idseq谱系物种去重_20211222

1. 代码1

import pandas as pd

# df5.to_csv('%s/tmp_blastn_match_taxid_lineage_add_kgs' % outputpath,index=False, sep='\t')
df5=pd.read_csv(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs.txt',sep='\t')
df1=df5
# print(df1['% identity'].value_counts(ascending=False))

# 检查比对一致性是否大于80
# for i in range(len(df1['% identity'])):
#     if df1['% identity'][i] > 80:
#         i += 1
#     else:
#         print("unmeet")
#         break
print(df1)

dict1=df1[["Query id", "species"]].set_index("Query id").to_dict(orient='dict')["species"]
dict2=df1[["Query id", "species"]].set_index("Query id").to_dict()["species"]
print(dict1)
print(dict2)

list1 = df1['Query id'].unique().tolist()


list3 = []
for i in range(len(list1)):
    list2 = df1[df1['Query id'] == list1[i]]['species'].tolist()
    # print(list2)
    # m=m+1
    # print(m)
    #   if len(set(list2))==1               怎么判定一个List里面的元素是不是全部一样
    for j in range(1, len(list2)):
        if str(list2[j]).split(' ', 2)[0] != str(list2[0]).split(' ', 2)[0]:
            # print("不一样！")
            # break
            # print(list1[i])
            list3.append(list1[i])
            break
        else:
            # print("一样")
            j = j + 1

# print(list3)
for i in range(len(list3)):
    df1 = df1[~df1['Query id'].isin([str(list3[i])])]  # 删除df表中包含指定字符串的行数据
# print(df1)

df2 = df1.reset_index(drop=True)  # 重建索引
# print(df2)
df2.to_csv('%s/tmp_blastn_match_taxid_lineage_add_kgs_delrepeat' % outputpath,index=None, sep='\t')

2.代码2

# import pandas as pd
# df5=pd.read_csv(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs.txt',sep='\t')
# df1=df5

A = {}
with open(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs.txt') as f:
    f.readline()
    for line in f:
        line = line.strip('\n')
        t_list = line.split('\t')
        head = t_list[2]
        species = t_list[-1]
        if head in A:
            B = A[head]
            # print(B)
            if species in B:
                A[head][species] += 1
            else:
                A[head][species] = 1
        else:

            A[head] = {species: 1}
            # print(head)
            # print(A[head])
            # print(A)
# print(A)
# print(A.values())
# print(A.keys())
# # print(A.keys()[0])
# print(len(A)) #多少key
# print("___________________")
print(list(A.keys()))

for key,value in list(A.items()):
    # print(value)
    # print(len(value))
    # print(key)
    if len(value)==1:
        # print(A[key])
        del A[key]
    # print("___________________")
print(A)
# print(len(A))
print(list(A.keys()))

# for i in range(len(list(A.keys()))):
#     df1 = df1[~df1['Query id'].isin([str(list(A.keys())[i])])]
#
# df2 = df1.reset_index(drop=True)
# df2.to_csv(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs_delrep.txt' ,index=None, sep='\t')

with open(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs.txt') as oldfile, open(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs_deldelrept.txt', 'w') as newfile:
    for line in oldfile:
        if not any(bad_word in line for bad_word in list(A.keys())):
            newfile.write(line)

# lines_seen=set()
# with open(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs_deldelrept.txt') as f,open(r'2021-10\K200005137_L01_126_nt_virus_blastn_match_taxid_lineage_add_kgs_deldelrept1.txt', 'a+') as outfile:
#     for line in f:
#         if line not in lines_seen:
#             outfile.write(line)
#             lines_seen.add(line)