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

fit-alessandro-berti · fit-alessandro-berti · commit 8bea3b6cf773 · 2020-11-10T09:22:46.000+01:00
diff --git a/RELEASE_NOTES b/RELEASE_NOTES
@@ -1,3 +1,6 @@
+===== PM4Py 2.0.1.2 =====
+This is a minor release, fixing the compatibility of the streaming package with Python 3.5.x - 3.7.x
+
 ===== PM4Py 2.0.1 =====
 This is a minor release, consisting of the following changes:
 1. commit 81579e19e
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -24,9 +24,9 @@
 author = 'Fraunhofer FIT'
 
 # The short X.Y version
-version = '2.0'
+version = '2.0.1'
 # The full version, including alpha/beta/rc tags
-release = '4'
+release = '2.0.1'
 
 # -- General configuration ---------------------------------------------------
 
diff --git a/examples/pn_to_pt.py b/examples/pn_to_pt.py
@@ -6,7 +6,6 @@
 from pm4py.evaluation.wf_net import evaluator as is_wf_net
 from pm4py.objects.conversion.process_tree import converter as pt_converter
 from pm4py.objects.conversion.wf_net import converter as wf_net_converter
-from pm4py.objects.process_tree.util import fold
 
 
 def execute_script():
@@ -30,25 +29,17 @@ def execute_script():
                                            parameters={woflan.Parameters.RETURN_ASAP_WHEN_NOT_SOUND: True,
                                                        woflan.Parameters.PRINT_DIAGNOSTICS: False}))
     try:
-        tree_alpha = wf_net_converter.apply(alpha_petri_net, alpha_im, alpha_fm, parameters={"debug": False})
-        if tree_alpha is not None:
-            tree_alpha = fold(tree_alpha)
+        tree_alpha = wf_net_converter.apply(alpha_petri_net, alpha_im, alpha_fm)
         print(tree_alpha)
     except:
         traceback.print_exc()
     try:
-        tree_heuristics = wf_net_converter.apply(heuristics_petri_net, heuristics_im, heuristics_fm,
-                                                 parameters={"debug": False})
-        if tree_heuristics is not None:
-            tree_heuristics = fold(tree_heuristics)
+        tree_heuristics = wf_net_converter.apply(heuristics_petri_net, heuristics_im, heuristics_fm)
         print(tree_heuristics)
     except:
         traceback.print_exc()
     try:
-        tree_inductive = wf_net_converter.apply(inductive_petri_net, inductive_im, inductive_fm,
-                                                parameters={"debug": False})
-        if tree_inductive is not None:
-            tree_inductive = fold(tree_inductive)
+        tree_inductive = wf_net_converter.apply(inductive_petri_net, inductive_im, inductive_fm)
         print(tree_inductive)
         pm4py.view_process_tree(tree_inductive, format="svg")
     except:
diff --git a/examples/streaming_conformance_footprints.py b/examples/streaming_conformance_footprints.py
@@ -32,7 +32,7 @@ def execute_script():
     # the conditions on the closure of all the cases are checked
     # (for each case, it is checked whether the end activity of the case
     # is possible according to the footprints)
-    diagn_df = conf_obj._current_result()
+    diagn_df = conf_obj.get()
     conf_obj.terminate_all()
     print(diagn_df)
     print(diagn_df[diagn_df["is_fit"] == False])
diff --git a/examples/streaming_conformance_tbr.py b/examples/streaming_conformance_tbr.py
@@ -29,7 +29,7 @@ def execute_script():
     # sends a termination signal to the conformance checking algorithm;
     # the conditions on the closure of all the cases are checked
     # (for each case, it is checked whether the final marking is reached)
-    diagn_df = conf_obj._current_result()
+    diagn_df = conf_obj.get()
     conf_obj.terminate_all()
     print(diagn_df)
     print(diagn_df[diagn_df["is_fit"] == False])
diff --git a/examples/streaming_discovery_dfg.py b/examples/streaming_discovery_dfg.py
@@ -25,7 +25,7 @@ def execute_script():
     # stops the live event stream
     live_stream.stop()
     # gets the DFG along with the start and end activities from the stream
-    dfg, activities, start_activities, end_activities = stream_dfg_disc._current_result()
+    dfg, activities, start_activities, end_activities = stream_dfg_disc.get()
     # visualize the DFG
     gviz = dfg_visualizer.apply(dfg, variant=dfg_visualizer.Variants.FREQUENCY, activities_count=activities,
                                 parameters={"start_activities": start_activities, "end_activities": end_activities})
diff --git a/pm4py/__init__.py b/pm4py/__init__.py
@@ -55,7 +55,7 @@
 else:
     logging.error("intervaltree is not available. This can lead some features of PM4Py to not work correctly!")
 
-__version__ = '2.0.1.1'
+__version__ = '2.0.1.2'
 __doc__ = "Process Mining for Python (PM4Py)"
 __author__ = 'Fraunhofer Institute for Applied Technology'
 __author_email__ = 'pm4py@fit.fraunhofer.de'
@@ -78,8 +78,8 @@
 from pm4py.stats import get_start_activities, get_end_activities, get_attributes, get_attribute_values, get_variants, \
     get_trace_attributes
 
-# this package is available only for Python >= 3.7
-if sys.version_info >= (3, 7):
+# this package is available only for Python >= 3.5
+if sys.version_info >= (3, 5):
     from pm4py import streaming
 
     if pkgutil.find_loader("sympy"):
diff --git a/pm4py/filtering.py b/pm4py/filtering.py
@@ -1,31 +1,5 @@
-import pkgutil
-
-from pm4py.util import constants, xes_constants
-
-
-def check_is_dataframe(log):
-    if pkgutil.find_loader("pandas"):
-        import pandas as pd
-        return type(log) is pd.DataFrame
-
-    return False
-
-
-def check_dataframe_columns(df):
-    """
-    Checks if the dataframe contains all the required columns.
-    If not, raise an exception
-
-    Parameters
-    --------------
-    df
-        Pandas dataframe
-    """
-    if len(set(df.columns).intersection(
-            set([constants.CASE_CONCEPT_NAME, xes_constants.DEFAULT_NAME_KEY,
-                 xes_constants.DEFAULT_TIMESTAMP_KEY]))) < 3:
-        raise Exception(
-            "please format your dataframe accordingly! df = pm4py.format_dataframe(df, case_id='<name of the case ID column>', activity_key='<name of the activity column>', timestamp_key='<name of the timestamp column>')")
+from pm4py.util import constants
+from pm4py.util.pandas_utils import check_is_dataframe, check_dataframe_columns
 
 
 def filter_start_activities(log, admitted_start_activities):
diff --git a/pm4py/read.py b/pm4py/read.py
@@ -59,8 +59,9 @@ def read_csv(file_path, sep=",", quotechar=None, encoding='utf-8', nrows=1000000
         logging.error(
             "Less than three columns were imported from the CSV file. Please check the specification of the separation and the quote character!")
     else:
-        logging.warning(
-            "Please specify the format of the dataframe: df = pm4py.format_dataframe(df, case_id='<name of the case ID column>', activity_key='<name of the activity column>', timestamp_key='<name of the timestamp column>')")
+        #logging.warning(
+        #    "Please specify the format of the dataframe: df = pm4py.format_dataframe(df, case_id='<name of the case ID column>', activity_key='<name of the activity column>', timestamp_key='<name of the timestamp column>')")
+        pass
 
     return df
 
@@ -99,8 +100,8 @@ def format_dataframe(df, case_id=constants.CASE_CONCEPT_NAME, activity_key=xes_c
     df = pandas_utils.insert_index(df, INDEX_COLUMN)
     # sorts the dataframe
     df = df.sort_values([constants.CASE_CONCEPT_NAME, xes_constants.DEFAULT_TIMESTAMP_KEY, INDEX_COLUMN])
-    logging.warning(
-        "please convert the dataframe for advanced process mining applications. log = pm4py.convert_to_event_log(df)")
+    # logging.warning(
+    #    "please convert the dataframe for advanced process mining applications. log = pm4py.convert_to_event_log(df)")
     return df
 
 
diff --git a/pm4py/stats.py b/pm4py/stats.py
@@ -1,29 +1,4 @@
-import pkgutil
-
-from pm4py.util import constants, xes_constants
-
-
-def check_is_dataframe(log):
-    if pkgutil.find_loader("pandas"):
-        import pandas as pd
-        return type(log) is pd.DataFrame
-    return False
-
-
-def check_dataframe_columns(df):
-    """
-    Checks if the dataframe contains all the required columns.
-    If not, raise an exception
-
-    Parameters
-    --------------
-    df
-        Pandas dataframe
-    """
-    if len(set(df.columns).intersection(
-            {constants.CASE_CONCEPT_NAME, xes_constants.DEFAULT_NAME_KEY, xes_constants.DEFAULT_TIMESTAMP_KEY})) < 3:
-        raise Exception(
-            "please format your dataframe accordingly! df = pm4py.format_dataframe(df, case_id='<name of the case ID column>', activity_key='<name of the activity column>', timestamp_key='<name of the timestamp column>')")
+from pm4py.util.pandas_utils import check_is_dataframe, check_dataframe_columns
 
 
 def get_start_activities(log):
diff --git a/pm4py/streaming/algo/interface.py b/pm4py/streaming/algo/interface.py
@@ -1,6 +1,6 @@
 import abc
 from threading import Lock
-from typing import final
+#from typing import final
 
 
 class StreamingAlgorithm(abc.ABC):
@@ -15,13 +15,12 @@ def _process(self, event):
     def _current_result(self):
         pass
 
-    @final
     def get(self):
         self._lock.acquire()
-        self._current_result()
+        ret = self._current_result()
         self._lock.release()
+        return ret
 
-    @final
     def receive(self, event):
         self._lock.acquire()
         self._process(event)
diff --git a/pm4py/util/pandas_utils.py b/pm4py/util/pandas_utils.py
@@ -1,4 +1,6 @@
-from pm4py.util import constants
+import pkgutil
+
+from pm4py.util import constants, xes_constants
 
 
 def to_dict_records(df):
@@ -52,3 +54,40 @@ def insert_index(df, column_name=constants.DEFAULT_INDEX_KEY):
     df = df.copy()
     df[column_name] = df.index
     return df
+
+
+def check_is_dataframe(log):
+    """
+    Checks if a log object is a dataframe
+
+    Parameters
+    -------------
+    log
+        Log object
+
+    Returns
+    -------------
+    boolean
+        Is dataframe?
+    """
+    if pkgutil.find_loader("pandas"):
+        import pandas as pd
+        return type(log) is pd.DataFrame
+    return False
+
+
+def check_dataframe_columns(df):
+    """
+    Checks if the dataframe contains all the required columns.
+    If not, raise an exception
+
+    Parameters
+    --------------
+    df
+        Pandas dataframe
+    """
+    if len(set(df.columns).intersection(
+            set([constants.CASE_CONCEPT_NAME, xes_constants.DEFAULT_NAME_KEY,
+                 xes_constants.DEFAULT_TIMESTAMP_KEY]))) < 3:
+        raise Exception(
+            "please format your dataframe accordingly! df = pm4py.format_dataframe(df, case_id='<name of the case ID column>', activity_key='<name of the activity column>', timestamp_key='<name of the timestamp column>')")
diff --git a/tests/wf_to_pt.py b/tests/wf_to_pt.py
