aboutsummaryrefslogtreecommitdiff
path: root/backend/tol_data/gen_pop_data.py
diff options
context:
space:
mode:
authorTerry Truong <terry06890@gmail.com>2023-01-29 11:30:47 +1100
committerTerry Truong <terry06890@gmail.com>2023-01-29 11:30:47 +1100
commit8781fdb2b8c530a6c1531ae9e82221eb062e34fb (patch)
treeffd824aa9b945d69b47f012617ee13d98764d078 /backend/tol_data/gen_pop_data.py
parentf5e87ae628bab0eef97b3e3e62f6d71cca9c99c0 (diff)
Adjust backend coding style
Add line spacing, section comments, and import consistency
Diffstat (limited to 'backend/tol_data/gen_pop_data.py')
-rwxr-xr-xbackend/tol_data/gen_pop_data.py15
1 files changed, 8 insertions, 7 deletions
diff --git a/backend/tol_data/gen_pop_data.py b/backend/tol_data/gen_pop_data.py
index e6a646e..4280a12 100755
--- a/backend/tol_data/gen_pop_data.py
+++ b/backend/tol_data/gen_pop_data.py
@@ -5,7 +5,9 @@ Reads enwiki page view info from a database, and stores it
as node popularity values in the database.
"""
-import os, sqlite3
+import argparse
+import os
+import sqlite3
PAGEVIEWS_DB = os.path.join('enwiki', 'pageview_data.db')
DB_FILE = 'data.db'
@@ -13,7 +15,7 @@ DB_FILE = 'data.db'
def genData(pageviewsDb: str, dbFile: str) -> None:
dbCon = sqlite3.connect(dbFile)
dbCur = dbCon.cursor()
- #
+
print('Getting view counts')
pdbCon = sqlite3.connect(pageviewsDb)
pdbCur = pdbCon.cursor()
@@ -23,23 +25,22 @@ def genData(pageviewsDb: str, dbFile: str) -> None:
iterNum += 1
if iterNum % 1e4 == 0:
print(f'At iteration {iterNum}') # Reached 1.6e6
- #
+
row = dbCur.execute('SELECT name FROM wiki_ids WHERE id = ?', (wikiId,)).fetchone()
if row is not None:
nodeToViews[row[0]] = views
pdbCon.close()
- #
+
print(f'Writing {len(nodeToViews)} entries to db')
dbCur.execute('CREATE TABLE node_pop (name TEXT PRIMARY KEY, pop INT)')
for nodeName, views in nodeToViews.items():
dbCur.execute('INSERT INTO node_pop VALUES (?, ?)', (nodeName, 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)