def db_from_df(train, test, bs=1024):
# Create TensorDatasets
train_ds = TensorDataset(torch.tensor(train.values),
torch.tensor(train.values))
valid_ds = TensorDataset(torch.tensor(test.values),
torch.tensor(test.values))
# Create DataLoaders
train_dl, valid_dl = get_data(train_ds, valid_ds, bs=bs)
# Return DataBunch
return basic_data.DataBunch(train_dl, valid_dl)
def train_evaluate_model(model_class, num_epochs):
model = model_class()
train_dl, valid_dl, train_x, train_y, test_x, test_y = load_data(batch_size = 256)
db = basic_data.DataBunch(train_dl, valid_dl)
loss_func = nn.MSELoss()
bn_wd = False # Don't use weight decay fpr batchnorm layers
true_wd = True # wd will be used for all optimizers
wd = 1e-6
plots_path, model_name = make_plots_dir(model_class)
learn = basic_train.Learner(data=db, model=model, loss_func=loss_func, wd=wd, callback_fns=ActivationStats, bn_wd=bn_wd, true_wd=true_wd)
#tr.lr_find(learn, start_lr=1e-8)
#losses = [loss.item() for loss in learn.recorder.losses]
#lr = round(learn.recorder.lrs[np.argmin(np.array(losses))], 4)
#lr_plot = learn.recorder.plot(return_fig=True)
#lr_plot.savefig('lr_plot.png')
lr = 3e-4
learn.fit(num_epochs, lr=lr, wd=wd)
learn.save(model_name)
loss_plot = learn.recorder.plot_losses(return_fig=True)
loss_plot.savefig(plots_path + 'loss_plot.png')
plt.plot(learn.recorder.val_losses, marker='>')
plt.savefig(plots_path + 'val_losses.png')
plot_activations(learn, save = plots_path)
loss = learn.validate()[0]
plt.close('all')
current_save_folder = plots_path
make_plots(model, train_x, train_y, test_x, test_y, current_save_folder, model_name)
return loss
test = pd.read_pickle(BIN + 'processed_data/aod/custom_normalized_test_10percent')
# Remove Width and WidthPhi
train.pop('Width')
train.pop('WidthPhi')
test.pop('Width')
test.pop('WidthPhi')
bs = 4096
# Create TensorDatasets
train_ds = TensorDataset(torch.tensor(train.values, dtype=torch.float), torch.tensor(train.values, dtype=torch.float))
valid_ds = TensorDataset(torch.tensor(test.values, dtype=torch.float), torch.tensor(test.values, dtype=torch.float))
# Create DataLoaders
train_dl, valid_dl = get_data(train_ds, valid_ds, bs=bs)
# Return DataBunch
db = basic_data.DataBunch(train_dl, valid_dl)
# loss_func = RMSELoss()
loss_func = nn.MSELoss()
bn_wd = False # Don't use weight decay for batchnorm layers
true_wd = True # wd will be used for all optimizers
# Figures setup
plt.close('all')
unit_list = ['[GeV]', '[rad]', '[rad]', '[GeV]']
variable_list = [r'$p_T$', r'$\eta$', r'$\phi$', r'$E$']
line_style = ['--', '-']
colors = ['orange', 'c']
markers = ['*', 's']
def prepare_data(X, bs):
train_ds = TensorDataset(torch.tensor(X), torch.tensor(X))
valid_ds = TensorDataset(torch.tensor(X_test), torch.tensor(X_test))
train_dl, valid_dl = get_data(train_ds, valid_ds, bs=bs)
db = basic_data.DataBunch(train_dl, valid_dl)
return db
