MPI events, and some general realism changes

pipit/trace.py

@@ -5,6 +5,7 @@
 
 import numpy as np
 import pandas as pd
+import ast
 
 
 class Trace:
@@ -72,6 +73,13 @@ def from_csv(filename):
         # ensure that ranks are ints
         events_dataframe = events_dataframe.astype({"Process": "int32"})
 
+        # ensure that the attributes are a dict, not a string
+        if "Attributes" in events_dataframe.columns:
+            # use literal_eval so we're not running a security risk
+            events_dataframe["Attributes"] = events_dataframe["Attributes"].apply(
+                ast.literal_eval
+            )
+
         # make certain columns categorical
         events_dataframe = events_dataframe.astype(
             {

pipit/util/fake.py

@@ -1,9 +1,12 @@
 from pipit import Trace
 import numpy as np
-from faketest import gen_fake_tree, emit_tree_file
+from faketest import gen_fake_tree, emit_tree_file, gen_forest
 import pandas as pd
 
 
+function_names = ["foo", "bar", "baz", "quux", "grault", "garply", "waldo"]
+
+
 def test_with_fake_data():
     """
     Generate a fake test file and ground truth file, read the test file
@@ -12,7 +15,8 @@ def test_with_fake_data():
     """
     num_processes = 8
     # generate one fake tree per process, 2000 functions in the tree
-    trees = [gen_fake_tree(2000) for n in range(num_processes)]
+    seed_tree = gen_fake_tree(200, function_names)
+    trees = gen_forest(seed_tree, num_processes)
     test_file = open("fake.csv", "w")
     ground_truth = open("fake_ground.csv", "w")
     emit_tree_file(trees, test_file, ground_truth)