我正在尝试通过使用索引来优化对 SQLite 数据库的简单查询的性能。例如,表有 5M 行,5 列;该SELECT
语句是拾取所有列,该WHERE
语句仅检查 2 列。但是,除非我在多列索引中拥有所有列,否则查询的性能比没有任何索引时要差。
我是否错误地索引了列,或者在选择所有列时,我是否应该将所有列都包含在索引中以提高性能?
在每种情况下 # 是我在硬盘中创建 SQLite 数据库时得到的结果。但是,由于某种原因,使用该':memory:'
模式使得所有索引案例都比没有索引更快。
import sqlite3
import datetime
import pandas as pd
import numpy as np
import os
import time
# Simulate the data
size = 5000000
apps = [f'{i:010}' for i in range(size)]
dates = np.random.choice(pd.date_range('2016-01-01', '2019-01-01').to_pydatetime().tolist(), size)
prod_cd = np.random.choice([f'PROD_{i}' for i in range(30)], size)
models = np.random.choice([f'MODEL{i}' for i in range(15)], size)
categories = np.random.choice([f'GROUP{i}' for i in range(10)], size)
# create a db in memory
conn = sqlite3.connect(':memory:', detect_types=sqlite3.PARSE_DECLTYPES)
c = conn.cursor()
# Create table and insert data
c.execute("DROP TABLE IF EXISTS experiment")
c.execute("CREATE TABLE experiment (appId TEXT, dtenter TIMESTAMP, prod_cd TEXT, model TEXT, category TEXT)")
c.executemany("INSERT INTO experiment VALUES (?, ?, ?, ?, ?)", zip(apps, dates, prod_cd, models, categories))
# helper functions
def time_it(func):
def wrapper(*args, **kwargs):
start = time.time()
result = func(*args, **kwargs)
print("time for {} function is {}".format(func.__name__, time.time() - start))
return result
return wrapper
@time_it
def read_db(query):
df = pd.read_sql_query(query, conn)
return df
@time_it
def run_query(query):
output = c.execute(query).fetchall()
print(output)
# The main query
query = "SELECT * FROM experiment WHERE prod_cd IN ('PROD_1', 'PROD_5', 'PROD_10') AND dtenter >= '2018-01-01'"
# CASE #1: WITHOUT ANY INDEX
run_query("EXPLAIN QUERY PLAN " + query)
df = read_db(query)
>>> time for read_db function is 2.4783718585968018
# CASE #2: WITH INDEX FOR COLUMNS IN WHERE STATEMENT
run_query("DROP INDEX IF EXISTs idx")
run_query("CREATE INDEX idx ON experiment(prod_cd, dtenter)")
run_query("EXPLAIN QUERY PLAN " + query)
df = read_db(query)
>>> time for read_db function is 3.221407890319824
# CASE #3: WITH INDEX FOR MORE THEN WHAT IN WHERE STATEMENT, BUT NOT ALL COLUMNS
run_query("DROP INDEX IF EXISTs idx")
run_query("CREATE INDEX idx ON experiment(prod_cd, dtenter, appId, category)")
run_query("EXPLAIN QUERY PLAN " + query)
df = read_db(query)
>>>time for read_db function is 3.176532745361328
# CASE #4: WITH INDEX FOR ALL COLUMNS
run_query("DROP INDEX IF EXISTs idx")
run_query("CREATE INDEX idx ON experiment(prod_cd, dtenter, appId, category, model)")
run_query("EXPLAIN QUERY PLAN " + query)
df = read_db(query)
>>> time for read_db function is 0.8257918357849121