int main(){
apop_opts.db_engine='s'; //SQLite only.
apop_query("create table atab (a numeric)");
for (int i=0; i< 1e5; i++)
apop_query("insert into atab values(ran())");
apop_query("create table powa as "
"select a, pow(a, 2) as sq, pow(a, 0.5) as sqrt "
"from atab");
//compare the std dev of a uniform as reported by the
//database routine, the matrix routine, and math.
double db_pop_stddev = apop_query_to_float("select stddev_pop(a) from powa");
apop_data *d = apop_query_to_data("select * from powa");
apop_data *cov = apop_data_covariance(d);
double matrix_pop_stddev = sqrt(apop_data_get(cov)*(d->matrix->size1/(d->matrix->size1-1.)));
assert(fabs(db_pop_stddev - matrix_pop_stddev) < 1e-4);
double actual_stddev = sqrt(2*gsl_pow_3(.5)/3);
assert(fabs(db_pop_stddev - actual_stddev) < 1e-3);
float sq_mean = apop_query_to_float("select avg(sq) from powa");
float actual_sq_mean = 1./3;
assert(fabs(sq_mean - actual_sq_mean) < 1e-3);
float sqrt_mean = apop_query_to_float("select avg(sqrt) from powa");
float actual_sqrt_mean = 2./3;
assert(fabs(sqrt_mean - actual_sqrt_mean) < 1e-3);
}
apop_data *query_data(){
apop_db_open("data-census.db");
return apop_query_to_data(" select postcode as row_names, "
" m_per_100_f, population/1e6 as population, median_age "
" from geography, income,demos,postcodes "
" where income.sumlevel= '040' "
" and geography.geo_id = demos.geo_id "
" and income.geo_name = postcodes.state "
" and geography.geo_id = income.geo_id ");
}
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_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");
}
int main(){
char outfile[] = "scatter.gplot";
apop_db_open("data-metro.db");
apop_data *data = apop_query_to_data("select riders, year from riders where station like 'Silver%%' and riders>0");
apop_db_close();
//The regression destroys your data, so copy it first.
apop_data *data_copy = apop_data_copy(data);
//Run OLS, display results on terminal
apop_model *est = apop_estimate(data, apop_OLS);
apop_model_show(est);
//Prep the file with a header, then call the function.
FILE *f = fopen(outfile, "w");
fprintf(f,"set term postscript;\n set output \"scatter.eps\"\n set yrange [0:*]\n");
apop_plot_line_and_scatter(data_copy, est, .output_pipe=f);
fclose(f);
}
#include <apop.h>
int main(void){
apop_text_to_db(.text_file="data", .tabname="d");
apop_data *data = apop_query_to_data("select * from d");
apop_model *est = apop_estimate(data, apop_ols);
apop_model_show(est);
Apop_settings_add_group(est, apop_pm, .index =1);
apop_model *first_param_distribution = apop_parameter_model(data, est);
Apop_row(est->parameters, 1, param);
double area_under_p = apop_cdf(param, first_param_distribution);
apop_data_set(param, 0, -1, .val=0);
double area_under_zero = apop_cdf(param, first_param_distribution);
printf("reject the null for x_1 with %g percent confidence.\n",
2*fabs(area_under_p-area_under_zero));
}
