From 989390388e67ea22f4be5750e30ef757a4bd2a6c Mon Sep 17 00:00:00 2001 From: Nathaniel Kim Date: Mon, 8 Feb 2021 16:13:02 -0800 Subject: [PATCH] update bucket name, also notes --- backend/resumes/download.py | 3 ++- backend/resumes/notes.txt | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/backend/resumes/download.py b/backend/resumes/download.py index 55e1e8df..1aabc53a 100644 --- a/backend/resumes/download.py +++ b/backend/resumes/download.py @@ -8,7 +8,8 @@ from dev_settings_sensitive import GOOGLE_APPLICATION_CREDENTIALS # constants, please configure -GCLOUD_BUCKET_RESUMES = 'bc20-resumes' +# NOTE - Make sure to update GCLOUD_BUCKET_RESUMES! +GCLOUD_BUCKET_RESUMES = 'bc21-resumes' USERS_ALL_PATH = os.path.join(FILE_PATH, 'users_all.csv') USERS_TEAMS_PATH = os.path.join(FILE_PATH, 'users_teams.csv') NUM_RETRIES = 5 diff --git a/backend/resumes/notes.txt b/backend/resumes/notes.txt index d8dc2a34..efd5f4cb 100644 --- a/backend/resumes/notes.txt +++ b/backend/resumes/notes.txt @@ -1,6 +1,7 @@ First, we need info about all of the users. See `sql.txt` for two scripts, that produce two files (users_all.csv, users_teams.csv). Run the scripts and save the csvs, according to the instructions in sql.txt. -Next, run the `download.py` script. For posterity, here's an outline of what it does: +Next, run the `download.py` script. **Make sure to update GCLOUD_BUCKET_RESUMES!** +For posterity, here's an outline of what it does: pull all resumes (for all verified ones), preserve user ids for each group of users (hs us, hs intl, college us, college intl, others that aren't devs): in ascending scrim rank, find associated resume