def execute_script():
stream1 = [{
"event_id": "1",
"event_activity": "A",
"event_timestamp": parser.parse("1970-01-01 00:00:00"),
"order": ["O1"]
}, {
"event_id": "2",
"event_activity": "B",
"event_timestamp": parser.parse("1970-01-01 00:00:00"),
"order": ["O1"],
"item": ["I1, I2"]
}]
df = pd.DataFrame(stream1)
df.type = "succint"
stream2 = [{
"object_id": "O1",
"object_type": "order",
"object_buyer": "Alessandro"
}, {
"object_id": "I1",
"object_type": "item",
"object_cost": 600
}]
obj_df = pd.DataFrame(stream2)
mdl_exporter.apply(df, "prova.mdl", obj_df=obj_df)
df, obj_df = mdl_importer.apply("prova.mdl", return_obj_dataframe=True)
orders = obj_df[obj_df["object_type"] == "order"].dropna(how="all", axis=1)
items = obj_df[obj_df["object_type"] == "item"].dropna(how="all", axis=1)
print(df)
print(orders)
print(items)
mdl_exporter.apply(df, "prova2.mdl", obj_df=obj_df)
os.remove("prova.mdl")
os.remove("prova2.mdl")
def __init__(self, name, mdl_path, shared_logs):
self.shared_logs = shared_logs
self.shared_logs_names = []
self.parent = self
self.obj_types_str = None
self.act_obj_types = None
self.initial_act_obj_types = None
self.activities = []
self.obj_types = []
self.clusters = {}
self.clustersrepr = ""
self.clusterid = str(id(self))
self.stream = None
self.nodes = None
self.events_corr = None
self.events_corr2 = None
self.matrix = None
self.powered_matrix = None
self.powered_matrix_2 = None
self.graph = None
self.row_sum = None
self.overall_sum = 0
self.selected_act_obj_types = None
self.name = name
self.mdl_path = mdl_path
if "ocel" in self.mdl_path:
self.succint_dataframe, odataframe = ocel_importer.apply(
self.mdl_path)
else:
self.succint_dataframe = mdl_importer.apply(self.mdl_path)
self.succint_dataframe = self.succint_dataframe.dropna(
subset=["event_activity"])
self.succint_dataframe.type = "succint"
self.exploded_dataframe = succint_mdl_to_exploded_mdl.apply(
self.succint_dataframe)
self.exploded_dataframe.type = "exploded"
self.session_objects = {}
self.possible_model_types = {
"mvp_frequency": "MVP (frequency)",
"mvp_performance": "MVP (performance)",
"process_tree": "oc-PTree",
"petri_alpha": "oc-Net-Alpha",
"petri_inductive": "oc-Net-Inductive",
"dfg": "oc-DFG",
"multigraph": "OC Multigraph"
}
self.selected_model_type = defaults.DEFAULT_MODEL_TYPE
self.possible_classifiers = {"activity", "combined"}
self.selected_classifier = "activity"
self.selected_aggregation_measure = "events"
self.selected_decoration_measure = "frequency"
self.selected_projection = "no"
self.selected_min_acti_count = 800
self.selected_min_edge_freq_count = 800
self.epsilon = 0.0
self.noise_threshold = 0.0
self.model_view = ""
def newExtractorDownloadSvg():
parameters = request.args.get("parameters")
parameters = __process_parameters(parameters)
file_name = parameters["file_name"]
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
df = mdl_importer.apply(file_name)
from pm4pymdl.algo.mvp.gen_framework3 import discovery as mvp_discovery
model = mvp_discovery.apply(df)
from pm4pymdl.visualization.mvp.gen_framework3 import visualizer as mvp_visualizer
gviz = mvp_visualizer.apply(model, parameters={"format": "svg"})
ser = pm4py.visualization.dfg.visualizer.serialize(gviz).decode("utf-8")
return ser
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
import os
df, obj_df = mdl_importer.apply("../example_logs/mdl/mdl-running-example-w-objects.mdl", return_obj_dataframe=True)
print(df)
print(obj_df)
df.to_csv("only_events.csv", index=False)
obj_df.to_csv("all_objects.csv", index=False)
products = obj_df[obj_df["object_type"] == "products"].dropna(how="all", axis=1)
customers = obj_df[obj_df["object_type"] == "customers"].dropna(how="all", axis=1)
print(products)
print(customers)
products.to_csv("products.csv", index=False)
customers.to_csv("customers.csv", index=False)
os.remove("only_events.csv")
os.remove("all_objects.csv")
os.remove("products.csv")
os.remove("customers.csv")
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.gen_framework import algorithm as discovery
from pm4pymdl.visualization.mvp.gen_framework import visualizer as vis_factory
df = mdl_importer.apply("../example_logs/mdl/order_management.mdl")
model = discovery.apply(df,
model_type_variant="model3",
node_freq_variant="type31",
edge_freq_variant="type11")
gviz = vis_factory.apply(model, parameters={"format": "svg"})
vis_factory.view(gviz)
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.utils import succint_mdl_to_exploded_mdl
from pm4pymdl.objects.mdl.exporter import exporter as mdl_exporter
import random
import pandas as pd
succint_df = mdl_importer.apply("example_logs/mdl/mdl-running-example.mdl")
df = succint_mdl_to_exploded_mdl.apply(succint_df)
products = df["products"].dropna().unique()
customers = df["customers"].dropna().unique()
objects = []
for p in products:
objects.append({
"object_id": p,
"object_type": "products",
"object_cost": random.randrange(100, 500),
"object_producer": random.choice(["A", "B", "C"])
})
for c in customers:
objects.append({
"object_id": c,
"object_type": "customers",
"object_age": random.randrange(30, 60),
"object_bankaccount": random.randrange(1000, 100000)
})
print(objects)
obj_df = pd.DataFrame(objects)
mdl_exporter.apply(df, "mdl-running-example-w-objects.mdl", obj_df=obj_df)
#!/usr/bin/env python3.8
import sys
filename = sys.argv[1]
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.gen_framework import algorithm as discovery
from pm4pymdl.visualization.mvp.gen_framework import visualizer as vis_factory
df = mdl_importer.apply(filename)
model = discovery.apply(df,
model_type_variant="model1",
node_freq_variant="type1",
edge_freq_variant="type11")
gviz = vis_factory.apply(model, parameters={"format": "svg"})
vis_factory.view(gviz)
model = discovery.apply(df,
model_type_variant="model2",
node_freq_variant="type21",
edge_freq_variant="type211")
gviz = vis_factory.apply(model, parameters={"format": "svg"})
vis_factory.view(gviz)
model = discovery.apply(df,
model_type_variant="model3",
node_freq_variant="type31",
edge_freq_variant="type11")
gviz = vis_factory.apply(model, parameters={"format": "svg"})
vis_factory.view(gviz)
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.gen_framework3 import discovery, conformance
from pm4pymdl.visualization.mvp.gen_framework3 import visualizer as visualizer
dataframe = mdl_importer.apply("../example_logs/mdl/o2c_red.mdl")
model = discovery.apply(dataframe,
parameters={
"epsilon": 0.1,
"noise_threshold": 0.1
})
conf_result = conformance.apply(dataframe, model)
fitness = len([x for x in conf_result if len(x) == 0]) / len(conf_result)
print(fitness)
gviz = visualizer.apply(model,
parameters={
"min_act_freq": 500,
"min_edge_freq": 500
})
visualizer.view(gviz)
for el in conf_result:
if el:
print(el)
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.gen_framework import algorithm as discovery
from pm4pymdl.visualization.mvp.gen_framework import visualizer as vis_factory
import pandas as pd
df_offer = mdl_importer.apply("../example_logs/parquet/bpic2017_offer.parquet")
df_offer["event_idx_log_0"] = df_offer.index
df_offer = df_offer.sort_values(["event_timestamp", "event_idx_log_0"])
df_application = mdl_importer.apply(
"../example_logs/parquet/bpic2017_application.parquet")
df_application["event_idx_log_0"] = df_application.index
df_application = df_application.sort_values(
["event_timestamp", "event_idx_log_0"])
#df_application.fillna(value=pd.np.nan, inplace=True)
df = pd.concat([df_offer, df_application])
df["event_idx_log"] = df.index
df = df.reset_index()
df = df.sort_values(["event_timestamp", "event_idx_log"])
df.drop(columns="index", inplace=True)
model = discovery.apply(df)
gviz = vis_factory.apply(model,
parameters={
"dfg_cleaning_threshold": 0.15,
"max_edge_ratio": 0.99,
"format": "svg"
})
vis_factory.view(gviz)
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
# import a log in Parquet format, that is stored as exploded MDL table
exploded_table = mdl_importer.apply("../example_logs/parquet/pkdd99.parquet")
print(exploded_table.columns)
# focus on the account ID: we wish to calculate the time from the previous event
exploded_table = exploded_table.dropna(subset=["account_id"], how="any")
exploded_table_prev_ev = exploded_table.copy()
exploded_table_prev_ev["@@index"] = exploded_table_prev_ev.index
exploded_table_prev_ev = exploded_table_prev_ev.reset_index()
exploded_table_prev_ev = exploded_table_prev_ev.sort_values(["account_id", "event_timestamp", "@@index"])
shifted_table = exploded_table_prev_ev.shift()
exploded_table_prev_ev["@@time_prev"] = (
exploded_table_prev_ev["event_timestamp"] - shifted_table["event_timestamp"]).astype('timedelta64[s]')
exploded_table_prev_ev = exploded_table_prev_ev[exploded_table_prev_ev["account_id"] == shifted_table["account_id"]]
exploded_table_prev_ev = exploded_table_prev_ev.dropna(subset=["@@time_prev"])
exploded_table_prev_ev = exploded_table_prev_ev.sort_values(["@@time_prev", "event_timestamp", "@@index"])
# keep only the lowest difference between times
exploded_table_prev_ev = exploded_table_prev_ev.groupby("event_id").first().reset_index()
print(exploded_table_prev_ev)
# focus on the account_id
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.utils import succint_mdl_to_exploded_mdl
from pm4pymdl.algo.mvp.gen_framework import algorithm as discovery
from pm4pymdl.visualization.mvp.gen_framework import visualizer as vis_factory
from pm4pymdl.objects.mdl.exporter import exporter as mdl_exporter
# import a succint MDL table
succint_table = mdl_importer.apply("../example_logs/mdl/order_management.mdl")
print(len(succint_table), succint_table.type)
# convert it into an exploded MDL table
exploded_table = succint_mdl_to_exploded_mdl.apply(succint_table)
print(len(exploded_table), exploded_table.type)
# keeps only events related to orders that have a profit >= 200
# to make the filtering on the exploded table we have to follow the procedure:
f0 = exploded_table[exploded_table["event_profit"] >= 200]
f1 = exploded_table[exploded_table["order"].isin(f0["order"])]
filtered_exploded_table = exploded_table[exploded_table["event_id"].isin(
f1["event_id"])]
# suppose that we want to get also the packages related to the filtered orders, then:
f2 = exploded_table[exploded_table["package"].isin(
filtered_exploded_table["package"])]
filtered_table_2 = exploded_table[
exploded_table["event_id"].isin(filtered_exploded_table["event_id"])
| exploded_table["event_id"].isin(f2["event_id"])]
# mine a process model out of the filtered table
model = discovery.apply(filtered_table_2)
gviz = vis_factory.apply(model)
vis_factory.view(gviz)
from pm4pymdl.objects.mdl.importer import importer as mdl_importer
from pm4pymdl.algo.mvp.utils import succint_mdl_to_exploded_mdl, succint_stream_to_exploded_stream
from copy import deepcopy
import numpy as np
from sklearn.metrics import pairwise_distances
from scipy.spatial.distance import cosine
import networkx as nx
from networkx.algorithms.community import asyn_lpa_communities
from networkx.algorithms.community import quality
log0 = mdl_importer.apply("example_logs/mdl/log_opp_red.mdl")
log = succint_mdl_to_exploded_mdl.apply(log0)
stream = log.to_dict('r')
nodes = dict()
for ev in stream:
ev2 = {x: y for x, y in ev.items() if str(y) != "nan"}
id = "event_id=" + str(ev2["event_id"])
activity = "event_activity=" + ev2["event_activity"]
if id not in nodes:
nodes[id] = len(nodes)
if activity not in nodes:
nodes[activity] = len(nodes)
for col in ev2:
if not col.startswith("event_"):
val = ev2[col]
oid = "object_id=" + str(val)
cla = "class=" + str(col)
if oid not in nodes:
nodes[oid] = len(nodes)
if cla not in nodes:
nodes[cla] = len(nodes)
