Merge remote-tracking branch 'upstream/hotfixes' into release

process-intelligence-solutions · Nov 15, 2023 · 55c2912 · 55c2912
2 parents d0b03d6 + 5633153
commit 55c2912
Show file tree

Hide file tree

Showing 33 changed files with 338 additions and 217 deletions.
diff --git a/examples/activity_position.py b/examples/activity_position.py
@@ -5,7 +5,7 @@
 
 
 def execute_script():
-    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"))
     dataframe["time:timestamp"] = pd.to_datetime(dataframe["time:timestamp"], utc=True, format="ISO8601")
     # prints the summary of the positions of two activities
     print(pm4py.get_activity_position_summary(dataframe, "Confirmation of receipt"))

diff --git a/examples/corr_mining.py b/examples/corr_mining.py
@@ -12,7 +12,7 @@
 
 
 def execute_script():
-    df = pd.read_csv("../tests/input_data/interval_event_log.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv("../tests/input_data/interval_event_log.csv")
     df = dataframe_utils.convert_timestamp_columns_in_df(df, timest_format="ISO8601")
     act_count = dict(df["concept:name"].value_counts())
     parameters = {}

diff --git a/examples/dataframe_prefix_and_fea_extraction.py b/examples/dataframe_prefix_and_fea_extraction.py
@@ -6,7 +6,7 @@
 
 def execute_script():
     # loads a dataframe. setup dates
-    df = pd.read_csv("../tests/input_data/receipt.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv("../tests/input_data/receipt.csv")
     df = dataframe_utils.convert_timestamp_columns_in_df(df, timest_format="ISO8601")
     print(df)
     # insert the case index in the dataframe

diff --git a/examples/df_to_log_postpro.py b/examples/df_to_log_postpro.py
@@ -6,7 +6,7 @@
 
 
 def execute_script():
-    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "running-example.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "running-example.csv"))
     dataframe = pm4py.format_dataframe(dataframe, timest_format="ISO8601")
     log = log_converter.apply(dataframe, variant=log_converter.Variants.TO_EVENT_LOG, parameters={"stream_postprocessing": False})
     pm4py.write_xes(log, "non_postprocessed.xes")

diff --git a/examples/dfg_min_ex_pandas.py b/examples/dfg_min_ex_pandas.py
@@ -18,7 +18,7 @@
 
 def execute_script():
     log_path = os.path.join("..", "tests", "input_data", "interval_event_log.csv")
-    dataframe = pd.read_csv(log_path, dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv(log_path)
     log_path = os.path.join("..", "tests", "input_data", "reviewing.xes")
     log = pm4py.read_xes(log_path)
     dataframe = pm4py.convert_to_dataframe(log)

diff --git a/examples/events_distribution.py b/examples/events_distribution.py
@@ -9,7 +9,7 @@
 
 
 def execute_script():
-    df = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"))
     df["time:timestamp"] = pd.to_datetime(df["time:timestamp"], utc=True, format="ISO8601")
     # plots the distribution of the events over the days of a month
     x0, y0 = attr_get.get_events_distribution(df, distr_type="days_month")

diff --git a/examples/heuminer_plusplus.py b/examples/heuminer_plusplus.py
@@ -8,7 +8,7 @@
 
 
 def execute_script():
-    df = pd.read_csv("../tests/input_data/interval_event_log.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv("../tests/input_data/interval_event_log.csv")
     df["time:timestamp"] = pd.to_datetime(df["time:timestamp"], utc=True, format="ISO8601")
     df["start_timestamp"] = pd.to_datetime(df["start_timestamp"], utc=True, format="ISO8601")
     log = pm4py.read_xes("../tests/input_data/interval_event_log.xes")

diff --git a/examples/link_analysis_vbfa.py b/examples/link_analysis_vbfa.py
@@ -5,7 +5,7 @@
 
 
 def execute_script():
-    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "ocel", "VBFA.zip"), compression="zip", dtype="str", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv(os.path.join("..", "tests", "input_data", "ocel", "VBFA.zip"), compression="zip", dtype="str")
     dataframe["time:timestamp"] = dataframe["ERDAT"] + " " + dataframe["ERZET"]
     dataframe["time:timestamp"] = pd.to_datetime(dataframe["time:timestamp"], format="%Y%m%d %H%M%S")
     dataframe["RFWRT"] = dataframe["RFWRT"].astype(float)

diff --git a/examples/merging_case_relations.py b/examples/merging_case_relations.py
@@ -7,11 +7,11 @@
 
 
 def execute_script():
-    dataframe1 = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_even.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe1 = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_even.csv"))
     dataframe1["time:timestamp"] = pd.to_datetime(dataframe1["time:timestamp"], utc=True, format="ISO8601")
-    dataframe2 = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_odd.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe2 = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_odd.csv"))
     dataframe2["time:timestamp"] = pd.to_datetime(dataframe2["time:timestamp"], utc=True, format="ISO8601")
-    case_relations = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "case_relations.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    case_relations = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "case_relations.csv"))
     merged = case_relations_merging.apply(dataframe1, dataframe2, case_relations)
     dfg, sa, ea = pm4py.discover_dfg(merged)
     pm4py.view_dfg(dfg, sa, ea, format=examples_conf.TARGET_IMG_FORMAT)

diff --git a/examples/perf_spectrum_visualization.py b/examples/perf_spectrum_visualization.py
@@ -9,7 +9,7 @@ def execute_script():
     log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "receipt.xes"))
     pm4py.view_performance_spectrum(log, ["Confirmation of receipt", "T04 Determine confirmation of receipt",
                                          "T10 Determine necessity to stop indication"], format=examples_conf.TARGET_IMG_FORMAT)
-    df = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"))
     df["time:timestamp"] = pd.to_datetime(df["time:timestamp"], utc=True, format="ISO8601")
     pm4py.view_performance_spectrum(df, ["Confirmation of receipt", "T04 Determine confirmation of receipt",
                                          "T10 Determine necessity to stop indication"], format=examples_conf.TARGET_IMG_FORMAT)

diff --git a/examples/simplified_interface.py b/examples/simplified_interface.py
@@ -12,7 +12,7 @@ def execute_script():
     log1 = pm4py.read_xes("../tests/input_data/running-example.xes")
 
     # reads a CSV into a dataframe
-    df = pd.read_csv("../tests/input_data/running-example.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    df = pd.read_csv("../tests/input_data/running-example.csv")
     df["time:timestamp"] = pd.to_datetime(df["time:timestamp"], utc=True, format="ISO8601")
     df["case:concept:name"] = df["case:concept:name"].astype("string")
 

diff --git a/examples/temporal_profile_dataframe.py b/examples/temporal_profile_dataframe.py
@@ -6,7 +6,7 @@
 
 
 def execute_script():
-    dataframe = pd.read_csv("../tests/input_data/receipt.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv("../tests/input_data/receipt.csv")
     dataframe = dataframe_utils.convert_timestamp_columns_in_df(dataframe, timest_format="ISO8601")
     tf = temporal_profile_discovery.apply(dataframe)
     conformance = temporal_profile_conformance.apply(dataframe, tf, parameters={"zeta": 6.0})

diff --git a/examples/timestamp_granularity.py b/examples/timestamp_granularity.py
@@ -5,7 +5,7 @@
 
 
 def execute_script():
-    dataframe = pd.read_csv("../tests/input_data/receipt.csv", dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    dataframe = pd.read_csv("../tests/input_data/receipt.csv")
     dataframe = pm4py.format_dataframe(dataframe, timest_format="ISO8601")
 
     # prints the original timestamp column of the dataframe

diff --git a/examples/timestamp_interleavings.py b/examples/timestamp_interleavings.py
@@ -7,11 +7,11 @@
 
 
 def execute_script():
-    receipt_even = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_even.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    receipt_even = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_even.csv"))
     receipt_even["time:timestamp"] = pd.to_datetime(receipt_even["time:timestamp"], utc=True, format="ISO8601")
-    receipt_odd = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_odd.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    receipt_odd = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "receipt_odd.csv"))
     receipt_odd["time:timestamp"] = pd.to_datetime(receipt_odd["time:timestamp"], utc=True, format="ISO8601")
-    case_relations = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "case_relations.csv"), dtype_backend=constants.DEFAULT_PANDAS_PARSING_DTYPE_BACKEND)
+    case_relations = pd.read_csv(os.path.join("..", "tests", "input_data", "interleavings", "case_relations.csv"))
     interleavings_dataframe = interleavings_miner.apply(receipt_even, receipt_odd, case_relations)
     print(interleavings_dataframe)
     # print the frequency and the direction of the interleavings