File size: 12,833 Bytes
e60e568
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
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
111
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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
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
236
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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
'''
    This file is part of PM4Py (More Info: https://pm4py.fit.fraunhofer.de).

    PM4Py is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
    the Free Software Foundation, either version 3 of the License, or
    (at your option) any later version.

    PM4Py is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
    GNU General Public License for more details.

    You should have received a copy of the GNU General Public License
    along with PM4Py.  If not, see <https://www.gnu.org/licenses/>.
'''
from pm4py.objects.log.util import xes
from pm4py.algo.discovery.log_skeleton import trace_skel
from pm4py.util import xes_constants
from pm4py.util import variants_util, pandas_utils
from pm4py.util import exec_utils
from typing import Optional, Dict, Any, Union, List, Set
from pm4py.objects.log.obj import EventLog, Trace
import pandas as pd

from enum import Enum
from pm4py.util.constants import PARAMETER_CONSTANT_ACTIVITY_KEY, PARAMETER_CONSTANT_CASEID_KEY, CASE_CONCEPT_NAME


class Parameters(Enum):
    # parameter for the noise threshold
    NOISE_THRESHOLD = "noise_threshold"
    # considered constraints in conformance checking among: equivalence, always_after, always_before, never_together, directly_follows, activ_freq
    CONSIDERED_CONSTRAINTS = "considered_constraints"
    # default choice for conformance checking
    DEFAULT_CONSIDERED_CONSTRAINTS = ["equivalence", "always_after", "always_before", "never_together",
                                      "directly_follows", "activ_freq"]
    CASE_ID_KEY = PARAMETER_CONSTANT_CASEID_KEY
    ACTIVITY_KEY = PARAMETER_CONSTANT_ACTIVITY_KEY
    PARAMETER_VARIANT_DELIMITER = "variant_delimiter"


NOISE_THRESHOLD = Parameters.NOISE_THRESHOLD
CONSIDERED_CONSTRAINTS = Parameters.CONSIDERED_CONSTRAINTS
DEFAULT_CONSIDERED_CONSTRAINTS = Parameters.DEFAULT_CONSIDERED_CONSTRAINTS
ACTIVITY_KEY = Parameters.ACTIVITY_KEY
PARAMETER_VARIANT_DELIMITER = Parameters.PARAMETER_VARIANT_DELIMITER


class DiscoveryOutputs(Enum):
    EQUIVALENCE = "equivalence"
    ALWAYS_AFTER = "always_after"
    ALWAYS_BEFORE = "always_before"
    NEVER_TOGETHER = "never_together"
    DIRECTLY_FOLLOWS = "directly_follows"
    ACTIV_FREQ = "activ_freq"


class Outputs(Enum):
    DEVIATIONS = "deviations"
    NO_DEV_TOTAL = "no_dev_total"
    NO_CONSTR_TOTAL = "no_constr_total"
    DEV_FITNESS = "dev_fitness"
    IS_FIT = "is_fit"


def apply_log(log: Union[EventLog, pd.DataFrame], model: Dict[str, Any], parameters: Optional[Dict[Union[str, Parameters], Any]] = None) -> List[Set[Any]]:
    """
    Apply log-skeleton based conformance checking given an event log
    and a log-skeleton model

    Parameters
    --------------
    log
        Event log
    model
        Log-skeleton model
    parameters
        Parameters of the algorithm, including:
        - Parameters.ACTIVITY_KEY
        - Parameters.CONSIDERED_CONSTRAINTS, among: equivalence, always_after, always_before, never_together, directly_follows, activ_freq

    Returns
    --------------
    aligned_traces
        Conformance checking results for each trace:
        - Outputs.IS_FIT => boolean that tells if the trace is perfectly fit according to the model
        - Outputs.DEV_FITNESS => deviation based fitness (between 0 and 1; the more the trace is near to 1 the more fit is)
        - Outputs.DEVIATIONS => list of deviations in the model
    """
    if parameters is None:
        parameters = {}

    activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes.DEFAULT_NAME_KEY)

    if pandas_utils.check_is_pandas_dataframe(log):
        case_id_key = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, CASE_CONCEPT_NAME)
        traces = [tuple(x) for x in log.groupby(case_id_key)[activity_key].agg(list).to_dict().values()]
    else:
        traces = [tuple(y[activity_key] for y in x) for x in log]
    grouped_traces = {}
    gtk = []
    inv_idxs = {}
    for i in range(len(traces)):
        tr = traces[i]
        if not tr in grouped_traces:
            grouped_traces[tr] = []
            gtk.append(tr)
        grouped_traces[tr].append(i)
        inv_idxs[i] = gtk.index(tr)

    res0 = []
    for trace in grouped_traces:
        res0.append(apply_actlist(trace, model, parameters=parameters))

    res = []
    for i in range(len(traces)):
        res.append(res0[inv_idxs[i]])

    return res


def apply_trace(trace: Trace, model: Dict[str, Any], parameters: Optional[Dict[Union[str, Parameters], Any]] = None) -> List[Set[Any]]:
    """
    Apply log-skeleton based conformance checking given a trace
    and a log-skeleton model

    Parameters
    --------------
    trace
        Trace
    model
        Log-skeleton model
    parameters
        Parameters of the algorithm, including:
        - the activity key (pm4py:param:activity_key)
        - the list of considered constraints (considered_constraints) among: equivalence, always_after, always_before, never_together, directly_follows, activ_freq

    Returns
    --------------
    aligned_trace
        Containing:
        - is_fit => boolean that tells if the trace is perfectly fit according to the model
        - dev_fitness => deviation based fitness (between 0 and 1; the more the trace is near to 1 the more fit is)
        - deviations => list of deviations in the model
    """
    if parameters is None:
        parameters = {}

    activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes.DEFAULT_NAME_KEY)
    trace = [x[activity_key] for x in trace]

    return apply_actlist(trace, model, parameters=parameters)


def apply_actlist(trace, model, parameters=None):
    """
    Apply log-skeleton based conformance checking given the list of activities of a trace
    and a log-skeleton model

    Parameters
    --------------
    trace
        List of activities of a trace
    model
        Log-skeleton model
    parameters
        Parameters of the algorithm, including:
        - the activity key (pm4py:param:activity_key)
        - the list of considered constraints (considered_constraints) among: equivalence, always_after, always_before, never_together, directly_follows, activ_freq

    Returns
    --------------
    aligned_trace
        Containing:
        - is_fit => boolean that tells if the trace is perfectly fit according to the model
        - dev_fitness => deviation based fitness (between 0 and 1; the more the trace is near to 1 the more fit is)
        - deviations => list of deviations in the model
    """
    if parameters is None:
        parameters = {}

    consid_constraints = exec_utils.get_param_value(Parameters.CONSIDERED_CONSTRAINTS, parameters, Parameters.DEFAULT_CONSIDERED_CONSTRAINTS.value)
    trace_info = trace_skel.get_trace_info(trace)

    ret = {}
    ret[Outputs.DEVIATIONS.value] = []
    dev_total = 0
    conf_total = 0

    default_considered_constraints = Parameters.DEFAULT_CONSIDERED_CONSTRAINTS.value

    i = 0
    while i < len(default_considered_constraints):
        if default_considered_constraints[i] in consid_constraints:
            if default_considered_constraints[i] == DiscoveryOutputs.ACTIV_FREQ.value:
                this_constraints = {x: y for x, y in model[default_considered_constraints[i]].items()}
                conf_total += len(list(act for act in trace_info[i] if act in this_constraints)) + len(list(act for act in trace_info[i] if act not in this_constraints)) + len(list(act for act in this_constraints if min(this_constraints[act]) > 0 and not act in trace))
                for act in trace_info[i]:
                    if act in this_constraints:
                        if trace_info[i][act] not in this_constraints[act]:
                            dev_total += 1
                            ret[Outputs.DEVIATIONS.value].append((default_considered_constraints[i], (act, trace_info[i][act])))
                    else:
                        dev_total += 1
                        ret[Outputs.DEVIATIONS.value].append((default_considered_constraints[i], (act, 0)))
                for act in this_constraints:
                    if min(this_constraints[act]) > 0 and not act in trace:
                        dev_total += 1
                        ret[Outputs.DEVIATIONS.value].append((default_considered_constraints[i], (act, 0)))
            elif default_considered_constraints[i] == DiscoveryOutputs.NEVER_TOGETHER.value:
                this_constraints = {x for x in model[default_considered_constraints[i]] if x[0] in trace}
                conf_total += len(this_constraints)
                setinte = this_constraints.intersection(trace_info[i])
                dev_total += len(setinte)
                if len(setinte) > 0:
                    ret[Outputs.DEVIATIONS.value].append((default_considered_constraints[i], tuple(setinte)))
            else:
                this_constraints = {x for x in model[default_considered_constraints[i]] if x[0] in trace}
                conf_total += len(this_constraints)
                setdiff = this_constraints.difference(trace_info[i])
                dev_total += len(setdiff)
                if len(setdiff) > 0:
                    ret[Outputs.DEVIATIONS.value].append((default_considered_constraints[i], tuple(setdiff)))
        i = i + 1
    ret[Outputs.NO_DEV_TOTAL.value] = dev_total
    ret[Outputs.NO_CONSTR_TOTAL.value] = conf_total
    ret[Outputs.DEV_FITNESS.value] = 1.0 - float(dev_total)/float(conf_total) if conf_total > 0 else 1.0
    ret[Outputs.DEVIATIONS.value] = sorted(ret[Outputs.DEVIATIONS.value], key=lambda x: (x[0], x[1]))
    ret[Outputs.IS_FIT.value] = len(ret[Outputs.DEVIATIONS.value]) == 0
    return ret


def apply_from_variants_list(var_list, model, parameters=None):
    """
    Performs conformance checking using the log skeleton,
    applying it from a list of variants

    Parameters
    --------------
    var_list
        List of variants
    model
        Log skeleton model
    parameters
        Parameters

    Returns
    --------------
    conformance_dictio
        Dictionary containing, for each variant, the result
        of log skeleton checking
    """
    if parameters is None:
        parameters = {}

    conformance_output = {}

    for cv in var_list:
        v = cv[0]
        trace = variants_util.variant_to_trace(v, parameters=parameters)

        conformance_output[v] = apply_trace(trace, model, parameters=parameters)

    return conformance_output


def after_decode(log_skeleton):
    """
    Prepares the log skeleton after decoding

    Parameters
    --------------
    log_skeleton
        Log skeleton

    Returns
    --------------
    log_skeleton
        Log skeleton (with sets instead of lists)
    """
    log_skeleton[DiscoveryOutputs.EQUIVALENCE.value] = set(log_skeleton[DiscoveryOutputs.EQUIVALENCE.value])
    log_skeleton[DiscoveryOutputs.ALWAYS_AFTER.value] = set(log_skeleton[DiscoveryOutputs.ALWAYS_AFTER.value])
    log_skeleton[DiscoveryOutputs.ALWAYS_BEFORE.value] = set(log_skeleton[DiscoveryOutputs.ALWAYS_BEFORE.value])
    log_skeleton[DiscoveryOutputs.NEVER_TOGETHER.value] = set(log_skeleton[DiscoveryOutputs.NEVER_TOGETHER.value])
    log_skeleton[DiscoveryOutputs.DIRECTLY_FOLLOWS.value] = set(log_skeleton[DiscoveryOutputs.DIRECTLY_FOLLOWS.value])
    for act in log_skeleton[DiscoveryOutputs.ACTIV_FREQ.value]:
        log_skeleton[DiscoveryOutputs.ACTIV_FREQ.value][act] = set(log_skeleton[DiscoveryOutputs.ACTIV_FREQ.value][act])
    return log_skeleton


def get_diagnostics_dataframe(log, conf_result, parameters=None):
    """
    Gets the diagnostics dataframe from a log and the results
    of log skeleton-based conformance checking

    Parameters
    --------------
    log
        Event log
    conf_result
        Results of conformance checking

    Returns
    --------------
    diagn_dataframe
        Diagnostics dataframe
    """
    if parameters is None:
        parameters = {}

    case_id_key = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, xes_constants.DEFAULT_TRACEID_KEY)

    import pandas as pd

    diagn_stream = []

    for index in range(len(log)):
        case_id = log[index].attributes[case_id_key]

        no_dev_total = conf_result[index][Outputs.NO_DEV_TOTAL.value]
        no_constr_total = conf_result[index][Outputs.NO_CONSTR_TOTAL.value]
        dev_fitness = conf_result[index][Outputs.DEV_FITNESS.value]

        diagn_stream.append({"case_id": case_id, "no_dev_total": no_dev_total, "no_constr_total": no_constr_total, "dev_fitness": dev_fitness})

    return pandas_utils.instantiate_dataframe(diagn_stream)