生信脚本练习（8）合并文件 ①

这道题有难度，要把这三个文件合并到一起。

文件一
1   161514631   T   C|0.132632|(272,140,47,16)
2   222301193   A   C|0.078624|(260,115,23,9)
3   89259567    A   C|0.043716|(200,150,8,8) 
4   55979552    G   A|0.211921|(236,121,59,37) 
6   26032069    C   G|0.078212|(247,83,23,5)
6   93973579    A   G|0.066667|(96,30,5,4)
7   87168642    G   C|0.062016|(84,37,4,4)
文件二
2   222301193   A   C|0.181507|(312,166,78,28)
6   93973579    A   G|0.168981|(282,77,52,21)
14  102551631   T   G|0.291411|(195,36,72,23)
19  54410004    C   T|0.486056|(96,33,70,52)
20  30671857    C   A|0.130909|(336,142,42,30)
文件三
2   222301193   A   C|0.181507|(312,166,78,28)
17  78867580    C   T|0.223464|(296,121,83,37)
19  2207712     C   T|0.093567|(89,66,8,8)
19  54410004    C   T|0.486056|(96,33,70,52)
20  30671857    C   A|0.130909|(336,142,42,30)

要求合并成这样子：
Chr Position    Ref test03_1    test03_2    test03_3
1   161514631   T   C|0.132632|(272,140,47,16)      -   -
2   222301193   A   C|0.078624|(260,115,23,9)       C|0.181507|(312,166,78,28)  C|0.181507|(312,166,78,28)
3   89259567    A   C|0.043716|(200,150,8,8)        -   -
4   55979552    G   A|0.211921|(236,121,59,37)      -   -
6   26032069    C   G|0.078212|(247,83,23,5)        -   -
6   93973579    A   G|0.066667|(96,30,5,4)      G|0.168981|(282,77,52,21)   -
7   87168642    G   C|0.062016|(84,37,4,4)      -   -
14  102551631   T   -       G|0.291411|(195,36,72,23)   -
19  54410004    C   -       T|0.486056|(96,33,70,52)    T|0.486056|(96,33,70,52)
20  30671857    C   -       A|0.130909|(336,142,42,30)  A|0.130909|(336,142,42,30)
17  78867580    C   -       -   T|0.223464|(296,121,83,37)
19  2207712     C   -       -   T|0.093567|(89,66,8,8)

我用了逐个合并的方法，合并一次生成一个字典。
像吃糖葫芦，一个一个吞

file1 = 'c:/Test3_1.info'
file2 = 'c:/Test3_2.info'
file3 = 'c:/Test3_3.info'
list_all = dict()
#list_title = []
#list_2d = {{'1':'2'}:'3'}
list_2d = {}
def read(file):   
    dictt = {}
    array = []
    fragment = []
    f = open(file,"r")
    try:
        line = f.readlines()
        array = line[:]
        for i in array:
            fragment.append(i.strip().split("\t"))
    finally:
        f.close()
    for arr in fragment:
        dictt[(arr)[0]+"\t"+(arr)[1]+"\t"+(arr)[2]] = (arr)[3]
    return dictt
list1 = (read(file1))
list2 = (read(file2))
list3 = (read(file3))
list_all.update(list1)
list_all.update(list2)
list_all.update(list3)
list_all_2.update(list1)
list_all_2.update(list2)
list_all_2.update(list3)
#生成一个包含所有染色体的字典,值全是“-”
for k,v in list_all.items():
    list_all[k] = "-"

for k,v in list_all_2.items():
    list_all[k] = "-"

for k in list1:
    for key in list_all:
        if k in key:
            list_all[key] = list1[k]            
for k in list2:
    for key in list_all_2:
        if k in key:
            list_all_2[key] = list2[k]            
for k in list3:
    for key in list_all_2:
        if k in key:
            list_all_3[key] = list3[k]   

#生成key中包含list1的字典
list_all_all = []
for k,v in list_all.items():
    list_all_all.append(str(k)+"\t"+str(v)+"\t")         
dic_all_all = {}
for i in list_all_all:
    dic_all_all[i] = "-"
#添加第2个文件！
for k in list2:
    for key in dic_all_all:
        if k in key:
            dic_all_all[key] = list2[k]
#生成key中包含list1,2的字典
list_all_all2 = []
for k,v in dic_all_all.items():
    list_all_all2.append(str(k)+"\t"+str(v)+"\t")         
dic_all_all2 = {}
for i in list_all_all2:
    dic_all_all2[i] = "-"
#添加第3个文件！
for k in list3:
    for key in dic_all_all2:
        if k in key:
            dic_all_all2[key] = list3[k]
#print(dic_all_all) 
#for k,v in list_all.items():
    #print(k,v) 
#for k,v in dic_all_all.items():
    #print(k,v)
for k,v in dic_all_all2.items():
    print(k,v)
with open("t3.txt","w") as f:
    f.write("Chr\tPosition\tRef\ttest03_1\ttest03_2\ttest03_3\n")
    #f.write(str(dic_all_all2))
    for k,v in dic_all_all2.items():
        f.write(str(k)+str(v)+"\n")

8.14 更新更好的解法，函数式编程
但是感觉还是不够模块化
以后能不能用class写一下？

import os 
import re
path = 'c:/Users
os.chdir(path)
road = os.listdir(path)

def find_file(road): 
    file_list = []
    regex = re.compile(r'Test3_\d.info')
    for i in road:
        m = re.findall(regex,i)
        if m:
            m = m[0]
            file_list.append(m)
            file_list.sort()
    return file_list

def read(file):  
    dict_all = {}
    dictt = {}
    fragment = []
    f = open(file,"r")
    try:
        line = f.readlines()
        for i in line:
            fragment.append(i.strip().split("\t"))
    finally:
        f.close()
    for arr in fragment:
        dictt[(arr)[0]+"\t"+(arr)[1]+"\t"+(arr)[2]] = (arr)[3]
    return [line,dictt]

def update(file): 
    dict_all = {}
    file_list = find_file(road)
    for file in file_list:
        dict_all.update(read(file)[1])        
    for k in dict_all: 
        dict_all[k] = ''
    return dict_all
dict_all = update(file)     

def add(road):
    for f in find_file(road):    
        r = read(f)
        for k in dict_all:
            if k not in r[1]:  
                dict_all[k] +='\t' + '-'
            else:
                dict_all[k] += '\t' +  r[1][k] 
    return dict_all
all = add(road)    

with open("tt3.txt","w") as f:
    f.write("Chr\tPosition\tRef\t")
    for i in find_file(road):
        f.write(i.split('.')[0]+'\t')
        f.write('\t')
    f.write('\n')

感觉代码可以维护了！