利用深度学习解决直播支付风控

   chenzhen$ pip install --upgrade pip

   chenzhen$ pip install keras
...
installing collected packages: numpy, scipy, six, theano, pyyaml, keras
Successfully installed keras-1.2.1 numpy-1.12.0 pyyaml-3.12 scipy-0.18.1 six-1.10.0 theano-0.8.2

   chenzhen$ export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.0.0rc2-py2-none-any.whl
chenzhen$ pip install --upgrade $TF_BINARY_URL
...
Installing collected packages: funcsigs, pbr, mock, wheel, pyparsing, packaging, appdirs, setuptools, protobuf, tensorflow
  Found existing installation: wheel 0.24.0
    Uninstalling wheel-0.24.0:
      Successfully uninstalled wheel-0.24.0
  Found existing installation: setuptools 18.0.1
    Uninstalling setuptools-18.0.1:
      Successfully uninstalled setuptools-18.0.1
Successfully installed appdirs-1.4.0 funcsigs-1.0.2 mock-2.0.0 packaging-16.8 pbr-1.10.0 protobuf-3.2.0 pyparsing-2.1.10 setuptools-34.1.1 tensorflow-1.0.0rc2 wheel-0.29.0

   chenzhen$ python -c "import keras; print keras.__version__"
Using TensorFlow backend.
1.2.1

   chenzhen$ cat ~/.keras/keras.json
{
    "image_dim_ordering": "tf", 
    "epsilon": 1e-07, 
    "floatx": "float32", 
    "backend": "tensorflow"
}

   chenzhen$ pip install h5py
...
Installing collected packages: h5py
Successfully installed h5py-2.6.0

   chenzhen$ pip install scikit-learn
...
Installing collected packages: scikit-learn
Successfully installed scikit-learn-0.18.1

   pip install hyperas

   chenzhen$ cat deep.py 
from keras.models import Sequential
from keras.layers import Dense
import numpy
dataset = numpy.loadtxt("0207.csv", delimiter=",")
X = dataset[:,0:8]
Y = dataset[:,8]
dataset2 = numpy.loadtxt("0208.csv", delimiter=",")
Z = dataset2[:,0:8]
Q = dataset2[:,8]

# 输入8个参数，隐藏层12个神经元，先用relu激活，输出用sigmoid激活
model = Sequential()
model.add(Dense(12, input_dim=8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

# loss用mse 优化用Adamax  准确率衡量
model.compile(loss='mse', optimizer='Adamax', metrics=['accuracy'])

# 训练100次，每次取60行
history = model.fit(X, Y, nb_epoch=100, batch_size=60)

# 测试数据
loss, accuracy = model.evaluate(Z, Q)
print("\nLoss: %.2f, Accuracy: %.2f%%" % (loss, accuracy*100))

# 保存下来训练好的模型供线上使用
# serialize model to JSON
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("model.h5")
print("Saved model to disk")

   chenzhen$ cat run.py 
from keras.models import Sequential
from keras.layers import Dense
from keras.models import model_from_json
import numpy

dataset2 = numpy.loadtxt("0208.csv", delimiter=",")
Z = dataset2[:,0:8]
Q = dataset2[:,8]
# load json and create model
json_file = open('model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
# load weights into new model
loaded_model.load_weights("model.h5")
print("Loaded model from disk")
# test data
loaded_model.compile(loss='mse', optimizer='Adamax', metrics=['accuracy'])
score = loaded_model.evaluate(Z, Q, verbose=0)
print "for test %s: %.2f%%" % (loaded_model.metrics_names[1], score[1]*100)

# prediction probabilities里有预测的结果，需要启动一个简单的server对外服务即可。
probabilities = loaded_model.predict(Z)
predictions = [float(round(x)) for x in probabilities]
accuracy = numpy.mean(predictions == Q)
print("Prediction Accuracy: %.2f%%" % (accuracy*100))

   chenzhen$ python test1.py
Best: 0.696000 using {'nb_epoch': 50, 'batch_size': 10}

   chenzhen$ python test1.py
Best: 0.686000 using {'optimizer': 'Adam'}

   chenzhen$ python test3.py
Best: 0.654000 using {'learn_rate': 0.001, 'momentum': 0.8}

   chenzhen$ python testh.py
Evalutation of best performing model:
192/200 [===========================>..] - ETA: 0s[0.35499999999999998, 0.64500000000000002]