关于计划大量数据的建议

Question

我正在研制一种非常便宜的地震仪，主要用于教育和一些研究。我想每隔几个小时用matplotlib显示一个地震道的地震信号，如我所附的图像。你知道吗

问题是，每秒钟我就得到100个数据点，当我在树莓pi上绘制这些数据时，通常会挂起并停止工作。你知道吗

我为每个4小时子图绘制数据的方法是再次读取所有数据并仅在子图的界限之间绘制，但我发现这没有效率，可能是悬钩子的原因。你知道吗

我已经想了好几天了，怎么做才能避免每个子地块占用大量内存，但我找不到答案，因为我是地质学家，编程对我来说是个大问题。你知道吗

有人有更好的主意吗？你知道吗

import matplotlib.pyplot as plt
import time
import os.path
import datetime
import sys
import numpy
import pytz
import matplotlib.dates as mdates
import ftplib
from pylab import *
import numpy as np
from itertools import islice
from time import sleep
from matplotlib.pyplot import specgram
from scipy.signal import medfilt
import csv
archivo='sismo1545436800'

def subirftp(archivosubir):
    session = ftplib.FTP('---', 's---   ', '----')
    file = open(archivosubir+'.png', 'rb')  # file to send
    session.storbinary('STOR '+ archivosubir +'.png', file)  # send the file
    dirlist = session.retrlines('LIST')
    file.close()  # close file and FTP
    session.quit()

font = {'family': 'serif',
            'color': 'darkred',
            'weight': 'normal',
            'size': 16,
            }

fu = open('Z:/nchazarra/sismografos/' + str(archivo) + '.txt')
nr_of_lines = sum(1 for line in fu)
fu.close()
f = open('Z:/nchazarra/sismografos/' + str(archivo) + '.txt')

print(nr_of_lines)
csv_f = csv.reader(f)
#row_count = sum(1 for row in csv_f)
#print(row_count)
tiempo = []
valora = []
valores = []
tiempor = []
i=0
final=0
empiezo=time.time()

for row in islice(csv_f,0,nr_of_lines-1):
        # print (row[0])
        if i == 0:
            inicio = double(row[0])
            valor = datetime.datetime.fromtimestamp(float(row[0]),tz=pytz.utc)
            tiempo.append(valor)
            i = i + 1
        else:
            valor = datetime.datetime.fromtimestamp(float(row[0]),tz=pytz.utc)
            #print(valor)
            tiempo.append(valor)
            # print(row)

        try:
            valora.append(int(row[1]))
            # print(row[0])
        except IndexError:
            valora.append(0)
        except ValueError:
            valora.append(0)

valores = valora
tiempor = tiempo
mediana = np.mean(valores)
minimo = np.amin(valores)
maximo = np.amax(valores)
std = np.std(valores)
for index in range(len(valores)):
        valores[index] = float(((valores[index] - minimo) / (maximo - minimo))-1)

mediananueva = float(np.median(valores))
for index in range(len(valores)):
    valores[index] = float(valores[index] - mediananueva)

valores2=np.asarray(valores)
tiempo2=np.asarray(tiempo)

#Franja de 0 a 4
franja1=plt.subplot(611)
franja1.axis([datetime.datetime(2018, 12, 22,00,00), datetime.datetime(2018, 12, 22,3,59,59),-0.05,0.05])
franja1.plot(tiempo2, valores2, lw=0.2,color='red')
#Franja de 4 a 8
franja2=plt.subplot(612)
franja2.axis([datetime.datetime(2018, 12, 22,4,00), datetime.datetime(2018, 12, 22,8,00),-0.05,0.05])
franja2.plot(tiempo2, valores2, lw=0.2,color='green')

#Franja de 8 a 12
franja3=plt.subplot(613)
franja3.axis([datetime.datetime(2018, 12, 22,8,00), datetime.datetime(2018, 12, 22,12,00),-0.05,0.05])
franja3.plot(tiempo2, valores2, lw=0.2,color='blue')
#Franja de 12 a 16

franja4=plt.subplot(614)
franja4.axis([datetime.datetime(2018, 12, 22,12,00), datetime.datetime(2018, 12, 22,16,00),-0.05,0.05])
franja4.plot(tiempo2, valores2, lw=0.2,color='red')

#franja de 16 a 20

franja5=plt.subplot(615)
franja5.axis([datetime.datetime(2018, 12, 22,16,00), datetime.datetime(2018, 12, 22,20,00),-0.05,0.05])
franja5.plot(tiempo2, valores2, lw=0.2,color='green')

#Franja de 20 a 24
franja6=plt.subplot(616)
franja6.axis([datetime.datetime(2018, 12, 22,20,00), datetime.datetime(2018, 12, 22,23,59,59),-0.05,0.05])
franja6.plot(tiempo2, valores2, lw=0.2,color='blue')

franja1.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja2.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja3.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja4.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja5.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja6.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))

acabo=time.time()
cuantotardo=acabo-empiezo
print('Madre mía, he tardado en hacer esto '+str(cuantotardo)+' segundos')

savefig(archivo + ".png", dpi=300)
subirftp(archivo)
plt.show()

Answer 1

是否需要绘制每个数据点？你可以考虑每100左右绘制一次。只要你的信号频率不太高，我想它可以工作。像这样：

import matplotlib.pyplot as plt
import numpy as np

X = np.arange(10000) / 10000 * 2 * np.pi
Y = np.sin(X) + np.random.normal(size=10000) / 10

plt.plot(X[::100], Y[::100])

对所有点：

Answer 2

通过在绘制阵列之前对其进行子设置，可以节省大量内存：

import datetime

import matplotlib.pyplot as plt
import matplotlib.dates as mdates
import numpy as np

n_times = 24 * 60 * 60 * 100
times = [
    datetime.datetime(2018, 12, 22,00,00) +
    datetime.timedelta(milliseconds=10 * x) for x in range(n_times)]
tiempo2 = np.array(times)
valores2 = np.random.normal(size=n_times)

#Franja de 0 a 4
franja1=plt.subplot(611)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 0, 0),
                       tiempo2 < datetime.datetime(2018, 12, 22, 4, 0, 0))
franja1.plot(tiempo2[index], valores2[index], lw=0.2,color='red')

#Franja de 4 a 8
franja2=plt.subplot(612)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 4, 0),
                       tiempo2 < datetime.datetime(2018, 12, 22, 8, 0, 0))
franja2.plot(tiempo2[index], valores2[index], lw=0.2,color='green')

#Franja de 8 a 12
franja3=plt.subplot(613)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 8, 0),
                       tiempo2 < datetime.datetime(2018, 12, 22, 12, 0, 0))
franja3.plot(tiempo2[index], valores2[index], lw=0.2,color='blue')
#Franja de 12 a 16

franja4=plt.subplot(614)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 12, 0),
                       tiempo2 < datetime.datetime(2018, 12, 22, 16, 0, 0))
franja4.plot(tiempo2[index], valores2[index], lw=0.2,color='red')

#franja de 16 a 20

franja5=plt.subplot(615)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 16, 0),
                       tiempo2 < datetime.datetime(2018, 12, 22, 20, 0, 0))
franja5.plot(tiempo2[index], valores2[index], lw=0.2,color='green')

#Franja de 20 a 24
franja6=plt.subplot(616)
index = np.logical_and(tiempo2 >= datetime.datetime(2018, 12, 22, 20, 0),
                       tiempo2 < datetime.datetime(2018, 12, 23, 0, 0, 0))
franja6.plot(tiempo2[index], valores2[index], lw=0.2,color='blue')

franja1.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja2.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja3.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja4.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja5.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))
franja6.xaxis.set_major_formatter(mdates.DateFormatter('%H:%M'))

plt.show()