Data prepare:将liblinear格式的数据,转化成keras下的向量格式的文件
raw_train_data = open("/mnt/software/train_data")
f = file("train_data","w+")
cnt = 0
for t_data in raw_train_data:
farr = t_data.split(" ")
y = int(farr[0])
cnt = cnt+1
if cnt%10000 == 0:
print ("progress="+str(cnt))
features = [0]*78
if y>0:
f.write(str(1))
else:
f.write(str(0))
f.write(" ")
for i in range(1,10):
kv = farr[i].split(":")
idx_str = kv[0]
val = kv[1]
idx = int(idx_str)
features[idx] = val
for feature in features:
f.write(str(feature))
f.write(" ")
f.write("\n")
file.close()
f.close()
训练代码:
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation
from keras.optimizers import SGD
import numpy as np
model = Sequential()
# Dense(64) is a fully-connected layer with 64 hidden units.
# in the first layer, you must specify the expected input data shape:
# here, 20-dimensional vectors.
model.add(Dense(78, activation='relu', input_dim=78))
model.add(Dropout(0.5))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='binary_crossentropy',
optimizer=sgd,
metrics=['accuracy'])
#x_train = np.random.random((100000, 20))
#y_train = np.random.random((100000, 10))
train_data = np.loadtxt("train_data")
print train_data.shape
y_train = train_data[0:400000,0:1]
x_train = train_data[0:400000,1:79]
model.fit(x_train, y_train,
epochs=20,
batch_size=128)
# score = model.evaluate(x_test, y_test, batch_size=128)
model.save("/root/merge_model")