python-为什么不总是缓存所有不变的对象?

我不确定下面代码的python对象模型到底发生了什么。

您可以从此下载ctabus.csv文件的数据 link

import csv

def read_as_dicts(filename):
    records = []
    with open(filename) as f:
        rows = csv.reader(f)
        headers = next(rows)

        for row in rows:
            route = row[0]
            date = row[1]
            daytype = row[2]
            rides = int(row[3])
            records.append({
                    'route': route,
                    'date': date,
                    'daytype': daytype,
                    'rides': rides})

    return records

# read data from csv
rows = read_as_dicts('ctabus.csv')
print(len(rows)) #736461

# record route ids (object ids)
route_ids = set()
for row in rows:
    route_ids.add(id(row['route']))

print(len(route_ids)) #690072

# unique_routes
unique_routes = set()
for row in rows:
    unique_routes.add(row['route'])

print(len(unique_routes)) #185

当我呼唤 print(len(route_ids)) 资讯科技印刷 "690072" . 为什么python最终创建了这些多个对象?

我估计这个数字是185或736461。因为,当我计算集合中的唯一路线时,集合的长度为185。736461因为,这是csv文件中记录的总数。

这个奇怪的数字“690072”是什么?

我试图理解为什么这种部分缓存?为什么python不能执行像下面这样的完全缓存。

import csv

route_cache = {}

#some hack to cache
def cached_route(routename):
    if routename not in route_cache:
        route_cache[routename] = routename
    return route_cache[routename]

def read_as_dicts(filename):
    records = []
    with open(filename) as f:
        rows = csv.reader(f)
        headers = next(rows)

        for row in rows:
            row[0] = cached_route(row[0]) #cache trick
            route = row[0]
            date = row[1]
            daytype = row[2]
            rides = int(row[3])
            records.append({
                    'route': route,
                    'date': date,
                    'daytype': daytype,
                    'rides': rides})

    return records

# read data from csv
rows = read_as_dicts('ctabus.csv')
print(len(rows)) #736461

# unique_routes
unique_routes = set()
for row in rows:
    unique_routes.add(row['route'])

print(len(unique_routes)) #185

# record route ids (object ids)
route_ids = set()
for row in rows:
    route_ids.add(id(row['route']))

print(len(route_ids)) #185