def PFN_AUC_calculation(jet_array_1, jet_array_2, train_size, test_size):
X = np.concatenate([jet_array_1, jet_array_2])[:,:,:4]
y = np.concatenate([np.ones(len(jet_array_1)), np.zeros(len(jet_array_2))])
################################### SETTINGS ###################################
# data controls
train, val, test = train_size, X.shape[0]-train_size-test_size, test_size
use_pids = True
# network architecture parameters
Phi_sizes, F_sizes = (100, 100, 128), (100, 100, 100)
# network training parameters
num_epoch = 10
batch_size = 500
################################################################################
# convert labels to categorical
Y = to_categorical(y, num_classes=2)
# preprocess by centering jets and normalizing pts
for x in X:
mask = x[:,0] > 0
yphi_avg = np.average(x[mask,1:3], weights=x[mask,0], axis=0)
x[mask,1:3] -= yphi_avg
x[mask,0] /= x[:,0].sum()
# handle particle id channel
if use_pids:
remap_pids(X, pid_i=3)
else:
X = X[:,:,:3]
# do train/val/test split
(X_train, X_val, X_test,
Y_train, Y_val, Y_test) = data_split(X, Y, val=val, test=test)
# build architecture
pfn = 0
with suppress_stdout():
pfn = PFN(input_dim=X.shape[-1], Phi_sizes=Phi_sizes, F_sizes=F_sizes)
# train model
pfn.fit(X_train, Y_train,
epochs=num_epoch,
batch_size=batch_size,
validation_data=(X_val, Y_val),
verbose=0)
# get predictions on test data
preds = pfn.predict(X_test, batch_size=1000)
# get area under the ROC curve
auc = roc_auc_score(Y_test[:,1], preds[:,1])
return auc
x[mask, 3] = map_func(x[mask, 3])
return X
if __name__ == '__main__':
phi_sizes = (16, 32, 64, 128)
f_sizes = (128, 64, 32, 16)
X, Y = load_data(2000000, 'final_efn_train')
X = preprocess(X)
Y = ef.utils.to_categorical(Y)
X_train, X_val, X_test, Y_train, Y_val, Y_test = split_data(
X, Y, test_prop=1.0 / 5, val_prop=1.0 / 5)
adam = optimizers.Adam(lr=.0006)
pfn = PFN(input_dim=X_train.shape[-1],
Phi_sizes=phi_sizes,
F_sizes=f_sizes,
optimizer=adam)
pfn.fit(X_train,
Y_train,
epochs=NUM_EPOCHS,
batch_size=250,
validation_data=(X_val, Y_val),
verbose=1)
preds = pfn.predict(X_test, batch_size=1000)
fpr, tpr, thresholds = roc_curve(Y_test[:, 1], preds[:, 1])
print('AUC: ' + str(auc(fpr, tpr)))
# Shuffle loaded datasets and begin
inds = range(len(X_train))
np.random.shuffle(inds)
X_epoch, Y_epoch, W_epoch, MVA_epoch = X_train[inds], Y[inds], W_train[
inds], MVA_epoch[inds]
if (np.min(W_train) == np.nan): continue
if (np.min(W_train) == np.inf): continue
model.fit(X_epoch, Y_epoch, epochs=1, batch_size=4 * 512, verbose=1)
pd.DataFrame(X_epoch).to_csv("X_example.csv", index=False)
pd.DataFrame(Y_epoch).to_csv("Y_example.csv", index=False)
pd.DataFrame(MVA_epoch).to_csv("MVA_example.csv", index=False)
if (epoch % 10 == 0):
model.save(
'/beegfs/desy/user/dydukhle/TauId/models/keras__deep_set__%i.model'
% (epoch))
preds = model.predict(X_epoch, batch_size=1 * 2048)
mva = MVA_train
df_preds = pd.DataFrame({
"pred": [i[0] for i in preds],
"labels": [y for y in Y_epoch]
}) #, 'mva':[m[0] for m in mva] })
df_preds.to_csv(
"./DeepSets_res/labels_and_pred_e_{0}.csv".format(epoch))
df_mva = pd.DataFrame(mva)
df_mva.to_csv("./DeepSets_res/mva_{0}.csv".format(epoch))
# Get next batch from background loader res
X_train, Y, W_train, MVA_train = utils.BuildBatch(
) #res.get(timeout=180)