Commit 258fa6b2 authored by Jaime Arias's avatar Jaime Arias
Browse files

update timeout

parent bdc02871
%% Cell type:code id: tags:
``` python
import os
import pandas as pd
import plotly.io as pio
import plotly.express as px
import plotly.graph_objs as go
from itertools import combinations
from plotly.subplots import make_subplots
import plotly.io as pio
# render figures in notebook
pio.renderers.default = "notebook_connected"
# templates figures
px.defaults.template = "simple_white"
pio.templates.default = "simple_white"
# layout for all figures
LAYOUT_FIGURES = dict(
autosize=False,
width = 500,
height = 500,
xaxis = dict(
constrain="domain",
mirror=True,
showexponent="all",
exponentformat="power"
),
yaxis = dict(
scaleanchor = "x",
scaleratio = 1,
mirror=True,
showexponent="all",
exponentformat="power"
),
title = dict(
y = 0.9,
x = 0.5,
xanchor = 'center',
yanchor = 'top'
)
)
```
%% Cell type:markdown id: tags:
# Auxiliary Functions
%% Cell type:code id: tags:
``` python
def create_folder(path):
"""Creates a folder if it does not exist
Parameters
----------
path : str
Path of the new folder
Examples
--------
>>> create_folder('./results')
"""
if not os.path.exists(path):
os.makedirs(path)
```
%% Cell type:code id: tags:
``` python
def create_figure(df, model):
"""Creates a scatter figure showing the time taken by each tool to verify each property of a model
Parameters
----------
df : pandas.Dataframe
Dataframe containing the results of the experiments
model : string
model to be plotted
Returns
-------
plotly.graph_objects.Figure
Scatter figure
Examples
--------
>>> import os
>>> import pandas as pd
>>> csv_file = os.path.join("results", "output.csv")
>>> df = pd.read_csv(csv_file)
>>> fig = create_figure(df, 'philo10')
"""
model_df = df[df.model == model]
figure = px.scatter(model_df,
x="formula", y="time",
title=model,
color="tool",
symbol_sequence=['x'])
figure.update_layout(yaxis_title="time (s)", title=LAYOUT_FIGURES['title'])
return figure
```
%% Cell type:code id: tags:
``` python
def get_axis_title(experiment, show_strategy=True):
"""Get the axis title of a figure depending on the experiment being plotted
Parameters
----------
experiment : str
String with the experiment information
show_strategy : bool, optional
Flag to show the information related to the strategy used by the tool
Returns
-------
str
axis title
Examples
--------
>>> get_axis_title('pmc-sog_otfL_couv99-default_1_1', True)
pmc-sog (Lace, strategy: couv99-default, # cores: 1)
"""
information = experiment.split('_')
tool_name = information[0]
info = []
if (len(information) == 5):
library = 'Lace' if (information[1] == 'otfL') else 'Pthreads'
info.append(library)
if (show_strategy):
info.append('strategy: {}'.format(information[-3]))
nb_nodes = int(information[-2])
if (nb_nodes > 1):
info.append('# nodes: {}'.format(nb_nodes))
info.append('# cores: {}'.format(information[-1]))
title = '{} ({})'.format(tool_name, ', '.join(info))
return title
```
%% Cell type:code id: tags:
``` python
def create_log_figure(table, table_errors, model, tool_x, tool_y, show_strategy=True):
"""Creates a Scatter figure in logarithmic scale comparing the performance of two tools
Parameters
----------
table : pandas.Dataframe
Dataframe with the times of each experiment
table_errors : pandas.Dataframe
Dataframe with the errors of each experiment
model : string
Model to be analyzed
tool_x : string
Tool to be compared and plotted on the x-axis
tool_y : string
Tool to be compared and plotted on the y-axis
show_strategy : bool
Flag to show the stretagy used by the tools
Returns
-------
plotly.graph_objects.Figure
Scatter figure
Examples
--------
>>> import os
>>> import pandas as pd
>>> csv_file = os.path.join("results", "output.csv")
>>> df = pd.read_csv(csv_file)
>>> table = df.set_index(['model', 'formula', 'tool'], drop=True).unstack('tool')
>>> fig = create_log_figure(table['time'], table['error'], 'philo10', 'pmc-sog_otfL_couv99-default_1_8', 'pmc-sog_otfP_couv99-default_1_8')
"""
try:
min_values = table.loc[model].min()
max_values = table.loc[model].max()
min_value = min(min_values[tool_x], min_values[tool_y])/2.
max_value = max(max_values[tool_x], max_values[tool_y])
figure = px.scatter(table.loc[model],
title=model,
x=tool_x, y=tool_y,
log_x=True, log_y=True,
range_x=[min_value, max_value],
range_y=[min_value, max_value],
color="property",
hover_data=[
['formula #{}'.format(i) for i in table.loc[model].index],
table_errors.loc[model, tool_x],
table_errors.loc[model, tool_y]
],
color_discrete_map={"T": "green", "F": "red", "U": "black"},
symbol_sequence=["circle-open"])
line = go.Scatter(x=[min_value, max_value],
y=[min_value, max_value],
mode='lines', showlegend=False,
line=dict(color='black', width=1))
figure.add_traces(line)
figure.update_layout(LAYOUT_FIGURES,
xaxis_title=get_axis_title(tool_x, show_strategy),
yaxis_title=get_axis_title(tool_y, show_strategy))
return figure
except Exception as e:
print("Error when ploting model: {} - tool_x: {} - tool_y: {}".format(model, tool_x, tool_y))
print(e)
```
%% Cell type:code id: tags:
``` python
# Experiment filters
def versus_dfs(experiments):
"""Selects only experiments using DFS strategy"""
exp1, exp2 = experiments
strategy_exp1= exp1.split('_')[1]
strategy_exp2= exp2.split('_')[1]
return strategy_exp1 == 'dfs' or strategy_exp2 == 'dfs'
def versus_sequential(experiments):
"""Selects only experiments run sequentially """
exp1, exp2 = experiments
nodes_exp1, threads_exp1 = exp1.split('_')[-2:]
nodes_exp2, threads_exp2 = exp2.split('_')[-2:]
return (nodes_exp1 == '1' and nodes_exp2 == '1') and \
(threads_exp1 == '1' or threads_exp2 == '1')
def same_tool(experiments, tool):
"""Selects only experiments comparing the same tool"""
exp1, exp2 = experiments
tool_exp1= exp1.split('_')[0]
tool_exp2= exp2.split('_')[0]
return tool_exp1.startswith(tool) and tool_exp2.startswith(tool)
def same_number_threads(experiments):
"""Selects only experiments comparing the same number of processes and cores"""
exp1, exp2 = experiments
nodes_exp1, threads_exp1 = exp1.split('_')[-2:]
nodes_exp2, threads_exp2 = exp2.split('_')[-2:]
return (nodes_exp1 == nodes_exp2) and (threads_exp1 == threads_exp2)
def same_thread_library(experiments):
"""Selects only experiments comparing the same parallelization library"""
exp1, exp2 = experiments
library_exp1 = exp1.split('_')[1]
library_exp2 = exp2.split('_')[1]
return library_exp1 == library_exp2
def same_strategy(experiments):
"""Selects only experiments comparing the same strategy"""
exp1, exp2 = experiments
strategy_exp1 = exp1.split('_')[2]
strategy_exp2 = exp2.split('_')[2]
return strategy_exp1 == strategy_exp2
def only_couvreur_strategy(experiments):
"""Selects only experiments comparing couvreur emptiness check algorithm"""
exp1, exp2 = experiments
strategy_exp1 = exp1.split('_')[2]
strategy_exp2 = exp2.split('_')[2]
return strategy_exp1.startswith('couv99') and strategy_exp2.startswith('couv99')
def compare_threads_library(experiments):
"""Compares parallization libraries used in pmc-sog.
It selects experiments where the tool is only pmc-sog and the strategy, number of threads,
number of processus are the same.
"""
return same_tool(experiments, 'pmc-sog') and \
same_strategy(experiments) and \
same_number_threads(experiments) and \
not same_thread_library(experiments)
def compare_couvreur_strategies(experiments):
"""Compares couvreurs strategies used in pmc-sog.
It selects experiments where the tool is only pmc-sog, the strategy is couvreur, and
the parallelization library, number of threads, number of processus are the same.
"""
return only_couvreur_strategy(experiments) and \
same_thread_library(experiments) and \
same_number_threads(experiments)
def compare_tools(experiments):
"""Compares pmc-sog and pnml2lts-mc using the DFS algorithm.
It selects experiments where the tools are not the same, the exploration algorithm is DFS and
the number of processus and cores are the same.
"""
return same_number_threads(experiments) and \
not (same_tool(experiments, 'pmc-sog') or same_tool(experiments,'pnml2lts-mc')) and \
versus_dfs(experiments)
def compare_multithreading(experiments):
"""Compares the sequential and multi-core version of pmc-sog.
It selects experiments where the tools is pmc-sog, the parallelization library, the emptiness check
strategy are the same. Here the number of processus and cores are different.
"""
return same_tool(experiments, 'pmc-sog') and \
same_thread_library(experiments) and \
same_strategy(experiments) and \
versus_sequential(experiments)
# Plots to be created
plots = {
'compare_thread_library': compare_threads_library,
'compare_couvreur_algorithm': compare_couvreur_strategies,
'compare_tools': compare_tools,
'compare_multicore': compare_multithreading
}
```
%% Cell type:markdown id: tags:
# Load Data
%% Cell type:code id: tags:
``` python
# Root folder
PROJECT_FOLDER = os.path.abspath(os.pardir)
# csv file with the output
csv_file = os.path.join(PROJECT_FOLDER, "results", "output.csv")
# Output folder
OUTPUT_FOLDER = os.path.join(PROJECT_FOLDER,"results", "figures")
create_folder(OUTPUT_FOLDER)
```
%% Cell type:code id: tags:
``` python
# read data
df = pd.read_csv(csv_file)
# merge the information related to the experiment (# nodes, # threads, strategy) to the tool column
df['tool'] = df[['tool', 'strategy', 'num_nodes', 'num_threads']].astype(str).apply('_'.join, axis=1)
df = df.drop(columns=['strategy', 'num_nodes', 'num_threads'])
df.head()
```
%%%% Output: execute_result
model formula tool time property error
0 philo10 1 pmc-sog_otfL_couv99-default_1_1 59.017 F OK
1 philo10 1 pmc-sog_otfL_couv99-default_1_8 11.856 F OK
2 philo10 1 pmc-sog_otfL_couv99-default_1_12 8.421 F OK
3 philo10 1 pmc-sog_otfL_couv99-default_1_16 6.552 F OK
4 philo10 1 pmc-sog_otfL_couv99-default_1_20 5.413 F OK
%% Cell type:code id: tags:
``` python
# ground truth for properties
p_df = pd.read_csv(csv_file)
p_df =p_df[
(p_df.tool=='pnml2lts-mc') &
(p_df.strategy == 'ndfs') &
(p_df.num_nodes == 1) &
(p_df.num_threads == 1)]
# only property column is needed
p_df = p_df.drop(columns=['tool', 'strategy', 'num_nodes', 'num_threads', 'time', 'error'])
p_df.fillna('U', inplace=True)
p_df.set_index(['model', 'formula'], inplace=True)
p_df.sort_index(inplace=True)
p_df.head()
```
%%%% Output: execute_result
property
model formula
philo10 1 F
2 F
3 F
4 F
5 F
%% Cell type:code id: tags:
``` python
# table with times, verification output and error for each experiment
table = df.set_index(['model', 'formula', 'tool'], drop=True).unstack('tool')
table.head()
```
%%%% Output: execute_result
time \
tool pmc-sog_otfL_couv99-default_1_1
model formula
philo10 1 59.017
2 25.394
3 NaN
4 NaN
5 34.287
\
tool pmc-sog_otfL_couv99-default_1_12
model formula
philo10 1 8.421
2 4.064
3 NaN
4 NaN
5 5.484
\
tool pmc-sog_otfL_couv99-default_1_16
model formula
philo10 1 6.552
2 3.134
3 NaN
4 NaN
5 4.257
\
tool pmc-sog_otfL_couv99-default_1_20
model formula
philo10 1 5.413
2 2.586
3 NaN
4 NaN
5 3.541
\
tool pmc-sog_otfL_couv99-default_1_8 pmc-sog_otfL_couv99-shy_1_1
model formula
philo10 1 11.856 46.157
2 5.639 41.311
3 NaN NaN
4 NaN NaN
5 7.612 55.165
\
tool pmc-sog_otfL_couv99-shy_1_12 pmc-sog_otfL_couv99-shy_1_16
model formula
philo10 1 7.477 5.732
2 6.367 5.006
3 NaN NaN
4 NaN NaN
5 9.004 6.980
... \
tool pmc-sog_otfL_couv99-shy_1_20 pmc-sog_otfL_couv99-shy_1_8 ...
model formula ...
philo10 1 4.728 10.394 ...
2 4.125 8.907 ...
3 NaN NaN ...
4 NaN NaN ...
5 5.767 12.671 ...
error \
tool pnml2lts-mc_dfs_1_16 pnml2lts-mc_dfs_1_20
model formula
philo10 1 OK OK
2 OK OK
3 OK OK
4 OK OK
5 OK OK
\
tool pnml2lts-mc_dfs_1_40 pnml2lts-mc_dfs_1_8 pnml2lts-mc_ndfs_1_1
model formula
philo10 1 NaN OK OK
2 NaN OK OK
3 NaN OK OK
4 NaN OK OK
5 NaN OK OK
\
tool pnml2lts-mc_ndfs_1_12 pnml2lts-mc_ndfs_1_16
model formula
philo10 1 OK OK
2 OK OK
3 OK OK
4 OK OK
5 OK OK
\
tool pnml2lts-mc_ndfs_1_20 pnml2lts-mc_ndfs_1_40
model formula
philo10 1 OK NaN
2 OK NaN
3 OK NaN
4 OK NaN
5 OK NaN
tool pnml2lts-mc_ndfs_1_8
model formula
philo10 1 OK
2 OK
3 OK
4 OK
5 OK
[5 rows x 144 columns]
%% Cell type:markdown id: tags:
# Preprocessing of data
%% Cell type:code id: tags:
``` python
ZERO = 10e-5
TIMEOUT = 3 * 60 # 3 minutes = 180 seconds
TIMEOUT = 5 * 60 # 5 minutes = 300 seconds
```
%% Cell type:code id: tags:
``` python
# table with times for each experiment
table_time = table['time'].copy()
# replace non finished experiments with a dummy value, e.g. timeout
table_time.fillna(TIMEOUT, inplace=True)
# replace 0.00 time for 10^(-5), we cannot plot log(0)
table_time.replace(0.0, ZERO, inplace=True)
# add verification output to the table
table_time = pd.concat([table_time, p_df], axis=1)
table_time.head()
```
%%%% Output: execute_result
pmc-sog_otfL_couv99-default_1_1 \
model formula
philo10 1 59.017
2 25.394
3 180.000
4 180.000
5 34.287
pmc-sog_otfL_couv99-default_1_12 \
model formula
philo10 1 8.421
2 4.064
3 180.000
4 180.000
5 5.484
pmc-sog_otfL_couv99-default_1_16 \
model formula
philo10 1 6.552
2 3.134
3 180.000
4 180.000
5 4.257
pmc-sog_otfL_couv99-default_1_20 \
model formula
philo10 1 5.413
2 2.586
3 180.000
4 180.000
5 3.541
pmc-sog_otfL_couv99-default_1_8 pmc-sog_otfL_couv99-shy_1_1 \
model formula
philo10 1 11.856 46.157
2 5.639 41.311
3 180.000 180.000
4 180.000 180.000
5 7.612 55.165
pmc-sog_otfL_couv99-shy_1_12 pmc-sog_otfL_couv99-shy_1_16 \
model formula
philo10 1 7.477 5.732
2 6.367 5.006
3 180.000 180.000
4 180.000 180.000
5 9.004 6.980
pmc-sog_otfL_couv99-shy_1_20 pmc-sog_otfL_couv99-shy_1_8 \
model formula
philo10 1 4.728 10.394
2 4.125 8.907
3 180.000 180.000
4 180.000 180.000
5 5.767 12.671
... pnml2lts-mc_dfs_1_20 pnml2lts-mc_dfs_1_40 \
model formula ...
philo10 1 ... 0.78 180.0
2 ... 0.63 180.0
3 ... 1.24 180.0
4 ... 0.72 180.0
5 ... 0.72 180.0
pnml2lts-mc_dfs_1_8 pnml2lts-mc_ndfs_1_1 \
model formula
philo10 1 1.39 0.29
2 1.09 0.20
3 2.56 0.63
4 1.26 0.47
5 1.30 0.14
pnml2lts-mc_ndfs_1_12 pnml2lts-mc_ndfs_1_16 \
model formula
philo10 1 0.13 0.12
2 0.09 0.09
3 0.12 0.10
4 0.10 0.14
5 0.06 0.07