From c428e91f28c4f511b4ef083d917bd3878bcf2d84 Mon Sep 17 00:00:00 2001
From: Tim Burton <tburton@nd.edu>
Date: Thu, 26 Oct 2017 22:02:51 -0400
Subject: [PATCH 1/2] first

---
 Exercise08_1.py | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 Exercise08_1.py

diff --git a/Exercise08_1.py b/Exercise08_1.py
new file mode 100644
index 0000000..2422e44
--- /dev/null
+++ b/Exercise08_1.py
@@ -0,0 +1,32 @@
+#Exercise 8, Python question 1
+#10/13/17, MMD
+import vcf
+import re
+#Open files to read and write
+vcffile = open("Cflorida.vcf","r")
+outfile = open("CfloridaCounts.txt","w")
+
+#assign regex to variable name, or compile to variable name
+
+lineNumber=0
+#loop over file
+for line in vcffile:#look at old code to see how you looped over a file
+    #strip end of line
+    line=line.strip()
+    if lineNumber==0: #how can you tell if this is the header line?
+        outfile.write(line+"\n")
+        #write unchanged header line to file
+    elif lineNumber==1: #how can you tell if this is the line with the column headings?
+        #standardize (replace) sample names with TX and FL regexes
+        re.sub(([CF|cf]{1}.*\.[Aa]{1}.*\.),(Cf.Sfa.),line)
+        re.sub(([CF|cf]{1}.*\.[Gg]{1}.*\.),(Cf.Gai.),line)
+        #write new version of line to file
+        outfile.write(line+"\n")
+    else: #now you're in the data
+        #replace full SNP info with allele counts only
+        #replace missing data with NA
+        #write new version of line to new file
+        
+#Close files
+
+

From 44d7a44a02dc964b31484da871abcb6f9a176c59 Mon Sep 17 00:00:00 2001
From: Patrick Doherty <pdoherty31@gmail.com>
Date: Thu, 26 Oct 2017 23:49:47 -0400
Subject: [PATCH 2/2] Attempt to fix Regex, will not work

---
 Exercise08_1.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Exercise08_1.py b/Exercise08_1.py
index 2422e44..4362f62 100644
--- a/Exercise08_1.py
+++ b/Exercise08_1.py
@@ -18,8 +18,8 @@
         #write unchanged header line to file
     elif lineNumber==1: #how can you tell if this is the line with the column headings?
         #standardize (replace) sample names with TX and FL regexes
-        re.sub(([CF|cf]{1}.*\.[Aa]{1}.*\.),(Cf.Sfa.),line)
-        re.sub(([CF|cf]{1}.*\.[Gg]{1}.*\.),(Cf.Gai.),line)
+        re.sub(((CF|cf){1}.?{4}\.,(Cf.Sfa.),line) ###Having trouble gettig re.sub to work, syntax not working. Trying to replace CF and then any 4 characters leading to a period
+        re.sub(((CF|cf){1}.?{4}\.,(Cf.Gai.),line)
         #write new version of line to file
         outfile.write(line+"\n")
     else: #now you're in the data