From d70b96295d768aa0c80bf66639ad7a56bdef92a8 Mon Sep 17 00:00:00 2001
From: Terry Truong <terry06890@gmail.com>
Date: Sun, 2 Oct 2022 12:23:19 +1100
Subject: Add gen_pop_data.py

---
 backend/hist_data/gen_pop_data.py | 49 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100755 backend/hist_data/gen_pop_data.py

(limited to 'backend/hist_data/gen_pop_data.py')

diff --git a/backend/hist_data/gen_pop_data.py b/backend/hist_data/gen_pop_data.py
new file mode 100755
index 0000000..46c9c68
--- /dev/null
+++ b/backend/hist_data/gen_pop_data.py
@@ -0,0 +1,49 @@
+#!/usr/bin/python3
+
+"""
+Adds Wikipedia page view info to the database as popularity values.
+"""
+
+import os, sqlite3
+
+PAGEVIEWS_DB = os.path.join('enwiki', 'pageview_data.db')
+DB_FILE = 'data.db'
+
+def genData(pageviewsDb: str, dbFile: str) -> None:
+	dbCon = sqlite3.connect(dbFile)
+	dbCur = dbCon.cursor()
+	#
+	print('Getting event data')
+	titleToId: dict[str, int] = {}
+	for eventId, title in dbCur.execute('SELECT id, title FROM events'):
+		titleToId[title] = eventId
+	#
+	print('Getting view counts')
+	pdbCon = sqlite3.connect(pageviewsDb)
+	pdbCur = pdbCon.cursor()
+	titleToViews: dict[str, int] = {}
+	iterNum = 0
+	for title, views in pdbCur.execute('SELECT title, views from views'):
+		iterNum += 1
+		if iterNum % 1e6 == 0:
+			print(f'At iteration {iterNum}')
+		#
+		if title not in titleToId:
+			continue
+		titleToViews[title] = views
+	pdbCon.close()
+	#
+	print(f'Result: {len(titleToViews)} out of {len(titleToId)}')
+	dbCur.execute('CREATE TABLE pop (id INT PRIMARY KEY, pop INT)')
+	for title, views in titleToViews.items():
+		dbCur.execute('INSERT INTO pop VALUES (?, ?)', (titleToId[title], views))
+	#
+	dbCon.commit()
+	dbCon.close()
+
+if __name__ == '__main__':
+	import argparse
+	parser = argparse.ArgumentParser(description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter)
+	args = parser.parse_args()
+	#
+	genData(PAGEVIEWS_DB, DB_FILE)
-- 
cgit v1.2.3