X_tr.astype('float32'), y=Y_tr.astype('float32'))
#取出X中对应5000样本进行训练
X_tr_monitor, Y_tr_monitor_target = X_tr[monitor_idx_tr, :], Y_tr_target[monitor_idx_tr, :]
#设置多层感知机的隐含层计算方式
h1_layer = p2_md_mlp.Tanh(layer_name='h1', dim=n_hidden, irange=init_vals[0], W_lr_scale=1.0, b_lr_scale=1.0)
#设置多层感知机的输出层计算方式
o_layer = p2_md_mlp.Linear(layer_name='y', dim=out_size, irange=0.0001, W_lr_scale=lr_scale, b_lr_scale=1.0)
#设置好模型
model = p2_md_mlp.MLP(nvis=in_size, layers=[h1_layer, o_layer], seed=1)
#设置dropout比例
dropout_cost = p2_ct_mlp_dropout.Dropout(input_include_probs={'h1':1.0, 'y':include_rate},
input_scales={'h1':1.0,
'y':np.float32(1.0/include_rate)})
#设置训练算法（batch大小，学习速率，学习规则，终止条件，dropout比例）
algorithm = p2_alg_sgd.SGD(batch_size=b_size, learning_rate=l_rate,
learning_rule = p2_alg_lr.Momentum(momentum),
termination_criterion=p2_termcri.EpochCounter(max_epochs=1000),
cost=dropout_cost)
#设置训练类（数据集，训练模型，训练算法）
train = pylearn2.train.Train(dataset=data_tr, model=model, algorithm=algorithm)
train.setup()
x = T.matrix()
y = model.fprop(x) #训练好的模型对X的预测值
f = theano.function([x], y)
MAE_va_old = 10.0
MAE_va_best = 10.0
MAE_tr_old = 10.0
MAE_te_old = 10.0
MAE_1000G_old = 10.0
MAE_1000G_best = 10.0
MAE_GTEx_old = 10.0
outlog = open(base_name + '.log', 'w')
log_str = '\t'.join(map(str, ['epoch', 'MAE_va', 'MAE_va_change', 'MAE_te', 'MAE_te_change',
'MAE_1000G', 'MAE_1000G_change', 'MAE_GTEx', 'MAE_GTEx_change',
'MAE_tr', 'MAE_tr_change', 'learing_rate', 'time(sec)']))
print log_str
outlog.write(log_str + '\n')
sys.stdout.flush() #刷新缓冲区
for epoch in range(0, n_epoch):
t_old = time.time() #开始时间
train.algorithm.train(train.dataset)#训练
#计算不同数据集预测值
Y_va_hat = f(X_va.astype('float32')).astype('float64')
Y_te_hat = f(X_te.astype('float32')).astype('float64')
Y_tr_hat_monitor = f(X_tr_monitor.astype('float32')).astype('float64')
Y_1000G_hat = f(X_1000G.astype('float32')).astype('float64')
Y_GTEx_hat = f(X_GTEx.astype('float32')).astype('float64')
#计算预测值与真实值的MAE
MAE_va = np.abs(Y_va_target - Y_va_hat).mean()
MAE_te = np.abs(Y_te_target - Y_te_hat).mean()
MAE_tr = np.abs(Y_tr_monitor_target - Y_tr_hat_monitor).mean()
MAE_1000G = np.abs(Y_1000G_target - Y_1000G_hat).mean()
MAE_GTEx = np.abs(Y_GTEx_target - Y_GTEx_hat).mean()
#计算迭代误差
MAE_va_change = (MAE_va - MAE_va_old)/MAE_va_old
MAE_te_change = (MAE_te - MAE_te_old)/MAE_te_old
MAE_tr_change = (MAE_tr - MAE_tr_old)/MAE_tr_old
MAE_1000G_change = (MAE_1000G - MAE_1000G_old)/MAE_1000G_old
MAE_GTEx_change = (MAE_GTEx - MAE_GTEx_old)/MAE_GTEx_old
#更新MAE
MAE_va_old = MAE_va
MAE_te_old = MAE_te
MAE_tr_old = MAE_tr
MAE_1000G_old = MAE_1000G
MAE_GTEx_old = MAE_GTEx
t_new = time.time() #终止时间
l_rate = train.algorithm.learning_rate.get_value()
log_str = '\t'.join(map(str, [epoch+1, '%.6f'%MAE_va, '%.6f'%MAE_va_change, '%.6f'%MAE_te, '%.6f'%MAE_te_change,
'%.6f'%MAE_1000G, '%.6f'%MAE_1000G_change, '%.6f'%MAE_GTEx, '%.6f'%MAE_GTEx_change,
'%.6f'%MAE_tr, '%.6f'%MAE_tr_change, '%.5f'%l_rate, int(t_new-t_old)]))
print log_str
outlog.write(log_str + '\n')
sys.stdout.flush()
if MAE_tr_change > 0: #如果误差增大，减小学习速率
l_rate = l_rate*decay_factor
if l_rate < l_rate_min: #学习速率最小为l_rate_min
l_rate = l_rate_min
train.algorithm.learning_rate.set_value(np.float32(l_rate)) #更改训练类的学习速率参数
#更新Validation误差值
if MAE_va < MAE_va_best:
MAE_va_best = MAE_va
outmodel = open(base_name + '_bestva_model.pkl', 'wb')
pkl.dump(model, outmodel)
outmodel.close()
np.save(base_name + '_bestva_Y_te_hat.npy', Y_te_hat)
np.save(base_name + '_bestva_Y_va_hat.npy', Y_va_hat)
#更新1000G误差值
if MAE_1000G < MAE_1000G_best:
MAE_1000G_best = MAE_1000G
outmodel = open(base_name + '_best1000G_model.pkl', 'wb')
pkl.dump(model, outmodel)
outmodel.close()
np.save(base_name + '_best1000G_Y_1000G_hat.npy', Y_1000G_hat)
np.save(base_name + '_best1000G_Y_GTEx_hat.npy', Y_GTEx_hat)
print 'MAE_va_best : %.6f' % (MAE_va_best)
print 'MAE_1000G_best : %.6f' % (MAE_1000G_best)
outlog.write('MAE_va_best : %.6f' % (MAE_va_best) + '\n')
outlog.write('MAE_1000G_best : %.6f' % (MAE_1000G_best) + '\n')
outlog.close()
def main():
base_name = sys.argv[
1] # 获取第一个参数 sys.argv[ ]记录（获取）命令行参数 sys(system) argv(argument variable)参数变量，该变量为list列表
n_epoch = int(sys.argv[2]) #获取第二个参数
n_hidden = int(sys.argv[3]) #获取第三个参数作为隐层神经元个数
include_rate = float(sys.argv[4])
in_size = 1001 #输入层神经元个数（标记基因个数）
out_size = 1 #输出层神经元个数
b_size = 200 #偏差值
l_rate = 5e-4 #学习速率
l_rate_min = 1e-5 #学习速率最小值
decay_factor = 0.9 #衰减因数
lr_scale = 3.0
momentum = 0.5
init_vals = np.sqrt(6.0 / (np.array([in_size, n_hidden]) +
np.array([n_hidden, out_size]))) #初始值，返回平方根
print 'loading data...' #显示载入数据
X_tr = np.load(
'geno_X_tr_float64.npy') # tr(traing)以numpy专用二进制类型保存训练数据集的数据
Y_tr = np.load('pheno_Y_tr_0-4760_float64.npy')
Y_tr_pheno = np.array(Y_tr)
X_va = np.load(
'geno_X_va_float64.npy') #验证集（模型选择，在学习到不同复杂度的模型中，选择对验证集有最小预测误差的模型）
Y_va = np.load('pheno_Y_va_0-4760_float64.npy')
Y_va_target = np.array(Y_va)
X_te = np.load('geno_te_float64.npy') #测试集（对学习方法的评估）
Y_te = np.load('pheno_Y_te_0-4760_float64.npy')
Y_te_target = np.array(Y_te)
random.seed(0) #设置生成随机数用的整数起始值。调用任何其他random模块函数之前调用这个函数
monitor_idx_tr = random.sample(range(88807), 5000) #监测训练
#将训练数据集类型设为32位浮点型，The DenseDesignMatrix class and related code Functionality for representing data that can be described as a dense matrix (rather than a sparse matrix) with each row containing an example and each column corresponding to a different feature.
data_tr = p2_dt_dd.DenseDesignMatrix(X=X_tr.astype('float32'),
y=Y_tr.astype('float32'))
X_tr_monitor, Y_tr_monitor_target = X_tr[monitor_idx_tr, :], Y_tr_target[
monitor_idx_tr, :]
#一个隐层，用Tanh（）作激活函数; 输出层用线性函数作激活函数
h1_layer = p2_md_mlp.Tanh(layer_name='h1',
dim=n_hidden,
irange=init_vals[0],
W_lr_scale=1.0,
b_lr_scale=1.0)
o_layer = p2_md_mlp.Linear(layer_name='y',
dim=out_size,
irange=0.0001,
W_lr_scale=lr_scale,
b_lr_scale=1.0)
#Multilayer Perceptron；nvis(Number of “visible units” input units) layers(a list of layer objects，最后1层指定MLP的输出空间)
model = p2_md_mlp.MLP(nvis=in_size, layers=[h1_layer, o_layer], seed=1)
dropout_cost = p2_ct_mlp_dropout.Dropout(input_include_probs={
'h1': 1.0,
'y': include_rate
},
input_scales={
'h1':
1.0,
'y':
np.float32(1.0 / include_rate)
})
#随机梯度下降法
algorithm = p2_alg_sgd.SGD(
batch_size=b_size,
learning_rate=l_rate,
learning_rule=p2_alg_lr.Momentum(momentum),
termination_criterion=p2_termcri.EpochCounter(max_epochs=1000),
cost=dropout_cost)
#训练 根据前面的定义 ：dataset为一个密集型矩阵，model为MLP多层神经网络，algorithm为SGD
train = pylearn2.train.Train(dataset=data_tr,
model=model,
algorithm=algorithm)
train.setup()
x = T.matrix() #定义为一个二维数组
#fprop(state_below) does the forward prop transformation
y = model.fprop(x)
f = theano.function([x], y) #定义一个function函数，输入为x,输出为y
MAE_va_old = 10.0 #平均绝对误差
MAE_va_best = 10.0
MAE_tr_old = 10.0 #训练误差
MAE_te_old = 10.0
MAE_1000G_old = 10.0
MAE_1000G_best = 10.0
MAE_GTEx_old = 10.0
#base_name = sys.argv[1] # 获取第一个参数 sys.argv[ ]记录（获取）命令行参数
outlog = open(base_name + '.log', 'w')
log_str = '\t'.join(
map(str, [
'epoch', 'MAE_va', 'MAE_va_change', 'MAE_te', 'MAE_te_change',
'MAE_tr', 'MAE_tr_change', 'learing_rate', 'time(sec)'
]))
print log_str #输出运行日志
outlog.write(log_str + '\n')
#Python的标准输出缓冲（这意味着它收集“写入”标准出来之前，将其写入到终端的数据）。调用sys.stdout.flush()强制其“缓冲
sys.stdout.flush()
for epoch in range(0, n_epoch):
t_old = time.time()
train.algorithm.train(train.dataset)
Y_va_hat = f(X_va.astype('float32')).astype('float64')
Y_te_hat = f(X_te.astype('float32')).astype('float64')
Y_tr_hat_monitor = f(X_tr_monitor.astype('float32')).astype('float64')
#计算平均绝对误差
MAE_va = np.abs(Y_va_target - Y_va_hat).mean()
MAE_te = np.abs(Y_te_target - Y_te_hat).mean()
MAE_tr = np.abs(Y_tr_monitor_target - Y_tr_hat_monitor).mean()
#误差变换率
MAE_va_change = (MAE_va - MAE_va_old) / MAE_va_old
MAE_te_change = (MAE_te - MAE_te_old) / MAE_te_old
MAE_tr_change = (MAE_tr - MAE_tr_old) / MAE_tr_old
#将old误差值更新为当前误差值
MAE_va_old = MAE_va
MAE_te_old = MAE_te
MAE_tr_old = MAE_tr
#返回当前的时间戳（1970纪元后经过的浮点秒数）
t_new = time.time()
l_rate = train.algorithm.learning_rate.get_value()
log_str = '\t'.join(
map(str, [
epoch + 1,
'%.6f' % MAE_va,
'%.6f' % MAE_va_change,
'%.6f' % MAE_te,
'%.6f' % MAE_te_change,
'%.6f' % MAE_tr,
'%.6f' % MAE_tr_change,
'%.5f' % l_rate,
int(t_new - t_old)
]))
print log_str
outlog.write(log_str + '\n')
sys.stdout.flush()
if MAE_tr_change > 0: #训练误差变换率大于0时，学习速率乘上一个衰减因子
l_rate = l_rate * decay_factor
if l_rate < l_rate_min: #学习速率小于最小速率时，更新为最小速率
l_rate = l_rate_min
train.algorithm.learning_rate.set_value(np.float32(l_rate))
if MAE_va < MAE_va_best:
MAE_va_best = MAE_va
outmodel = open(base_name + '_bestva_model.pkl', 'wb')
pkl.dump(model, outmodel)
outmodel.close()
np.save(base_name + '_bestva_Y_te_hat.npy', Y_te_hat)
np.save(base_name + '_bestva_Y_va_hat.npy', Y_va_hat)
print 'MAE_va_best : %.6f' % (MAE_va_best)
outlog.write('MAE_va_best : %.6f' % (MAE_va_best) + '\n')
outlog.close()
def main():
base_name = sys.argv[1]
n_epoch = int(sys.argv[2])
n_hidden = int(sys.argv[3])
include_rate = float(sys.argv[4])
in_size = 943
out_size = 4760
b_size = 200
l_rate = 3e-4
l_rate_min = 1e-5
decay_factor = 0.9
lr_scale = 3.0
momentum = 0.5
init_vals = np.sqrt(6.0/(np.array([in_size, n_hidden, n_hidden, n_hidden])+np.array([n_hidden, n_hidden, n_hidden, out_size])))
print 'loading data...'
X_tr = np.load('bgedv2_X_tr_float64.npy')
Y_tr = np.load('bgedv2_Y_tr_4760-9520_float64.npy')
Y_tr_target = np.array(Y_tr)
X_va = np.load('bgedv2_X_va_float64.npy')
Y_va = np.load('bgedv2_Y_va_4760-9520_float64.npy')
Y_va_target = np.array(Y_va)
X_te = np.load('bgedv2_X_te_float64.npy')
Y_te = np.load('bgedv2_Y_te_4760-9520_float64.npy')
Y_te_target = np.array(Y_te)
X_1000G = np.load('1000G_X_float64.npy')
Y_1000G = np.load('1000G_Y_4760-9520_float64.npy')
Y_1000G_target = np.array(Y_1000G)
X_GTEx = np.load('GTEx_X_float64.npy')
Y_GTEx = np.load('GTEx_Y_4760-9520_float64.npy')
Y_GTEx_target = np.array(Y_GTEx)
random.seed(0)
monitor_idx_tr = random.sample(range(88807), 5000)
data_tr = p2_dt_dd.DenseDesignMatrix(X=X_tr.astype('float32'), y=Y_tr.astype('float32'))
X_tr_monitor, Y_tr_monitor_target = X_tr[monitor_idx_tr, :], Y_tr_target[monitor_idx_tr, :]
h1_layer = p2_md_mlp.Tanh(layer_name='h1', dim=n_hidden, irange=init_vals[0], W_lr_scale=1.0, b_lr_scale=1.0)
h2_layer = p2_md_mlp.Tanh(layer_name='h2', dim=n_hidden, irange=init_vals[1], W_lr_scale=lr_scale, b_lr_scale=1.0)
h3_layer = p2_md_mlp.Tanh(layer_name='h3', dim=n_hidden, irange=init_vals[2], W_lr_scale=lr_scale, b_lr_scale=1.0)
o_layer = p2_md_mlp.Linear(layer_name='y', dim=out_size, irange=0.0001, W_lr_scale=lr_scale, b_lr_scale=1.0)
model = p2_md_mlp.MLP(nvis=in_size, layers=[h1_layer, h2_layer, h3_layer, o_layer], seed=1)
dropout_cost = p2_ct_mlp_dropout.Dropout(input_include_probs={'h1':1.0, 'h2':include_rate, 'h3':include_rate,
'y':include_rate},
input_scales={'h1':1.0, 'h2':np.float32(1.0/include_rate),
'h3':np.float32(1.0/include_rate),
'y':np.float32(1.0/include_rate)})
algorithm = p2_alg_sgd.SGD(batch_size=b_size, learning_rate=l_rate,
learning_rule = p2_alg_lr.Momentum(momentum),
termination_criterion=p2_termcri.EpochCounter(max_epochs=1000),
cost=dropout_cost)
train = pylearn2.train.Train(dataset=data_tr, model=model, algorithm=algorithm)
train.setup()
x = T.matrix()
y = model.fprop(x)
f = theano.function([x], y)
MAE_va_old = 10.0
MAE_va_best = 10.0
MAE_tr_old = 10.0
MAE_te_old = 10.0
MAE_1000G_old = 10.0
MAE_1000G_best = 10.0
MAE_GTEx_old = 10.0
outlog = open(base_name + '.log', 'w')
log_str = '\t'.join(map(str, ['epoch', 'MAE_va', 'MAE_va_change', 'MAE_te', 'MAE_te_change',
'MAE_1000G', 'MAE_1000G_change', 'MAE_GTEx', 'MAE_GTEx_change',
'MAE_tr', 'MAE_tr_change', 'learing_rate', 'time(sec)']))
print log_str
outlog.write(log_str + '\n')
sys.stdout.flush()
for epoch in range(0, n_epoch):
t_old = time.time()
train.algorithm.train(train.dataset)
Y_va_hat = f(X_va.astype('float32')).astype('float64')
Y_te_hat = f(X_te.astype('float32')).astype('float64')
Y_tr_hat_monitor = f(X_tr_monitor.astype('float32')).astype('float64')
Y_1000G_hat = f(X_1000G.astype('float32')).astype('float64')
Y_GTEx_hat = f(X_GTEx.astype('float32')).astype('float64')
MAE_va = np.abs(Y_va_target - Y_va_hat).mean()
MAE_te = np.abs(Y_te_target - Y_te_hat).mean()
MAE_tr = np.abs(Y_tr_monitor_target - Y_tr_hat_monitor).mean()
MAE_1000G = np.abs(Y_1000G_target - Y_1000G_hat).mean()
MAE_GTEx = np.abs(Y_GTEx_target - Y_GTEx_hat).mean()
MAE_va_change = (MAE_va - MAE_va_old)/MAE_va_old
MAE_te_change = (MAE_te - MAE_te_old)/MAE_te_old
MAE_tr_change = (MAE_tr - MAE_tr_old)/MAE_tr_old
MAE_1000G_change = (MAE_1000G - MAE_1000G_old)/MAE_1000G_old
MAE_GTEx_change = (MAE_GTEx - MAE_GTEx_old)/MAE_GTEx_old
MAE_va_old = MAE_va
MAE_te_old = MAE_te
MAE_tr_old = MAE_tr
MAE_1000G_old = MAE_1000G
MAE_GTEx_old = MAE_GTEx
t_new = time.time()
l_rate = train.algorithm.learning_rate.get_value()
log_str = '\t'.join(map(str, [epoch+1, '%.6f'%MAE_va, '%.6f'%MAE_va_change, '%.6f'%MAE_te, '%.6f'%MAE_te_change,
'%.6f'%MAE_1000G, '%.6f'%MAE_1000G_change, '%.6f'%MAE_GTEx, '%.6f'%MAE_GTEx_change,
'%.6f'%MAE_tr, '%.6f'%MAE_tr_change, '%.5f'%l_rate, int(t_new-t_old)]))
print log_str
outlog.write(log_str + '\n')
sys.stdout.flush()
if MAE_tr_change > 0:
l_rate = l_rate*decay_factor
if l_rate < l_rate_min:
l_rate = l_rate_min
train.algorithm.learning_rate.set_value(np.float32(l_rate))
if MAE_va < MAE_va_best:
MAE_va_best = MAE_va
outmodel = open(base_name + '_bestva_model.pkl', 'wb')
pkl.dump(model, outmodel)
outmodel.close()
np.save(base_name + '_bestva_Y_te_hat.npy', Y_te_hat)
np.save(base_name + '_bestva_Y_va_hat.npy', Y_va_hat)
if MAE_1000G < MAE_1000G_best:
MAE_1000G_best = MAE_1000G
outmodel = open(base_name + '_best1000G_model.pkl', 'wb')
pkl.dump(model, outmodel)
outmodel.close()
np.save(base_name + '_best1000G_Y_1000G_hat.npy', Y_1000G_hat)
np.save(base_name + '_best1000G_Y_GTEx_hat.npy', Y_GTEx_hat)
print 'MAE_va_best : %.6f' % (MAE_va_best)
print 'MAE_1000G_best : %.6f' % (MAE_1000G_best)
outlog.write('MAE_va_best : %.6f' % (MAE_va_best) + '\n')
outlog.write('MAE_1000G_best : %.6f' % (MAE_1000G_best) + '\n')
outlog.close()
X_tr = np.load('geno_X_tr.npy') # tr(traing)以numpy专用二进制类型保存训练数据集的数据
Y_tr = np.load('pheno_Y_tr.npy')
Y_tr_pheno = np.array(Y_tr)
X_va = np.load('geno_X_va.npy') #验证集（模型选择，在学习到不同复杂度的模型中，选择对验证集有最小预测误差的模型）
Y_va = np.load('pheno_Y_va.npy')
Y_va_target = np.array(Y_va)
X_te = np.load('geno_X_te.npy') #测试集（对学习方法的评估）
Y_te = np.load('pheno_Y_te.npy')
Y_te_target = np.array(Y_te)
random.seed(0) #设置生成随机数用的整数起始值。调用任何其他random模块函数之前调用这个函数
monitor_idx_tr = random.sample(range(88807), 5000) #监测训练
#将训练数据集类型设为32位浮点型，The DenseDesignMatrix class and related code Functionality for representing data that can be described as a dense matrix (rather than a sparse matrix) with each row containing an example and each column corresponding to a different feature.
data_tr = p2_dt_dd.DenseDesignMatrix(X=X_tr.astype('float32'), y=Y_tr.astype('float32'))
X_tr_monitor, Y_tr_monitor_target = X_tr[monitor_idx_tr, :], Y_tr_target[monitor_idx_tr, :]
#一个隐层，用Tanh（）作激活函数; 输出层用线性函数作激活函数
h1_layer = p2_md_mlp.Tanh(layer_name='h1', dim=n_hidden, irange=init_vals[0], W_lr_scale=1.0, b_lr_scale=1.0)
o_layer = p2_md_mlp.Linear(layer_name='y', dim=out_size, irange=0.0001, W_lr_scale=lr_scale, b_lr_scale=1.0)
#Multilayer Perceptron；nvis(Number of “visible units” input units) layers(a list of layer objects，最后1层指定MLP的输出空间)
model = p2_md_mlp.MLP(nvis=in_size, layers=[h1_layer, o_layer], seed=1)
dropout_cost = p2_ct_mlp_dropout.Dropout(input_include_probs={'h1':1.0, 'y':include_rate},
input_scales={'h1':1.0,
'y':np.float32(1.0/include_rate)})
#随机梯度下降法
algorithm = p2_alg_sgd.SGD(batch_size=b_size, learning_rate=l_rate,
learning_rule = p2_alg_lr.Momentum(momentum),
termination_criterion=p2_termcri.EpochCounter(max_epochs=1000),
cost=dropout_cost)
#训练 根据前面的定义 ：dataset为一个密集型矩阵，model为MLP多层神经网络，algorithm为SGD
def generate(opc):
"""
Summary (Generates a dataset with the chosen transformation).
Parameters
----------
opc: string
Only two options, shifts or rotations.
"""
dim = 19 # outer square
# A bigger image is used to avoid empty pixels in the
# borders.
reg = 13 # inner square
total = 20000 # Number of training examples
im1 = numpy.zeros((total, reg, reg, 1), dtype='float32')
im2 = numpy.zeros((total, reg, reg, 1), dtype='float32')
Y = numpy.zeros((total, 1), dtype='uint8')
rng = make_np_rng(9001, [1, 2, 3], which_method="uniform")
transformation = opc
if transformation == 'shifts':
# Shifts
# only shifts between [-3, +3] pixels
shifts = list(itertools.product(range(-3, 4), range(-3, 4)))
t = 0
while t < total:
x = rng.uniform(0, 1, (dim, dim))
x = numpy.ceil(x * 255)
im_x = x[3:16, 3:16][:, :, None]
ind = rng.randint(0, len(shifts))
Y[t] = ind
txy = shifts[ind]
tx, ty = txy
im_y = x[(3 + tx):(16 + tx), (3 + ty):(16 + ty)][:, :, None]
im1[t, :] = im_x
im2[t, :] = im_y
t += 1
else:
assert transformation == 'rotations'
# Rotations
import Image
# import cv2
angs = numpy.linspace(0, 359, 90)
t = 0
while t < total:
x = rng.uniform(0, 1, (dim, dim))
x = numpy.ceil(x * 255)
im_x = x[3:16, 3:16][:, :, None]
ind = rng.randint(0, len(angs))
Y[t] = ind
ang = angs[ind]
y = numpy.asarray(Image.fromarray(x).rotate(ang))
# scale = 1
# M1 = cv2.getRotationMatrix2D((dim/2, dim/2), ang, scale)
# y = cv2.warpAffine(x, M1, (dim, dim))
im_y = y[3:16, 3:16][:, :, None]
im1[t, :] = im_x
im2[t, :] = im_y
t += 1
view_converter = dense_design_matrix.DefaultViewConverter((reg, reg, 1))
design_X = view_converter.topo_view_to_design_mat(im1)
design_Y = view_converter.topo_view_to_design_mat(im2)
# Normalize data:
pipeline = preprocessing.Pipeline()
gcn = preprocessing.GlobalContrastNormalization(sqrt_bias=10.,
use_std=True)
pipeline.items.append(gcn)
XY = numpy.concatenate((design_X, design_Y), 0)
XY_ImP = dense_design_matrix.DenseDesignMatrix(X=XY)
XY_ImP.apply_preprocessor(preprocessor=pipeline, can_fit=True)
X1 = XY_ImP.X[0:design_X.shape[0], :]
X2 = XY_ImP.X[design_X.shape[0]:, :]
# As a Conv2DSpace
topo_X1 = view_converter.design_mat_to_topo_view(X1)
topo_X2 = view_converter.design_mat_to_topo_view(X2)
axes = ('b', 0, 1, 'c')
data_specs = (CompositeSpace([
Conv2DSpace((reg, reg), num_channels=1, axes=axes),
Conv2DSpace((reg, reg), num_channels=1, axes=axes),
VectorSpace(1)
]), ('featuresX', 'featuresY', 'targets'))
train = VectorSpacesDataset((topo_X1, topo_X2, Y), data_specs=data_specs)
# As a VectorSpace
# data_specs = (CompositeSpace(
# [VectorSpace(reg * reg),
# VectorSpace(reg * reg),
# VectorSpace(1)]),
# ('featuresX', 'featuresY', 'targets'))
# train = VectorSpacesDataset(data=(X1, X2, Y), data_specs=data_specs)
import os
save_path = os.path.dirname(os.path.realpath(__file__))
serial.save(os.path.join(save_path, 'train_preprocessed.pkl'), train)
