Can I speedup YAML?

Question

I made a little test case to compare YAML and JSON speed :

import json
import yaml
from datetime import datetime
from random import randint

NB_ROW=1024

pri         


        

Answer 1

For reference, I compared a couple of human-readable formats and indeed Python's yaml reader is by far the slowest. (Note the log-scaling in the below plot.) If you're looking for speed, you want one of the JSON loaders, e.g., orjson:

---

Code to reproduce the plot:

import numpy
import perfplot

import json
import ujson
import orjson
import toml
import yaml
from yaml import Loader, CLoader
import pandas


def setup(n):
    numpy.random.seed(0)
    data = numpy.random.rand(n, 3)

    with open("out.yml", "w") as f:
        yaml.dump(data.tolist(), f)

    with open("out.json", "w") as f:
        json.dump(data.tolist(), f, indent=4)

    with open("out.dat", "w") as f:
        numpy.savetxt(f, data)

    with open("out.toml", "w") as f:
        toml.dump({"data": data.tolist()}, f)


def yaml_python(arr):
    with open("out.yml", "r") as f:
        out = yaml.load(f, Loader=Loader)
    return out


def yaml_c(arr):
    with open("out.yml", "r") as f:
        out = yaml.load(f, Loader=CLoader)
    return out


def json_load(arr):
    with open("out.json", "r") as f:
        out = json.load(f)
    return out


def ujson_load(arr):
    with open("out.json", "r") as f:
        out = ujson.load(f)
    return out


def orjson_load(arr):
    with open("out.json", "rb") as f:
        out = orjson.loads(f.read())
    return out


def loadtxt(arr):
    with open("out.dat", "r") as f:
        out = numpy.loadtxt(f)
    return out


def pandas_read(arr):
    out = pandas.read_csv("out.dat", header=None, sep=" ")
    return out.values


def toml_load(arr):
    with open("out.toml", "r") as f:
        out = toml.load(f)
    return out["data"]


perfplot.save(
    "out.png",
    setup=setup,
    kernels=[
        yaml_python,
        yaml_c,
        json_load,
        loadtxt,
        pandas_read,
        toml_load,
        ujson_load,
        orjson_load,
    ],
    n_range=[2 ** k for k in range(18)],
)