mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

concat data for final stuff

Browse Source
This commit is contained in:
Matthew Gaughan 2023-12-17 18:12:22 -06:00
parent f0f2647b39
commit f1060e47af
2 changed files with 5122 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5106
expanded_data_final.csv Normal file
View File

File diff suppressed because it is too large Load Diff

22
text_pp.py
View File

@ -2,7 +2,7 @@ import os
import csv import csv
import json import json
path = '/data/users/mgaughan/kkex_comment_data_120523/' path = '/data/users/mgaughan/kkex_comment_final/'
empty_file_dict = {'data': {'repository': {'issues': {'edges': []}}}} empty_file_dict = {'data': {'repository': {'issues': {'edges': []}}}}
@ -22,10 +22,8 @@ def check_files_for_content(filelist):
os.remove(filepath) os.remove(filepath)
opened_file.close() opened_file.close()
continue continue
list_of_issues= file_contents['data']['repository']['issues']['edges'] #list_of_issues= file_contents['data']['repository']['issues']['edges']
handle_repo_issues(list_of_issues) #handle_repo_issues(list_of_issues)
if x > 7:
break
#print(bad_data_files) #print(bad_data_files)
def handle_repo_issues(list_of_issues): def handle_repo_issues(list_of_issues):
@ -42,6 +40,18 @@ def handle_issue_comments(list_of_comments):
print("------------------") print("------------------")
print(comment_body) print(comment_body)
def concat_csv():
with open("121223_expanded_data.csv", "r") as f1:
first_block = f1.read()
with open("121323_expanded_data.csv", "r") as f2:
second_block = f2.read()
with open("expanded_data_final.csv", "w") as f3:
f3.write(first_block)
f3.write("\n")
f3.write(second_block)
if __name__ == "__main__": if __name__ == "__main__":
check_files_for_content(os.listdir(path)) #check_files_for_content(os.listdir(path))
concat_csv()