python - 使用嵌套的 'for' 语句加速 Python 'if' 循环

Question

我正在尝试加快我正在运行的循环，以将数据分为两类。通常我不会太在意速度，但我发现现在这段代码的速度在多次迭代后实际上正在急剧下降。这是我编写代码的方式:

plane1Data = []
plane2Data = []
plane1Times = []
plane2Times = []
plane1Dets = []
plane2Dets = []
t1 = time.time()
for i in range(0,len(adcBoardVals)):#10000):
    tic = time.time()
    if adcBoardVals[i] == 5:
        if adcChannel[i] == 0:
            #detectorVal = detectorVal + [0]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [0]
        elif adcChannel[i] == 1:
            #detectorVal = detectorVal + [1]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [1]
        elif adcChannel[i] == 2:
            #detectorVal = detectorVal + [2]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [2]
        elif adcChannel[i] == 3:
            #detectorVal = detectorVal + [3]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [3]
        elif adcChannel[i] == 4:
            #detectorVal = detectorVal + [4]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            #plane1Dets = plane1Dets + [4]
        elif adcChannel[i] == 5:
            #detectorVal = detectorVal + [5]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [5]
        elif adcChannel[i] == 6:
            #detectorVal = detectorVal + [6]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [6]
        elif adcChannel[i] == 7:
            #detectorVal = detectorVal + [7]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [7]
    elif adcBoardVals[i] == 7:
        if adcChannel[i] == 0:
            #detectorVal = detectorVal + [16]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [16]
        elif adcChannel[i] == 1:
            #detectorVal = detectorVal + [17]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [17]
        elif adcChannel[i] == 2:
            #detectorVal = detectorVal + [18]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [18]
        elif adcChannel[i] == 3:
            #detectorVal = detectorVal + [19]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [19]
        elif adcChannel[i] == 4:
            #detectorVal = detectorVal + [20]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [20]
        elif adcChannel[i] == 5:
            #detectorVal = detectorVal + [21]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [21]
        elif adcChannel[i] == 6:
            #detectorVal = detectorVal + [22]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [22]
        elif adcChannel[i] == 7:
            #detectorVal = detectorVal + [23]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [23]
    elif adcBoardVals[i] == 6:
        if adcChannel[i] == 0:
            #detectorVal = detectorVal + [8]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [8]
        elif adcChannel[i] == 1:
            #detectorVal = detectorVal + [9]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [9]
        elif adcChannel[i] == 2:
            #detectorVal = detectorVal + [10]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [10]
        elif adcChannel[i] == 3:
            #detectorVal = detectorVal + [11]
            plane1Data = plane1Data + [rawDataMat[i,:]]
            plane1Times = plane1Times + [timeVals[i]]
            plane1Dets = plane1Dets + [11]
        elif adcChannel[i] == 4:
            #detectorVal = detectorVal + [12]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [12]
        elif adcChannel[i] == 5:
            #detectorVal = detectorVal + [13]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [13]
        elif adcChannel[i] == 6:
            #detectorVal = detectorVal + [14]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [14]
        elif adcChannel[i] == 7:
            #detectorVal = detectorVal + [15]
            plane2Data = plane2Data + [rawDataMat[i,:]]
            plane2Times = plane2Times + [timeVals[i]]
            plane2Dets = plane2Dets + [15]
    if i%100000 == 0:
        print('k = ',i)   
        toc = time.time()
        print('tictoc = ',toc-tic)
        print('elapsed = ',toc-t1)
    elif i>900000:
        if i%1000 == 0:
            print('k = ',i)
            toc = time.time()
            print('tictoc = ',toc-tic)
            print('elapsed = ',toc-t1)

#detectorVal = np.array(detectorVal,dtype='float')
plane1Data = np.array(plane1Data,dtype='float')
plane2Data = np.array(plane2Data,dtype='float')
plane1Times = np.array(plane1Times,dtype='float')
plane2Times = np.array(plane2Times,dtype='float')
plane1Dets = np.array(plane1Dets,dtype='int')
plane2Dets = np.array(plane2Dets,dtype='int')

我依稀记得不久前参加的一门 C++ 类(class)，你可以创建比嵌套的“if”语句运行得更快的列表。这是正确的吗？如果是这样，我可以在 python 中执行此操作吗？我现在正在运行 python 3.5。感谢您的帮助。

Answer 1

你的问题，是一个主要时间浪费，是表单的陈述

list_variable = list_variable + [ new_value ]

你在每个循环迭代中调用其中三个，例如:

plane1Data = plane1Data + [rawDataMat[i,:]]

因为您可能对 list_variable 指向的列表有额外的引用，Python 会在每次调用时构造列表的完整副本，只有在执行赋值时才会丢弃原始列表。对所有列表扩展使用以下表格，您会看到天文数字的改进:

list_variable += [ new_value ]

这是这确实发生的证据:

>>> from timeit import timeit
>>> x=list(range(100000))
>>> timeit("x += [99]", "from __main__ import x", number=1000)
0.00023529794998466969
>>> x=list(range(100000))
>>> timeit("x = x + [99]", "from __main__ import x", number=1000)
0.7576854809885845
>>> 0.7576854809885845 / 0.00023529794998466969
3220.110846855868

给你。对于这个包含 100000 个元素的列表，就地追加比复制和分配快 三千倍。如果您想衡量 yield ，您可以分析自己数据的一个子集。