def test_csv1documentation(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
import os
from pm4py.objects.log.importer.csv import factory as csv_importer
event_log = csv_importer.import_event_stream(
os.path.join("input_data", "running-example.csv"))
event_log_length = len(event_log)
del event_log_length
from pm4py.objects.log import transform
log = transform.transform_event_stream_to_event_log(
event_log, case_glue="case:concept:name")
del log
from pm4py.objects.log.importer.csv.versions import pandas_df_imp
dataframe = pandas_df_imp.import_dataframe_from_path(
os.path.join("input_data", "running-example.csv"))
event_log = log_conv_fact.apply(dataframe,
variant=log_conv_fact.TO_EVENT_STREAM)
log = log_conv_fact.apply(event_log)
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export(event_log, "outputFile1.csv")
os.remove("outputFile1.csv")
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export(log, "outputFile2.csv")
os.remove("outputFile2.csv")
def test_importExportCSVtoCSV(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
event_log = csv_importer.import_event_stream(
os.path.join(INPUT_DATA_DIR, "running-example.csv"))
event_log = sorting.sort_timestamp(event_log)
event_log = sampling.sample(event_log)
event_log = index_attribute.insert_event_index_as_event_attribute(
event_log)
log = log_conv_fact.apply(event_log)
log = sorting.sort_timestamp(log)
log = sampling.sample(log)
log = index_attribute.insert_trace_index_as_event_attribute(log)
event_log_transformed = log_conv_fact.apply(
log, variant=log_conv_fact.TO_EVENT_STREAM)
csv_exporter.export(
event_log_transformed,
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_imported_after_export = csv_importer.import_event_stream(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
log_imported_after_export = log_conv_fact.apply(
event_log_imported_after_export)
self.assertEqual(len(log), len(log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR,
"running-example-exported.csv"))
def xes_to_csv(xes_path, csv_path):
"""
Imports .xes given the xes_path, and converts and saves it to a .csv file
Args:
xes_path (str) : path of .xes compliant input event log
csv_path (str) : path of .csv output event log
"""
log = xes_import_factory.apply(xes_path)
csv_exporter.export(log, csv_path)
def test_importExportXEStoCSV(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
log = xes_importer.import_log(os.path.join(INPUT_DATA_DIR, "running-example.xes"))
event_log = log_conv_fact.apply(log, variant=log_conv_fact.TO_EVENT_STREAM)
csv_exporter.export(event_log, os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
event_log_newimport = csv_importer.import_event_stream(
os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
log_imported_after_export = log_conv_fact.apply(event_log_newimport)
self.assertEqual(len(log), len(log_imported_after_export))
os.remove(os.path.join(OUTPUT_DATA_DIR, "running-example-exported.csv"))
def test_pdimp_csvexp(self):
log0 = csv_import_adapter.import_dataframe_from_path(
os.path.join("input_data", "running-example.csv"))
log = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_EVENT_LOG)
stream = log_conv_factory.apply(
log0, variant=log_conv_factory.TO_EVENT_STREAM)
df = log_conv_factory.apply(log0,
variant=log_conv_factory.TO_DATAFRAME)
csv_exporter_factory.export(log, "ru.csv")
csv_exporter_factory.export(stream, "ru.csv")
csv_exporter_factory.export(df, "ru.csv")
os.remove('ru.csv')
#set parameters
filePath = sys.argv[1]
k = sys.argv[2]
t = sys.argv[3]
anon = sys.argv[4]
dbName = sys.argv[5]
secure_token = sys.argv[6]
sys.setrecursionlimit(3000)
filePath = filePath.replace(" ", "_")
if filePath.endswith(".xes"):
log = xes_import_factory.apply(filePath)
file_path_xes_csv = filePath + ".csv"
csv_exporter.export(log, file_path_xes_csv)
targetFilePath = file_path_xes_csv.replace(".xes.csv",
"_k%s_pretsa.csv" % (k))
#run PRETSA
if file_path_xes_csv.endswith(".xes.csv"):
xes_csv_file = pd.read_csv(file_path_xes_csv,
delimiter=",",
skipinitialspace=True,
encoding="utf-8-sig",
keep_default_na=False,
na_values=[
'-1.#IND', '1.#QNAN', '1.#IND',
'-1.#QNAN', '#N/A N/A', '#N/A', 'N/A',
'n/a', '', '#NA', 'NULL', 'null', 'NaN',
'-NaN', 'nan', '-nan', ''
import pandas as pd
import sqlite3
import os
import random
from pm4py.objects.log.importer.xes import factory as xes_import_factory
from pm4py.objects.log.exporter.csv import factory as csv_exporter
#set parameters
secure_token = sys.argv[1]
filePath = filePath.replace(" ", "_")
if filePath.endswith(".xes"):
log = xes_import_factory.apply(filePath)
filePath = filePath + ".csv"
csv_exporter.export(log, filePath)
targetFilePath = filePath.replace(".csv", "_columns.csv")
#run PRETSA
if filePath.endswith(".xes.csv"):
xes_csv_file = pd.read_csv(filePath,
delimiter=",",
skipinitialspace=True,
encoding="utf-8-sig")
xes_csv_file.rename(columns={
'concept:name': 'Activity',
'case:concept:name': 'Case ID'
},
inplace=True)
if not 'Duration' in xes_csv_file.columns:
xes_csv_file.loc[:, "Duration"] = 0.0
xes_csv_file.to_csv(filePath,
#Topic:
#-----------------------------
#libraries
from pm4py.algo.discovery.alpha import factory as alpha_miner
from pm4py.objects.log.importer.xes import factory as importer
from pm4py.visualization.petrinet import factory as visualizer
from pm4py.objects.log.importer.csv import factory as csv_importer
event_stream = csv_importer.import_event_stream(
os.path.join("pmdata/", "running-example.csv"))
event_stream
event_stream_length = len(event_stream)
print(event_stream_length)
for event in event_stream:
print(event)
from pm4py.objects.conversion.log import factory as conversion_factory
log = conversion_factory.apply(event_stream)
from pm4py.objects.log.exporter.csv import factory as csv_exporter
csv_exporter.export(event_stream, "data/outputFile1.csv")
#log = importer.apply('pmdata/running-example.xes')
net, initial_marking, final_marking = alpha_miner.apply(log)
gviz = visualizer.apply(net, initial_marking, final_marking)
visualizer.view(gviz)
return inductive_evaluation_result
number_of_experiment_to_run = 100
results = []
for _ in range(number_of_experiment_to_run):
# Generate a random process tree and get traces from the process tree
tree = tree_gen_factory.apply()
log = semantics.generate_log(tree, no_traces=1000)
size_tree, leafs = rec_node([tree], [])
leafs = set(leafs).union(set('τ'))
tree = {
'tree': str(tree),
'tree_size': size_tree
}
csv_exporter.export(log, 'temp.csv')
original_df = pd.read_csv('temp.csv')
os.remove('temp.csv')
log_for_eval = copy.deepcopy(log)
# Try different level of noise
for noise_ratio in np.arange(0, 1.01, 0.05):
noise_ratio = round(noise_ratio,2)
# Alter the event log
df = original_df.copy()
df = randomly_remove_log(df, noise_ratio)
# The classic approach is simply to apply the inductive miner
# on the traces that might contain truncated traces.
result = {'type':'classic', 'noise':noise_ratio}
from pm4py.objects.log.importer.xes import factory as xes_import_factory
from pm4py.objects.log.exporter.csv import factory as csv_exporter
#set parameters
filePath = sys.argv[1]
dbName = sys.argv[2]
secure_token = sys.argv[3]
print("Retrieving case and event attribute names")
filePath = filePath.replace(" ", "_")
log = xes_import_factory.apply(filePath)
targetFilePath = filePath.replace(".xes", "_renamed.csv")
file_path_buffer = filePath.replace(".xes", "_buffer.csv")
csv_exporter.export(log, file_path_buffer)
xes_csv_file = pd.read_csv(file_path_buffer,
delimiter=",",
skipinitialspace=True,
encoding="utf-8-sig",
keep_default_na=False,
na_values=[
'-1.#IND', '1.#QNAN', '1.#IND', '-1.#QNAN',
'#N/A N/A', '#N/A', 'N/A', 'n/a', '', '#NA',
'NULL', 'null', 'NaN', '-NaN', 'nan',
'-nan', ''
])
#####################################################
if not 'Activity' in xes_csv_file.columns:
from pm4py.objects.log.importer.xes import factory as xes_import_factory path_log = "C:\personal projects\ISMFieldproject\data\Hospital_log.xes" path_billing = "C:\personal projects\ISMFieldproject\data\Hospital Billing - Event Log.xes.gz" path_sepsis = "C:\personal projects\ISMFieldproject\data\Sepsis Cases - Event Log.xes.gz" # %% we read in the event docs from xes hospital_log = xes_import_factory.apply(path_log) hospital_billing = xes_import_factory.apply(path_billing) sepsis_cases = xes_import_factory.apply(path_sepsis) # %% we transform the documents into csv files from pm4py.objects.log.exporter.csv import factory as csv_exporter csv_exporter.export(hospital_log, "hospital_log.csv") csv_exporter.export(hospital_billing, "hospital_billing.csv") csv_exporter.export(sepsis_cases, "sepsis_cases.csv")
#log = xes_import_factory.apply(r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_1.xes")
#
#csv_exporter.export(log, r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_1.csv")
#
#print("2")
#log = xes_import_factory.apply(r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_2.xes")
#
#csv_exporter.export(log, r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_2.csv")
#
#
#print("3")
#log = xes_import_factory.apply(r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_3.xes")
#
#csv_exporter.export(log, r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_3.csv")
#
#
#print("4")
#log = xes_import_factory.apply(r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_4.xes")
#
#csv_exporter.export(log, r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\BPIC15_4.csv")
print("5")
log = xes_import_factory.apply(
r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\Sepsis Cases - Event Log (1).xes"
)
csv_exporter.export(
log,
r"C:\Gamal Elkoumy\PhD\OneDrive - Tartu Ülikool\Secure MPC\Business Process Mining SourceCode\Datasets\Sepsis Cases - Event Log.csv"
)
case_id, pred, rel_scores = grm_model.predict(trace)
if len(rel_scores) > 1:
most_relevant = max(rel_scores.items(), key=operator.itemgetter(1))[0]
log_trace = attributes_filter.apply_events(
log, [case_id],
parameters={
attributes_filter.PARAMETER_CONSTANT_ATTRIBUTE_KEY:
name_of_case_id,
"positive": True
})
trace_without_most = attributes_filter.apply_events(
log_trace, [most_relevant],
parameters={
attributes_filter.PARAMETER_CONSTANT_ATTRIBUTE_KEY:
"concept:name",
"positive": False
})
trace_without_most = trace_without_most[0]
filtered_log._list.append(trace_without_most)
log = conversion_factory.apply(filtered_log)
csv_exporter.export(log, "sp2020_without_most_relevant.csv")
run_experiment(log,
hyper_params=hyper_params,
k=k,
ml_flow_run_name_prefix=logfile)
log = conversion_factory.apply(event_stream) from pm4py.algo.discovery.alpha import factory as alpha_miner net, initial_marking, final_marking = alpha_miner.apply(log) from pm4py.objects.log.importer.xes import factory as xes_import_factory xes_path = 'C:/Users/vince_000/Documents/BPI Challenge 2019/INV after GR - with SRM/01_01_01_Service/' xes_file = '01_01_01_Invoice_after_GR_with_SRM_Service.xes' log = xes_import_factory.apply(xes_path + xes_file) log[0] from pm4py.objects.log.exporter.csv import factory as csv_exporter csv_exporter.export(log, "C:/Users/vince_000/Documents/BPI Challenge 2019/test/outputFile1.csv") from pm4py.algo.discovery.alpha import factory as alpha_miner net, initial_marking, final_marking = alpha_miner.apply(log) from pm4py.visualization.petrinet import factory as pn_vis_factory gviz = pn_vis_factory.apply(net, initial_marking, final_marking) pn_vis_factory.view(gviz) log[0]
def load(file_path):
csv_path = file_path + ".csv"
if not os.path.isfile(csv_path):
log = xes_importer.apply(file_path)
csv_exporter.export(log, csv_path)
return pd.read_csv(csv_path)
