From 141f310d87f4fd7c3a4c728bf278c10fadc19606 Mon Sep 17 00:00:00 2001 From: Terry Truong Date: Wed, 5 Oct 2022 22:45:52 +1100 Subject: Add reduce_event_data.py Add unit test, update README --- backend/hist_data/README.md | 3 +++ backend/hist_data/reduce_event_data.py | 39 ++++++++++++++++++++++++++++++++++ 2 files changed, 42 insertions(+) create mode 100755 backend/hist_data/reduce_event_data.py (limited to 'backend/hist_data') diff --git a/backend/hist_data/README.md b/backend/hist_data/README.md index 96c31b5..bfecc1e 100644 --- a/backend/hist_data/README.md +++ b/backend/hist_data/README.md @@ -73,3 +73,6 @@ Some of the scripts use third-party packages: 1. Additional events can be described in `picked/events.json`, with images for them put in `picked` (see the README for details). 1. Can run `gen_picked_data.py` to add those described events to the database. + +## Remove Events Without Images/Descs +1. Run `reduce_event_data.py` to remove data for events that have no image/description. diff --git a/backend/hist_data/reduce_event_data.py b/backend/hist_data/reduce_event_data.py new file mode 100755 index 0000000..15c2ab5 --- /dev/null +++ b/backend/hist_data/reduce_event_data.py @@ -0,0 +1,39 @@ +#!/usr/bin/python3 + +""" +Delete extraneous events from the database that have no image (and consequently no description) +""" + +import argparse +import sqlite3 + +DB_FILE = 'data.db' + +def reduceData(dbFile: str) -> None: + dbCon = sqlite3.connect(dbFile) + dbCur = dbCon.cursor() + # + print('Getting events to delete') + eventsToDel = set() + query = 'SELECT events.id FROM events LEFT JOIN event_imgs ON events.id = event_imgs.id WHERE event_imgs.id IS NULL' + for (eventId,) in dbCur.execute(query): + eventsToDel.add(eventId) + # + print('Deleting events') + iterNum = 0 + for eventId in eventsToDel: + iterNum += 1 + if iterNum % 1e5 == 0: + print(f'At iteration {iterNum}') + # + dbCur.execute('DELETE from events where id = ?', (eventId,)) + dbCur.execute('DELETE from pop where id = ?', (eventId,)) + # + dbCon.commit() + dbCon.close() + +if __name__ == '__main__': + parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter) + args = parser.parse_args() + # + reduceData(DB_FILE) -- cgit v1.2.3