const char reg_preamble[] = "/*\n This program contains functions which return estimates\n"
" and confidence intervals for a linear model. The EXPORT subcommand\n"
-" of the REGRESSION procedure of GNU PSPP generated this program.\n*/\n\n";
+" of the REGRESSION procedure of GNU PSPP generated this program.\n*/\n\n"
+"#include <string.h>\n#include <math.h>\n#define PSPP_REG_MAXLEN 1024\n\n";
const char reg_mean_cmt[] = "/*\n Estimate the mean of Y, the dependent variable for\n"
" the linear model of the form \n\n"
"\n\tresult *= pspp_reg_t_quantile ((1.0 + p) / 2.0);\n\t"
"result += pspp_reg_estimate (var_vals, var_names);\n\treturn result;\n}\n";
+/*
+ Change categorical values to binary vectors. The routine will use
+ an encoding in which a categorical variable with n values is mapped
+ to a vector with n-1 entries. Value 0 is mapped to the zero vector,
+ value 1 is mapped to a vector whose first entry is 1 and all others are
+ 0, etc. For example, if a variable can have 'a', 'b' or 'c' as values,
+ then the value 'a' will be encoded as (0,0), 'b' as (1,0) and 'c' as
+ (0,1). If the design matrix used to create the model used a different
+ encoding, then the function pspp_reg_categorical_encode () will return
+ a vector which does not match its categorical value in the model.
+ */
+const char reg_export_categorical_encode_1[] = "struct pspp_reg_categorical_variable\n"
+"{\n\tchar * name;\n\tsize_t n_vals;\n\tchar *values[1024];\n};\n\n"
+"/*\n This function returns the binary vector which corresponds to the value\n"
+" of the categorical variable stored in 'value'. The name of the variable is\n"
+" stored in the 'var' argument. Notice the values stored in the\n"
+" pspp_categorical_variable structures all end with a space character.\n"
+" That means the values of the categorical variables you pass to any function\n"
+" in this program should also end with a space character.\n*/\n"
+"static\ndouble * pspp_reg_get_value_vector (char *var, char *value)\n{\n\tdouble *result;\n\t"
+"int i;\n\t";
+
+const char reg_export_categorical_encode_2[] = "int v_index = 0;\n\t"
+"while (v_index < n_vars && strncmp (var, varlist[i]->name, PSPP_REG_MAXLEN) != 0)\n\t{\n\t\t"
+"v_index++;\n\t}\n\tresult = (double *) malloc (varlist[v_index]->n_vals * sizeof (*result));\n\t"
+"for (i = 0; i < varlist[v_index]->n_vals; i++)\n\t{\n\t\t"
+"if (strncmp ( (varlist[v_index]->values)[i], value, PSPP_REG_MAXLEN) == 0)\n\t\t{\n\t\t\t"
+"result[i] = 1.0;\n\t\t}\n\t\telse result[i] = 0.0;\n\t}\n\n\t"
+"return result;\n}\n\n";
#endif