Y = data['gender'].values
trX = X[:-ntest]
teX = X[-ntest:]
trY = Y[:-ntest]
teY = Y[-ntest:]
return trX, teX, trY, teY
trX, teX, trY, teY = load_gender_data(
ntrain=10000) #Can increase up to 250K or so
tokenizer = Tokenizer(min_df=10, max_features=50000)
print trX[1:2] #see a blog example
trX = tokenizer.fit_transform(trX)
teX = tokenizer.transform(teX)
print tokenizer.inverse_transform(trX[1:2]) #see what words are kept
print tokenizer.n_features
layers = [
Embedding(size=128, n_features=tokenizer.n_features),
GatedRecurrent(size=256,
activation='tanh',
gate_activation='steeper_sigmoid',
init='orthogonal',
seq_output=False),
Dense(size=1, activation='sigmoid',
init='orthogonal') #sigmoid for binary classification
]
model = RNN(
layers=layers, cost='bce'
