Python 2.7 序列化python 2.x/3.x的性能差异

在将pandas帧序列化为CSV时，我遇到了python 2.7和3.5之间的一些性能差异

于是在谷歌上快速搜索，找到了这个基准：

并根据我的需要对其进行了一些修改：

import pandas as pd
from time import time
import platform

def timeit(func, n=5):
    start = time()
    for i in range(n):
        func()
    end = time()
    return (end - start) / n


def csvdumps(s):
    s.to_csv('foo')
    return 'foo'

def csvloads(fn):
    return pd.read_csv(fn)

def hdfdumps(s):
    s.to_hdf('foo', 'bar', mode='w')
    return ('foo', 'bar')

def hdfloads(path):
    return pd.read_hdf('foo', 'bar')

df = pd.DataFrame({'text': [str(i % 1000) for i in range(1000000)],
                   'numbers': range(1000000)})

keys = ['csv', 'hdfstore']

d = {'csv': [csvloads, csvdumps],
     'hdfstore': [hdfloads, hdfdumps]}


result = dict()
for name, (loads, dumps) in d.items():
    text = dumps(df.text)
    numbers = dumps(df.numbers)
    result[name] = {'text': {'dumps': timeit(lambda: dumps(df.text)),
                             'loads': timeit(lambda: loads(text))},
                 'numbers': {'dumps': timeit(lambda: dumps(df.numbers)),
                             'loads': timeit(lambda: loads(numbers))}}
########
# Plot #
########

# Much of this was taken from
# http://nbviewer.ipython.org/gist/mwaskom/886b4e5cb55fed35213d
# by Michael Waskom

import matplotlib.pyplot as plt
import seaborn as sns
sns.set(style="whitegrid", font_scale=1.3)

w, h = 7, 7
f, (left, right) = plt.subplots(nrows=1, ncols=2, sharex=True, figsize=(w*2, h), squeeze=True)

df = pd.DataFrame({'loads': [result[key]['text']['loads'] for key in keys],
                   'dumps': [result[key]['text']['dumps'] for key in keys],
                   'storage': keys})
df = pd.melt(df, "storage", value_name="duration", var_name="operation")

sns.barplot("duration", "storage", "operation", data=df, ax=left)
left.set(xlabel="Duration (s)", ylabel="")
sns.despine(bottom=True)
left.set_title('Cost to Serialize Text')
left.legend(loc="lower center", ncol=2, frameon=True, title="operation")

df = pd.DataFrame({'loads': [result[key]['numbers']['loads'] for key in keys],
                   'dumps': [result[key]['numbers']['dumps'] for key in keys],
                   'storage': keys})
df = pd.melt(df, "storage", value_name="duration", var_name="operation")

sns.barplot("duration", "storage", "operation", data=df, ax=right)
right.set(xlabel="Duration (s)", ylabel="")
sns.despine(bottom=True)
right.set_title('Cost to Serialize Numerical Data')
right.legend(loc="lower center", ncol=2, frameon=True, title="operation")

plt.savefig('serialize_py'+'.'.join(platform.python_version_tuple())+'.png')

正如您在python 3的结果中所看到的，序列化速度要慢得多：

        python 2.7  python 3.5  diff
load    0.3504s     0.329005s   +06.50%
dump    1.2784s     3.333152s   -61.65%

有人知道为什么吗