改变分隔符_202111

# 加上界属种成功
# import pandas as pd
#
# file1=r"2021-10\SRR1370913_nr_virus_blastx_match_taxid1_totaxid_lineage.txt"
# df1=pd.read_csv(file1,sep='\t',header=None)
# print(df1)
#
# file2=r"2021-10\SRR1370913_nr_virus_blastx_match_taxid_lineage"
# df2=pd.read_csv(file2,sep='\t',header=None)
# print(df2)
#
# df3=df2.iloc[:,0:df2.shape[1]-1]
# df3.columns=['taxid','taxnomy_k_g_s','Query id','accession.version','% identity','alignment length','mismatches','gap openings',
#               'q. start','q. end','s. start','s. end','e-value','bit score']
# print(df3)
# # print(df3.loc[2])
#
# df4=df3['taxnomy_k_g_s'].str.split(';',expand=True)
# df4.columns=['kingdom','genus','species']
# print(df4)
#
# df5=pd.concat([df3,df4],axis=1,names=['kingdom','genus','species'])
# print(df5)
# print(df5.columns)
#
# df5.to_csv(r"2021-10\SRR1370913_nr_virus_blastx_match_taxid_lineage_add_kgs",
#            index=False,sep='\t') # 可加header=None

import pandas as pd
file=r"2021-10\SRR1370913_rapsearch2.m8.m8"
df=pd.read_csv(file,sep='\t',header=None,skiprows=[i for i in range(0,5)])
#df=pd.read_csv(file,sep='\t',header=None,skiprows=[0,1,2,3,4])
#rapsearch2的结果需要去掉前5行内容（注释），只保留结果信息
print(df)