'{:.0E}'.format(lam))
my_path = Path('..', 'model_output', 'part_2', filename + '_train.json')
train_path = Path(__file__).parent.resolve().joinpath(my_path)
# Make output directory if doesn't exist.
output_dir = train_path.parent.resolve()
if not Path(output_dir).exists():
Path(output_dir).mkdir()
with open(train_path, 'w') as f:
json.dump(learned_model, f, indent=4)
# If gradient didn't explode, get predictions on validation set.
if learned_model['exploding'] is False:
print('Calculating predictions on validation set...')
# Grab weights to input to prediction method.
weights = learned_model['weights']
predictions = model.predict_validation(weights)
# Output for predictions and SSE for validation set.
dev_filename = filename + '_dev.json'
dev_path = train_path.with_name(dev_filename)
with open(dev_path, 'w') as f:
json.dump(predictions, f, indent=4)
print('Predictions complete.\n')
print('Part 2 complete.\n')
from models.linear_model import LinearModel
pp = pprint.PrettyPrinter()
model = LinearModel(train='data/PA1_train.pkl',
validation='data/PA1_dev.pkl',
test='data/PA1_test.pkl',
target='price',
rate=1e-05,
lam=0.001,
eps=0.5,
normalize=True)
names = model.weight_labels
learned_model = model.train_model(50000)
val_predictions = model.predict_validation(
learned_model['weights'])['predictions']
test_predictions = model.predict_test(
(learned_model['weights']))['predictions']
prediction_output = pathlib.Path('model_output/predictions.pkl')
prediction_file = pathlib.Path('model_output/predictions.txt')
pred_output_path = pathlib.Path(__file__).parent.resolve().joinpath(
prediction_output)
pred_file_path = pathlib.Path(__file__).parent.resolve().joinpath(
prediction_file)
# Save predictions
with open(pred_output_path, 'wb') as fp:
pickle.dump(test_predictions, fp, pickle.HIGHEST_PROTOCOL)
