Created
May 27, 2018 01:24
-
-
Save llllllllll/8e2307dd50a8bc0e534ee0015d4d5588 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
import networkx | |
import toolz | |
df = pd.read_csv('/home/joe/downloads/debug.csv', escapechar='\\') | |
df.columns = ['stack', 'module', 'function', 'lineno', 'id', 'type', 'repr'] | |
g = networkx.DiGraph() | |
for row in df[df.module == '__main__'].itertuples(): | |
g.add_node('.'.join((row.module, row.function)), **{row.id: row.type}) | |
for u, v in toolz.sliding_window(2, row.stack.split(';')): | |
u = u.split(':', 1)[0] | |
v = v.split(':', 1)[0] | |
g.add_edge(v, u) | |
def f(group): | |
stacks = [ | |
[v.split(':', 1)[0] for v in stack] | |
for stack in group['stack'].str.split(';').tolist() | |
] | |
it = iter(stacks) | |
head = next(it) | |
for e in it: | |
if e[-len(head):] != head: | |
head = e | |
else: | |
print( | |
f'{group.iloc[0]["id"]}={group.iloc[0]["repr"]} {e}', | |
) | |
df.groupby('id').apply(f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment