Skip to content

Commit

Permalink
Merge remote-tracking branch 'upstream/hotfixes' into release
Browse files Browse the repository at this point in the history
  • Loading branch information
@fit-alessandro-berti
fit-alessandro-berti committed Jan 22, 2024
2 parents bb99ed1 + 4cf8849 commit 31603fa
Show file tree
Hide file tree
Showing 5 changed files with 126 additions and 82 deletions.
2 changes: 1 addition & 1 deletion Dockerfile
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ RUN apt-get -y install libtool flex bison pkg-config g++ libssl-dev automake
RUN apt-get -y install libjemalloc-dev libboost-dev libboost-filesystem-dev libboost-system-dev libboost-regex-dev python3-dev autoconf flex bison cmake
RUN apt-get -y install libxml2-dev libxslt-dev libfreetype6-dev libsuitesparse-dev
RUN pip install -U wheel six pytest
RUN pip install colorama==0.4.6 contourpy==1.2.0 cycler==0.12.1 deprecation==2.1.0 fonttools==4.44.3 graphviz==0.20.1 intervaltree==3.1.0 kiwisolver==1.4.5 lxml==4.9.3 matplotlib==3.8.2 networkx==3.2.1 numpy==1.26.2 packaging==23.2 pandas==2.1.3 Pillow==10.1.0 pydotplus==2.0.2 pyparsing==3.1.1 python-dateutil==2.8.2 pytz==2023.3.post1 scipy==1.11.4 six==1.16.0 sortedcontainers==2.4.0 StringDist==1.0.9 tqdm==4.66.1 tzdata==2023.3
RUN pip install colorama==0.4.6 contourpy==1.2.0 cycler==0.12.1 deprecation==2.1.0 fonttools==4.47.2 graphviz==0.20.1 intervaltree==3.1.0 kiwisolver==1.4.5 lxml==5.1.0 matplotlib==3.8.2 networkx==3.2.1 numpy==1.26.3 packaging==23.2 pandas==2.2.0 pillow==10.2.0 pydotplus==2.0.2 pyparsing==3.1.1 python-dateutil==2.8.2 pytz==2023.3.post1 scipy==1.12.0 six==1.16.0 sortedcontainers==2.4.0 StringDist==1.0.9 tqdm==4.66.1 tzdata==2023.4

COPY . /app
RUN cd /app && python setup.py install
180 changes: 112 additions & 68 deletions pm4py/algo/conformance/tokenreplay/variants/token_replay.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -912,6 +912,42 @@ def get_variant_from_trace(trace, activity_key, disable_variants=False):
return variants_util.get_variant_from_trace(trace, parameters=parameters)


def transcribe_result(t, return_object_names=True):
corr_value = {"trace_is_fit": copy(t.t_fit),
"trace_fitness": float(copy(t.t_value)),
"activated_transitions": copy(t.act_trans),
"reached_marking": copy(t.reached_marking),
"enabled_transitions_in_marking": copy(
t.enabled_trans_in_mark),
"transitions_with_problems": copy(
t.trans_probl),
"missing_tokens": int(t.missing),
"consumed_tokens": int(t.consumed),
"remaining_tokens": int(t.remaining),
"produced_tokens": int(t.produced)}

if return_object_names:
corr_value["activated_transitions_labels"] = [x.label for x in
corr_value[
"activated_transitions"]]
corr_value["activated_transitions"] = [x.name for x in corr_value[
"activated_transitions"]]
corr_value["enabled_transitions_in_marking_labels"] = [x.label for x in
corr_value[
"enabled_transitions_in_marking"]]
corr_value["enabled_transitions_in_marking"] = [x.name for x in
corr_value[
"enabled_transitions_in_marking"]]
corr_value["transitions_with_problems"] = [x.name for x in
corr_value[
"transitions_with_problems"]]
corr_value["reached_marking"] = {x.name: y for x, y in
corr_value[
"reached_marking"].items()}

return corr_value


def apply_log(log, net, initial_marking, final_marking, enable_pltr_fitness=False, consider_remaining_in_fitness=False,
activity_key="concept:name", reach_mark_through_hidden=True, stop_immediately_unfit=False,
walk_through_hidden_trans=True, places_shortest_path_by_hidden=None,
Expand Down Expand Up @@ -987,86 +1023,94 @@ def apply_log(log, net, initial_marking, final_marking, enable_pltr_fitness=Fals
trans_map[t.label] = t

if pandas_utils.check_is_pandas_dataframe(log):
traces = [tuple(x) for x in log.groupby(case_id_key)[activity_key].agg(list).to_dict().values()]
traces = [(tuple(x), y) for y, x in log.groupby(case_id_key)[activity_key].agg(list).to_dict().items()]
traces = [(traces[i][0], i) for i in range(len(traces))]
else:
traces = [tuple(x[activity_key] for x in trace) for trace in log]
traces = [(tuple(x[activity_key] for x in log[i]), i) for i in range(len(log))]

variants = dict()
for t in traces:
if t[0] not in variants:
variants[t[0]] = list()
variants[t[0]].append(t[1])

variants = Counter(traces)
traces = [t[0] for t in traces]

vc = [(k, v) for k, v in variants.items()]
vc = list(sorted(vc, key=lambda x: (x[1], x[0]), reverse=True))
vc = list(sorted(vc, key=lambda x: (len(x[1]), x[0]), reverse=True))

threads_results = {}

progress = None

if importlib.util.find_spec("tqdm") and show_progress_bar and len(variants) > 1:
from tqdm.auto import tqdm
progress = tqdm(total=len(variants), desc="replaying log with TBR, completed variants :: ")

threads = {}
threads_results = {}
if disable_variants and not pandas_utils.check_is_pandas_dataframe(log):
progress = tqdm(total=len(traces), desc="replaying log with TBR, completed traces :: ")
else:
progress = tqdm(total=len(variants), desc="replaying log with TBR, completed traces :: ")

for i in range(len(vc)):
variant = vc[i][0]
considered_case = variants_util.variant_to_trace(variant, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key})

threads[variant] = ApplyTraceTokenReplay(considered_case, net, initial_marking, final_marking,
trans_map, enable_pltr_fitness, place_fitness_per_trace,
transition_fitness_per_trace,
notexisting_activities_in_model,
places_shortest_path_by_hidden,
consider_remaining_in_fitness,
activity_key=activity_key,
reach_mark_through_hidden=reach_mark_through_hidden,
stop_immediately_when_unfit=stop_immediately_unfit,
walk_through_hidden_trans=walk_through_hidden_trans,
post_fix_caching=post_fix_cache,
marking_to_activity_caching=marking_to_activity_cache,
is_reduction=is_reduction,
thread_maximum_ex_time=thread_maximum_ex_time,
cleaning_token_flood=cleaning_token_flood,
s_components=s_components, trace_occurrences=vc[i][1],
consider_activities_not_in_model_in_fitness=consider_activities_not_in_model_in_fitness)
threads[variant].run()
if progress is not None:
progress.update()

t = threads[variant]
threads_results[variant] = {"trace_is_fit": copy(t.t_fit),
"trace_fitness": float(copy(t.t_value)),
"activated_transitions": copy(t.act_trans),
"reached_marking": copy(t.reached_marking),
"enabled_transitions_in_marking": copy(
t.enabled_trans_in_mark),
"transitions_with_problems": copy(
t.trans_probl),
"missing_tokens": int(t.missing),
"consumed_tokens": int(t.consumed),
"remaining_tokens": int(t.remaining),
"produced_tokens": int(t.produced)}

if return_object_names:
threads_results[variant]["activated_transitions_labels"] = [x.label for x in
threads_results[variant][
"activated_transitions"]]
threads_results[variant]["activated_transitions"] = [x.name for x in threads_results[variant][
"activated_transitions"]]
threads_results[variant]["enabled_transitions_in_marking_labels"] = [x.label for x in
threads_results[variant][
"enabled_transitions_in_marking"]]
threads_results[variant]["enabled_transitions_in_marking"] = [x.name for x in
threads_results[variant][
"enabled_transitions_in_marking"]]
threads_results[variant]["transitions_with_problems"] = [x.name for x in
threads_results[variant][
"transitions_with_problems"]]
threads_results[variant]["reached_marking"] = {x.name: y for x, y in
threads_results[variant][
"reached_marking"].items()}
del threads[variant]

for trace_variant in traces:
if trace_variant in threads_results:
t = threads_results[trace_variant]
aligned_traces.append(t)
all_cases = vc[i][1]

if disable_variants and not pandas_utils.check_is_pandas_dataframe(log):
for j in range(len(all_cases)):
case_position = all_cases[j]
considered_case = log[case_position]
t = ApplyTraceTokenReplay(considered_case, net, initial_marking, final_marking,
trans_map, enable_pltr_fitness, place_fitness_per_trace,
transition_fitness_per_trace,
notexisting_activities_in_model,
places_shortest_path_by_hidden,
consider_remaining_in_fitness,
activity_key=activity_key,
reach_mark_through_hidden=reach_mark_through_hidden,
stop_immediately_when_unfit=stop_immediately_unfit,
walk_through_hidden_trans=walk_through_hidden_trans,
post_fix_caching=post_fix_cache,
marking_to_activity_caching=marking_to_activity_cache,
is_reduction=is_reduction,
thread_maximum_ex_time=thread_maximum_ex_time,
cleaning_token_flood=cleaning_token_flood,
s_components=s_components, trace_occurrences=1,
consider_activities_not_in_model_in_fitness=consider_activities_not_in_model_in_fitness)
t.run()
threads_results[case_position] = transcribe_result(t, return_object_names=return_object_names)
if progress is not None:
progress.update()
else:
considered_case = variants_util.variant_to_trace(variant, parameters={constants.PARAMETER_CONSTANT_ACTIVITY_KEY: activity_key})
t = ApplyTraceTokenReplay(considered_case, net, initial_marking, final_marking,
trans_map, enable_pltr_fitness, place_fitness_per_trace,
transition_fitness_per_trace,
notexisting_activities_in_model,
places_shortest_path_by_hidden,
consider_remaining_in_fitness,
activity_key=activity_key,
reach_mark_through_hidden=reach_mark_through_hidden,
stop_immediately_when_unfit=stop_immediately_unfit,
walk_through_hidden_trans=walk_through_hidden_trans,
post_fix_caching=post_fix_cache,
marking_to_activity_caching=marking_to_activity_cache,
is_reduction=is_reduction,
thread_maximum_ex_time=thread_maximum_ex_time,
cleaning_token_flood=cleaning_token_flood,
s_components=s_components, trace_occurrences=len(vc[i][1]),
consider_activities_not_in_model_in_fitness=consider_activities_not_in_model_in_fitness)
t.run()

for j in range(len(all_cases)):
case_position = all_cases[j]

threads_results[case_position] = transcribe_result(t, return_object_names=return_object_names)

if progress is not None:
progress.update()

for i in range(len(traces)):
aligned_traces.append(threads_results[i])

# gracefully close progress bar
if progress is not None:
Expand Down
2 changes: 1 addition & 1 deletion requirements_complete.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ networkx
numpy
packaging
pandas
Pillow
pillow
pydotplus
pyparsing
python-dateutil
Expand Down
6 changes: 3 additions & 3 deletions requirements_stable.txt
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,13 @@ matplotlib==3.8.2
networkx==3.2.1
numpy==1.26.3
packaging==23.2
pandas==2.1.4
Pillow==10.2.0
pandas==2.2.0
pillow==10.2.0
pydotplus==2.0.2
pyparsing==3.1.1
python-dateutil==2.8.2
pytz==2023.3.post1
scipy==1.11.4
scipy==1.12.0
six==1.16.0
sortedcontainers==2.4.0
StringDist==1.0.9
Expand Down
18 changes: 9 additions & 9 deletions third_party/LICENSES_TRANSITIVE.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -5,29 +5,29 @@ PM4Py depends upon. This is a best effort attempt to describe the library's depe
libraries are added/removed.

| Name | URL | License | Version |
| --------------------------- | ------------------------------------------------------------ | ---------------------- | ------------------- |
| --------------------------- | ------------------------------------------------------------ | ----------- | ------------------- |
| colorama | https://pypi.org/project/colorama | BSD License | 0.4.6 |
| contourpy | https://pypi.org/project/contourpy | BSD License | 1.2.0 |
| cycler | https://pypi.org/project/cycler | BSD License | 0.12.1 |
| deprecation | https://pypi.org/project/deprecation | Apache Software License (Apache 2) | 2.1.0 |
| fonttools | https://pypi.org/project/fonttools | MIT License (MIT) | 4.44.3 |
| fonttools | https://pypi.org/project/fonttools | MIT License (MIT) | 4.47.2 |
| graphviz | https://pypi.org/project/graphviz | MIT License (MIT) | 0.20.1 |
| intervaltree | https://pypi.org/project/intervaltree | Apache Software License (Apache License, Version 2.0) | 3.1.0 |
| intervaltree | https://pypi.org/project/intervaltree | Apache Software License | 3.1.0 |
| kiwisolver | https://pypi.org/project/kiwisolver | BSD License | 1.4.5 |
| lxml | https://pypi.org/project/lxml | BSD License (BSD-3-Clause) | 4.9.3 |
| lxml | https://pypi.org/project/lxml | BSD License (BSD-3-Clause) | 5.1.0 |
| matplotlib | https://pypi.org/project/matplotlib | Python Software Foundation License (PSF) | 3.8.2 |
| networkx | https://pypi.org/project/networkx | BSD License | 3.2.1 |
| numpy | https://pypi.org/project/numpy | BSD License | 1.26.2 |
| numpy | https://pypi.org/project/numpy | BSD License | 1.26.3 |
| packaging | https://pypi.org/project/packaging | Apache Software License, BSD License | 23.2 |
| pandas | https://pypi.org/project/pandas | BSD License | 2.1.3 |
| Pillow | https://pypi.org/project/Pillow | Historical Permission Notice and Disclaimer (HPND) (HPND) | 10.1.0 |
| pandas | https://pypi.org/project/pandas | BSD License | 2.2.0 |
| pillow | https://pypi.org/project/pillow | Historical Permission Notice and Disclaimer (HPND) (HPND) | 10.2.0 |
| pydotplus | https://pypi.org/project/pydotplus | MIT License (UNKNOWN) | 2.0.2 |
| pyparsing | https://pypi.org/project/pyparsing | MIT License | 3.1.1 |
| python-dateutil | https://pypi.org/project/python-dateutil | Apache Software License, BSD License (Dual License) | 2.8.2 |
| pytz | https://pypi.org/project/pytz | MIT License (MIT) | 2023.3.post1 |
| scipy | https://pypi.org/project/scipy | BSD License | 1.11.4 |
| scipy | https://pypi.org/project/scipy | BSD License | 1.12.0 |
| six | https://pypi.org/project/six | MIT License (MIT) | 1.16.0 |
| sortedcontainers | https://pypi.org/project/sortedcontainers | Apache Software License (Apache 2.0) | 2.4.0 |
| StringDist | https://pypi.org/project/StringDist | MIT License (MIT) | 1.0.9 |
| tqdm | https://pypi.org/project/tqdm | MIT License, Mozilla Public License 2.0 (MPL 2.0) (MPL-2.0 AND MIT) | 4.66.1 |
| tzdata | https://pypi.org/project/tzdata | Apache Software License (Apache-2.0) | 2023.3 |
| tzdata | https://pypi.org/project/tzdata | Apache Software License (Apache-2.0) | 2023.4 |

0 comments on commit 31603fa

Please sign in to comment.