int main(){
apop_data *d = apop_text_alloc(apop_data_alloc(6), 6, 1);
apop_data_fill(d, 1, 2, 3, 3, 1, 2);
apop_text_fill(d, "A", "A", "A", "A", "A", "B");
asprintf(&d->names->title, "Original data set");
printdata(d);
//binned, where bin ends are equidistant but not necessarily in the data
apop_data *binned = apop_data_to_bins(d, NULL);
asprintf(&binned->names->title, "Post binning");
printdata(binned);
assert(apop_sum(binned->weights)==6);
assert(fabs(//equal distance between bins
(apop_data_get(binned, 1, -1) - apop_data_get(binned, 0, -1))
- (apop_data_get(binned, 2, -1) - apop_data_get(binned, 1, -1))) < 1e-5);
//compressed, where the data is as in the original, but weights
//are redome to accommodate repeated observations.
apop_data_pmf_compress(d);
asprintf(&d->names->title, "Post compression");
printdata(d);
assert(apop_sum(d->weights)==6);
apop_model *d_as_pmf = apop_estimate(d, apop_pmf);
Apop_row(d, 0, firstrow); //1A
assert(fabs(apop_p(firstrow, d_as_pmf) - 2./6 < 1e-5));
}
int main(){
apop_db_open("data-climate.db");
apop_data *data = apop_query_to_data("select pcp from precip");
apop_data_pmf_compress(data); //creates a weights vector
apop_vector_normalize(data->weights);
apop_data_sort(data);
apop_model *pmf = apop_estimate(data, apop_pmf);
FILE *outfile = fopen("out.h", "w");
apop_model_print(pmf, outfile);
apop_model *kernel = apop_model_set_parameters(apop_normal, 0., 0.1);
apop_model *k = apop_model_copy(apop_kernel_density);
Apop_settings_add_group(k, apop_kernel_density, .base_pmf=pmf, .kernel=kernel);
plot(k, "out.k");
printf("plot 'out.h' with lines title 'data', 'out.k' with lines title 'smoothed'\n");
}
/** Create a histogram from data by putting data into bins of fixed width.
\param indata The input data that will be binned. This is copied and the copy will be modified.
\param close_top_bin Normally, a bin covers the range from the point equal to its minimum to points strictly less than
the minimum plus the width. if \c 'y', then the top bin includes points less than or equal to the upper bound. This solves the problem of displaying histograms where the top bin is just one point.
\param binspec This is an \ref apop_data set with the same number of columns as \c indata.
If you want a fixed size for the bins, then the first row of the bin spec is the bin width for each column.
This allows you to specify a width for each dimension, or specify the same size for all with something like:
\param bin_count If you don't provide a bin spec, I'll provide this many evenly-sized bins. Default: \f$\sqrt(N)\f$. \code
Apop_data_row(indata, 0, firstrow);
apop_data *binspec = apop_data_copy(firstrow);
gsl_matrix_set_all(binspec->matrix, 10); //bins of size 10 for all dim.s
apop_data_to_bins(indata, binspec);
\endcode
The presumption is that the first bin starts at zero in all cases. You can add a second row to the spec to give the offset for each dimension. Default: NULL. if no binspec and no binlist, then a grid with offset equal to the min of the column, and bin size such that it takes \f$\sqrt{N}\f$ bins to cover the range to the max element.
\return A pointer to a binned \ref apop_data set. If you didn't give me a binspec, then I attach one to the output set as a page named \c \<binspec\>, so you can snap a second data set to the same grid using
\code
apop_data_to_bins(first_set, NULL);
apop_data_to_bins(second_set, apop_data_get_page(first_set, "<binspec>"));
\endcode
The text segment, if any, is not binned. I use \ref apop_data_pmf_compress as the final step in the binning,
and that does respect the text segment.
Here is a sample program highlighting the difference between \ref apop_data_to_bins and \ref apop_data_pmf_compress .
\include binning.c
*/
APOP_VAR_HEAD apop_data *apop_data_to_bins(apop_data *indata, apop_data *binspec, int bin_count, char close_top_bin){
apop_data *apop_varad_var(indata, NULL);
Apop_assert_c(indata, NULL, 1, "NULL input data set, so returning NULL output data set.");
apop_data *apop_varad_var(binspec, NULL);
char apop_varad_var(close_top_bin, 'n');
int apop_varad_var(bin_count, 0);
APOP_VAR_ENDHEAD
Get_vmsizes(indata); //firstcol, vsize, msize1, msize2
double binwidth, offset, max=0;
apop_data *out = apop_data_copy(indata);
apop_data *bs = binspec ? binspec
: apop_data_add_page(out,
apop_data_alloc(vsize? 2: 0, msize1? 2: 0, indata->matrix ? msize2: 0),
"<binspec>");
for (int j= firstcol; j< msize2; j++){
Apop_col(out, j, onecol);
if (binspec){
binwidth = apop_data_get(binspec, 0, j);
offset = ((binspec->vector && binspec->vector->size==2 )
||(binspec->matrix && binspec->matrix->size1==2)) ? apop_data_get(binspec, 1, j) : 0;
} else {
Apop_col(bs, j, abin);
max = gsl_vector_max(onecol);
offset = abin->data[1] = gsl_vector_min(onecol);
binwidth = abin->data[0] = (max - offset)/(bin_count ? bin_count : sqrt(onecol->size));
}
for (int i=0; i< onecol->size; i++){
double val = gsl_vector_get(onecol, i);
if (close_top_bin=='y' && val == max && val!=offset)
val -= 2*GSL_DBL_EPSILON;
gsl_vector_set(onecol, i, (floor((val -offset)/binwidth))*binwidth+offset);
}
}
apop_data_pmf_compress(out);
return out;
}
