def test_case_statistics(self):
from pm4py.statistics.traces.pandas import case_statistics
df = self.get_dataframe()
case_statistics.get_cases_description(df)
case_statistics.get_variants_df(df)
case_statistics.get_variant_statistics(df)
#case_statistics.get_variant_statistics_with_case_duration(df)
case_statistics.get_events(df, "N77802")
case_statistics.get_variants_df_with_case_duration(df)
case_statistics.get_variants_df_and_list(df)
case_statistics.get_kde_caseduration(df)
def get_case_duration_svg(dataframe, parameters=None):
"""
Gets the SVG of the case duration graph
Parameters
-------------
dataframe
Dataframe
parameters
Possible parameters of the algorithm
Returns
-------------
graph
Case duration graph
"""
if parameters is None:
parameters = {}
x, y = case_statistics.get_kde_caseduration(dataframe, parameters)
gviz = graphs_factory.apply_plot(x,
y,
variant="cases",
parameters={"format": "svg"})
gviz_base64 = base64.b64encode(str(gviz).encode('utf-8'))
ret = []
for i in range(len(x)):
ret.append((x[i], y[i]))
return get_base64_from_file(gviz), gviz_base64, ret
def test_dfCasedurationPlotSemilogx(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"
df = csv_import_adapter.import_dataframe_from_path(
os.path.join("input_data", "receipt.csv"))
x, y = pd_case_statistics.get_kde_caseduration(df)
json = pd_case_statistics.get_kde_caseduration_json(df)
del json
def test_dfCasedurationPlotSemilogx(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"
df = pd.read_csv(os.path.join("input_data", "receipt.csv"))
df = dataframe_utils.convert_timestamp_columns_in_df(df)
x, y = pd_case_statistics.get_kde_caseduration(df)
json = pd_case_statistics.get_kde_caseduration_json(df)
del json
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_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)
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.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)