/* Statistics code
* Make only one call to reading for a particular time range and compute all our stats
*/
void _compute_statistics(cdb_range_t *range, uint64_t *num_recs, cdb_record_t *records) {
uint64_t i = 0;
uint64_t valid = 0;
double sum = 0.0;
double *values = calloc(*num_recs, sizeof(double));
for (i = 0; i < *num_recs; i++) {
if (!isnan(records[i].value)) {
sum += values[valid] = records[i].value;
valid++;
}
}
range->num_recs = valid;
range->mean = gsl_stats_mean(values, 1, valid);
range->max = gsl_stats_max(values, 1, valid);
range->min = gsl_stats_min(values, 1, valid);
range->sum = sum;
range->stddev = gsl_stats_sd(values, 1, valid);
range->absdev = gsl_stats_absdev(values, 1, valid);
/* The rest need sorted data */
gsl_sort(values, 1, valid);
range->median = gsl_stats_median_from_sorted_data(values, 1, valid);
range->pct95th = gsl_stats_quantile_from_sorted_data(values, 1, valid, 0.95);
range->pct75th = gsl_stats_quantile_from_sorted_data(values, 1, valid, 0.75);
range->pct50th = gsl_stats_quantile_from_sorted_data(values, 1, valid, 0.50);
range->pct25th = gsl_stats_quantile_from_sorted_data(values, 1, valid, 0.25);
/* MAD must come last because it alters the values array
* http://en.wikipedia.org/wiki/Median_absolute_deviation */
for (i = 0; i < valid; i++) {
values[i] = fabs(values[i] - range->median);
if (values[i] < 0.0) {
values[i] *= -1.0;
}
}
/* Final sort is required MAD */
gsl_sort(values, 1, valid);
range->mad = gsl_stats_median_from_sorted_data(values, 1, valid);
free(values);
}
CAMLprim value ml_gsl_stats_absdev(value ow, value omean, value data)
{
size_t len = Double_array_length(data);
double result;
if(ow == Val_none)
if(omean == Val_none)
result = gsl_stats_absdev(Double_array_val(data), 1, len);
else
result = gsl_stats_absdev_m(Double_array_val(data), 1, len,
Double_val(Unoption(omean)));
else {
value w = Unoption(ow);
check_array_size(data, w);
if(omean == Val_none)
result = gsl_stats_wabsdev(Double_array_val(w), 1,
Double_array_val(data), 1, len);
else
result = gsl_stats_wabsdev_m(Double_array_val(w), 1,
Double_array_val(data), 1, len,
Double_val(Unoption(omean)));
}
return copy_double(result);
}