int main(int argc, char **argv){
char c, msg[1000];
int colnames = 'y',
rownames = 0,
tab_exists_check = 0;
char **field_names = NULL;
apop_data *field_name_data, *field_name_data_t;
sprintf(msg, "%s [-d delimiters] text_file table_name dbname\n"
"e.g.: %s -d\",|\" infile.txt a_table info.db\n"
"If the input text file name is a single dash, -, then read from STDIN.\n"
"Input must be plain ASCII or UTF-8.\n"
"-d\t\tThe single-character delimiters to use, e.g., -d \" ,\" or -d \"\\t\" (which you \n"
"\t\t\twill almost certainly have to write as -d \"\\\\t\"). Default: \"| ,\\t\", meaning \n"
"\t\t\tthat any of a pipe, space, comma, or tab will delimit separate entries\n"
"-nc\t\tData does not include column names\n"
"-n regex\t\tCase-insensitive regular expression indicating Null values. Default: NaN \n"
"-m\t\tUse a mysql database (default: SQLite)\n"
"-f\t\tfixed width field ends: -f\"3,8,12,17\" (first char is one, not zero)\n"
"-u\t\tmysql username\n"
"-p\t\tmysql password\n"
"-r\t\tData includes row names\n"
"-v\t\tVerbose\n"
"-N\t\tA comma-separated list of column names: -N\"apple,banana,carrot,durian\"\n"
"-O\t\tIf table exists, erase it and write from scratch (i.e., Overwrite)\n"
"-h\t\tPrint this help\n\n"
, argv[0], argv[0]);
int * field_list = NULL;
if(argc<3){
printf("%s", msg);
return 0;
}
while ((c = getopt (argc, argv, "n:d:f:hmp:ru:vN:O")) != -1)
if (c=='n') {
if (optarg[0]=='c')
colnames='n';
else
strcpy(apop_opts.db_nan, optarg);
}
else if (c=='N') {
apop_regex(optarg, " *([^,]*[^ ]) *(,|$) *", &field_name_data);
field_name_data_t = apop_data_transpose(field_name_data);
field_names = field_name_data_t->text[0];
}
else if (c=='d') strcpy(apop_opts.input_delimiters, optarg);
else if (c=='f') field_list = break_down(optarg);
else if (c=='h') printf("%s", msg);
else if (c=='m') apop_opts.db_engine = 'm';
else if (c=='u') strcpy(apop_opts.db_user, optarg);
else if (c=='p') strcpy(apop_opts.db_pass, optarg);
else if (c=='r') rownames++;
else if (c=='v') apop_opts.verbose=2;
else if (c=='O') tab_exists_check++;
apop_db_open(argv[optind + 2]);
if (tab_exists_check) apop_table_exists(argv[optind+1],1);
apop_query("begin;");
apop_text_to_db(argv[optind], argv[optind+1], rownames, colnames, field_names, .field_ends=field_list);
apop_query("commit;");
}
int main(int argc, char **argv){
int c;
char *msg;
int colnames = 'y',
rownames = 0,
tab_exists_check = 0;
char **field_names = NULL;
Asprintf(&msg, "Usage: %s [-d delimiters] text_file table_name dbname\n"
"\n"
"If the input text file name is a single dash, -, then read from STDIN.\n"
"Input must be plain ASCII or UTF-8.\n"
" -d\t\tthe single-character delimiters to use, e.g., -d \" ,\" or -d \"\\t\" (which you \n"
" \t\t\twill almost certainly have to write as -d \"\\\\t\") (default: \"|,\\t\", meaning \n"
" \t\t\tthat any of a pipe, comma, or tab will delimit separate entries)\n"
" -nc\t\tdata does not include column names\n"
" -n regex\t\tcase-insensitive regular expression indicating Null values (default: NaN)\n"
" -m\t\tuse a MySQL database (default: SQLite)\n"
" -f\t\tfixed width field ends: -f\"3,8,12,17\" (first char is one, not zero)\n"
" -u\t\tmysql username\n"
" -p\t\tmysql password\n"
" -r\t\tdata includes row names\n"
" -v\t\tverbosity\n"
" -N\t\ta comma-separated list of column names: -N\"apple,banana,carrot,durian\"\n"
" -en\t\tif table exists, do nothing and exit\n"
" -ed\t\tif table exists, retain the table, delete all data, refill with the new data (i.e., call 'delete * from your_table')\n"
" -eo\t\tif table exists, overwrite the table from scratch (deleting the previous table entirely)\n"
" -ea\t\tif table exists, append new data to the existing table\n"
" -h\t\tdisplay this help and exit\n"
"\n"
, argv[0]);
int * field_list = NULL;
char if_exists = 'n';
if(argc<3){
printf("%s", msg);
return 0;
}
while ((c = getopt (argc, argv, "n:d:e:f:hmp:ru:vN:O")) != -1)
if (c=='n') {
if (optarg[0]=='c') colnames='n';
else apop_opts.nan_string = optarg;
}
else if (c=='N') {
apop_data *field_name_data;
apop_regex(optarg, " *([^,]*[^ ]) *(,|$) *", &field_name_data);
Apop_stopif(!field_name_data, return 1, 0, "'%s' should be a "
"comma-delimited list of field names, but I had trouble "
"parsing it as such.", optarg);
apop_data_transpose(field_name_data);
field_names = field_name_data->text[0];
}
ykl_s make_yule(char const *zila, int y) {
static gsl_matrix *indices;
if (!indices) {
indices = gsl_matrix_calloc(65,1);
for (int i=0; i< 64; i++) gsl_matrix_set(indices, i,0, i);
}
apop_data *col = make_histo(zila, y);
apop_data ww = (apop_data) {
.weights=col->vector, .matrix=indices
};
apop_data *d = apop_data_transpose(col);
apop_data *exp = apop_data_rank_expand(d);
apop_model *m = apop_estimate(exp, apop_yule);
apop_model *n = apop_estimate(exp, apop_lognormal);
ykl_s out = (ykl_s) {
.yule=apop_data_get(m->parameters, .col=-1/*, .rowname="mu"*/),
.ln=apop_data_get(n->parameters, .col=-1/*, .rowname="mu"*/),
.lnstderr=sqrt(apop_data_get(n->parameters, .col=-1, .row=1/*, .rowname="mu"*/)),
.kl = apop_kl_divergence(apop_estimate(&ww, apop_pmf), m),
.lnkl = apop_kl_divergence(apop_estimate(&ww, apop_pmf), n),
.mean = apop_matrix_mean(col->matrix)
};
apop_data_free(d);
apop_data_free(exp);
apop_model_free(m);
return out;
}
int main() {
printf("zila|year|yule_p|kl_div|mu|ln_mu|ln_sigma|ln_kl\n");
apop_db_open("b.db");
apop_data *zilas = apop_query_to_text("select admname from ppl");
for (int i=0; i< *zilas->textsize; i++)
for (int y=2001; y<= 2005; y++) {
ykl_s ykl = make_yule(*zilas->text[i], y);
printf("%20s| %i| %g| %g| %g| %g| %g|%g\n", *zilas->text[i], y, ykl.yule, ykl.kl, ykl.mean, ykl.ln, ykl.lnstderr, ykl.lnkl);
}
//apop_plot_histogram(m->data->weights, 64, .output_file="histo");
}
