def TrainEM(train_scores,train_vad_ts,train_features_ts):
# prepare data for training
[input_matrix,target_matrix] = PrepareData(train_vad_ts,train_features_ts)
n_in = input_matrix.shape[2]
n_out = target_matrix.shape[2]
n_hidden = 10
not_converged = True
while not_converged:
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,\
learning_rate=0.001, learning_rate_decay=0.999,\
n_epochs=400, activation='tanh')
model.fit(input_matrix, target_matrix, validation_frequency=1000)
n_hidden = 5 # M
n_in = 3 # D
n_out = 1 # K
n_steps = 1 # the length of each sequence
n_seq = len(food_sel_scaled_train) # the number of datapoints (i.e. sequences)
#Creating input and output arrays for training RNN
rating = np.array(food_sel_scaled_train[['rating','price.tier','stats.checkinsCount']]).reshape(n_seq,n_steps,n_in)
score = np.array(food_sel_scaled_train['SCORE']).reshape(n_seq,n_steps,n_out)
#Creating the model and feeding it with training data set
model = MetaRNN(n_in=n_in, n_hidden=n_hidden, n_out=n_out,
learning_rate=0.001, learning_rate_decay=0.999,
n_epochs=50, activation='tanh')
model.fit(rating, score, validation_frequency=5000)
guess = model.predict(rating.reshape(len(rating), n_in))
scores_pred = pd.DataFrame(guess)
scores_pred.columns = ['predictions']
scores_pred.predictions.plot(kind='hist', bins=20, figsize=(6,4), grid=True, title = "Histogram of predicted DOH normalized Scores (IS)", alpha=0.8)
food_sel_scaled_train.SCORE.plot(kind='hist', bins=20, figsize=(6,4), grid=True, title = "Histogram of actual DOH normalized Scores (IS)", alpha=0.8)
#Creating parameters for training RNN
n_hidden = 5 # M
n_in = 3 # D
n_out = 1 # K
n_steps = 1 # the length of each sequence
#Creating input and output arrays for training RNN
rating = np.array(food_sel_scaled_train[[
'rating', 'price.tier', 'stats.checkinsCount'
]]).reshape(n_seq, n_steps, n_in)
score = np.array(food_sel_scaled_train['SCORE']).reshape(n_seq, n_steps, n_out)
#Creating the model and feeding it with training data set
model = MetaRNN(n_in=n_in,
n_hidden=n_hidden,
n_out=n_out,
learning_rate=0.001,
learning_rate_decay=0.999,
n_epochs=50,
activation='tanh')
model.fit(rating, score, validation_frequency=5000)
guess = model.predict(rating.reshape(len(rating), n_in))
scores_pred = pd.DataFrame(guess)
scores_pred.columns = ['predictions']
scores_pred.predictions.plot(
kind='hist',
bins=20,
figsize=(6, 4),
grid=True,
title="Histogram of predicted DOH normalized Scores (IS)",
alpha=0.8)
food_sel_scaled_train.SCORE.plot(
opt = hf_optimizer(p=model.rnn.params, inputs=[model.x, model.y],
s=model.rnn.y_pred,
costs=[model.rnn.loss(model.y)], h=model.rnn.h)
opt.train(gradient_dataset, cg_dataset, num_updates=300)'''
model = MetaRNN(n_in=n_in,
n_mul=n_hidden,
n_out=n_out,
learning_rate=0.001,
learning_rate_decay=0.999,
n_epochs=n_epochs,
L1_reg=0.005,
activation='tanh',
output_type='real',
index=index)
model.fit(seqs, targets, validation_frequency=1000)
print "traning over"
path = '/root/chentian/share/201605/ped2'
# os.makedirs(path)
path0 = path + '/predict.csv'
f3 = file(path0, "a")
for k in range(0, 3000):
guess = model.predict(test_seqs[k])
np.savetxt(f3, guess, delimiter=',')
f3.close()
error1 = np.zeros([1800, 1200])
pre_f = file(path0, "r")
pre = np.loadtxt(pre_f, delimiter=',')
pre_f.close()
