Extension of Julia's DataFrames by James

jDataFrames.jl

# This code is for extension of DataFrames.
# By the extension, fingerprint can be loaded via string. 
# Each fingerprint is a set of the binary integers in python. 
# However, it can be not be loaded directly in Julia, which directly 
# trainslate a binary integer string to big interger. It is automatic even if 
# quoto mark is aded. Hence, "Julia" is added on a binary string as a prefix. 
# By doing that, Julia can read them as a character string rather than a big integer value. 


# bs2ba() transform binary string to binary array. 
function bs2ba( fp)
	ln = sizeof( fp)
	
	x = zeros(  Float64, ln, 1)
	for ii = 1:ln
		x[ii, 1] = parse(Int, fp[ii])
	end
	return x
end	

# tofp transform binary string with a prefix of "Julia" to binary array after removal of the prefix
function tofp( fp_julia)
	# The prefix substring of Julia is removed so as to binary string can be used directly. 
	# Julia is appeded only for dataframe to be operated propertly in Julia
	lc = sizeof("Julia")
	fp = fp_julia[lc+1:end]
	return bs2ba( fp)
end

# to_xM translate an array of binary strings with a special prefix of "Julia" to 
# a matrix of binary integer elements where a binary integer can be one of 0, 1. 
# The output array is floatpoint since floatpoint is used in the machine learning library 
# such as in sklearn. 
function to_xM( fp_l)
	M = sizeof( fp_l[1]) - sizeof("Julia")
	N = size( fp_l)[1]
	xM = zeros( Float64, M, N)   
	for n=1:N
		xM[:, n] = tofp( fp_l[n])
	end
	return xM
end