lem_length = len(word2vec_model[','].tolist())
gram_length = len(word2vec_gram_model['_PNCT'].tolist())
length = (lem_length + gram_length + 1)* (2*winsize + 1)
if __name__ == '__main__':
files = os.listdir(CORPUS)
random.shuffle(files)
fs = files[len(files)/2 + 1:]
fs2 = files[:len(files)/2]
#fs2 = files[1000:2000]
#fs = files[:1000]
neurons, target, words, cls = data_utils.mklsts(CORPUS, fs, winsize, word2vec_model, word2vec_gram_model)
trainDS = data_utils.DataSet(neurons, target, words, cls)
model = net.NetworkBuilder(length, length / 2, 3, bias = True, fast = True, outclass = net.SoftmaxLayer)
engine = data_utils.Engine(trainData = trainDS, model = model)
engine.fit(engine.trainData, learningrate = 0.05, maxEpochs=200,
file = 'training.txt', verbose = True, modelfile = 'network.model', FOLDER = F)
del neurons
del target
del words
del cls
del engine.trainData
neurons1, target1, words1, cls1 = data_utils.mklsts(CORPUS, fs2, winsize, word2vec_model, word2vec_gram_model)
def main(model='mlp', num_epochs=500):
files = os.listdir(CORPUS)
random.shuffle(files)
random.seed(20)
print len(files)
fs2 = files[5000:6000] #train
fs3 = files[6000 : ] #evaluate
fs1 = files[:5000] #test
X_train, targets_train, words_train, y_train = data_utils.mklsts(CORPUS, fs1, winsize, word2vec_model, word2vec_gram_model)
X_val, targets_val, words_val, y_val = data_utils.mklsts(CORPUS, fs2, winsize, word2vec_model, word2vec_gram_model)
input_var = T.matrix('inputs')
target_var = T.ivector('targets')
network = build_mlp(input_var)
prediction = lasagne.layers.get_output(network)
loss = lasagne.objectives.categorical_crossentropy(prediction, target_var)
loss = loss.mean() + 1e-4 * lasagne.regularization.regularize_network_params(
network, lasagne.regularization.l2)
params = lasagne.layers.get_all_params(network, trainable=True)
updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=0.01, momentum=0.9)
eval_prediction = lasagne.layers.get_output(network, deterministic=True)
eval_loss = lasagne.objectives.categorical_crossentropy(eval_prediction,
target_var)
eval_loss = eval_loss.mean()
eval_acc = T.mean(T.eq(T.argmax(eval_prediction, axis=1), target_var),
dtype=theano.config.floatX)
train_fn = theano.function([input_var, target_var], loss, updates=updates)
val_fn = theano.function([input_var, target_var], [eval_loss, eval_acc])
for epoch in range(num_epochs):
# In each epoch, we do a full pass over the training data:
train_err = 0
train_batches = 0
start_time = time.time()
for batch in iterate_minibatches(X_train, y_train, 100, shuffle=True):
inputs, targets = batch
train_err += train_fn(inputs, targets)
train_batches += 1
# And a full pass over the validation data:
val_err = 0
val_acc = 0
val_batches = 0
for batch in iterate_minibatches(X_val, y_val, 100, shuffle=False):
inputs, targets = batch
err, acc = val_fn(inputs, targets)
val_err += err
val_acc += acc
val_batches += 1
# Then we print the results for this epoch:
print("Epoch {} of {} took {:.3f}s".format(
epoch + 1, num_epochs, time.time() - start_time))
print(" training loss:\t\t{:.6f}".format(train_err / train_batches))
print(" validation loss:\t\t{:.6f}".format(val_err / val_batches))
print(" validation accuracy:\t\t{:.2f} %".format(
val_acc / val_batches * 100))
del X_train, targets_train, words_train, y_train, X_val, targets_val, words_val, y_val
X_test, targets_test, words_test, y_test = data_utils.mklsts(CORPUS, fs3, winsize, word2vec_model, word2vec_gram_model)
np.savez('/home/anna/Documents/News Classifier/model.npz', *lasagne.layers.get_all_param_values(network))
test_prediction = lasagne.layers.get_output(network, deterministic=True)
predict_fn = theano.function([input_var], T.argmax(test_prediction, axis=1))
pred = list(predict_fn(X_test))# for _ in X_test)
print len(pred)
print len(y_test)
score = f1_score(pred, y_test, average=None)
print score
predannotations = setAnnotations(pred, {1: 'Location'}, exactness = 'lenient')
clsannotations = setAnnotations(y_test, {1: 'Location'}, exactness = 'lenient')
print Pr(predannotations, clsannotations)
print Re(predannotations, clsannotations)
print f1(predannotations, clsannotations)
np.savez('/home/anna/Documents/News Classifier/model.npz', *lasagne.layers.get_all_param_values(network))
