def do_train(args):
"""
Train the model using the provided arguments.
"""
# Assumption: it is cheap to store all the data in text form in
# memory (it's only about 144mb)
_, X, y = load_data_raw(args.input)
X_train, y_train, X_val, y_val = split_data(X, y, args.dev_split)
# Assumption: word vector model will also easily fit in memory.
wvecs = WordVectorModel.from_file(args.wvecs, False, '*UNKNOWN*')
# Typical values are 50, 50
input_shape = (1,args.n_words, wvecs.dim)
output_shape = len(LABELS)
# Build model
model = build_model(args, input_shape=input_shape, output_shape=output_shape, output_type=args.output_type)
# Training data on the other hand will not. Each input instance is
# 50x50 matrix with 8bytes per value: that's about 20kb.
# Assuming we want to store only about 500mb in memory at a time,
# that means we want at most 25k items in a batch.
# Typically minibatches of 32-128 are probably ok. Let's keep it
# that way?
for epoch in range(args.n_epochs):
log("== Training model, epoch {}", epoch)
scorer = Scorer(model)
for xy in tqdm(grouper(args.batch_size, zip(X_train, y_train))):
X_batch, y_batch = zip(*xy)
X_batch, y_batch = wvecs.embed_sentences(X_batch), array(make_one_hot(y_batch, len(LABELS)))
score = model.train_on_batch(X_batch, y_batch)
scorer.update(score, len(X_batch))
log("=== train error: {}", scorer)
scorer = Scorer(model)
for xy in tqdm(grouper(args.batch_size, zip(X_val, y_val))):
X_batch, y_batch = zip(*xy)
X_batch, y_batch = wvecs.embed_sentences(X_batch), array(make_one_hot(y_batch, len(LABELS)))
score = model.test_on_batch(X_batch, y_batch)
scorer.update(score, len(X_batch))
log("=== val error: {}", scorer)
## Save the model
save_model(model, args.model, args.weights)
def do_run(args):
"""
Run the neural net to predict on new data.
"""
# Load the model and weights
model = load_model(args.model, args.weights)
wvecs = WordVectorModel.from_file(args.wvecs, False, '*UNKNOWN*')
data = ((tweet.id, tokenize(to_ascii(tweet.text))) for tweet in RowObjectFactory.from_stream(csv.reader(args.input, delimiter="\t")))
writer = csv.writer(args.output, delimiter='\t')
writer.writerow(['id',] + LABELS)
for ix in tqdm(grouper(args.batch_size, data)):
ids_batch, X_batch = zip(*ix)
X_batch = wvecs.embed_sentences(X_batch)
labels = model.predict_on_batch(X_batch)
for id, label in zip(ids_batch, labels):
writer.writerow([id,] + [float(l) for l in label])
