def save_vis_events_per_time_graph(log: Union[EventLog, pd.DataFrame],
file_path: str):
"""
Saves the events per time graph in the specified path
Parameters
----------------
log
Log object
file_path
Destination path
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
if check_is_pandas_dataframe(log):
check_pandas_dataframe_columns(log)
from pm4py.statistics.attributes.pandas import get as attributes_get
graph = attributes_get.get_kde_date_attribute(
log, parameters=get_properties(log))
else:
from pm4py.statistics.attributes.log import get as attributes_get
graph = attributes_get.get_kde_date_attribute(
log, parameters=get_properties(log))
format = os.path.splitext(file_path)[1][1:]
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(
graph[0],
graph[1],
variant=graphs_visualizer.Variants.DATES,
parameters={"format": format})
graphs_visualizer.save(graph_vis, file_path)
def execute_script():
log = pm4py.read_xes("../tests/input_data/running-example.xes")
dfg, sa, ea = pm4py.discover_dfg(log)
tree = pm4py.discover_process_tree_inductive(log)
heu_net = pm4py.discover_heuristics_net(log)
net, im, fm = pm4py.discover_petri_net_alpha(log)
bpmn = pm4py.convert_to_bpmn(tree)
ts = ts_discovery.apply(log)
x_cases, y_cases = case_statistics.get_kde_caseduration(log)
gviz1 = dfg_visualizer.apply(dfg)
gviz2 = tree_visualizer.apply(tree)
gviz3 = hn_visualizer.apply(heu_net)
gviz4 = pn_visualizer.apply(net, im, fm)
gviz5 = bpmn_visualizer.apply(bpmn)
gviz6 = ts_visualizer.apply(ts)
gviz7 = graphs_visualizer.apply(x_cases, y_cases, variant=graphs_visualizer.Variants.CASES,
parameters={graphs_visualizer.Variants.CASES.value.Parameters.FORMAT: "svg"})
print("1", len(dfg_visualizer.serialize_dot(gviz1)))
print("1", len(dfg_visualizer.serialize(gviz1)))
print("2", len(tree_visualizer.serialize_dot(gviz2)))
print("2", len(tree_visualizer.serialize(gviz2)))
print("3", len(hn_visualizer.serialize(gviz3)))
print("4", len(pn_visualizer.serialize_dot(gviz4)))
print("4", len(pn_visualizer.serialize(gviz4)))
print("5", len(bpmn_visualizer.serialize_dot(gviz5)))
print("5", len(bpmn_visualizer.serialize(gviz5)))
print("6", len(ts_visualizer.serialize_dot(gviz6)))
print("6", len(ts_visualizer.serialize(gviz6)))
print("7", len(graphs_visualizer.serialize(gviz7)))
def view_events_per_time_graph(log: Union[EventLog, pd.DataFrame],
format: str = "png"):
"""
Visualizes the events per time graph
Parameters
-----------------
log
Log object
format
Format of the visualization (png, svg, ...)
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
if check_is_pandas_dataframe(log):
check_pandas_dataframe_columns(log)
from pm4py.statistics.attributes.pandas import get as attributes_get
graph = attributes_get.get_kde_date_attribute(
log, parameters=get_properties(log))
else:
from pm4py.statistics.attributes.log import get as attributes_get
graph = attributes_get.get_kde_date_attribute(
log, parameters=get_properties(log))
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(
graph[0],
graph[1],
variant=graphs_visualizer.Variants.DATES,
parameters={"format": format})
graphs_visualizer.view(graph_vis)
def execute_script():
log = pm4py.read_xes(
os.path.join("..", "tests", "input_data", "receipt.xes"))
# calculates the graph:
# values of y more distant from 0 signal executions that differ from the mainstream behavior
x, y = locally_linear_embedding.apply(log)
gviz = visualizer.apply(x,
y,
variant=visualizer.Variants.DATES,
parameters={
"title": "Locally Linear Embedding",
"format": "svg",
"y_axis": "Intensity"
})
visualizer.view(gviz)
def view_events_per_time_graph(log: Union[EventLog, pd.DataFrame], format: str = "png"):
"""
Visualizes the events per time graph
Parameters
-----------------
log
Log object
format
Format of the visualization (png, svg, ...)
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.statistics.attributes.pandas import get as attributes_get
graph = attributes_get.get_kde_date_attribute(log)
else:
from pm4py.statistics.attributes.log import get as attributes_get
graph = attributes_get.get_kde_date_attribute(log)
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(graph[0], graph[1], variant=graphs_visualizer.Variants.DATES,
parameters={"format": format})
graphs_visualizer.view(graph_vis)
def view_case_duration_graph(log: Union[EventLog, pd.DataFrame], format: str = "png"):
"""
Visualizes the case duration graph
Parameters
-----------------
log
Log object
format
Format of the visualization (png, svg, ...)
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.statistics.traces.pandas import case_statistics
graph = case_statistics.get_kde_caseduration(log)
else:
from pm4py.statistics.traces.log import case_statistics
graph = case_statistics.get_kde_caseduration(log)
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(graph[0], graph[1], variant=graphs_visualizer.Variants.CASES,
parameters={"format": format})
graphs_visualizer.view(graph_vis)
def save_vis_events_distribution_graph(log: Union[EventLog, pd.DataFrame],
file_path: str,
distr_type: str = "days_week"):
"""
Saves the distribution of the events in a picture file
Parameters
----------------
log
Event log
file_path
Destination path (including the extension)
distr_type
Type of distribution (default: days_week):
- days_month => Gets the distribution of the events among the days of a month (from 1 to 31)
- months => Gets the distribution of the events among the months (from 1 to 12)
- years => Gets the distribution of the events among the years of the event log
- hours => Gets the distribution of the events among the hours of a day (from 0 to 23)
- days_week => Gets the distribution of the events among the days of a week (from Monday to Sunday)
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
format = os.path.splitext(file_path)[1][1:]
title, x_axis, y_axis, x, y = __builds_events_distribution_graph(
log, distr_type)
parameters = copy(get_properties(log))
parameters["title"] = title
parameters["x_axis"] = x_axis
parameters["y_axis"] = y_axis
parameters["format"] = format
from pm4py.visualization.graphs import visualizer as graphs_visualizer
gviz = graphs_visualizer.apply(x,
y,
variant=graphs_visualizer.Variants.BARPLOT,
parameters=parameters)
graphs_visualizer.save(gviz, file_path)
def view_events_distribution_graph(log: Union[EventLog, pd.DataFrame],
distr_type: str = "days_week",
format="png"):
"""
Shows the distribution of the events in the specified dimension
Parameters
----------------
log
Event log
distr_type
Type of distribution (default: days_week):
- days_month => Gets the distribution of the events among the days of a month (from 1 to 31)
- months => Gets the distribution of the events among the months (from 1 to 12)
- years => Gets the distribution of the events among the years of the event log
- hours => Gets the distribution of the events among the hours of a day (from 0 to 23)
- days_week => Gets the distribution of the events among the days of a week (from Monday to Sunday)
- weeks => Gets the distribution of the events among the weeks of a year (from 0 to 52)
format
Format of the visualization (default: png)
"""
if type(log) not in [pd.DataFrame, EventLog, EventStream]:
raise Exception(
"the method can be applied only to a traditional event log!")
title, x_axis, y_axis, x, y = __builds_events_distribution_graph(
log, distr_type)
parameters = copy(get_properties(log))
parameters["title"] = title
parameters["x_axis"] = x_axis
parameters["y_axis"] = y_axis
parameters["format"] = format
from pm4py.visualization.graphs import visualizer as graphs_visualizer
gviz = graphs_visualizer.apply(x,
y,
variant=graphs_visualizer.Variants.BARPLOT,
parameters=parameters)
graphs_visualizer.view(gviz)
def save_vis_events_per_time_graph(log: Union[EventLog, pd.DataFrame], file_path: str):
"""
Saves the events per time graph in the specified path
Parameters
----------------
log
Log object
file_path
Destination path
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.statistics.attributes.pandas import get as attributes_get
graph = attributes_get.get_kde_date_attribute(log)
else:
from pm4py.statistics.attributes.log import get as attributes_get
graph = attributes_get.get_kde_date_attribute(log)
format = file_path[file_path.index(".") + 1:].lower()
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(graph[0], graph[1], variant=graphs_visualizer.Variants.DATES,
parameters={"format": format})
graphs_visualizer.save(graph_vis, file_path)
def save_vis_case_duration_graph(log: Union[EventLog, pd.DataFrame], file_path: str):
"""
Saves the case duration graph in the specified path
Parameters
----------------
log
Log object
file_path
Destination path
"""
if check_is_dataframe(log):
check_dataframe_columns(log)
from pm4py.statistics.traces.pandas import case_statistics
graph = case_statistics.get_kde_caseduration(log)
else:
from pm4py.statistics.traces.log import case_statistics
graph = case_statistics.get_kde_caseduration(log)
format = file_path[file_path.index(".") + 1:].lower()
from pm4py.visualization.graphs import visualizer as graphs_visualizer
graph_vis = graphs_visualizer.apply(graph[0], graph[1], variant=graphs_visualizer.Variants.CASES,
parameters={"format": format})
graphs_visualizer.save(graph_vis, file_path)
if True:
# ignore this part in true PowerBI executions
import os
import pandas as pd
from pm4py.objects.log.util import dataframe_utils
log_path = os.path.join("..", "..", "tests", "input_data", "running-example.csv")
dataset = pd.read_csv(log_path)
dataset = dataframe_utils.convert_timestamp_columns_in_df(dataset)
import pandas as pd
# this part is required because the dataframe provided by PowerBI has strings
dataset["time:timestamp"] = pd.to_datetime(dataset["time:timestamp"])
dataset = dataset.sort_values("time:timestamp")
from pm4py.statistics.traces.generic.pandas import case_statistics
from pm4py.visualization.graphs import visualizer as graphs_visualizer
x_cases, y_cases = case_statistics.get_kde_caseduration(dataset)
graph_cases = graphs_visualizer.apply(x_cases, y_cases, variant=graphs_visualizer.Variants.CASES,
parameters={graphs_visualizer.Variants.CASES.value.Parameters.FORMAT: "png"})
graphs_visualizer.matplotlib_view(graph_cases)
if True:
# ignore this part in true PowerBI executions
from pm4py.objects.log.adapters.pandas import csv_import_adapter
dataset = csv_import_adapter.import_dataframe_from_path(
"C:/running-example.csv")
import pandas as pd
# this part is required because the dataframe provided by PowerBI has strings
dataset["time:timestamp"] = pd.to_datetime(dataset["time:timestamp"])
from pm4py.statistics.attributes.pandas import get as attributes_filter
from pm4py.visualization.graphs import visualizer as graphs_visualizer
# visualize events over time graph
x_dates, y_dates = attributes_filter.get_kde_date_attribute(dataset)
graph_dates = graphs_visualizer.apply(
x_dates,
y_dates,
variant=graphs_visualizer.Variants.DATES,
parameters={
graphs_visualizer.Variants.DATES.value.Parameters.FORMAT: "png"
})
graphs_visualizer.matplotlib_view(graph_dates)