我编写了一些示例脚本来创建您的数据库并遍历其所有元素。它看起来比你在评论中写的要快得多。您确定数据库访问是瓶颈吗?也许在你的脚本中你做了更多的事情,这需要很多时间。
我检查了 2 个数据库 SQLite 和 MongoDB,有 500 万个项目。对于 SQLite,插入所有行大约需要 1200 秒,选择它们大约需要 300 秒。MongoDB 更快,插入大约需要 400 秒,而选择不到 100 秒。
请用我的示例检查您的代码,并检查您的选择是否相似。我使用游标而不是 LIMIT/OFFSET。如果这仍然没有帮助,那么我认为 MongoDB 值得一试。它有一个缺点 - 它需要 64 位操作系统来支持大型数据库(如您的)。如果您之前使用过它,那么这里是 Windows 的最短安装指南:
这是我用于 SQLite 的 python 3.x 测试脚本
import sqlite3
from time import time
conn = sqlite3.connect('test.dbase')
c = conn.cursor()
c.execute("""PRAGMA journal_mode = OFF""")
c.execute("""PRAGMA synchronous = 0""")
c.execute("""PRAGMA locking_mode = EXCLUSIVE""")
c.execute("""PRAGMA count_change = OFF""")
c.execute("""PRAGMA temp_store = 2""")
c.execute("""CREATE TABLE tmpTranscripts_arm_3R_transcripts (id INTEGER PRIMARY KEY, name varchar(255), chromosome varchar(255), start int(11), end int(11), direction tinyint(4), tags varchar(1023), bin int(11), exons varchar(10000))""")
c.execute("""CREATE INDEX 'iTranscript_arm_3R_14943' ON 'tmpTranscripts_arm_3R_transcripts' (start, end, direction)""")
t1 = time()
for i in range(0, 5000000):
c.execute("""INSERT INTO tmpTranscripts_arm_3R_transcripts (name, chromosome, start, end, direction, tags, bin, exons) VALUES ('SRR060644.1', 'arm_3R', %d, %d, %d, 'feature=transcript;bestRegion=(self);nbGaps=0;nbMismatches=0;ID=SRR060644.1;identity=100.0', 300011450, '')""" % ((i+123)%352, (i+523)%422, (i+866)%536))
if(not i%10000):
print("Insert:", i)
t2 = time()
print("Insert time", t2-t1)
conn.commit()
t1 = time()
c.execute("""SELECT * FROM tmpTranscripts_arm_3R_transcripts ORDER BY start, end, direction""")
i = 0
for row in c:
a = row[0]
if(not i%10000):
print("Get:", i, row)
i+=1
t2 = time()
print("Sort time", t2-t1)
c.close()
对于 MongoDB
from pymongo import Connection
from pymongo import ASCENDING, DESCENDING
from time import time
connection = Connection()
connection = Connection('localhost', 27017)
db = connection['test-database']
collection = db['test-collection']
posts = db.posts
posts.create_index([("start", ASCENDING), ("end", ASCENDING), ("direction", ASCENDING)])
t1 = time()
for i in range(0, 5000000):
post = { "name": 'SRR060644.1',
"chromosome": 'arm_3R',
"start": (i+123)%352,
"end": (i+523)%422,
"direction": (i+866)%536,
"tags": 'feature=transcript;bestRegion=(self);nbGaps=0;nbMismatches=0;ID=SRR060644.1;identity=100.0',
"bin": 300011450,
"exons": ''}
posts.insert(post)
if(not i%10000):
print("Insert:", i)
t2 = time()
print("Insert time", t2-t1)
t1 = time()
i = 0
for post in posts.find().sort([("start", ASCENDING), ("end", ASCENDING), ("direction", ASCENDING)]):
if(not i%10000):
print("Get:", i, post)
i+=1
t2 = time()
print("Sort time", t2-t1)