GTseqTools/binary.py at main · stevemussmann/GTseqTools · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import collections
import pandas

from majmin import MajMin

class Binary():
	'Class for converting pandas dataframe to binary format'

	def __init__(self, df, popdata):
		self.pdf = df
		self.pd = popdata
		mm = MajMin(self.pdf, 0, 1, 2)
		self.recode12 = mm.getMajorMinor() #stores major/minor allele for converting to binary format. 2 = missing, 0 = major, 1 = minor

	def convert(self):
		output = list()

		output = self.makeBinary(output)

		return output

	def makeBinary(self, output):
		# make header and append to output
		headerList = list()
		headerList.append("Sample")
		headerList.append("Population_ID")
		columns = list(self.pdf)
		for col in columns:
			headerList.append(col)
			headerList.append("")

		headerLine = ' '.join(headerList)
		output.append(headerLine)

		for sampleName, row in self.pdf.iterrows():
			lineList = list()

			lineList.append(sampleName)
			lineList.append(self.pd[sampleName])

			# add population name here if desired

			for (locus, genotype) in row.items():
				alleles = self.split(str(genotype))

				# next line is testing for original data missing value (0) instead of binary recoded missing value (2).
				if len(alleles) == 1 and alleles[0] == "0":
					lineList.append(self.recode12[locus][alleles[0]])
					lineList.append(self.recode12[locus][alleles[0]])
				else:
					for allele in alleles:
						lineList.append(self.recode12[locus][allele])

			lineString = ' '.join(lineList)

			output.append(lineString)

		return output

	def split(self, word):
		return [char for char in word]