chaopower
/
pipeline
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

bug

master
chaopower 2024-01-11 11:11:35 +08:00
parent 4bbd628d64
commit befe5b7693
1 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
codes/postprocess.py
View File

@ -234,16 +234,23 @@ class PostProcess:
cols = list(filter_sum_df.columns) cols = list(filter_sum_df.columns)
tmb_file_check = check_file_exist_and_empty(tmb_file) tmb_file_check = check_file_exist_and_empty(tmb_file)
filter_sum_df = filter_sum_df.sort_index()
if not tmb_file_check: if not tmb_file_check:
tmb_df = pd.read_csv(tmb_file, sep='\t') tmb_df = pd.read_csv(tmb_file, sep='\t')
key_cols = ['Chr', 'Start', 'End'] key_cols = ['Chr', 'Start', 'End']
filter_sum_df = filter_sum_df.set_index(key_cols) filter_sum_df = filter_sum_df.set_index(key_cols)
filter_sum_df = filter_sum_df.sort_index()
tmb_df = tmb_df.set_index(key_cols) tmb_df = tmb_df.set_index(key_cols)
# 在filter_sum_df中的process列中追加字符串";tmb"，对应tmb_df中的行 并且 是非 1，2类突变 # 在filter_sum_df中的process列中追加字符串";tmb"，对应tmb_df中的行 并且 是非 1，2类突变
filter_sum_df['process'] = filter_sum_df.index.map( # filter_sum_df['process'] = filter_sum_df.index.map(
lambda x: filter_sum_df.at[x, 'process'] + ';tmb' if x in tmb_df.index and filter_sum_df.at[ # lambda x: filter_sum_df.at[x, 'process'] + ';tmb' if (x in tmb_df.index) and (filter_sum_df.at[
x, 'AMP_mut_level'] not in ['I', 'II'] else filter_sum_df.at[x, 'process']) # x, 'AMP_mut_level'] not in ['I', 'II']) else filter_sum_df.at[x, 'process'])
for index, row in filter_sum_df.iterrows():
amp_mut_level = row['AMP_mut_level']
process = row['process']
if (index in tmb_df.index) and (amp_mut_level not in ['I', 'II']):
filter_sum_df.loc[index, 'process'] = process + ';tmb'
# 找到tmb_df中不在filter_sum_df中的行，并将这些新的行添加到filter_sum_df中 # 找到tmb_df中不在filter_sum_df中的行，并将这些新的行添加到filter_sum_df中
new_rows = tmb_df[~tmb_df.index.isin(filter_sum_df.index)] new_rows = tmb_df[~tmb_df.index.isin(filter_sum_df.index)]