diff options
Diffstat (limited to 'deprecated/mem_tests/clean_data.py')
-rwxr-xr-x | deprecated/mem_tests/clean_data.py | 29 |
1 files changed, 0 insertions, 29 deletions
diff --git a/deprecated/mem_tests/clean_data.py b/deprecated/mem_tests/clean_data.py deleted file mode 100755 index 1433ba41..00000000 --- a/deprecated/mem_tests/clean_data.py +++ /dev/null @@ -1,29 +0,0 @@ -#!/usr/bin/python2 -"""Cleans output from other scripts to eliminate duplicates. - -When frequently sampling data, we see that records occasionally will contain -the same timestamp (due to perf recording twice in the same second). - -This removes all of the duplicate timestamps for every record. Order with -respect to timestamps is not preserved. Also, the assumption is that the log -file is a csv with the first value in each row being the time in seconds from a -standard time. - -""" - -import argparse - -parser = argparse.ArgumentParser() -parser.add_argument('filename') -args = parser.parse_args() - -my_file = open(args.filename) -output_file = open('clean2.csv', 'a') -dictionary = dict() - -for line in my_file: - new_time = int(line.split(',')[0]) - dictionary[new_time] = line - -for key in dictionary.keys(): - output_file.write(dictionary[key]) |