- android - 多次调用 OnPrimaryClipChangedListener
- android - 无法更新 RecyclerView 中的 TextView 字段
- android.database.CursorIndexOutOfBoundsException : Index 0 requested, 光标大小为 0
- android - 使用 AppCompat 时,我们是否需要明确指定其 UI 组件(Spinner、EditText)颜色
我写了一个 python 代码来管理大量数据,因此需要很多时间。所以,我发现了 Cython,并开始更改我的代码。
基本上,我所做的就是更改函数的声明(cdef 类型名称(带有变量类型的参数)),声明 cdef 变量及其类型,并声明 cdef 类。我正在写所有 .pyx
使用 Eclipse,我正在使用命令 python setup.py build_ext --inplace
进行编译并使用 eclipse 运行它。
我的问题是比较 python 和 cython 的速度,没有任何区别。
我运行命令 cython -a <file>
生成一个html文件,里面有很多黄线。
我不知道我做错了什么,我应该包括其他东西,我不知道如何删除这些黄线。
我只是粘贴了一些代码行,那是我想加快速度的部分,因为代码很长。
'''there are a lot of ndarray objects stored in a file and in this step I get each of them until there are no more items '''
cdef ReadWavePoints (WavePointManagement wavePointManagement, ColumnManagement columnManagement):
cdef int runReadWavePoints
wavePointManagement.OpenWavePointFileLoad(wavePointsFile)
runReadWavePoints = 1
while runReadWavePoints == 1:
try:
wavePointManagement.LoadWavePointFile()
wavePointManagement.RoundCoordinates()
wavePointManagement.SortWavePointList()
GroupColumnsVoxels(wavePointManagement.GetWavePointList(), columnManagement)
except:
wavePointManagement.CloseWavePointFile()
columnManagement.CloseWriteColumnFile()
break
'''I check which points are in the same XYZ (voxel) and in the same XY (column)'''
cdef GroupColumnsVoxels (object wavePointList, ColumnManagement columnManagement):
cdef int indexWavePointRef, indexWavePoint
cdef int saved
cdef double voxelValue
cdef int sizeWavePointList
sizeWavePointList = len(wavePointList)
indexWavePointRef = 0
while indexWavePointRef < sizeWavePointList - 1:
saved = 0
voxelValue = (wavePointList[indexWavePointRef]).GetValue()
for indexWavePoint in xrange(indexWavePointRef + 1, len(wavePointList)):
if (wavePointList[indexWavePointRef]).GetX() == (wavePointList[indexWavePoint]).GetX() and (wavePointList[indexWavePointRef]).GetY() == (wavePointList[indexWavePoint]).GetY():
if (wavePointList[indexWavePointRef]).GetZ() == (wavePointList[indexWavePoint]).GetZ():
if voxelValue < (wavePointList[indexWavePoint]).GetValue():
voxelValue = (wavePointList[indexWavePoint]).GetValue()
else:
saved = 1
CheckVoxel((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ(), voxelValue)
indexWavePointRef = indexWavePoint
if indexWavePointRef == sizeWavePointList - 1:
CheckVoxel((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ(), (wavePointList[indexWavePointRef]).GetValue())
break
else:
saved = 1
CheckVoxel((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ(), voxelValue)
columnObject = columnInstance.Column((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY())
columnManagement.AddColumn(columnObject)
MaximumHeightColumn((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ())
indexWavePointRef = indexWavePoint
break
if saved == 0:
CheckVoxel((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ(), voxelValue)
indexWavePointRef = indexWavePoint
columnObject = columnInstance.Column((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY())
columnManagement.AddColumn(columnObject)
MaximumHeightColumn((wavePointList[indexWavePointRef]).GetX(), (wavePointList[indexWavePointRef]).GetY(), (wavePointList[indexWavePointRef]).GetZ())
'''I check if the data stored in a voxel is lower than the new one; if its the case, I store it'''
cdef CheckVoxel (double X, double Y, double Z, double newValue):
cdef object bandVoxel, structvalCheckVoxel, out_str
cdef tuple valueCheckVoxel
bandVoxel = datasetVoxels.GetRasterBand(int(math.floor(Z/0.3))+1)
structvalCheckVoxel = bandVoxel.ReadRaster(int(math.floor((X-Xmin)/0.25)), int(math.floor((Ymax-Y)/0.25)), 1, 1, buf_type=gdal.GDT_Float32)
valueCheckVoxel = struct.unpack('f', structvalCheckVoxel)
if newValue > valueCheckVoxel[0]:
out_str = struct.pack('f', newValue)
bandVoxel.WriteRaster(int(math.floor((X-Xmin)/0.25)), int(math.floor((Ymax-Y)/0.25)), 1, 1, out_str)
'''I check if this point has the highest Z and I store this information'''
cdef MaximumHeightColumn(double X, double Y, double newZ):
cdef object bandMetricMaximumHeightColumn, structvalMaximumHeightColumn, out_strMaximumHeightColumn
cdef tuple valueMaximumHeightColumn
bandMetricMaximumHeightColumn = datasetMetrics.GetRasterBand(10)
structvalMaximumHeightColumn = bandMetricMaximumHeightColumn.ReadRaster(int(math.floor((X-Xmin)/0.25)), int(math.floor((Ymax-Y)/0.25)), 1, 1, buf_type=gdal.GDT_Float32)
valueMaximumHeightColumn = struct.unpack('f', structvalMaximumHeightColumn)
if newZ > round(valueMaximumHeightColumn[0], 1):
out_strMaximumHeightColumn = struct.pack('f', newZ)
bandMetricMaximumHeightColumn.WriteRaster(int(math.floor((X-Xmin)/0.25)), int(math.floor((Ymax-Y)/0.25)), 1, 1, out_strMaximumHeightColumn)
'''this class serializes, rounds and sorts the points of each ndarray'''
import cPickle as pickle
import numpy as np
cimport numpy as np
import math
cdef class WavePointManagement(object):
'''
This class manages all the points extracted from the waveform
'''
cdef object fileObject, wavePointList
__slots__ = ('wavePointList', 'fileObject')
def __cinit__(self):
'''
Constructor
'''
self.fileObject = None
self.wavePointList = np.array([])
cdef object GetWavePointList(self):
return self.wavePointList
cdef void OpenWavePointFileLoad (self, object fileName):
self.fileObject = file(fileName, 'rb')
cdef void LoadWavePointFile (self):
self.wavePointList = None
self.wavePointList = pickle.load(self.fileObject)
cdef void SortWavePointList (self):
self.wavePointList = sorted(self.wavePointList, key=lambda k: (k.x, k.y, k.z))
cdef void RoundCoordinates (self):
cdef int indexPointObject, sizeWavePointList
for pointObject in self.GetWavePointList():
pointObject.SetX(round(math.floor(pointObject.GetX()/0.25)*0.25, 2))
pointObject.SetY(round(math.ceil(pointObject.GetY()/0.25)*0.25, 2))
pointObject.SetZ(round(math.floor(pointObject.GetZ()/0.3)*0.3, 1))
cdef void CloseWavePointFile(self):
self.fileObject.close()
from distutils.core import setup
from distutils.extension import Extension
from Cython.Distutils import build_ext
import numpy
ext = Extension("main", ["main.pyx"], include_dirs = [numpy.get_include()])
setup (ext_modules=[ext],
cmdclass = {'build_ext' : build_ext}
)
'''this is the file I run with eclipse after compiling'''
from main import main
main()
我怎样才能加快这段代码的速度?
最佳答案
您的代码在使用 numpy 数组和列表之间来回跳转。因此,cython 生成的代码几乎没有区别。
下面的代码生成一个python列表,key函数也是一个纯python函数。
self.wavePointList = sorted(self.wavePointList, key=lambda k: (k.x, k.y, k.z))
您需要使用 ndarray.sort
(如果您不想就地排序,则可以使用 numpy.sort
)。为此,您还需要更改对象在数组中的存储方式。也就是说,您需要使用 structured array .参见 numpy.sort
有关如何对结构化数组进行排序的示例 - 特别是页面上的最后两个示例。
将数据存储在 numpy 数组中后,您需要告诉 cython 数据是如何存储在数组中的。这包括提供类型信息和数组的维度。 This page提供了有关如何高效使用 numpy 数组的更多信息。
创建和排序结构化数组的示例:
import numpy as np
cimport numpy as np
DTYPE = [('name', 'S10'), ('height', np.float64), ('age', np.int32)]
cdef packed struct Person:
char name[10]
np.float64_t height
np.int32_t age
ctypedef Person DTYPE_t
def create_array():
values = [('Arthur', 1.8, 41), ('Lancelot', 1.9, 38),
('Galahad', 1.7, 38)]
return np.array(values, dtype=DTYPE)
cpdef sort_by_age_then_height(np.ndarray[DTYPE_t, ndim=1] arr):
arr.sort(order=['age', 'height'])
最后,您需要将代码从使用 Python 方法转换为使用标准 C 库方法,以进一步加快速度。下面是一个使用 RoundCoordinates
的例子。 ``cpdef` 意味着该函数也通过包装函数暴露给 python。
cimport cython
cimport numpy as np
from libc.math cimport floor, ceil, round
import numpy as np
DTYPE = [('x', np.float64), ('y', np.float64), ('z', np.float64)]
cdef packed struct Point3D:
np.float64_t x, y, z
ctypedef Point3D DTYPE_t
# Caution should be used when turning the bounds check off as it can lead to undefined
# behaviour if you use an invalid index.
@cython.boundscheck(False)
cpdef RoundCoordinates_cy(np.ndarray[DTYPE_t] pointlist):
cdef int i
cdef DTYPE_t point
for i in range(len(pointlist)): # this line is optimised into a c loop
point = pointlist[i] # creates a copy of the point
point.x = round(floor(point.x/0.25)*2.5) / 10
point.y = round(ceil(point.y/0.25)*2.5) / 10
point.z = round(floor(point.z/0.3)*3) / 10
pointlist[i] = point # overwrites the old point data with the new data
最后,在重写整个代码库之前,您应该分析代码以查看程序花费大部分时间的函数并在优化其他函数之前优化这些函数。
关于python - 加速cython代码,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/28276078/
我尝试理解[c代码 -> 汇编]代码 void node::Check( data & _data1, vector& _data2) { -> push ebp -> mov ebp,esp ->
我需要在当前表单(代码)的上下文中运行文本文件中的代码。其中一项要求是让代码创建新控件并将其添加到当前窗体。 例如,在Form1.cs中: using System.Windows.Forms; ..
我有此 C++ 代码并将其转换为 C# (.net Framework 4) 代码。有没有人给我一些关于 malloc、free 和 sprintf 方法的提示? int monate = ee; d
我的网络服务器代码有问题 #include #include #include #include #include #include #include int
给定以下 html 代码,将列表中的第三个元素(即“美丽”一词)以斜体显示的 CSS 代码是什么?当然,我可以给这个元素一个 id 或一个 class,但 html 代码必须保持不变。谢谢
关闭。这个问题不符合Stack Overflow guidelines .它目前不接受答案。 我们不允许提问寻求书籍、工具、软件库等的推荐。您可以编辑问题,以便用事实和引用来回答。 关闭 7 年前。
我试图制作一个宏来避免重复代码和注释。 我试过这个: #define GrowOnPage(any Page, any Component) Component.Width := Page.Surfa
我正在尝试将我的旧 C++ 代码“翻译”成头条新闻所暗示的 C# 代码。问题是我是 C# 中的新手,并不是所有的东西都像 C++ 中那样。在 C++ 中这些解决方案运行良好,但在 C# 中只是不能。我
在 Windows 10 上工作,R 语言的格式化程序似乎没有在 Visual Studio Code 中完成它的工作。我试过R support for Visual Studio Code和 R-T
我正在处理一些报告(计数),我必须获取不同参数的计数。非常简单但乏味。 一个参数的示例查询: qCountsEmployee = ( "select count(*) from %s wher
最近几天我尝试从 d00m 调试网络错误。我开始用尽想法/线索,我希望其他 SO 用户拥有可能有用的宝贵经验。我希望能够提供所有相关信息,但我个人无法控制服务器环境。 整个事情始于用户注意到我们应用程
我有一个 app.js 文件,其中包含如下 dojo amd 模式代码: require(["dojo/dom", ..], function(dom){ dom.byId('someId').i
我对“-gencode”语句中的“code=sm_X”选项有点困惑。 一个例子:NVCC 编译器选项有什么作用 -gencode arch=compute_13,code=sm_13 嵌入库中? 只有
我为我的表格使用 X-editable 框架。 但是我有一些问题。 $(document).ready(function() { $('.access').editable({
我一直在通过本教程学习 flask/python http://blog.miguelgrinberg.com/post/the-flask-mega-tutorial-part-i-hello-wo
我想将 Vim 和 EMACS 用于 CNC、G 代码和 M 代码。 Vim 或 EMACS 是否有任何语法或模式来处理这种类型的代码? 最佳答案 一些快速搜索使我找到了 this vim 和 thi
关闭。这个问题不符合Stack Overflow guidelines .它目前不接受答案。 想改进这个问题?更新问题,使其成为 on-topic对于堆栈溢出。 7年前关闭。 Improve this
这个问题在这里已经有了答案: Enabling markdown highlighting in Vim (5 个回答) 6年前关闭。 当我在 Vim 中编辑包含 Markdown 代码的 READM
我正在 Swift3 iOS 中开发视频应用程序。基本上我必须将视频 Assets 和音频与淡入淡出效果合并为一个并将其保存到 iPhone 画廊。为此,我使用以下方法: private func d
pipeline { agent any stages { stage('Build') { steps { e
我是一名优秀的程序员,十分优秀!