Skip to content

Update calculate_enrichment_barcodes_z_test.py #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
luca8651 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Update calculate_enrichment_barcodes_z_test.py #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 2 additions & 19 deletions calculate_enrichment_barcodes_z_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,25 +1,20 @@
##!/usr/bin/env python3.5
import csv

import os
import re
import sys
from difflib import ndiff
from difflib import SequenceMatcher
import numpy as np
from statsmodels.stats.proportion import proportions_ztest


#script to check for presence and count a set of barcodes in a file
#
#usage: calculate_enrichment_barcodes_z_test.py countfile countfile2

#outdir = sys.argv[1]

countfile = sys.argv[1]
countfile2 = sys.argv[2]

cont=0
#cont2=0

count_dict = dict([])
seq_dict= dict([])
Expand All @@ -31,7 +26,6 @@

with open(countfile,'r') as f:
for line in f:
#reader=csv.reader(line,delimiter='\t')
line1=line.split("\t")
seq=line1[1]
count=line1[0]
Expand All @@ -41,7 +35,6 @@
nobs2=0
with open(countfile2,'r') as f:
for line in f:
#reader=csv.reader(line,delimiter='\t')
line1=line.split("\t")
seq=line1[1]
count=line1[0]
Expand All @@ -59,14 +52,4 @@
# pval=str('{0:0.3f}'.format(pval))
print(str(seq)+"\t"+str(count)+"\t"+str(count2)+"\t"+str(nobs)+"\t"+str(nobs2)+"\t"+str(pval) )

#with open(filename,'r') as f:
# for line in f:
# seq=line
# seq=seq.strip('\n')
# seq_dict[seq]=seq
# print("count for seq "+ seq + " is "+count_dict[seq])
# if seq in count_dict:
# print(count_dict[seq]+"\t"+seq)
# else:
# print("0\t"+seq)
#