def infox(table, col, res_col):
"""
informacja atrybutu
"""
s = 0 # sum
for subt in table_helpers.get_subtables(table, col):
s += (float(len(subt[col])) / len(table[col])) * info(subt, res_col)
return s
def main_c45(table, result):
"""
zwraca drzewo tree z wynikiem algorytmu C4.5 w postaci listy lis
przyjmuje słownik table i klucz to vartości z wynikiem result
"""
refactor_table_numbers(table)
col = max([(k, gain(table, k, result)) for k in table.keys() if k != result],
key=lambda x: x[1])[0]
tree = []
for subt in get_subtables(table, col):
v = subt[col][0]
if is_mono(subt[result]):
tree.append(['%s=%s' % (col, v),
'%s=%s' % (result, subt[result][0])])
else:
del subt[col]
tree.append(['%s=%s' % (col, v)] + main_c45(subt, result))
return tree