# # Writes to: # DBTestM.csv # CalcList.csv # MultList.txt # MultSummary.txt

import os,sys from Tkinter import * from string import * from Permute import *

class FileCombo(Frame):

• def init(self,parent=None):

  • Frame.init(self,parent) print 'Choices are:' print ' 1. Convert Sorted Combined list to Species No. and Subspecies No' print ' creates DBTestM.csv ' print ' 2. Make two lists: All species detected - Species and All sites detected - Sites.' print ' Then Adds data from CDMS (Intensity,Smu2 and Einstein A) from DBTestM.csv' print ' creates CalcList.csv ' print ' 3. Reads CalcList.csv and identifies all lines in a site that have 3 or more lines' print ' creates MultList.txt and a Summary MultSummary.txt. ' print ' 4. Run each in sequence'

• Sel=raw_input('Choice') Ch=eval(Sel) if Ch==1:
  • self.XDBAccess() exit()
  if Ch==2:

  • self.MakeSiteList() self.CalculationList() quit()

  if Ch==3:

  • self.FindMultiples() quit()

  if Ch==4:
  • self.XDBAccess()

    self.MakeSiteList() self.CalculationList() self.FindMultiples() quit()

• def XDBAccess(self):

  • # GoodCombineAllSorted is a combination of the three SLCombine files cleaned for errors. Sorted by: Species, RestF site. # Two columns are added at the beginning of each line of the form shown below. # The result is saved in Lines F1='/home/ghurtig3/Desktop/NewASAP_09/DATA/GoodCombineAllSorted.csv' FL1=open(F1,'r') sa=FL1.readlines() Lines2=[] la=len(sa) print len(sa) #Strip whitespaces i=0 while i < la:

    • sb=sa[i].strip() Lines2.append(sb) i=i+1 continue
    Lines=[] #print len(Lines2) # Create a csv file Starting with [ 1, 0, Site, .....] i=0 for line in Lines2:
    • line=line.split("\t") #line1=line[0][0:-1] #print line #Lis1="1"+","+"0"+"," Lis1= "0" line.insert(0,Lis1) Lis1="1" line.insert(0,Lis1) #print line #raw_input("Pause1") #Lines1=Lis1.split(",") #Now creatine file Lines Lines.append(line) i=i+1 continue #Lines[x][0]=Specie # #Lines[x][1]=Sub Specie #Lines[x][2]=Site #Lines[x][3]=Specie #Lines[x][4]=Rest Freq #Lines[x][5]=Obs Freq #Lines[x][6]=DelF #Lines[x][7]=Intensity #Lines[x][8]=FWHM #Lines[x][9]=DelV #Lines[x][10]=Area #Lines[x][11]=Offset #Lines[x][12]=Normalize
    FL1.close() #print i #raw_input("Pause2") # A sub specie is added to the masterdatabase and written to 'DBTestM.csv' i=0 #Line # LL=len(Lines) #print Lines #print LL #print Lines[LL-2]

    k=0 #SubSpecie # m=0 #Specie # while i< LL-3: #Line #

    • #print "i= ",i if Lines[i][3]==Lines[i+1][3]: #Tests for specie change:
      • Lines[i+1][1]=0 Lines[i][0]=m Lines[i+1][0]=m if Lines[i][4]==Lines[i+1][4]:#Tests for sub specie change
        • Lines[i][1]=k Lines[i+1][1]=k
        else:
        • Lines[i][1]=k Lines[i+1][1]=k+1 k=k+1
        i=i+1 continue
      else:
      • Lines[i+1][0]=m+1 Lines[i][1]=k k=0 Lines[i+1][1]=k m=m+1 k=k+1 i=i+1
      #Lines[i][1]=k #k=0 continue
    print i, k, m raw_input("Pause3") F6='/home/ghurtig3/Desktop/NewASAP_09/DATA/DBTestM.csv' FL6=open(F6,'w') j=0

    while j< LL-3:

    • FR=str(Lines[j][0])+','+str(Lines[j][1])+','+str(Lines[j][2])+','+str(Lines[j][3])+','+str(Lines[j][4])+','+str(Lines[j][5])+','+str(Lines[j][6])+','+str(Lines[j][7])+','+str(Lines[j][8])+','+str(Lines[j][9])+','+str(Lines[j][10])+','+str(Lines[j][11])+"\n" FL6.write(FR) #print FR #print j #print Lines[j] #raw_input('Pause') j=j+1 continue
    FL6.close() return

  def MakeSiteList(self):

# This creates two internal lists from DBTestM.csv. Species is # all of the species detected and Sites is all of the sites read.

• F1='/home/ghurtig3/Desktop/NewASAP_09/DATA/DBTestM.csv' FL1=open(F1,'r') Lines=[] Sites=[] Species=[] i=0 for line in FL1:
  • line=line.split(',') Lines.append(line) if line[2] in Sites:
    • i=i+1 continue
    else:
    • Sites.append(line[2]) i=i+1
    continue
  FL1.close() F1='/home/ghurtig3/Desktop/NewASAP_09/DATA/DBTestM.csv' FL1=open(F1,'r') i=0 for line in FL1:
  • line=line.split(',') Lines.append(line) if line[3] in Species:
    • i=i+1 continue
    else:
    • Species.append(line[3]) i=i+1
    continue
  FL1.close() self.Sites=Sites self.Species=Species print Sites print Species return

• def CalculationList(self):

#This def takes the observation data that has been cleaned and put #into DBTestM.csv and combines each specie and sub-specie with the #data from CDMS (Intensity, Smu2 and Einsteins A. Puts data into # CalcList.csv.

• T1=[] F3='/home/ghurtig3/Desktop/NewASAP_09/DATA/DBTestM.csv' FL3=open(F3,'r') F2='/home/ghurtig3/Desktop/NewASAP_09/DATA/CalcList.csv' FL2=open(F2,'w') Lines=[] for line in FL3:
  • T1.append("0") line1=line.split(',') Lines.append(line1)
  LL=len(Lines) print LL Sites=self.Sites A="" B="" print type(Sites) for Si in Sites:
  • H1='Site= '+Si for Sp in self.Species:
    • Head=' Species= '+Sp+'\n' i=1

      while i< LL-1:

      • if (Lines[i][2]==Si) and (Lines[i][3]==Sp):
        • if (Lines[i][2] == A) is False:
          • print print print '***** ',Lines[i][2],' *****' print Lines[i][3] Freq=eval(Lines[i][4]) L=Lines[i] E=L.pop() E=E[:-2] L.append(E) B=Lines[i][3]
          if((Lines[i][3]==B))is False:
          • print print Lines[i][3]
          Freq=eval(Lines[i][4]) L=Lines[i] E=L.pop() E=E[:-2] L.append(E) DBLine=self.ReadCDMS(Freq) print Freq if DBLine==None:
          • DBLine=['Not in CDBMS'] print DBLine
          T1[i]=L+DBLine Ln=Lines[i] A=Lines[i][2] B=Lines[i][3] Ln=str(Ln) FL2.write(str(T1[i])+'\n') i=i+1 continue
        else:
        • i=i+1 continue
  FL3.close() FL2.close() #Lines[x][0]=Specie # #Lines[x][1]=Sub Specie #Lines[x][2]=Site #Lines[x][3]=Specie #Lines[x][4]=Rest Freq #Lines[x][5]=Obs Freq #Lines[x][6]=DelF #Lines[x][7]=Intensity #Lines[x][8]=FWHM #Lines[x][9]=DelV #Lines[x][10]=Area #Lines[x][11]=Offset #Lines[x][12]=Normalize #Lines[x][13]=Rest Freq #Lines[x][14]=log(intensity) #Lines[x][15]=log(Smu2) #Lines[x][16]=log(A) #Lines[x][17]=El #Lines[x][18]=gup #Lines[x][19]=Quant Nos #Lines[x][20]=Species #Lines[x][21]=Vt #Lines[x][22]=V

• def FindMultiples(self):

#This def is created by DBA.py and reads CalcList.csv #and then identifies all species that have 3 or more #lines in a site.It writes these in MultList.txt and #summarizes the data in MultSummary.txt #Species is entered at tests are reported.

• SP=raw_input('Species? ') F1='/home/ghurtig3/Desktop/NewASAP_09/DATA/MultList.txt' FL1=open(F1,'w') F2='/home/ghurtig3/Desktop/NewASAP_09/DATA/CalcList.csv' FL2=open(F2,'r') F3='/home/ghurtig3/Desktop/NewASAP_09/DATA/MultSummary.txt' FL3=open(F3,'w') F4='/home/ghurtig3/Desktop/NewASAP_09/DATA/MultLines.txt' FL4=open(F4,'w') Lines=[] Lines=FL2.readlines() LL=len(Lines) print LL L2=Lines[0].split(',') #print L2[2] N1=[] L4=[] N3=[] i=1 k=1

  while i<LL:

  • L1=Lines[i].split(',')

    if L1[12]==" ": #Checks for a ratio.

    • i=i+1 continue
    if L1[3]==L2[3]:
    • k=k+1 if k==3:
      • N1=[] FL1.write(Lines[i-2]+'\n') FL1.write(Lines[i-1]+'\n') FL1.write(Lines[i]+'\n') LM2=Lines[i-2].split(',') LM1=Lines[i-1].split(',') LM0=Lines[i].split(',') N6=LM2[12] N7=N6[1:] N7=N7[:-2] if N7 != "'Not in CDBMS'":
        • N6=N6[1:] N6=eval(N6) N1.append(N6)
        N6=LM1[12] N7=N6[1:] N7=N7[:-2] if N7 != "'Not in CDBMS'":
        • N6=N6[1:] N6=eval(N6) N1.append(N6)
        N6=LM0[12] N7=N6[1:] N7=N7[:-2] if N7 != "'Not in CDBMS'":
        • N6=N6[1:] N6=eval(N6) N1.append(N6)

      if k>3:

      • FL1.write(Lines[i]+'\n') #LM=Lines[i].split(',') N6=L1[12] N7=N6[1:] N7=N7[:-2] if N7 != "'Not in CDBMS'":
        • N6=N6[1:] N6=eval(N6) N1.append(N6)
      L2=L1 i=i+1 continue
    else:

    • if k>2:

      • FL3.write(L2[2]+','+L2[3]+','+str(k)+'\n') L3=L2[3][2:] L3=L3[:-1] if L3==SP:
        • N2=L2[2]

          N2=N2.replace('.',) N2=N2.replace('gau',) L4.append(N2) #L4 is a list of sites containing SP N3.append(N1) #N3 is a list of intensities for each site.

      k=1 L2=L1 i=i+1 continue
  FL1.close() FL2.close() FL3.close() #Perm(L4,N3)#Calculates pair statistics exit()

• def ReadCDMS(self,Freq):
  • Lines1=[] Lines1=self.ReadCDMSData()

    DBLine=self.FindLine(Freq, Lines1) return DBLine

  def ReadCDMSData(self):
  • F1='CDMS_ISA.txt' FL1=open(F1, 'r') Lines1=[] i=0 for line in FL1:
    • line=capwords((line)) line=line.split(',') if line[0]=="":
      • continue
      else:
      • Lines1.append(line) i=i+1 continue
    return Lines1

  def FindLine(self,Fr1,Lines1): #finds a line in the CDMS for a particular frequency.

  • i=1

    while i < len(Lines1):

    • if abs(eval(Lines1[i][0])-Fr1)<0.25:

      • #print Lines[i] return Lines1[i]
      else:
      • i=i+1 continue
    #raw_input('P') return

if name == 'main':

• FileCombo().mainloop()