long KNN_prune_kCoverage
(
///////////////////////////////
// Parameters //
///////////////////////////////
Pattern p, // source
//
Categories c, // source
//
long y, // source instance index
//
long k, // k(!)
//
long * indices // Out: kCoverage set
//
)
{
Melder_assert(y <= p->ny);
Melder_assert(k > 0 && k <= p->ny);
long cc = 0;
FeatureWeights fws = FeatureWeights_create(p->nx);
if (fws)
{
long *tempindices = NUMlvector (0, p->ny - 1);
for (long yy = 1; yy <= p->ny; yy++)
{
if (y != yy && FRIENDS(c->item[y], c->item[yy]))
{
// long n = KNN_kNeighboursSkip(p, p, fws, yy, k, tempindices, 0); .OS.081011
long n = KNN_kNeighboursSkip(p, p, fws, yy, k, tempindices, y);
while (n)
{
Melder_assert (n <= p->ny);
if (tempindices[--n] == y)
{
indices[cc++] = yy;
break;
}
}
}
}
NUMlvector_free (tempindices, 0);
forget(fws);
}
return(cc);
}
int KNN_prune_superfluous
(
///////////////////////////////
// Parameters //
///////////////////////////////
Pattern p, // source
//
Categories c, // source
//
long y, // source instance index
//
long k, // k(!)
//
long skipper // Skipping instance skipper
//
)
{
if (y > p->ny) y = p->ny; // safety belt
if (k > p->ny) k = p->ny;
FeatureWeights fws = FeatureWeights_create(p->nx);
if (fws)
{
long *indices = NUMlvector (0, k - 1);
long *freqindices = NUMlvector (0, k - 1);
double *distances = NUMdvector (0, k - 1);
double *freqs = NUMdvector (0, k - 1);
// KNN_kNeighboursSkip(p, p, fws, y, k, indices, skipper); .OS.081011 ->
if(!KNN_kNeighboursSkip(p, p, fws, y, k, indices, skipper))
return(0);
// .OS.081011 <-
long ncategories = KNN_kIndicesToFrequenciesAndDistances(c, k, indices, distances, freqs, freqindices);
forget(fws);
int result = FRIENDS(c->item[y], c->item[freqindices[KNN_max(freqs, ncategories)]]);
NUMlvector_free (indices, 0);
NUMlvector_free (freqindices, 0);
NUMdvector_free (distances, 0);
NUMdvector_free (freqs, 0);
if (result)
return 1;
}
return 0;
}
int main(int argc, char *argv[], char *envp[])
{
//FIXME:user could choose only a website no all website.which means --host is available.
static const struct option options[] = {
{"debug", 0, NULL, 'd'},
{"verbose", 0, NULL, 'V'},
{"action", 1, NULL, 'A'},
{"logfile", 1, NULL, 'L'},
{"shrink-urls", 0, NULL, 's'},
{"help", 0, NULL, 'h'},
{"bash", 0, NULL, 'b'},
{"background", 0, NULL, 'B'},
{"dry-run", 0, NULL, 'n'},
{"page", 1, NULL, 'g'},
{"version", 0, NULL, 'v'},
{"config", 1, NULL, 'c'},
{"replyto", 1, NULL, 'r'},
{"retweet", 1, NULL, 'w'},
{}
};
struct session *session;
pid_t child;
int retval = 0;
int option;
char *home;
const char *config_file;
time_t t;
int page_nr;
char *tweet;
debug = 0;
session = session_alloc();
if (!session) {
fprintf(stderr, "no more memory...\n");
return -1;
}
/* get the current time so that we can log it later */
time(&t);
session->time = strdup(ctime(&t));
session->time[strlen(session->time) - 1] = 0x00;
/*
* Get the home directory so we can try to find a config file.
* If we have no home dir set up, look in /etc/bti
*/
home = getenv("HOME");
if (home) {
/* We have a home dir, so this might be a user */
session->homedir = strdup(home);
config_file = config_user_default;
} else {
session->homedir = strdup("");
config_file = config_default;
}
/* set up a default config file location (traditionally ~/.bti) */
session->configfile =
zalloc(strlen(session->homedir) + strlen(config_file) + 7);
sprintf(session->configfile, "%s/%s", session->homedir, config_file);
session_readline_init(session);
struct account *account = parse_configfile(session);
if (account == NULL) {
fprintf(stderr, "parse err, goto exit\n");
exit(-1);
}
while (1) {
option = getopt_long_only(argc, argv,
"dp:P:H:a:A:u:c:hg:G:sr:nVvw:",
options, NULL);
if (option == -1)
break;
switch (option) {
case 'd':
debug = 1;
break;
case 'V':
session->verbose = 1;
break;
case 'g':
page_nr = atoi(optarg);
dbg("page = %d\n", page_nr);
session->page = page_nr;
break;
case 'r':
session->replyto = strdup(optarg);
dbg("in_reply_to_status_id = %s\n", session->replyto);
break;
case 'A':
if (strcasecmp(optarg, "update") == 0)
session->action = ACTION_UPDATE;
else if (strcasecmp(optarg, "friends") == 0)
session->action = ACTION_FRIENDS;
else if (strcasecmp(optarg, "user") == 0)
session->action = ACTION_USER;
else if (strcasecmp(optarg, "replies") == 0)
session->action = ACTION_REPLIES;
else if (strcasecmp(optarg, "public") == 0)
session->action = ACTION_PUBLIC;
else if (strcasecmp(optarg, "group") == 0)
session->action = ACTION_GROUP;
else if (strcasecmp(optarg, "retweet") == 0)
session->action = ACTION_RETWEET;
else
session->action = ACTION_UNKNOWN;
dbg("action = %d\n", session->action);
break;
case 'u':
if (session->user)
free(session->user);
session->user = strdup(optarg);
dbg("user = %s\n", session->user);
break;
case 'G':
if (session->group)
free(session->group);
session->group = strdup(optarg);
dbg("group = %s\n", session->group);
break;
case 'L':
if (session->logfile)
free(session->logfile);
session->logfile = strdup(optarg);
dbg("logfile = %s\n", session->logfile);
break;
case 's':
session->shrink_urls = 1;
break;
case 'b':
session->bash = 1;
/* fall-through intended */
case 'B':
session->background = 1;
break;
case 'c':
if (session->configfile)
free(session->configfile);
session->configfile = strdup(optarg);
dbg("configfile = %s\n", session->configfile);
/*
* read the config file now. Yes, this could override
* previously set options from the command line, but
* the user asked for it...
*/
//bti_parse_configfile(session);
break;
case 'h':
display_help();
goto exit;
case 'n':
session->dry_run = 1;
break;
case 'v':
display_version();
goto exit;
default:
display_help();
goto exit;
}
}
/*
* Show the version to make it easier to determine what
* is going on here
*/
if (debug)
display_version();
if (session->action == ACTION_UNKNOWN) {
fprintf(stderr, "Unknown action, valid actions are:\n"
"'update', 'friends', 'public', 'replies', 'group' or 'user'.\n");
goto exit;
}
dbg("config file = %s\n", session->configfile);
dbg("action = %d\n", session->action);
/* fork ourself so that the main shell can get on
* with it's life as we try to connect and handle everything
*/
if (session->background) {
child = fork();
if (child) {
dbg("child is %d\n", child);
exit(0);
}
}
switch (session->action) {
case ACTION_PUBLIC:
PUBLIC(account, session, retval);
break;
case ACTION_UPDATE:
if (session->background || !session->interactive)
tweet = get_string_from_stdin();
else
tweet = session->readline("tweet: ");
if (!tweet || strlen(tweet) == 0) {
dbg("no tweet?\n");
return -1;
}
if (session->shrink_urls)
tweet = shrink_urls(tweet);
session->tweet = zalloc(strlen(tweet) + 10);
if (session->bash)
sprintf(session->tweet, "%c %s",
getuid()? '$' : '#', tweet);
else
sprintf(session->tweet, "%s", tweet);
if (tweet)
free(tweet);
dbg("tweet = %s\n", session->tweet);
UPDATE(account, session, retval);
break;
case ACTION_FRIENDS:
FRIENDS(account, session, retval);
break;
case ACTION_REPLIES:
REPLIES(account, session, retval);
break;
default:
retval = -1;
break;
}
// retval = send_request(session);
if (retval && !session->background)
fprintf(stderr, "operation failed\n");
/* log_session(session, retval); */
DESTORY(account);
exit:
session_readline_cleanup(session);
session_free(session);
return retval;;
}
Categories Pattern_to_Categories_cluster
(
///////////////////////////////
// Parameters //
///////////////////////////////
Pattern p, // source
//
FeatureWeights fws, // feature weights
//
long k, // k(!)
//
double s, // clustersize constraint 0 < s <= 1
//
long m // reseed maximum
//
)
{
Categories categories = NULL, output = NULL;
KNN knn = NULL;
Pattern centroids = NULL;
double *sizes = NULL, *beta = NULL;
long *seeds = NULL;
categories = Categories_sequentialNumbers (k); cherror
if (k == p->ny)
return categories;
knn = KNN_create(); cherror
if(p->ny % k)
if (s > (double) (p->ny / k) / (double) (p->ny / k + 1))
s = (double) (p->ny / k) / (double) (p->ny / k + 1);
double progress = m;
sizes = NUMdvector (0, k); cherror
seeds = NUMlvector (0, k); cherror
centroids = Pattern_create (k, p->nx);
beta = NUMdvector (0, centroids->nx);
do
{
double delta;
long nfriends = 0;
if (!Melder_progress1(1 - (progress - m) / progress, L"")) break;
for (long y = 1; y <= centroids->ny; y++)
{
int friend = 1;
long ys = (long) lround(NUMrandomUniform(1, p->ny));
if (nfriends)
{
while (friend)
{
ys = (long) lround(NUMrandomUniform(1, p->ny));
for (long fc = 0; fc < nfriends; fc++)
{
friend = 0;
Melder_assert (fc < k);
if (seeds [fc] == ys)
{
friend = 1;
break;
}
}
}
}
Melder_assert (nfriends <= k);
seeds [nfriends++] = ys;
for (long x = 1; x <= centroids->nx; x++)
centroids->z[y][x] = p->z[ys][x];
}
do
{
delta = 0;
KNN_learn (knn, centroids, categories, kOla_REPLACE, kOla_SEQUENTIAL);
Categories interim = KNN_classifyToCategories (knn, p, fws, 1, kOla_FLAT_VOTING);
for (long x = 1; x <= k; x++)
sizes [x] = 0;
for (long yp = 1; yp <= categories->size; yp++)
{
double alfa = 1;
Melder_assert (yp <= centroids->ny);
for (long x = 1; x <= centroids->nx; x++)
{
beta[x] = centroids->z[yp][x];
}
for (long ys = 1; ys <= interim->size; ys++)
{
if (FRIENDS(categories->item[yp], interim->item[ys]))
{
for (long x = 1; x <= p->nx; x++)
{
Melder_assert (ys <= p->ny);
if (alfa == 1)
{
centroids->z[yp][x] = p->z[ys][x];
}
else
{
centroids->z[yp][x] += (p->z[ys][x] - centroids->z[yp][x]) / alfa;
}
}
Melder_assert (yp <= k);
sizes [yp] ++;
alfa++;
}
}
for (long x = 1; x <= centroids->nx; x++)
{
delta += fabs (beta[x] - centroids->z[yp][x]);
}
}
forget (interim);
}
while (delta);
double smax = sizes [1];
double smin = sizes [1];
for (long x = 1; x <= k; x++)
{
if (smax < sizes [x]) smax = sizes [x];
if (smin > sizes [x]) smin = sizes [x];
}
sizes [0] = smin / smax;
--m;
}
while (sizes[0] < s && m > 0);
Melder_progress1(1.0, NULL);
output = KNN_classifyToCategories (knn, p, fws, 1, kOla_FLAT_VOTING); cherror
end:
forget (centroids);
forget (categories);
forget (knn);
NUMdvector_free (sizes, 0);
NUMdvector_free (beta, 0);
NUMlvector_free (seeds, 0);
iferror return NULL;
return output;
}
