列表上的循环导致索引器出错

Question

我试图用PYTHON计算带有RLE（运行长度编码）格式数字的文件的面积。我的FOR和IF语句有问题。你知道吗

我试图计算包含值201的单元格的面积。你知道吗

My current error:

Traceback (most recent call last):
  File "D:\2016-2017\Fall2016\SpatialDataStructures\Labs\Lab4\Area_Calc_from_RLE.py", line 68, in <module>
    if cellValuesAsIntList[i] == 201:
IndexError: string index out of range

Here is the file I am working with:

ncols         40
nrows         40
xllcorner     -2.3036649208516
yllcorner     -1.1518324594945
cellsize      25
NODATA_value  -9999
13, 0, 1, 201, 26, 0, 1, 3, 12, 0, 1, 201, 39, 0, 1, 201, 39, 0, 1, 201, 39, 0, 2, 201, 33, 0, 4, 501, 2, 0, 2, 201, 32, 0, 4, 501, 3, 0, 3, 201, 29, 0, 5, 501, 5, 0, 2, 201, 26, 0, 7, 501, 6, 0, 1, 201, 25, 0, 8, 501, 6, 0, 1, 201, 25, 0, 7, 501, 7, 0, 1, 201, 25, 0, 6, 501, 8, 0, 1, 201, 25, 0, 6, 501, 8, 0, 1, 201, 6, 0, 4, 102, 15, 0, 7, 501, 7, 0, 1, 201, 6, 0, 6, 102, 14, 0, 7, 501, 5, 0, 2, 201, 6, 0, 6, 102, 15, 0, 6, 501, 5, 0, 1, 201, 7, 0, 5, 102, 16, 0, 6, 501, 5, 0, 1, 201, 7, 0, 4, 102, 18, 0, 8, 501, 2, 0, 5, 201, 3, 0, 3, 102, 19, 0, 9, 501, 5, 0, 2, 201, 25, 0, 8, 501, 6, 0, 1, 201, 29, 0, 4, 501, 6, 0, 1, 201, 29, 0, 4, 501, 6, 0, 1, 201, 9, 0, 1, 501, 5, 102, 15, 0, 2, 501, 7, 0, 1, 201, 9, 0, 6, 102, 23, 0, 2, 201, 8, 0, 1, 501, 6, 102, 3, 0, 4, 202, 15, 0, 2, 201, 4, 0, 6, 501, 6, 102, 2, 0, 2, 202, 2, 0, 8, 202, 5, 0, 4, 201, 4, 0, 8, 501, 4, 102, 3, 0, 1, 202, 5, 0, 2, 202, 3, 0, 6, 202, 1, 201, 7, 0, 8, 501, 2, 102, 1, 501, 21, 0, 1, 201, 6, 0, 11, 501, 22, 0, 1, 201, 6, 0, 8, 501, 25, 0, 1, 201, 6, 0, 8, 501, 25, 0, 1, 201, 1, 101, 5, 0, 8, 501, 25, 0, 1, 201, 1, 101, 5, 0, 8, 501, 14, 0, 3, 101, 8, 0, 1, 201, 1, 101, 5, 0, 11, 501, 12, 0, 4, 101, 6, 0, 2, 201, 1, 101, 4, 0, 12, 501, 11, 0, 4, 101, 6, 0, 1, 101, 1, 201, 1, 101, 4, 0, 12, 501, 21, 0, 1, 101, 1, 201, 5, 0, 11, 501, 23, 0, 1, 201, 5, 0, 8, 501, 26, 0, 1, 201, 5, 0, 8, 501, 26, 0, 1, 201, 5, 0, 7, 501, 27, 0, 1, 201, 5, 0, 8, 501, 8, 0

This is my code:

fi = open(r'D:\2016-2017\Fall2016\SpatialDataStructures\Labs\Lab4\Data\AsRLE.txt','r')
fileLines = fi.readlines()
fi.close
#---------------------------------------------------------------------

#---------------------------------------------------------------------
#Populated variables required for code from fileLines variable  
cellValuesAsString = []
lineNum = 0
for line in fileLines: # for each line the FileLines List
  # get number of cols, ncols, i.e. the 1st line in the file
  if lineNum == 0:
    ncols = int(line[14:])
  # get number of rows, nrows, i.e. the 2nd line in the file
  elif lineNum == 1:
    nrows = int(line[14:])
  # get cell size, cellsize, i.e. the 5th line in the file
  elif lineNum == 4:
    cellsize = int(line[14:])
  # get cell values in RLE format as String, , i.e. the 7th line in the file
  elif lineNum == 6:
    cellValuesAsString = line
  lineNum = lineNum + 1

# removes spaces
cellValuesAsString = cellValuesAsString.replace(" ", "")

# convert string into a list of strings split by comma
cellValuesAsStringList = cellValuesAsString.split(',')

# convert strings to integers
cellValuesAsIntList = cellValuesAsStringList
for index, item in enumerate(cellValuesAsStringList):
    cellValuesAsIntList[index] = int(cellValuesAsStringList[index])
#---------------------------------------------------------------------

#THIS IS WHERE YOU WRITE YOUR CODE

#---------------------------------------------------------------------
cellCode = 201
codeArea = 0

area = 0
npixels = 0
i = 1

for cellValuesAsIntList in line:
  if cellValuesAsIntList[i] == 201:
    b = cellValuesAsIntList[i-1]
    npixels = npixels + b
  else:
    i=i+2




print npixles
print "Area: " + npixels * cellSize

Answer 1

这看起来是一个很大的努力。您的问题是索引用完了，这会引发IndexError。尽管您的情况要求每个项都有一定程度的索引意识，但幸运的是您只需轮询先前迭代的值。你知道吗

对于这种情况，请尝试跟踪上一个值：

npixels = 0
cells = cellValuesAsIntList                         # for clarity

prev = None
for cell in cells:
    if cell == 201:
        npixels += prev                             # increment operator
    prev = cell

根据经验，避免变异指数和迭代。虽然这不是你的直接问题，但这种做法会导致许多副作用。如果可能，直接迭代一个序列并处理每个迭代项。避免通过其他方式改变索引，例如反向迭代、改变复制的序列或使用理解。你知道吗

Answer 2

假设你有：

>>> rle=[2,5,1,8,6,9,3,30,6,22,2,12]

您可以将其转换为运行长度元组，如下所示：

>>> zip(*[iter(rle)]*2)
[(2, 5), (1, 8), (6, 9), (3, 30), (6, 22), (2, 12)]

然后可以筛选包含一些目标值的值（我将使用2，即使您提到201作为目标，因为您的示例中没有201）：

>>> filter(lambda t: t[0]==2, zip(*[iter(rle)]*2))
[(2, 5), (2, 12)]

然后将其应用于您的文件：

with open(file_name) as f_in:
   for line in f_in:
       li_as_ints=map(int, line.split(","))
       fl=filter(lambda t: t[0]==201, zip(*[iter(li_as_ints)]*2))
       # produces all the values, expanded, with 121 as value...

请不要这样做：

fh=open(a_file_name)
lines=fh.readlines()
for line in lines:
   #process a line

您正在不必要地读取整个文件。你知道吗

改为：

with open(a_file_name) as f_in:
   for line in f_in:
     # process a line