from genda.formats.panVCF import VCF
from genda.formats.Snp_array import SNP_array
from genda.formats.PED import PED

v = VCF('./tests/data/chr22.test.vcf')

#Preview VCF
v.vcf.ix[0:10,0:7]

#Preview genotype matrix
v.geno.ix[0:10,0:7]



#Load in data from a SNP array which is formatted with both alleles in one column (eg. 23 and me data)
s = SNP_array('./tests/data/one-column-test-data', fileformat='one column', delim = '\t',
              encoding = {'rs4477212':'A/G','rs3094315':'A/G','rs3131972':'G/A','rs12124819':'A/G','rs11240777':'A/G',\
                          'rs6681049':'C/T','rs4970383':'T/C','rs4475691':'T/C','rs7537756':'A/T'})

#Preview data from SNP array
s.df.ix[0:10,:]

#Preview genotype data from SNP array
s.geno.ix[0:10,:]

#Load in data form a SNP array with two columns representing the alleles of an individual
t = SNP_array('tests/data/two-column-test-data', fileformat = 'two column', delim = '\t',\
              encoding = {'rs4477212':'A/G','rs3094315':'A/G','rs3131972':'G/A','rs12124819':'A/G',\
                          'rs11240777':'A/G','rs6681049':'C/T','rs4970383':'T/C','rs4475691':'T/C','rs7537756':'A/T'})

#Preview data
t.df.ix[0:10,0:4]

#Preview genotype matrix
t.geno.ix[0:10,0:7]



#Load in a PED file
p = PED('tests/data/test.ped', 'tests/data/test.map', {'snp1':'A/C','snp2':'A/C','snp3':'C/A','snp4':'T/G','snp5':'C/A'})

#See the parsed out PED file
p.PED

#See parsed out MAP file
p.MAP

#Vieing the genotype matrix
p.geno