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 cli(con):
print("\n\nP2P - Object-Centric Log\n")
dataframe = apply(con)
path = input(
"Insert the path where the log should be saved (default: p2p.mdl): ")
if not path:
path = "p2p.xmlocel"
if path.endswith("mdl"):
mdl_exporter.apply(dataframe, path)
elif path.endswith("jsonocel") or path.endswith("xmlocel"):
jmd_exporter.apply(dataframe, path)
def cli(con):
print("\n\nO2C Object-Centric Log Extractor\n\n")
min_extr_date = input(
"Insert the minimum extraction date (default: 2020-01-01 00:00:00): ")
if not min_extr_date:
min_extr_date = "2020-01-01 00:00:00"
gjahr = input("Insert the fiscal year (default: 2020):")
if not gjahr:
gjahr = "2020"
dataframe = apply(con, min_extr_date=min_extr_date, gjahr=gjahr)
path = input(
"Insert the path where the log should be saved (default: o2c.xmlocel): "
)
if not path:
path = "o2c.xmlocel"
if path.endswith("mdl"):
mdl_exporter.apply(dataframe, path)
elif path.endswith("jsonocel") or path.endswith("xmlocel"):
ocel_exporter.apply(dataframe, path)
def newExtractorPerformExtraction():
parameters = request.args.get("parameters")
parameters = __process_parameters(parameters)
db_type = parameters["db_type"] if "db_type" in parameters else "sqlite"
db_con_args = parameters[
"db_con_args"] if "db_con_args" in parameters else {
"path": "sap.sqlite"
}
tabnames = parameters["tabnames"]
key_spec = parameters["key_spec"]
mandt = parameters["mandt"]
c = database_factory.apply(db_type, db_con_args)
from sapextractor.utils.generic_extractors import extract_table
file_name = str(uuid.uuid4()) + ".parquet"
df = extract_table.apply_set_tables(c, tabnames, mandt=mandt)
from pm4pymdl.objects.mdl.exporter import exporter
exporter.apply(df, file_name)
obj_types = [x for x in df.columns if not x.startswith("event_")]
return {"file_name": file_name, "obj_types": obj_types}
def execute_script():
con = example_connection.get_con()
ol = sapextractor.get_ap_ar_obj_centr_log(con)
mdl_exporter.apply(ol, "ap_ar.mdl")
if __name__ == "__main__":
read_bseg()
read_tstct()
read_eban()
read_bkpf()
read_ekbe()
read_ekpo()
read_mseg()
read_rseg()
read_mara()
read_lfa1()
read_ekko()
read_mkpf()
read_rbkp()
write_events()
Shared.events = sorted(Shared.events, key=lambda x: x["event_timestamp"])
print("written events")
events_df = pd.DataFrame(Shared.events)
print("got dataframe")
events_df.type = "exploded"
ekpo_objects = pd.DataFrame(Shared.EKPO_objects)
mseg_objects = pd.DataFrame(Shared.MSEG_objects)
rseg_objects = pd.DataFrame(Shared.RSEG_objects)
mara_objects = pd.DataFrame(Shared.MARA_objects)
lfa1_objects = pd.DataFrame(Shared.LFA1_objects)
object_df = pd.concat([ekpo_objects, mseg_objects, rseg_objects, mara_objects, lfa1_objects])
print("exporting")
mdl_exporter.apply(events_df, "log_p2p.mdl", obj_df=object_df)
print("exported")
mdl_exporter.apply(events_df, "log_p2p.parquet", obj_df=object_df)
for col in succint_table.columns:
if not col.startswith("event"):
print(col)
succint_table[col] = succint_table[col].apply(f)
succint_table = succint_table.rename(columns=col_mapping)
mapping = {"XK01": "Create Vendor (Centrally)", "XK02": "Change Vendor (Centrally)", "FK02": "Change Vendor (Accounting)", "MK02": "Change Vendor (Purchasing)", "VD02": "Change Customer (Sales)", "XD01": "Create Customer (Centrally)", "XD02": "Change Customer (Centrally)", "FD02": "Change Customer (Accounting)", "XD07": "Change Customer Account Group", "FK08": "Confirm Vendor Individually (Acctng)"}
def f1(x):
return mapping[x]
succint_table["event_activity"] = succint_table["event_activity"].apply(f1)
succint_table.type = "succint"
mdl_exporter.apply(succint_table, "sap_withoutTrial.mdl")
stream = succint_table.to_dict('r')
tgroups = {}
for event in stream:
event_keys = list(event.keys())
for key in event_keys:
if event[key] is None:
del event[key]
event_keys = list(event.keys())
tcode = event["event_tcode"]
if not tcode in tgroups:
tgroups[tcode] = set()
this_list = []
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)
def execute_script():
con = example_connection.get_con()
ol = sapextractor.get_o2c_obj_centr_log(con, keep_first=True, min_extr_date="1990-01-01 00:00:00")
mdl_exporter.apply(ol, "o2c.mdl")
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)
# export the filtered version
mdl_exporter.apply(filtered_table_2, "filtered.mdl")
dct["G"] = "VERKBELEG" # contract
dct["W"] = "INDIP_REQ" # indipendent requisition
dct["I"] = "ORD_WO_CHARGE" # order without charge
dct["X"] = "HANDL_UNIT" # handling unit
"""
activities["A"] = "Create Inquiry"
activities["T"] = "Returns Delivery"
activities["D"] = "Item Proposal"
activities["V"] = "Create Purchase Order"
activities["N"] = "Invoice Cancellation"
activities["E"] = "Scheduling Agreement"
activities["O"] = "Create Credit Memo"
activities["K"] = "Create Credit Memo Request"
activities["B"] = "Create Quotation"
activities["G"] = "Create Contract"
activities["W"] = "Indipendent Requisition"
activities["I"] = "Create Order without Charge"
activities["X"] = "Handling Unit"
activities.update(Shared.tcodes)
df[Shared.activity_column] = df[Shared.activity_column].map(activities)
df = df.dropna(subset=[Shared.activity_column])
df = df[[x for x in df.columns if "named:" not in x]]
allowed_columns = [x for x in df.columns if not x.startswith("C_") and not x.startswith("event_")]
df = df.dropna(subset=allowed_columns, how="all")
df = df.sort_values(Shared.timestamp_column)
print(df)
df.type = "exploded"
from pm4pymdl.objects.mdl.exporter import exporter as mdl_exporter
mdl_exporter.apply(df, "sap.mdl")
mapping["FOSH"] = "Vacancy debit position"
mapping["FOUA"] = "Calculate sales settlement"
mapping["MF40"] = "Final backflush for make-to-stock production"
mapping["FBA8"] = "Clear Vendor Down Payment"
mapping["MB11"] = "Goods Movement"
mapping["MBSL"] = "Copy Material Document"
mapping["MB0A"] = "Post Goods Receipt for PO"
mapping["FOB6"] = "Input tax distribution"
mapping["FB1S"] = "Clear G/L Account"
mapping["WRX"] = "Account determination for GR/IR clearing account"
mapping["GBB"] = "Offsetting entry for inventory posting"
mapping["MB1B"] = "Enter Transfer Posting"
df["event_activity"] = df["event_activity"].apply(lambda x: mapping[x])
from pm4pymdl.objects.mdl.exporter import exporter as mdl_exporter
mdl_exporter.apply(df, "bkpf_bseg.mdl")
#print(df["event_activity"].unique())
#input()
#print(df)
model = mvp_disc_factory.apply(df,
parameters={
"min_dfg_occurrences": 3,
"performance": False,
"decreasing_factor_sa_ea": 0.0,
"dependency_thresh": 0.3,
"perspectives": ["belnr", "xblnr", "hkont"]
})
gviz = mvp_vis_factory.apply(model, parameters={"format": "svg"})
for l0 in logs:
df = pd.read_csv("pkdd99/"+l0, sep=";", quotechar="\"")
if "date" in df.columns:
df["date"] = pd.to_datetime(df["date"], format="%y%m%d")
if "issued" in df.columns:
df["issued"] = pd.to_datetime(df["issued"], format="%y%m%d %H:%M:%S")
if "birth_number" in df.columns:
df["birth_number"] = 1900 + df["birth_number"] // 10000
df["birth_number"] = pd.to_datetime(df["birth_number"], format="%Y", errors="ignore")
for column in case_id_columns:
if column in df.columns:
df[column] = df[column].astype(str)
df = do_column_mapping(df)
df = set_up_activity(l0, df)
if "event_activity" in df.columns and "event_timestamp" in df.columns:
df = df.dropna(subset=["event_timestamp", "event_activity"], how="any")
if len(df) > 0:
all_df.append(df)
df = pd.concat(all_df)
df = df.reset_index()
df["event_id"] = df.index
df["event_id"] = df["event_id"].astype(str)
df = df.sort_values(["event_timestamp", "event_id"])
df = df.reset_index()
df.type = "exploded"
del df["index"]
del df["level_0"]
print(df.columns)
mdl_exporter.apply(df, "pkdd99.parquet")