An alternative approach that is possibly more robust to unstructured input is to use a combination of the Python symbolic math package (sympy), and a few parsing tricks. This scales to the variables in the equations being written in an arbitrary order.
Although sympy has some tools for parsing, (your input is very close in appearance to Mathematica), it appears that the sympy.parsing.mathematica
module can't deal with some of the input (particularly leading minus signs).
import sympy
from sympy.parsing.sympy_parser import parse_expr
import re
def text_to_equations(text):
lines = text.split('\n')
lines = [line.split('=') for line in lines]
eqns = []
for lhs, rhs in lines:
# clobber all the spaces
lhs = lhs.replace(' ','')
# *assume* that a number followed by a letter is an
# implicit multiplication
lhs = re.sub(r'(\d)([a-z])', r'\g<1>*\g<2>', lhs)
eqns.append( (parse_expr(lhs), parse_expr(rhs)) )
return eqns
def get_all_symbols(eqns):
symbs = set()
for lhs, rhs in eqns:
for sym in lhs.atoms(sympy.Symbol):
symbs.add(sym)
return symbs
def text_to_eqn_matrix(text):
eqns = text_to_equations(text)
symbs = get_all_symbols(eqns)
n = len(eqns)
m = len(symbs)
A = numpy.zeros((m, n))
b = numpy.zeros((m, 1))
for i, (lhs, rhs) in enumerate(eqns):
d = lhs.as_coefficients_dict()
b[i] = int(rhs)
for j, s in enumerate(symbs):
A[i, j] = d[s]
x = sympy.Matrix([list(symbs)]).T
return sympy.Matrix(A), x, sympy.Matrix(b)
s = '''-38 y1 + 35 y2 + 31 y3 = -3047
11 y1 + -13 y2 + -34 y3 = 784
34 y1 + -21 y2 + 19 y3 = 2949'''
A, x, b = text_to_eqn_matrix(s)
print A
print x
print b