def fit(self,
dataset,
nb_epoch=10,
batch_size=50,
pad_batches=False,
**kwargs):
"""
Fits a model on data in a Dataset object.
"""
# TODO(rbharath/enf): We need a structured way to deal with potential GPU
# memory overflows.
for epoch in range(nb_epoch):
log("Starting epoch %s" % str(epoch + 1), self.verbosity)
losses = []
for (X_batch, y_batch, w_batch,
ids_batch) in dataset.iterbatches(batch_size,
pad_batches=pad_batches):
if self.fit_transformers:
X_batch, y_batch, w_batch = self.transform_on_batch(
X_batch, y_batch, w_batch)
if pad_batches:
X_batch, y_batch, w_batch, ids_batch = pad_batch(
batch_size, X_batch, y_batch, w_batch, ids_batch)
losses.append(self.fit_on_batch(X_batch, y_batch, w_batch))
log(
"Avg loss for epoch %d: %f" %
(epoch + 1, np.array(losses).mean()), self.verbosity)
def predict_proba_on_batch(self, support, test_batch):
"""Make predictions on batch of data."""
n_samples = len(test_batch)
X, y, w, ids = pad_batch(self.test_size, test_batch.X, test_batch.y,
test_batch.w, test_batch.ids)
padded_test_batch = NumpyDataset(X, y, w, ids)
feed_dict = self.construct_feed_dict(padded_test_batch, support)
# Get scores
pred = self.sess.run(self.pred_op, feed_dict=feed_dict)
# Remove padded elements
pred = np.asarray(pred[:n_samples])
return pred
def predict_on_batch(self, support, test_batch):
"""Make predictions on batch of data."""
n_samples = len(test_batch)
padded_test_batch = NumpyDataset(*pad_batch(
self.test_batch_size, test_batch.X, test_batch.y, test_batch.w,
test_batch.ids))
feed_dict = self.construct_feed_dict(padded_test_batch, support)
# Get scores
pred, scores = self.sess.run([self.pred_op, self.scores_op], feed_dict=feed_dict)
y_pred_batch = np.round(pred)
# Remove padded elements
y_pred_batch = y_pred_batch[:n_samples]
return y_pred_batch
def predict_on_batch(self, support, test_batch):
"""Make predictions on batch of data."""
n_samples = len(test_batch)
X, y, w, ids = pad_batch(self.test_batch_size, test_batch.X,
test_batch.y, test_batch.w, test_batch.ids)
padded_test_batch = NumpyDataset(X, y, w, ids)
feed_dict = self.construct_feed_dict(padded_test_batch, support)
# Get scores
pred, scores = self.sess.run([self.pred_op, self.scores_op],
feed_dict=feed_dict)
y_pred_batch = np.round(pred)
# Remove padded elements
y_pred_batch = y_pred_batch[:n_samples]
return y_pred_batch
def predict_proba_on_batch(self, support, test_batch):
"""Make predictions on batch of data."""
n_samples = len(test_batch)
padded_test_batch = NumpyDataset(*pad_batch(
self.test_batch_size, test_batch.X, test_batch.y, test_batch.w,
test_batch.ids))
feed_dict = self.construct_feed_dict(padded_test_batch, support)
# Get scores
pred, scores = self.sess.run([self.pred_op, self.scores_op], feed_dict=feed_dict)
# pred corresponds to prob(example == 1)
y_pred_batch = np.zeros((n_samples, 2))
# Remove padded elements
pred = pred[:n_samples]
y_pred_batch[:, 1] = pred
y_pred_batch[:, 0] = 1-pred
return y_pred_batch
def predict_proba_on_batch(self, support, test_batch):
"""Make predictions on batch of data."""
n_samples = len(test_batch)
X, y, w, ids = pad_batch(self.test_batch_size, test_batch.X,
test_batch.y, test_batch.w, test_batch.ids)
padded_test_batch = NumpyDataset(X, y, w, ids)
feed_dict = self.construct_feed_dict(padded_test_batch, support)
# Get scores
pred, scores = self.sess.run([self.pred_op, self.scores_op],
feed_dict=feed_dict)
# pred corresponds to prob(example == 1)
y_pred_batch = np.zeros((n_samples, 2))
# Remove padded elements
pred = pred[:n_samples]
y_pred_batch[:, 1] = pred
y_pred_batch[:, 0] = 1 - pred
return y_pred_batch
def fit(self, dataset, nb_epoch=10, batch_size=50, pad_batches=False, **kwargs):
"""
Fits a model on data in a Dataset object.
"""
# TODO(rbharath/enf): We need a structured way to deal with potential GPU
# memory overflows.
for epoch in range(nb_epoch):
log("Starting epoch %s" % str(epoch+1), self.verbosity)
losses = []
for (X_batch, y_batch, w_batch, ids_batch) in dataset.iterbatches(
batch_size, pad_batches=pad_batches):
if self.fit_transformers:
X_batch, y_batch, w_batch = self.transform_on_batch(X_batch, y_batch,
w_batch)
if pad_batches:
X_batch, y_batch, w_batch, ids_batch = pad_batch(
batch_size, X_batch, y_batch, w_batch, ids_batch)
losses.append(self.fit_on_batch(X_batch, y_batch, w_batch))
log("Avg loss for epoch %d: %f"
% (epoch+1,np.array(losses).mean()),self.verbosity)