spamwriter = csv.writer(csvfile, delimiter=',', quotechar='|', quoting=csv.QUOTE_MINIMAL)
spamwriter.writerow(["Prefix length", "Groud truth", "Predicted", "Levenshtein", "Damerau", "Jaccard", "Ground truth times", "Predicted times", "RMSE", "MAE", "Median AE"])
for prefix_size in range(prefix_size_pred_from, prefix_size_pred_to):
print(prefix_size)
for line, times, times2, times3 in zip(lines, lines_t, lines_t2, lines_t3):
prediction_end_reached = False
times.append(0)
cropped_line = ''.join(line[:prefix_size])
cropped_times = times[:prefix_size]
cropped_times3 = times3[:prefix_size]
if len(times2)<prefix_size:
continue # make no prediction for this case, since this case has ended already
# initialize root of the tree for beam search
total_predicted_time_initialization = 0
search_tree_root = MultileafTree(beam_size, encode(cropped_line, cropped_times, cropped_times3,maxlen,chars, char_indices, divisor, divisor2),
cropped_line, total_predicted_time_initialization)
prediction_end_reached = False
ground_truth = ''.join(line[prefix_size:prefix_size+predict_size])
ground_truth_t = times2[prefix_size-1]
case_end_time = times2[len(times2)-1]
ground_truth_t = case_end_time-ground_truth_t
predicted = ''
for i in range(predict_size):
#here we will take data from the node in the tree used to prun
def run_experiments(log_identificator, formula_type):
eventlog, path_to_model_file, beam_size, \
prefix_size_pred_from, prefix_size_pred_to, formula = activateSettings(log_identificator, formula_type)
current_path = os.path.abspath(getsourcefile(lambda: 0))
current_dir = os.path.dirname(current_path)
parent_dir = current_dir[:current_dir.rfind(os.path.sep)]
sys.path.insert(0, parent_dir)
start_time = time.time()
lines, lines_t, lines_t2, lines_t3, maxlen, chars, char_indices, divisor, divisor2, \
divisor3, predict_size, target_indices_char, target_char_indices = prepare_testing_data(eventlog)
# find cycles and modify the probability functionality goes here
stop_symbol_probability_amplifier_current = 1
# modify to be able to get second best prediction
def getSymbol(predictions, ith_best=0):
predictions[
0] = predictions[0] * stop_symbol_probability_amplifier_current
i = np.argsort(predictions)[len(predictions) - ith_best - 1]
return target_indices_char[i]
one_ahead_gt = []
one_ahead_pred = []
# load model, set this to the model generated by train.py
model = load_model(path_to_model_file)
stop_symbol_probability_amplifier_current = 1
# make predictions
with open(
'output_files/results/' + formula_type +
'/suffix_and_remaining_time2_%s' % eventlog, 'wb') as csvfile:
spamwriter = csv.writer(csvfile,
delimiter=',',
quotechar='|',
quoting=csv.QUOTE_MINIMAL)
spamwriter.writerow([
"Prefix length", "Groud truth", "Predicted", "Levenshtein",
"Damerau", "Jaccard", "Ground truth times", "Predicted times",
"RMSE", "MAE", "Median AE"
])
for prefix_size in range(prefix_size_pred_from, prefix_size_pred_to):
# here we checkout the prefixes with formulas verified only on the suffix phase
lines_s, lines_t_s, lines_t2_s, lines_t3_s = selectFormulaVerifiedTraces(
lines, lines_t, lines_t2, lines_t3, formula, prefix_size)
print("prefix size: " + str(prefix_size))
print("formulas verifited: " + str(len(lines_s)) + " out of : " +
str(len(lines)))
for line, times, times2, times3 in zip(lines_s, lines_t_s,
lines_t2_s, lines_t3_s):
prediction_end_reached = False
times.append(0)
cropped_line = ''.join(line[:prefix_size])
cropped_times = times[:prefix_size]
cropped_times3 = times3[:prefix_size]
if len(times2) < prefix_size:
continue # make no prediction for this case, since this case has ended already
# initialize root of the tree for beam search
total_predicted_time_initialization = 0
search_tree_root = MultileafTree(
beam_size,
encode(cropped_line, cropped_times, cropped_times3, maxlen,
chars, char_indices, divisor, divisor2),
cropped_line, total_predicted_time_initialization)
prediction_end_reached = False
ground_truth = ''.join(line[prefix_size:prefix_size +
predict_size])
ground_truth_t = times2[prefix_size - 1]
case_end_time = times2[len(times2) - 1]
ground_truth_t = case_end_time - ground_truth_t
predicted = ''
for i in range(predict_size):
# here we will take data from the node in the tree used to prun
enc = search_tree_root.data # encode(cropped_line, cropped_times, cropped_times3)
y = model.predict(enc, verbose=0) # make predictions
# split predictions into seperate activity and time predictions
y_char = y[0][0]
y_t = y[1][0][0]
stop_symbol_probability_amplifier_current, \
start_of_the_cycle_symbol = amplify(search_tree_root.cropped_line)
# cropped_line += prediction
if y_t < 0:
y_t = 0
# TOO not normalizing here seems like a bug
cropped_times.append(y_t)
ma = False
for i in range(beam_size):
prediction = getSymbolAmpl(
y_char, target_indices_char, target_char_indices,
start_of_the_cycle_symbol,
stop_symbol_probability_amplifier_current, i)
# end of case was just predicted, therefore, stop predicting further into the future
if prediction == '!':
if verify_formula_as_compliant(
search_tree_root.cropped_line, formula,
prefix_size):
one_ahead_pred.append(
search_tree_root.total_predicted_time)
one_ahead_gt.append(ground_truth_t)
print('! predicted, end case')
ma = True
break
# else:
# prediction_end_reached = True;
if ma:
break
# if the end of prediction was not reached we continue as always, and then function :choose_next_
# top_descendant: will earch for future prediction
# in not reached, function :choose_next_top_descendant: will backtrack
y_t = y_t * divisor3
if not prediction_end_reached:
cropped_times3.append(cropped_times3[-1] +
timedelta(seconds=y_t))
for i in range(beam_size):
temp_prediction = getSymbolAmpl(
y_char, target_indices_char,
target_char_indices, start_of_the_cycle_symbol,
stop_symbol_probability_amplifier_current, i)
if temp_prediction == '!':
continue
temp_cropped_line = search_tree_root.cropped_line + temp_prediction
# this means that we found the end in one of the alternatives.
temp_total_predicted_time = search_tree_root.total_predicted_time + y_t
temp_state_data = encode(temp_cropped_line,
cropped_times,
cropped_times3, maxlen,
chars, char_indices,
divisor, divisor2)
search_tree_root.descendants[i] = MultileafTree(
beam_size, temp_state_data, temp_cropped_line,
temp_total_predicted_time, search_tree_root)
search_tree_root = search_tree_root.choose_next_top_descendant(
)
if prediction_end_reached:
prediction_end_reached = False
if search_tree_root is None:
print(
"Cannot find any trace that is compliant with formula given current beam size"
)
break
output = []
if search_tree_root is None:
predicted = u""
total_predicted_time = 0
else:
predicted = (search_tree_root.cropped_line[prefix_size:])
total_predicted_time = search_tree_root.total_predicted_time
if len(ground_truth) > 0:
output.append(prefix_size)
output.append(unicode(ground_truth).encode("utf-8"))
output.append(unicode(predicted).encode("utf-8"))
output.append(
1 - distance.nlevenshtein(predicted, ground_truth))
dls = 1 - (damerau_levenshtein_distance(
unicode(predicted), unicode(ground_truth)) /
max(len(predicted), len(ground_truth)))
if dls < 0:
dls = 0
# we encountered problems with Damerau-Levenshtein Similarity on some linux machines where the
# default character encoding of the operating system caused it to be negative, this should never
# be the case
output.append(dls)
output.append(1 -
distance.jaccard(predicted, ground_truth))
output.append(ground_truth_t)
output.append(total_predicted_time)
output.append('')
output.append(
metrics.mean_absolute_error([ground_truth_t],
[total_predicted_time]))
output.append(
metrics.median_absolute_error([ground_truth_t],
[total_predicted_time]))
spamwriter.writerow(output)
print("TIME TO FINISH --- %s seconds ---" % (time.time() - start_time))
# lines_t2 = lines_t2[13:]
# lines_t3 = lines_t3[13:]
for line, times, times2, times3 in izip(lines, lines_t, lines_t2,
lines_t3):
times.append(0)
cropped_line = ''.join(line[:prefix_size])
cropped_times = times[:prefix_size]
cropped_times3 = times3[:prefix_size]
if len(times2) < prefix_size:
continue # make no prediction for this case, since this case has ended already
# initialize root of the tree for beam search
total_predicted_time_initialization = 0
search_node_root = NodePrediction(
encode(cropped_line, cropped_times, cropped_times3, maxlen,
chars, char_indices, divisor, divisor2), cropped_line,
total_predicted_time_initialization)
ground_truth = ''.join(line[prefix_size:prefix_size +
predict_size])
ground_truth_t = times2[prefix_size - 1]
case_end_time = times2[len(times2) - 1]
ground_truth_t = case_end_time - ground_truth_t
predicted = ''
queue_next_steps = PriorityQueue()
queue_next_steps.put(
(-search_node_root.probability_of, search_node_root))
queue_next_steps_future = PriorityQueue()
def runExperiments(logIdentificator, formulaType):
eventlog, path_to_model_file, beam_size, \
prefix_size_pred_from, prefix_size_pred_to, formula = activateSettings(logIdentificator, formulaType)
start_time = time.time()
lines, lines_t, lines_t2, lines_t3, maxlen, chars, char_indices,divisor, divisor2, \
divisor3, predict_size,target_indices_char,target_char_indices\
= prepare_testing_data(eventlog)
#
# lines = lines[0:300]
# lines_t= lines_t[0:300]
# lines_t2=lines_t2[0:300]
# lines_t3=lines_t3[0:300]
#this is the beam stack size, means how many "best" alternatives will be stored
one_ahead_gt = []
one_ahead_pred = []
#find cycles and modify the probability functionality goes here
stop_symbol_probability_amplifier_current = 1
# load model, set this to the model generated by train.py
model = load_model(path_to_model_file)
class NodePrediction():
def __init__(self,
data,
cropped_line,
total_predicted_time,
probability_of=0):
self.data = data
self.cropped_line = cropped_line
self.total_predicted_time = total_predicted_time
self.probability_of = probability_of
# make predictions
with open(
'output_files/results/' + formulaType +
'/suffix_and_remaining_time3_%s' % eventlog, 'wb') as csvfile:
spamwriter = csv.writer(csvfile,
delimiter=',',
quotechar='|',
quoting=csv.QUOTE_MINIMAL)
spamwriter.writerow([
"Prefix length", "Groud truth", "Predicted", "Levenshtein",
"Damerau", "Jaccard", "Ground truth times", "Predicted times",
"RMSE", "MAE", "Median AE"
])
for prefix_size in range(prefix_size_pred_from, prefix_size_pred_to):
print(prefix_size)
# lines = lines[13:]
# lines_t = lines_t[13:]
# lines_t2 = lines_t2[13:]
# lines_t3 = lines_t3[13:]
lines_s, lines_t_s, lines_t2_s, lines_t3_s = selectFormulaVerifiedTraces(
lines, lines_t, lines_t2, lines_t3, formula, prefix_size)
print("prefix size: " + str(prefix_size))
print("formulas verifited: " + str(len(lines_s)) + " out of : " +
str(len(lines)))
counterr = 0
for line, times, times2, times3 in izip(lines_s, lines_t_s,
lines_t2_s, lines_t3_s):
times.append(0)
cropped_line = ''.join(line[:prefix_size])
cropped_times = times[:prefix_size]
cropped_times3 = times3[:prefix_size]
if len(times2) < prefix_size:
continue # make no prediction for this case, since this case has ended already
# initialize root of the tree for beam search
total_predicted_time_initialization = 0
search_node_root = NodePrediction(
encode(cropped_line, cropped_times, cropped_times3, maxlen,
chars, char_indices, divisor, divisor2),
cropped_line, total_predicted_time_initialization)
ground_truth = ''.join(line[prefix_size:prefix_size +
predict_size])
ground_truth_t = times2[prefix_size - 1]
case_end_time = times2[len(times2) - 1]
ground_truth_t = case_end_time - ground_truth_t
predicted = ''
queue_next_steps = PriorityQueue()
queue_next_steps.put(
(-search_node_root.probability_of, search_node_root))
queue_next_steps_future = PriorityQueue()
start_of_the_cycle_symbol = " "
found_sattisfying_constraint = False
current_beam_size = beam_size
for i in range(predict_size):
for k in range(current_beam_size):
if queue_next_steps.empty():
break
_, current_prediction_premis = queue_next_steps.get()
if not found_sattisfying_constraint:
if verify_formula_as_compliant(
current_prediction_premis.cropped_line,
formula, prefix_size):
#the formula verified and we can just finish the predictions
#beam size is 1 because predict only sequence of events
current_beam_size = 1
#overwrite new queue
queue_next_steps_future = PriorityQueue()
found_sattisfying_constraint = True
enc = current_prediction_premis.data
temp_cropped_line = current_prediction_premis.cropped_line
y = model.predict(enc, verbose=0) # make predictions
# split predictions into seperate activity and time predictions
y_char = y[0][0]
y_t = y[1][0][0]
if y_t < 0:
y_t = 0
cropped_times.append(y_t)
if not i == 0:
stop_symbol_probability_amplifier_current, start_of_the_cycle_symbol = amplify(
temp_cropped_line)
#in not reached, function :choose_next_top_descendant: will backtrack
y_t = y_t * divisor3
cropped_times3.append(cropped_times3[-1] +
timedelta(seconds=y_t))
for j in range(current_beam_size):
temp_prediction = getSymbolAmpl(
y_char, target_indices_char,
target_char_indices, start_of_the_cycle_symbol,
stop_symbol_probability_amplifier_current, j)
if temp_prediction == '!': # end of case was just predicted, therefore, stop predicting further into the future
if verify_formula_as_compliant(
temp_cropped_line, formula,
prefix_size):
one_ahead_pred.append(
current_prediction_premis.
total_predicted_time)
one_ahead_gt.append(ground_truth_t)
stop_symbol_probability_amplifier_current = 1
print('! predicted, end case')
queue_next_steps = PriorityQueue()
break
else:
continue
temp_cropped_line = current_prediction_premis.cropped_line + temp_prediction
temp_total_predicted_time = current_prediction_premis.total_predicted_time + y_t
temp_state_data = encode(temp_cropped_line,
cropped_times,
cropped_times3, maxlen,
chars, char_indices,
divisor, divisor2)
probability_this = np.sort(y_char)[len(y_char) -
1 - j]
temp = NodePrediction(
temp_state_data, temp_cropped_line,
temp_total_predicted_time,
current_prediction_premis.probability_of +
np.log(probability_this))
queue_next_steps_future.put(
(-temp.probability_of, temp))
# print str(counterr) + ' ' + str(i) + ' ' + str(k) \
# + ' ' + str(j) + ' ' + temp_cropped_line[prefix_size:]\
# + " " + str(temp.probability_of)
queue_next_steps = queue_next_steps_future
queue_next_steps_future = PriorityQueue()
counterr += 1
if current_prediction_premis == None:
print "Cannot find any trace that is compliant with formula given current beam size"
break
output = []
if current_prediction_premis == None:
predicted = u""
total_predicted_time = 0
else:
predicted = (
current_prediction_premis.cropped_line[prefix_size:])
total_predicted_time = current_prediction_premis.total_predicted_time
if len(ground_truth) > 0:
output.append(prefix_size)
output.append(unicode(ground_truth).encode("utf-8"))
output.append(unicode(predicted).encode("utf-8"))
output.append(
1 - distance.nlevenshtein(predicted, ground_truth))
dls = 1 - (damerau_levenshtein_distance(
unicode(predicted), unicode(ground_truth)) /
max(len(predicted), len(ground_truth)))
if dls < 0:
dls = 0 # we encountered problems with Damerau-Levenshtein Similarity on some linux machines where the default character encoding of the operating system caused it to be negative, this should never be the case
output.append(dls)
output.append(1 -
distance.jaccard(predicted, ground_truth))
output.append(ground_truth_t)
output.append(total_predicted_time)
output.append('')
output.append(
metrics.mean_absolute_error([ground_truth_t],
[total_predicted_time]))
output.append(
metrics.median_absolute_error([ground_truth_t],
[total_predicted_time]))
spamwriter.writerow(output)
print("TIME TO FINISH --- %s seconds ---" % (time.time() - start_time))
