Python：在搜索csv文件时加速FOR循环

step 1 Open file1 for row1 in file1 Grab partnumber from row[1] step 2 open file2 for row2 in file2 if partnumber == row2[2] grab data from row[4] break

def PartSearch(): Partexists = "N" global SelectedObject with open(eval("file"+str(SelectedFile))) as f: r2 = csv.reader(f, delimiter = eval("file"+str(SelectedFile)+"Del")) for row2 in r2: if int(SelectedFile) == 1: if str(row2[int(file1PartNumber)]) == str(PartNumberobject): Partexists= "Y" SelectedObject = row2[int(SelectedCol)] break if int(SelectedFile) == 2: if row2[int(file2PartNumber)] == PartNumberobject: Partexists= "Y" SelectedObject = row2[int(SelectedCol)] break if int(SelectedFile) == 3: if row2[int(file3PartNumber)] == PartNumberobject: Partexists= "Y" SelectedObject = row2[int(SelectedCol)] break if int(SelectedFile) == 4: if row2[int(file4PartNumber)] == PartNumberobject: Partexists= "Y" SelectedObject = row2[int(SelectedCol)] break if Partexists != "Y": SelectedObject = "X" with open("C:\\Python34\\Python34\\Distributors\\ListOfDistributors.txt") as f: r3 = csv.reader(f, delimiter = "\t") for row3 in r3: distributor = row3[0] with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"files.txt") as f: r4 = csv.reader(f, delimiter = "\t") totalRows = sum(1 for _ in f) i = totalRows if totalRows == 1: with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"files.txt") as f: r4 = csv.reader(f, delimiter = "\t") for row4 in r4: file1 = row4[1] file1Del = row4[2] file1titles = row4[3] file1titles = row4[3] file1PartNumber = row4[4] if totalRows == 2: with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"files.txt") as f: r4 = csv.reader(f, delimiter = "\t") for row4 in r4: if i == 2: file1 = row4[1] file1Del = row4[2] file1titles = row4[3] file1titles = row4[3] file1PartNumber = row4[4] if i == 1: file2 = row4[1] file2Del = row4[2] file2titles = row4[3] file2titles = row4[3] file2PartNumber = row4[4] i = i-1 if totalRows == 3: with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"files.txt") as f: r4 = csv.reader(f, delimiter = "\t") for row4 in r4: if i == 3: file1 = row4[1] file1Del = row4[2] file1titles = row4[3] file1titles = row4[3] file1PartNumber = row4[4] if i == 2: file2 = row4[1] file2Del = row4[2] file2titles = row4[3] file2titles = row4[3] file2PartNumber = row4[4] if i == 1: file3 = row4[1] file3Del = row4[2] file3titles = row4[3] file3titles = row4[3] file3PartNumber = row4[4] i = i-1 if totalRows == 4: with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"files.txt") as f: r4 = csv.reader(f, delimiter = "\t") for row4 in r4: if i == 4: file1 = row4[1] file1Del = row4[2] file1titles = row4[3] file1titles = row4[3] file1PartNumber = row4[4] if i == 3: file2 = row4[1] file2Del = row4[2] file2titles = row4[3] file2titles = row4[3] file2PartNumber = row4[4] if i == 2: file3 = row4[1] file3Del = row4[2] file3titles = row4[3] file3titles = row4[3] file3PartNumber = row4[4] if i == 1: file4 = row4[1] file4Del = row4[2] file4titles = row4[3] file4titles = row4[3] file4PartNumber = row4[4] i = i-1 with open("C:\\Python34\\Python34\\Distributors\\"+distributor+"structure.txt") as f: r5 = csv.reader(f, delimiter = "\t") i=1 for row5 in r5: if i == 1: DistributorName = row5[0] PartNumberFile = row5[2] PartNumberCol = row5[3] AltPartNumberFile = row5[5] AltPartNumberCol = row5[6] VendorPartNumberFile = row5[8] VendorPartNumberCol = row5[9] AltVendorPartNumberFile = row5[11] AltVendorPartNumberCol = row5[12] DescriptionFile = row5[14] DescriptionCol = row5[15] BrandFile = row5[17] BrandCol = row5[18] CostFile = row5[20] CostCol = row5[21] RetailFile = row5[23] RetailCol = row5[24] StatusFile = row5[26] StatusCol = row5[27] WeightFile = row5[29] WeightCol = row5[30] if i == 2: if row5[2] == 0: NumofOnedaywarehouse = row5[2] if row5[2] == 1: NumofOnedaywarehouse = row5[2] Oneday1WarehouseFile = row5[4] Oneday1WarehouseCol = row5[5] if row5[2] == 2: NumofOnedaywarehouse = row5[2] Oneday1WarehouseFile = row5[4] Oneday1WarehouseCol = row5[5] Oneday2WarehouseFile = row5[7] Oneday2WarehouseCol = row5[8] if row5[2] == 3: NumofOnedaywarehouse = row5[2] Oneday1WarehouseFile = row5[4] Oneday1WarehouseCol = row5[5] Oneday2WarehouseFile = row5[7] Oneday2WarehouseCol = row5[8] Oneday3WarehouseFile = row5[10] Oneday3WarehouseCol = row5[11] if i == 3: if row5[2] == 0: NumofTwodaywarehouse = row5[2] if row5[2] == 1: NumofTwodaywarehouse = row5[2] Twoday1WarehouseFile = row5[4] Twoday1WarehouseCol = row5[5] if row5[2] == 2: NumofTwodaywarehouse = row5[2] Twoday1WarehouseFile = row5[4] Twoday1WarehouseCol = row5[5] Twoday2WarehouseFile = row5[7] Twoday2WarehouseCol = row5[8] if row5[2] == 3: NumofTwodaywarehouse = row5[2] Twoday1WarehouseFile = row5[4] Twoday1WarehouseCol = row5[5] Twoday2WarehouseFile = row5[7] Twoday2WarehouseCol = row5[8] Twoday3WarehouseFile = row5[10] Twoday3WarehouseCol = row5[11] if i == 4: if row5[2] == 0: NumofThreedaywarehouse = row5[2] if row5[2] == 1: NumofThreedaywarehouse = row5[2] Threeday1WarehouseFile = row5[4] Threeday1WarehouseCol = row5[5] if row5[2] == 2: NumofThreedaywarehouse = row5[2] Threeday1WarehouseFile = row5[4] Threeday1WarehouseCol = row5[5] Threeday2WarehouseFile = row5[7] Threeday2WarehouseCol = row5[8] if row5[2] == 3: NumofThreedaywarehouse = row5[2] Threeday1WarehouseFile = row5[4] Threeday1WarehouseCol = row5[5] Threeday2WarehouseFile = row5[7] Threeday2WarehouseCol = row5[8] Threeday3WarehouseFile = row5[10] Threeday3WarehouseCol = row5[11] if i == 5: if row5[2] == 0: NumofFourdaywarehouse = row5[2] if row5[2] == 1: NumofFourdaywarehouse = row5[2] Fourday1WarehouseFile = row5[4] Threeday1WarehouseCol = row5[5] if row5[2] == 2: NumofFourdaywarehouse = row5[2] Fourday1WarehouseFile = row5[4] Fourday1WarehouseCol = row5[5] Fourday2WarehouseFile = row5[7] Fourday2WarehouseCol = row5[8] if row5[2] == 3: NumofFourdaywarehouse = row5[2] Fourday1WarehouseFile = row5[4] Fourday1WarehouseCol = row5[5] Fourday2WarehouseFile = row5[7] Fourday2WarehouseCol = row5[8] Fourday3WarehouseFile = row5[10] Fourday3WarehouseCol = row5[11] if i == 6: if row5[2] == 0: NumofFivedaywarehouse = row5[2] if row5[2] == 1: NumofFivedaywarehouse = row5[2] Fiveday1WarehouseFile = row5[4] Fiveday1WarehouseCol = row5[5] if row5[2] == 2: NumofFivedaywarehouse = row5[2] Fiveday1WarehouseFile = row5[4] Fiveday1WarehouseCol = row5[5] Fiveday2WarehouseFile = row5[7] Fiveday2WarehouseCol = row5[8] if row5[2] == 3: NumofFivedaywarehouse = row5[2] Fiveday1WarehouseFile = row5[4] Fiveday1WarehouseCol = row5[5] Fiveday2WarehouseFile = row5[7] Fiveday2WarehouseCol = row5[8] Fiveday3WarehouseFile = row5[10] Fiveday3WarehouseCol = row5[11] i = i+1 """print(file1Del) PartNumberFile = 1 PartNumberCol = 1 CostFile = 2 CostCol = 2 SelectedFile = PartNumberFile SelectedCol = PartNumberCol number = 1""" #Program to grab Part Number with open(file1) as f: r = csv.reader(f, delimiter = file1Del) if file1titles == "Y": file=r.__next__() for row in r: PartNumberobject = row[int(file1PartNumber)] "start of data collection, save variables as SelectedFile and SelectedCol. Run PartSearch() then save Variable SelectedObject" SelectedFile = PartNumberFile SelectedCol = PartNumberCol PartSearch() FPartNumber = SelectedObject SelectedFile = AltPartNumberFile SelectedCol = AltPartNumberCol PartSearch() FAltPartNumber = SelectedObject SelectedFile = VendorPartNumberFile SelectedCol = VendorPartNumberCol PartSearch() FVendorPartNumber = SelectedObject SelectedFile = AltVendorPartNumberFile SelectedCol = AltVendorPartNumberCol PartSearch() FAltVendorPartNumber = SelectedObject SelectedFile = DescriptionFile SelectedCol = DescriptionCol PartSearch() FDescription = SelectedObject SelectedFile = BrandFile SelectedCol = BrandCol PartSearch() FBrand = SelectedObject SelectedFile = CostFile SelectedCol = CostCol PartSearch() FCost = SelectedObject SelectedFile = RetailFile SelectedCol = RetailCol PartSearch() FRetail = SelectedObject SelectedFile = StatusFile SelectedCol = StatusCol PartSearch() FStatus = SelectedObject SelectedFile = WeightFile SelectedCol = WeightCol PartSearch() FWeight = SelectedObject print(DistributorName, PartNumberobject, FAltPartNumber, FVendorPartNumber, FAltVendorPartNumber, FDescription, FBrand, FCost, FRetail, FStatus, FWeight)

2条回答

网友

1楼 · 编辑于 2024-09-29 17:21:09

既然你没有提供细节，我只能非常笼统地回答。你知道吗

考虑到您只想使用很少的csv文件，并且它们的大小大约为170k行，我假设这些数据适合内存。如果是这种情况，并且您想使用python（一个非常合理的选择），我强烈建议您投入一些时间来学习pandas。Pandas为您提供了大量处理表格数据的选项，包括强大的筛选或数据库样式的合并和联接操作。你知道吗

当你问一个更具体的问题时，我相信我们可以提供进一步的帮助。你知道吗

网友

2楼 · 编辑于 2024-09-29 17:21:09

如果零件文件足够小，可以放入内存中，可以通过将其加载到字典（高效、快速的访问数据结构）中来加快速度。当您在file2中循环时，您正在查找一行row[2] == partnumber，然后（可能）使用row[4]，因此row[2]作为键，row[4]作为值的字典将使查找非常快：

parts = {}
with [however you open CSV 2] as f:
    for row in f:
        parts[row[2]] = row[4]

然后，不要每次都重新打开该文件，只需执行以下操作：

data = parts[partnumber]

编辑：您还可以做一些其他事情来改进代码：

考虑遵循PEP8，因为这样会使其他人更容易阅读您的代码。有一堆以大写字母开头的变量，这会让网站上突出显示的语法误以为它们是类。你知道吗

使用True和False表示布尔值，而不是字符串“Y”和“N”。你知道吗

part_exists = False
if some_condition:
    part_exists = True
if part_exists:
    selected_object = "X" # not clear what this does so I'm not messing with it

将数组拆分为变量时，可以更轻松地执行以下操作：

for row4 in r4:
    file1, file1Del, file1titles, file1PartNumber = row

您需要重复大量代码来处理一行、两行、三行和四行的情况。考虑在这里使用循环和列表。它还可以让你摆脱那种eval。

这看起来像是无谓的吹毛求疵，但不太重复的代码更容易改进。你知道吗

相关问题更多 >

编程相关推荐

热门问题

热门文章