int main(){
apop_data *d = apop_data_alloc(10, 100);
gsl_rng *r = apop_rng_alloc(3242);
for (int i=0; i< 10; i++){
row_offset = gsl_rng_uniform(r)*2 -1; //declared and used above.
apop_vector_apply(Apop_rv(d, i), offset_rng);
}
int df = d->matrix->size2-1;
apop_data *means = apop_map(d, .fn_v = mu, .part ='r');
apop_data *tstats = apop_map(d, .fn_v = find_tstat, .part ='r');
apop_data *confidences = apop_map(tstats, .fn_dp = conf, .param = &df);
printf("means:\n"); apop_data_show(means);
printf("\nt stats:\n"); apop_data_show(tstats);
printf("\nconfidences:\n"); apop_data_show(confidences);
//Some sanity checks, for Apophenia's test suite.
for (int i=0; i< 10; i++){
//sign of mean == sign of t stat.
assert(apop_data_get(means, i, -1) * apop_data_get(tstats, i, -1) >=0);
//inverse of P-value should be the t statistic.
assert(fabs(gsl_cdf_tdist_Pinv(apop_data_get(confidences, i, -1), 99)
- apop_data_get(tstats, i, -1)) < 1e-5);
}
}
int main(){
apop_data *data = apop_data_falloc((2, 2),
30, 86,
24, 38 );
double stat, chisq;
stat = calc_chi_squared(data);
chisq = gsl_cdf_chisq_Q(stat, (data->matrix->size1 - 1)* (data->matrix->size2 - 1));
printf("chi squared statistic: %g; p, Chi-squared: %g\n", stat,chisq);
apop_data_show(apop_test_anova_independence(data));
apop_data_show(apop_test_fisher_exact(data));
}
apop_data *get_factors(SEXP ls, char const *varname){
int nls = LENGTH(ls);
if (isNull(ls)) return NULL;
//else:
apop_data *out = apop_text_alloc(NULL, nls, 1);
for (int i = 0; i < nls; i++)
apop_text_add(out, i, 0, translateChar(STRING_ELT(ls, i)));
asprintf(&out->names->title, "<categories for %s>", varname);
apop_data_show(out);
return out;
}
gsl_matrix *query(char *d, char *q, int no_plot){
apop_db_open(d);
apop_data *result = apop_query_to_data("%s", q);
apop_db_close(0);
Apop_stopif(!result, exit(2), 0, "Your query returned a blank table. Quitting.");
Apop_stopif(result->error, exit(2), 0, "Error running your query. Quitting.");
if (no_plot){
apop_data_show(result);
exit(0);
}
return result->matrix;
}
int main(){
apop_data *d1 = apop_text_alloc(NULL, 5, 1);
apop_data *d2 = apop_text_alloc(NULL, 5, 1);
apop_text_fill(d1, "A", "B", "C", "B", "B");
apop_text_fill(d2, "B", "A", "D", "B", "B");
apop_data_to_factors(d1);
apop_data_show(d1);
d2->more = apop_data_copy(apop_data_get_factor_names(d1, 0, 't'));
printf("-----\n");
apop_data_to_dummies(d2, .append='y');
apop_data_show(d2);
//some spot checks.
assert(apop_data_get(d1, 2)==2);
assert(apop_data_get(d2, 0, 0)==1);
assert(apop_data_get(d2, 2, 0)==0);
assert(apop_data_get(d2, 2, 1)==0);
assert(apop_data_get(d2, 2, 2)==1);
assert(apop_data_get(d2, 3, 0)==1);
}
/* This function prettyprints the \c apop_data set to a screen.
It is currently not in the documentation. It'd be nice to merge this w/apop_data_print.
This takes a lot of machinery. I write every last element to a text array, then measure column widths, then print to screen with padding to guarantee that everything lines up. There's no way to have the first element of a column line up with the last unless you interrogate the width of every element in the column, so printing columns really can't be a one-pass process.
So, I produce an \ref apop_data set with no numeric elements and a text element to be
filled with the input data set, and then print that. That means that I'll be using
(more than) twice the memory to print this. If this is a problem, you can use \ref
apop_data_print to dump your data to a text file, and view the text file, or print
subsets.
For more machine-readable printing, see \ref apop_data_print.
*/
void apop_data_show(const apop_data *in){
if (!in) {printf("NULL\n"); return;}
Get_vmsizes(in) //vsize, msize1, msize2, tsize
//Take inventory and get sizes
size_t hasrownames = (in->names && in->names->rowct) ? 1 : 0;
size_t hascolnames = in->names &&
(in->names->vector || in->names->colct || in->names->textct);
size_t hasweights = (in->weights != NULL);
size_t outsize_r = GSL_MAX(in->matrix ? in->matrix->size1 : 0, in->vector ? in->vector->size: 0);
outsize_r = GSL_MAX(outsize_r, in->textsize[0]);
outsize_r = GSL_MAX(outsize_r, wsize);
if (in->names) outsize_r = GSL_MAX(outsize_r, in->names->rowct);
outsize_r += hascolnames;
size_t outsize_c = msize2;
outsize_c += in->textsize[1];
outsize_c += (vsize>0);
outsize_c += (wsize>0);
outsize_c += hasrownames + hasweights;
//Write to the printout data set.
apop_data *printout = apop_text_alloc(NULL , outsize_r, outsize_c);
if (hasrownames)
for (size_t i=0; i < in->names->rowct; i ++)
apop_text_set(printout, i + hascolnames, 0, "%s", in->names->row[i]);
for (size_t i=0; i < vsize; i ++) //vsize may be zero.
apop_text_set(printout, i + hascolnames, hasrownames, "%g", gsl_vector_get(in->vector, i));
for (size_t i=0; i < msize1; i ++) //msize1 may be zero.
for (size_t j=0; j < msize2; j ++)
apop_text_set(printout, i + hascolnames, hasrownames + (vsize >0)+ j, "%g", gsl_matrix_get(in->matrix, i, j));
if (in->textsize[0])
for (size_t i=0; i < in->textsize[0]; i ++)
for (size_t j=0; j < in->textsize[1]; j ++)
apop_text_set(printout, i + hascolnames, hasrownames + (vsize>0)+ msize2 + j, "%s", in->text[i][j]);
if (hasweights)
for (size_t i=0; i < in->weights->size; i ++)
apop_text_set(printout, i + hascolnames, outsize_c-1, "%g", gsl_vector_get(in->weights, i));
//column names
if (hascolnames){
if (vsize && in->names->vector)
apop_text_set(printout, 0 , hasrownames, "%s", in->names->vector);
if (msize2 && in->names)
for (size_t i=0; i < in->names->colct; i ++)
apop_text_set(printout, 0 , hasrownames + (vsize>0) + i, "%s", in->names->col[i]);
if (in->textsize[1] && in->names)
for (size_t i=0; i < in->names->textct; i ++)
apop_text_set(printout, 0 , hasrownames + (vsize>0) + msize2 + i, "%s", in->names->text[i]);
if (hasweights)
apop_text_set(printout, 0 , outsize_c-1, "Weights");
}
//get column sizes
int colsizes[outsize_c];
for (size_t i=0; i < outsize_c; i ++){
colsizes[i] = strlen(printout->text[0][i]);
for (size_t j=1; j < outsize_r; j ++)
colsizes[i] = GSL_MAX(colsizes[i], strlen(printout->text[j][i]));
}
//Finally, print
if (in->names && in->names->title && strlen(in->names->title))
printf("\t%s\n\n", in->names->title);
for (size_t j=0; j < outsize_r; j ++){
for (size_t i=0; i < outsize_c; i ++){
white_pad(colsizes[i] - strlen(printout->text[j][i]) + 1);//one spare space.
printf("%s", printout->text[j][i]);
if (i > 0 && i< outsize_c-1)
printf(" %s ", apop_opts.output_delimiter);
}
printf("\n");
}
if (in->more) {
printf("\n");
apop_data_show(in->more);
}
apop_data_free(printout);
}
