plot-results.py 14.9 KB
Newer Older
1
2
3
#!/usr/bin/env python
# coding: utf-8

4
# In[2]:
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51


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'
    )
)


# # Auxiliary Functions

52
# In[3]:
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71


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)


72
# In[4]:
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110


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


111
# In[21]:
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141


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 = []
    library_dic = {
        'otfL': 'Lace',
        'otfP': 'Pthreads',
142
143
        'otfC': 'Cthreads',
        'otf': 'Hybrid'
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
    }
    
    if (len(information) == 5):
        info.append(library_dic[information[1]])

    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


163
# In[22]:
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235


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)


236
# In[31]:
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307


# 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)

308
309
310
311
312
313
314
def same_distributed_number_threads(experiments):
    """Selects only experiments where the multiplication of theirs nodes with cores are the same."""
    exp1, exp2 = experiments
    nodes_exp1, threads_exp1 = exp1.split('_')[-2:]
    nodes_exp2, threads_exp2 = exp2.split('_')[-2:]
    return (int(nodes_exp1) * int(threads_exp1)) == (int(nodes_exp2) * int(threads_exp2))

315
316
317
318
319
320
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.
    """
321
    return same_distributed_number_threads(experiments) and             not (same_tool(experiments, 'pmc-sog') or same_tool(experiments,'pnml2lts-mc')) and             versus_dfs(experiments)
322
323
324
325
326
327
328
329
330

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)

331
332
333
334
335
336
337
338
def against_hybrid(experiments):
    """Selects only experiments comparing with hybrid mode"""
    exp1, exp2 = experiments
    library_exp1 = exp1.split('_')[1]
    library_exp2 = exp2.split('_')[1]
    return (library_exp1 == 'otf') or (library_exp2 == 'otf')


339
340
def compare_distributed(experiments):
    """Compares the hybrid version of pmc-sog"""
341
    return same_tool(experiments, 'pmc-sog') and         same_strategy(experiments) and         same_distributed_number_threads(experiments) and         against_hybrid(experiments)
342

343
344
345
346
347
# Plots to be created
plots = {
    'compare_thread_library': compare_threads_library,
    'compare_couvreur_algorithm': compare_couvreur_strategies,
    'compare_tools': compare_tools,
348
349
    'compare_multicore': compare_multithreading,
    'compare_distributed': compare_distributed
350
351
352
353
354
}


# # Load Data

355
# In[8]:
356
357
358
359
360
361
362
363
364
365
366
367
368


# 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)


369
# In[9]:
370
371
372
373
374
375
376
377
378
379
380
381


# 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()


382
# In[10]:
383
384
385
386
387
388
389
390


# 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) & 
391
    (p_df.num_threads == 16)]
392
393
394
395
396
397
398
399
400
401

# 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()


402
# In[11]:
403
404
405
406
407
408
409
410
411


# table with times, verification output and error for each experiment
table = df.set_index(['model', 'formula', 'tool'], drop=True).unstack('tool')
table.head()


# # Preprocessing of data

412
# In[12]:
413
414
415
416
417
418


ZERO = 10e-5
TIMEOUT = 10 * 60 # 5 minutes = 300 seconds


419
# In[13]:
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436


# 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()


437
# In[14]:
438
439
440
441
442
443
444
445
446
447
448
449
450
451


# table with verification output for each experiment
table_property = table['property'].copy()

# replace non finished experiments with a dummy value
table_property.fillna('U', inplace=True)

# add ground truth to the table
table_property = pd.concat([table_property, p_df], axis=1)

table_property.head()


452
# In[15]:
453
454
455
456
457
458
459
460
461
462


# table with error for each experiment
table_error = table['error'].copy()

table_error.head()


# # Examples

463
# In[19]:
464
465


466
fig = create_figure(df, "philo10")
467
468
469
fig.show()


470
# In[23]:
471
472


473
fig = create_log_figure(table_time, table_error, "philo10", "pmc-sog_otf_couv99-default_2_8", "pnml2lts-mc_dfs_1_16")
474
475
476
477
478
fig.show()


# # Generate Figures

479
# In[24]:
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507


# models
models = df.model.unique()

# tools 
tools = df.tool.unique()


# In[52]:


# create all the figures formula vs time

folder = os.path.join(OUTPUT_FOLDER, 'time-plots')
create_folder(folder)

for model in models:
    try:
        fig = create_figure(df, model)
        
        # save figures in html and pdf
        fig.write_html(os.path.join(folder, model + '.html'))
        fig.write_image(os.path.join(folder, model + '.pdf'))
    except KeyError:
        print("Error: {} was not plotted".format(model))


Jaime Arias's avatar
Jaime Arias committed
508
# In[ ]:
509
510
511
512


# create all the log figures

Jaime Arias's avatar
Jaime Arias committed
513
tools_pairs = [sorted(t) for t in (combinations(tools, 2))]
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539

for plot, filter_method in plots.items():
    axes = list(filter(filter_method, tools_pairs))
    
    for model in models:
        folder = os.path.join(OUTPUT_FOLDER, plot, model)
        create_folder(folder)
        
        for axe in axes:
            try:
                show_strategy = plot == 'compare_couvreur_algorithm'
                fig = create_log_figure(table_time, table_error, model, axe[0], axe[1], show_strategy)
                
                # save figures in html and pdf
                figure_name = os.path.join(folder, '{}-{}-VS-{}-log'.format(model, axe[0], axe[1]))
                fig.write_html(figure_name + '.html')
                fig.write_image(figure_name + '.pdf')
            except KeyError:
                print("Error: {} was not plotted".format(model))


# In[ ]: