matplotlib绘图非常慢

Question

我有多个函数，我输入一个数组或字典以及一个路径作为参数，该函数将一个图保存到特定路径的路径。

试图保持例如尽可能小，但这里有两个功能：

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() 

一个很小的例子快译通是，但实际字典包含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} 
    } 

而且在我的电话：

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，我在控制台中得到了Starting pattern charting...，但函数花费了超长时间才绘制出来。

我在做什么错？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/值的出现次数的相同目标？我可以以某种方式更改我的GUI后端吗？欢迎任何建议。

Answer 1

这是我在上面提到的意见，导致测试：

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')