python合并空格_在python中合并数据时填补空白

>>> from collections import defaultdict

>>> import glob

>>> pos = defaultdict(dict)

>>> for index, infile in enumerate(glob.glob('D:\\DATA\\FP12210\\My Documents\\Temp\\Python\\sample*.vcf'), 1):

for line in open(infile):

# Convert value in integer already

val, letter = int(line.split()[1]), line.split()[3]

pos[val][index] = letter

>>> def print_pos(pos):

""" Formats pos """

# Print header by sorting keys of pos

values = sorted(pos.keys())

print ' ',

for val in range(values[0], values[-1] + 1):

print '{0:5}'.format(val),

print

# pos has keys according to row1, create pos2 with keys = sample #

pos2 = defaultdict(dict)

for val, d in pos.iteritems():

for index, letter in d.iteritems():

pos2[index][val] = letter

# Now easier to print lines

for index in sorted(pos2.keys()):

print ' sample{0:2} '.format(index),

for val in range(values[0], values[-1] + 1):

if val in pos2[index]:

print ' {0} '.format(pos2[index][val]),

else:

print ' NaN ',

print

>>> print_pos(pos)

2025 2026 2027 2028 2029 2030 2031 2032

sample 1 A NaN C T NaN NaN NaN NaN

sample 2 G A NaN NaN NaN NaN NaN T

>>>

我使用pos来收集值，我还使用pos2来收集相同的数据，因为：pos是面向值的，对于具有范围值很有用

pos2是面向样本的，对于给定样本号的值非常有用

为了避免范围过大，我使用了以下值：

-sample1.vcf:

^{pr2}$

-sample2.vcf:1 2025 blah G . blah PASS AC=0 GT:DP 0/0:61

2 2026 blah A . blah blah AC=0 GT:DP 0/0:61

3 2032 blah T . blah PASS AC=0 GT:DP 0/0:61