style: clean up remaining flake8 errors

docs/conf.py

@@ -32,14 +32,14 @@
 
 # -- Project information -----------------------------------------------------
 
-project = u"hatchet"
-copyright = u"2017-2019, Lawrence Livermore National Security, LLC"
-author = u"Abhinav Bhatele"
+project = "hatchet"
+copyright = "2017-2019, Lawrence Livermore National Security, LLC"
+author = "Abhinav Bhatele"
 
 # The short X.Y version
-version = u""
+version = ""
 # The full version, including alpha/beta/rc tags
-release = u""
+release = ""
 
 
 # -- General configuration ---------------------------------------------------
@@ -81,7 +81,7 @@
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path .
-exclude_patterns = [u"_build", "Thumbs.db", ".DS_Store"]
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 # The name of the Pygments (syntax highlighting) style to use.
 pygments_style = "sphinx"
@@ -159,15 +159,15 @@
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, "hatchet.tex", u"hatchet Documentation", u"Abhinav Bhatele", "manual")
+    (master_doc, "hatchet.tex", "hatchet Documentation", "Abhinav Bhatele", "manual")
 ]
 
 
 # -- Options for manual page output ------------------------------------------
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [(master_doc, "hatchet", u"hatchet Documentation", [author], 1)]
+man_pages = [(master_doc, "hatchet", "hatchet Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output ----------------------------------------------
@@ -179,7 +179,7 @@
     (
         master_doc,
         "hatchet",
-        u"hatchet Documentation",
+        "hatchet Documentation",
         author,
         "hatchet",
         "One line description of project.",

examples/caliper.py

@@ -12,9 +12,8 @@
 ##############################################################################
 
 from __future__ import print_function
-from hatchet import *
-import sys
 import pandas as pd
+import hatchet as ht
 
 pd.set_option("display.width", 1500)
 pd.set_option("display.max_colwidth", 20)
@@ -26,7 +25,7 @@
         "hatchet/tests/data/caliper-lulesh-json/lulesh-sample-annotation-profile.json"
     )
 
-    gf = GraphFrame()
+    gf = ht.GraphFrame()
     gf.from_caliper(filename)
 
     print(gf.dataframe)

examples/dag_literal.py

@@ -12,16 +12,16 @@
 ##############################################################################
 
 from __future__ import print_function
-from hatchet import *
-import sys
 import pandas as pd
+import hatchet as ht
+
 
 pd.set_option("display.width", 500)
 pd.set_option("display.max_colwidth", 30)
 
 
 if __name__ == "__main__":
-    gf = GraphFrame()
+    gf = ht.GraphFrame()
     gf.from_literal(
         [
             {

examples/gprof_dot.py

@@ -12,16 +12,15 @@
 ##############################################################################
 
 from __future__ import print_function
-from hatchet import *
-import sys
 import pandas as pd
+import hatchet as ht
 
 pd.set_option("display.width", 500)
 pd.set_option("display.max_colwidth", 30)
 
 
 if __name__ == "__main__":
-    gf = GraphFrame()
+    gf = ht.GraphFrame()
     gf.from_gprof_dot("hatchet/tests/data/gprof2dot-cpi/callgrind.dot.64042.0.1")
 
     print(gf.dataframe)

examples/hpctoolkit.py

@@ -12,9 +12,8 @@
 ##############################################################################
 
 from __future__ import print_function
-from hatchet import *
-import sys
 import pandas as pd
+import hatchet as ht
 
 pd.set_option("display.width", 500)
 pd.set_option("display.max_colwidth", 30)
@@ -23,7 +22,7 @@
 if __name__ == "__main__":
     dirname = "hatchet/tests/data/hpctoolkit-cpi-database"
 
-    gf = GraphFrame()
+    gf = ht.GraphFrame()
     gf.from_hpctoolkit(dirname)
 
     print(gf.dataframe.xs(0, level="rank"))

examples/tree_literal.py

@@ -12,16 +12,15 @@
 ##############################################################################
 
 from __future__ import print_function
-from hatchet import *
-import sys
 import pandas as pd
+import hatchet as ht
 
 pd.set_option("display.width", 500)
 pd.set_option("display.max_colwidth", 30)
 
 
 if __name__ == "__main__":
-    gf = GraphFrame()
+    gf = ht.GraphFrame()
     gf.from_literal(
         [
             {

hatchet/__init__.py

@@ -10,4 +10,10 @@
 # Please also read the LICENSE file for the MIT License notice.
 ##############################################################################
 
-from .graphframe import *
+# make flake8 unused names in this file.
+# flake8: noqa: F401
+
+from .graphframe import GraphFrame
+from .hpctoolkit_reader import HPCToolkitReader
+from .caliper_reader import CaliperReader
+from .gprof_dot_reader import GprofDotReader

hatchet/caliper_reader.py

@@ -137,14 +137,14 @@ def create_graphframe(self):
                         self.json_cols[idx]
                     ].apply(
                         lambda x: re.match(
-                            "(.*):(\d+)", self.json_nodes[x]["label"]
+                            r"(.*):(\d+)", self.json_nodes[x]["label"]
                         ).group(1)
                     )
                     self.df_json_data["line"] = self.df_json_data[
                         self.json_cols[idx]
                     ].apply(
                         lambda x: re.match(
-                            "(.*):(\d+)", self.json_nodes[x]["label"]
+                            r"(.*):(\d+)", self.json_nodes[x]["label"]
                         ).group(2)
                     )
                     self.df_json_data.drop(self.json_cols[idx], axis=1, inplace=True)

hatchet/external/printtree.py

@@ -73,8 +73,8 @@ def as_text(
     rank,
     threshold,
     expand_names,
-    indent=u"",
-    child_indent=u"",
+    indent="",
+    child_indent="",
     unicode=False,
     color=False,
 ):
@@ -107,15 +107,15 @@ def as_text(
 
         # add context (filename etc.) if requested
         if context in dataframe.columns:
-            result = u"{indent}{time_str} {function}  {c.faint}{code_position}{c.end}\n".format(
+            result = "{indent}{time_str} {function}  {c.faint}{code_position}{c.end}\n".format(
                 indent=indent,
                 time_str=time_str,
                 function=func_name,
                 code_position=dataframe.loc[df_index, context],
                 c=colors_enabled if color else colors_disabled,
             )
         else:
-            result = u"{indent}{time_str} {function}\n".format(
+            result = "{indent}{time_str} {function}\n".format(
                 indent=indent, time_str=time_str, function=func_name
             )
 
@@ -136,11 +136,11 @@ def as_text(
 
         for child in children:
             if child is not last_child:
-                c_indent = child_indent + (u"├─ " if unicode else "|- ")
-                cc_indent = child_indent + (u"│  " if unicode else "|  ")
+                c_indent = child_indent + ("├─ " if unicode else "|- ")
+                cc_indent = child_indent + ("│  " if unicode else "|  ")
             else:
-                c_indent = child_indent + (u"└─ " if unicode else "`- ")
-                cc_indent = child_indent + u"   "
+                c_indent = child_indent + ("└─ " if unicode else "`- ")
+                cc_indent = child_indent + "   "
             result += as_text(
                 child,
                 dataframe,

hatchet/frame.py

@@ -9,7 +9,6 @@
 # For details, see: https://github.com/LLNL/hatchet
 # Please also read the LICENSE file for the MIT License notice.
 ##############################################################################
-import sys
 
 from functools import total_ordering
 

hatchet/gprof_dot_reader.py

@@ -17,7 +17,7 @@
 from .graph import Graph
 from .frame import Frame
 from .util.timer import Timer
-from .util.config import *
+from .util.config import dot_keywords
 
 
 class GprofDotReader:

hatchet/graphframe.py

@@ -97,12 +97,10 @@ def parse_node_literal(child_dict, hparent):
         for i in range(len(graph_dict)):
             graph_root = Node(Frame({"name": graph_dict[i]["name"]}), None)
 
-            node_dicts.append(
-                dict(
-                    {"node": graph_root, "name": graph_dict[i]["name"]},
-                    **graph_dict[i]["metrics"]
-                )
-            )
+            node_dict = {"node": graph_root, "name": graph_dict[i]["name"]}
+            node_dict.update(**graph_dict[i]["metrics"])
+            node_dicts.append(node_dict)
+
             list_roots.append(graph_root)
 
             # call recursively on all children of root
@@ -196,7 +194,6 @@ def squash(self):
             filtered_nodes = self.dataframe.index
 
         node_clone = {}
-        old_to_new_id = {}
 
         # function to connect a node to the nearest descendants that are in the
         # list of filtered nodes
@@ -224,7 +221,6 @@ def rewire_tree(node, clone, is_root, roots):
                     node_label = new_child.frame
                     if node_label not in label_to_new_child.keys():
                         new_child_clone = Node(new_child.frame, clone)
-                        idx = squ_idx
                         squ_idx += 1
                         clone.add_child(new_child_clone)
                         label_to_new_child[node_label] = new_child_clone

hatchet/hpctoolkit_reader.py

@@ -41,7 +41,7 @@ def read_metricdb_file(args):
     """ Read a single metricdb file into a 1D array """
     filename, num_nodes, num_metrics, shape = args
     rank = int(
-        re.search("\-(\d+)\-(\d+)\-([\w\d]+)\-(\d+)\-\d.metric-db$", filename).group(1)
+        re.search(r"\-(\d+)\-(\d+)\-([\w\d]+)\-(\d+)\-\d.metric-db$", filename).group(1)
     )
 
     with open(filename, "rb") as metricdb:
@@ -84,8 +84,8 @@ def __init__(self, dir_name):
         # Read one metric-db file to extract the number of nodes in the CCT
         # and the number of metrics
         with open(metricdb_files[0], "rb") as metricdb:
-            tag = metricdb.read(18)
-            version = metricdb.read(5)
+            metricdb.read(18)  # skip tag
+            metricdb.read(5)  # skip version TODO: should we?
             endian = metricdb.read(1)
 
             if endian == b"b":

hatchet/tests/callgrind.py

@@ -10,9 +10,6 @@
 # Please also read the LICENSE file for the MIT License notice.
 ##############################################################################
 
-import sys
-import pytest
-
 from hatchet import GraphFrame, GprofDotReader
 
 roots = [

hatchet/util/timer.py

@@ -47,9 +47,9 @@ def end_phase(self):
 
     def __str__(self):
         out = StringIO()
-        out.write(u"Times:\n")
+        out.write("Times:\n")
         for phase, delta in self._times.items():
-            out.write(u"    %-20s %.2fs\n" % (phase + ":", delta.total_seconds()))
+            out.write("    %-20s %.2fs\n" % (phase + ":", delta.total_seconds()))
         return out.getvalue()
 
     @contextmanager

scripts/metricdb_reader.py

@@ -11,13 +11,16 @@
 # Please also read the LICENSE file for the MIT License notice.
 ##############################################################################
 
+from __future__ import print_function
+
 import glob
 import struct
 import numpy as np
+
 # np.set_printoptions(threshold=np.inf)
 
 # Read all .metric-db files in the current directory
-mdbfiles = glob.glob('*.metric-db')
+mdbfiles = glob.glob("*.metric-db")
 num_pes = len(mdbfiles)
 
 # Read header from one of the .metric-db files
@@ -28,15 +31,15 @@
 endian = metricdb.read(1)
 
 # Big endian
-if endian == 'b':
-    num_nodes = struct.unpack('>i', metricdb.read(4))[0]
-    num_metrics = struct.unpack('>i', metricdb.read(4))[0]
+if endian == "b":
+    num_nodes = struct.unpack(">i", metricdb.read(4))[0]
+    num_metrics = struct.unpack(">i", metricdb.read(4))[0]
 # TODO: complete for litte endian
 
 metricdb.close()
 
-print "Tag: %s Version: %s Endian: %s" % (tag, version, endian)
-print "Files: %d Nodes: %d Metrics: %d" % (num_pes, num_nodes, num_metrics)
+print("Tag: %s Version: %s Endian: %s" % (tag, version, endian))
+print("Files: %d Nodes: %d Metrics: %d" % (num_pes, num_nodes, num_metrics))
 
 # Create a single metrics array
 metrics = np.empty([num_pes, num_nodes, num_metrics])
@@ -47,8 +50,7 @@
     metricdb.seek(32)
     # currently assumes a big endian binary and reads all the metrics at once
     # into a numpy array
-    arr = np.fromfile(metricdb, dtype=np.dtype('>f8'),
-                      count = num_nodes * num_metrics)
+    arr = np.fromfile(metricdb, dtype=np.dtype(">f8"), count=num_nodes * num_metrics)
     metrics[index] = arr.reshape(num_nodes, num_metrics)
     # alternate method of reading the file one metric at a time
     # for i in range(0, num_nodes):