使用Lua，我下载了一个.csv文件，然后用第一行和最后一行来帮助我根据提供的开始和结束日期/时间直观地验证时间段。
我还想扫描这些值，并创建各种变量，例如在此期间报告的最高值、最低值和平均值。
.csv的格式如下。。
created_at,entry_id,field1,field2,field3,field4,field5,field6,field7,field8
2021-04-16 20:18:11 UTC,6097,17.5,21.1,20,20,19.5,16.1,6.7,15.10
2021-04-16 20:48:11 UTC,6098,17.5,21.1,20,20,19.5,16.3,6.1,14.30
2021-04-16 21:18:11 UTC,6099,17.5,21.1,20,20,19.6,17.2,5.5,14.30
2021-04-16 21:48:11 UTC,6100,17.5,21,20,20,19.4,17.9,4.9,13.40
2021-04-16 22:18:11 UTC,6101,17.5,20.8,20,20,19.1,18.5,4.4,13.40
2021-04-16 22:48:11 UTC,6102,17.5,20.6,20,20,18.7,18.9,3.9,12.40
2021-04-16 23:18:11 UTC,6103,17.5,20.4,19.5,20,18.4,19.2,3.5,12.40
我得到第一行和最后一行的代码如下
print("Part 1")
print("Start : check 2nd and last row of csv")
local ctr = 0
local i = 0
local csvfilename = "/home/pi/shared/feed12hr.csv"
local hFile = io.open(csvfilename, "r")
for _ in io.lines(csvfilename) do ctr = ctr + 1 end
print("...... Count : Number of lines downloaded = " ..ctr)
local linenumbera = 2
local linenumberb = ctr
for line in io.lines(csvfilename) do i = i + 1
if i == linenumbera then
secondline = line
print("...... 2nd Line is = " ..secondline) end
if i == linenumberb then
lastline = line
print("...... Last line is = " ..lastline)
-- return line
end
end
print("End : Extracted 2nd and last row of csv")
但我现在计划选择一列，最好是按名称(因为我希望能够将其用于其他结构相似的.csv导出。(并将.csv放入表/数组中。。。
我在这里找到了一个选项-Csv文件到Lua表，并作为新表或函数((访问行
见下文。。
#!/usr/bin/lua
print("Part 2")
print("Start : Convert .csv to table")
local csvfilename = "/home/pi/shared/feed12hr.csv"
local csv = io.open(csvfilename, "r")
local items = {} -- Store our values here
local headers = {} --
local first = true
for line in csv:gmatch("[^n]+") do
if first then -- this is to handle the first line and capture our headers.
local count = 1
for header in line:gmatch("[^,]+") do
headers[count] = header
count = count + 1
end
first = false -- set first to false to switch off the header block
else
local name
local i = 2 -- We start at 2 because we wont be increment for the header
for field in line:gmatch("[^,]+") do
name = name or field -- check if we know the name of our row
if items[name] then -- if the name is already in the items table then this is a field
items[name][headers[i]] = field -- assign our value at the header in the table with the given name.
i = i + 1
else -- if the name is not in the table we create a new index for it
items[name] = {}
end
end
end
end
print("End : .csv now in table/array structure")
但我得到了以下错误？？
pi@raspberrypi:/ $ lua home/pi/Documents/csv_to_table.lua
Part 2
Start : Convert .csv to table
lua: home/pi/Documents/csv_to_table.lua:12: attempt to call method 'gmatch' (a nil value)
stack traceback:
home/pi/Documents/csv_to_table.lua:12: in main chunk
[C]: ?
pi@raspberrypi:/ $
对此有什么想法吗？我可以确认.csv文件在那里吗？
一旦所有东西(希望(都在一个表中，我就希望能够根据所选列中的信息生成一个变量列表，然后我可以使用它并在推送通知或电子邮件中发送(我已经有了代码(。
以下是我到目前为止所能创建的内容，但我希望任何/所有人都能帮助我对所选列中的值进行更多分析，这样我就可以看到所有的东西，比如获得最高、最低、平均等。
print("Part 3")
print("Start : Create .csv analysis values/variables")
local total = 0
local count = 0
for name, item in pairs(items) do
for field, value in pairs(item) do
if field == "cabin" then
print(field .. " = ".. value)
total = total + value
count = count + 1
end
end
end
local average = tonumber(total/count)
local roundupdown = math.floor(average * 100)/100
print(count)
print(total)
print(total/count)
print(rounddown)
print("End : analysis values/variables created")
io.open在成功时返回一个文件句柄。不是一根绳子。
因此
local csv = io.open(csvfilename, "r")
--...
for line in csv:gmatch("[^n]+") do
--...
将引发错误。
您需要先将文件读取为字符串。
或者，可以使用file:lines(...)或io.lines迭代文件的行，就像您在代码中已经做的那样。
local csv = io.open(csvfilename, "r")
if csv then
for line in csv:lines() do
-- ...
您对文件的迭代次数超过了需要的次数。
编辑：
这就是在动态计算每一行的最大值时填充数据表的方法。这假设您总是有有效的行！正确的解决方案应该验证数据。
-- prepare a table to store the minima and maxima in
local colExtrema = {min = {}, max = {}}
local rows = {}
-- go over the file linewise
for line in csvFile:lines() do
-- split the line into 3 parts
local timeStamp, id, dataStr = line:match("([^,]+),(%d+),(.*)")
-- create a row container
local row = {timeStamp = timeStamp, id = id, data = {}}
-- fill the row data
for val in dataStr:gmatch("[%d%.]+") do
table.insert(row.data, val)
-- find the biggest value so far
-- our initial value is the smallest number possible
local oldMax = colExtrema[#row.data].max or -math.huge
-- store the bigger value as the new maximum
colExtrema.max[#row.data] = math.max(val, oldMax)
end
-- insert row data
table.insert(rows, row)
end