python - matplotlib 绘图速度非常慢

Question

我有多个函数，在其中输入数组或字典以及路径作为参数，该函数会将图形保存到特定路径的路径中。

尝试尽可能减少示例，但这里有两个函数:

def valueChartPatterns(dict,path):
    seen_values = Counter()

    for data in dict.itervalues():
        seen_values += Counter(data.values())

    seen_values = seen_values.most_common()
    seen_values_pct = map(itemgetter(1), tupleCounts2Percents(seen_values))
    seen_values_pct = ['{:.2%}'.format(item)for item in seen_values_pct]

    plt.figure()

    numberchart = plt.bar(range(len(seen_values)), map(itemgetter(1), seen_values), width=0.9,align='center')
    plt.xticks(range(len(seen_values)), map(itemgetter(0), seen_values))

    plt.title('Values in Pattern Dataset')
    plt.xlabel('Values in Data')
    plt.ylabel('Occurrences')

    plt.tick_params(axis='both', which='major', labelsize=6)
    plt.tick_params(axis='both', which='minor', labelsize=6)
    plt.tight_layout()

    plt.savefig(path)
    plt.clf()

def countryChartPatterns(dict,path):
    seen_countries = Counter()

    for data in dict.itervalues():
        seen_countries += Counter(data.keys())

    seen_countries = seen_countries.most_common()

    seen_countries_percentage = map(itemgetter(1), tupleCounts2Percents(seen_countries))
    seen_countries_percentage = ['{:.2%}'.format(item)for item in seen_countries_percentage]

    yvals = map(itemgetter(1), seen_countries)
    xvals = map(itemgetter(0), seen_countries)

    plt.figure()

    countrychart = plt.bar(range(len(seen_countries)), yvals, width=0.9,align='center')
    plt.xticks(range(len(seen_countries)), xvals)

    plt.title('Countries in Pattern Dataset')
    plt.xlabel('Countries in Data')
    plt.ylabel('Occurrences')

    plt.tick_params(axis='both', which='major', labelsize=6)
    plt.tick_params(axis='both', which='minor', labelsize=6)
    plt.tight_layout()

    plt.savefig(path)
    plt.clf()

一个非常小的示例字典是，但实际的字典包含 56000 个值:

dict = {"a": {"Germany": 20006.0, "United Kingdom": 20016.571428571428}, "b": {"Chad": 13000.0, "South Africa": 3000000.0},"c":{"Chad": 200061.0, "South Africa": 3000000.0}
    }

在我的脚本中，我调用:

if __name__ == "__main__":

    plt.close('all')

    print "Starting pattern charting...\n"

    countryChartPatterns(dict,'newPatternCountries.png'))

    valueChartPatterns(dict,'newPatternValues.png'))

注意，我加载import matplotlib.pyplot as plt。

在 PyCharm 中运行此脚本时，我在控制台中看到 Starting Pattern Charting...，但这些函数需要很长时间才能绘制。

我做错了什么？我是否应该使用直方图而不是条形图，因为这应该达到给出国家/值出现次数的相同目标？我可以以某种方式改变我的 GUI 后端吗？欢迎任何建议。

Answer 1

这是我在上面的评论中提到的测试，结果是:

Elapsed pre-processing = 13.79 s
Elapsed plotting = 0.17 s
Pre-processing / plotting = 83.3654562565

测试脚本:

import matplotlib.pylab as plt
from collections import Counter
from operator import itemgetter
import time

def countryChartPatterns(dict,path):
    # pre-processing -------------------
    t0 = time.time()

    seen_countries = Counter()

    for data in dict.itervalues():
        seen_countries += Counter(data.keys())

    seen_countries = seen_countries.most_common()

    yvals = map(itemgetter(1), seen_countries)
    xvals = map(itemgetter(0), seen_countries)

    dt1 = time.time() - t0
    print("Elapsed pre-processing = {0:.2f} s".format(dt1))

    t0 = time.time()

    # plotting -------------------
    plt.figure()

    countrychart = plt.bar(range(len(seen_countries)), yvals, width=0.9,align='center')
    plt.xticks(range(len(seen_countries)), xvals)

    plt.title('Countries in Pattern Dataset')
    plt.xlabel('Countries in Data')
    plt.ylabel('Occurrences')

    plt.tick_params(axis='both', which='major', labelsize=6)
    plt.tick_params(axis='both', which='minor', labelsize=6)
    plt.tight_layout()

    plt.savefig(path)
    plt.clf()

    dt2 = time.time() - t0 
    print("Elapsed plotting = {0:.2f} s".format(dt2))
    print("Pre-processing / plotting = {}".format(dt1/dt2))

if __name__ == "__main__":
    import random as rd
    import numpy as np

    countries = ["United States of America", "Afghanistan", "Albania", "Algeria", "Andorra", "Angola", "Antigua & Deps", "Argentina", "Armenia", "Australia", "Austria", "Azerbaijan"]

    def item():
        return {rd.choice(countries): np.random.randint(1e3), rd.choice(countries): np.random.randint(1e3)}
    dict = {}
    for i in range(1000000):
        dict[i] = item()

    print("Starting pattern charting...")

    countryChartPatterns(dict,'newPatternCountries.png')