azalea/CSC110-Project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[+] Add num postings data to processed user

Browse Source
This commit is contained in:
Hykilpikonna
2021-11-23 11:06:35 -05:00
parent 1efe0eface
commit 47255e9c46
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/process/twitter_process.py
+4 -1
View File
@@ -16,6 +16,8 @@ class UserPopularity(NamedTuple):
username: str username: str
# A measurement of a user's popularity, such as followers count # A measurement of a user's popularity, such as followers count
popularity: int popularity: int
# Number of tweets
num_postings: int
def process_users_popularity(user_dir: str = './data/twitter/user/') -> None: def process_users_popularity(user_dir: str = './data/twitter/user/') -> None:
@@ -39,7 +41,8 @@ def process_users_popularity(user_dir: str = './data/twitter/user/') -> None:
if filename.endswith('.json') and not filename.startswith('.'): if filename.endswith('.json') and not filename.startswith('.'):
# Read # Read
user = json.loads(read(f'{user_dir}/users/{filename}')) user = json.loads(read(f'{user_dir}/users/{filename}'))
users.append(UserPopularity(user['screen_name'], user['followers_count'])) users.append(UserPopularity(user['screen_name'], user['followers_count'],
user['statuses_count']))
# Log progress # Log progress
if len(users) % 2000 == 0: if len(users) % 2000 == 0: