void read_tree(Node **head, char **buffer) {
char ch;
Node *x = create_node(0,0);
*head = x;
ch = (*buffer)[0];
*buffer += 1;
if(ch == 'N') {
x->ch = ALPHABET;
read_tree(&x->left, buffer);
read_tree(&x->right, buffer);
} else {
x->ch = (*buffer)[0];
*buffer += 1;
}
}
static void pipe_right(t_node *tree, int *pipe_fd, t_data *data)
{
char *line;
off_t offset;
close(pipe_fd[1]);
if (data->tmp_pipeout == -1)
get_tmpfd(&data->tmp_pipeout, "/.temp_pipeout");
else
{
remove_tmp("/.temp_pipeout");
get_tmpfd(&data->tmp_pipeout, "/.temp_pipeout");
}
while (get_next_line(pipe_fd[0], &line) > 0)
{
ft_putendl_fd(line, data->tmp_pipeout);
ft_strdel(&line);
}
offset = lseek(data->tmp_pipeout, 0, SEEK_CUR);
lseek(data->tmp_pipeout, 0, SEEK_SET);
update_offset(&data, offset);
read_tree(tree->right);
remove_tmp("/.temp_pipeout");
if (g_pid.built == 0 || WEXITSTATUS(g_pid.id) != 0)
exit(EXIT_FAILURE);
else
exit(EXIT_SUCCESS);
}
static size_t read_extension(git_index *index, const char *buffer, size_t buffer_size)
{
const struct index_extension *source;
struct index_extension dest;
size_t total_size;
source = (const struct index_extension *)(buffer);
memcpy(dest.signature, source->signature, 4);
dest.extension_size = ntohl(source->extension_size);
total_size = dest.extension_size + sizeof(struct index_extension);
if (buffer_size - total_size < INDEX_FOOTER_SIZE)
return 0;
/* optional extension */
if (dest.signature[0] >= 'A' && dest.signature[0] <= 'Z') {
/* tree cache */
if (memcmp(dest.signature, INDEX_EXT_TREECACHE_SIG, 4) == 0) {
if (read_tree(index, buffer + 8, dest.extension_size) < 0)
return 0;
}
} else {
/* we cannot handle non-ignorable extensions;
* in fact they aren't even defined in the standard */
return 0;
}
return total_size;
}
int main(int argc, char **argv) {
unordered_map<int, TreeNode *> map;
TreeNode *root = read_tree(argc - 3, argv + 1);
add_to_map(map, root);
cout << Solution().lowestCommonAncestor(root,
map[atoi(argv[argc - 2])], map[atoi(argv[argc - 1])])->val << endl;
return 0;
}
int main(int argc, char **argv) {
BSTIterator i(read_tree(argc - 1, argv + 1));
while (i.hasNext()) {
cout << i.next() << " ";
}
cout << endl;
return 0;
}
int main( void ) {
tree *tp = read_tree();
if ((balanced(tp)) == 1) printf("BALANCED\n");
else printf("UNSTABLE\n");
return 0;
}
softmax_layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) layer.softmax_tree = read_tree(tree_file);
return layer;
}
void huffman_decoder::read_tree(size_t node_offset) {
code_node* node;
bool is_leaf = inbs->read_bit();
if (is_leaf) {
node = new code_node(chars.front());
chars.pop();
} else {
size_t l = used_nodes_count++;
read_tree(l);
size_t r = used_nodes_count++;
read_tree(r);
node = new code_node(nodes[l], nodes[r]);
}
nodes[node_offset] = node;
}
void BenchTree()
{
printf("\n************ ROOT/TTree I/O ************ \n");
const char *fname2 = "testio.root";
Double_t wbytes;
wbytes = write_tree(fname2,100000000,0);
read_tree(fname2,wbytes);
}
static int unpack_tree(unsigned char *sha1)
{
void *buffer;
unsigned long size;
buffer = read_object_with_reference(sha1, "tree", &size, 0);
if (!buffer)
return -1;
return read_tree(buffer, size, stage);
}
/* Build the Huffman tree recursively.
*/
void read_tree(file *f, huf_node *node, bool isRoot){
int bit = bitfile_get_bit(f);
if(bit==EOF){
if(isRoot) return;
else die_format();
}
if(!bit){ // internal node
huf_node *left = (huf_node *)malloc_or_die(2*sizeof(huf_node));
huf_node *right = left+1;
node->left = left;
node->right = right;
read_tree(f, left, false);
read_tree(f, right, false);
}else{ // leaf node
int s = bitfile_get_symbol(f, SYMBOL_LENGTH);
if(s==EOF) die_format();
node->symbol = s;
node->left = NULL;
node->right = NULL;
}
}
/*
* Read the tree specified with --with-tree option
* (typically, HEAD) into stage #1 and then
* squash them down to stage #0. This is used for
* --error-unmatch to list and check the path patterns
* that were given from the command line. We are not
* going to write this index out.
*/
void overlay_tree_on_cache(const char *tree_name, const char *prefix)
{
struct tree *tree;
unsigned char sha1[20];
const char **match;
struct cache_entry *last_stage0 = NULL;
int i;
if (get_sha1(tree_name, sha1))
die("tree-ish %s not found.", tree_name);
tree = parse_tree_indirect(sha1);
if (!tree)
die("bad tree-ish %s", tree_name);
/* Hoist the unmerged entries up to stage #3 to make room */
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
if (!ce_stage(ce))
continue;
ce->ce_flags |= CE_STAGEMASK;
}
if (prefix) {
static const char *(matchbuf[2]);
matchbuf[0] = prefix;
matchbuf[1] = NULL;
match = matchbuf;
} else
match = NULL;
if (read_tree(tree, 1, match))
die("unable to read tree entries %s", tree_name);
for (i = 0; i < active_nr; i++) {
struct cache_entry *ce = active_cache[i];
switch (ce_stage(ce)) {
case 0:
last_stage0 = ce;
/* fallthru */
default:
continue;
case 1:
/*
* If there is stage #0 entry for this, we do not
* need to show it. We use CE_UPDATE bit to mark
* such an entry.
*/
if (last_stage0 &&
!strcmp(last_stage0->name, ce->name))
ce->ce_flags |= CE_UPDATE;
}
}
}
void huffman_decoder::read_tree(std::istream & ins) {
nodes_count = nodes_count_by_chars_count(chars_count);
chars = std::queue< code_char_t >();
for (size_t i = 0; i < chars_count; i++) {
chars.push(ins.get());
}
nodes = new code_node*[nodes_count];
used_nodes_count = 1;
read_tree(0);
}
layer parse_region(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 4);
int classes = option_find_int(options, "classes", 20);
int num = option_find_int(options, "num", 1);
layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
assert(l.outputs == params.inputs);
l.log = option_find_int_quiet(options, "log", 0);
l.sqrt = option_find_int_quiet(options, "sqrt", 0);
l.softmax = option_find_int(options, "softmax", 0);
l.background = option_find_int_quiet(options, "background", 0);
l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0);
l.thresh = option_find_float(options, "thresh", .5);
l.classfix = option_find_int_quiet(options, "classfix", 0);
l.absolute = option_find_int_quiet(options, "absolute", 0);
l.random = option_find_int_quiet(options, "random", 0);
l.coord_scale = option_find_float(options, "coord_scale", 1);
l.object_scale = option_find_float(options, "object_scale", 1);
l.noobject_scale = option_find_float(options, "noobject_scale", 1);
l.mask_scale = option_find_float(options, "mask_scale", 1);
l.class_scale = option_find_float(options, "class_scale", 1);
l.bias_match = option_find_int_quiet(options, "bias_match",0);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
char *map_file = option_find_str(options, "map", 0);
if (map_file) l.map = read_map(map_file);
char *a = option_find_str(options, "anchors", 0);
if(a){
int len = strlen(a);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
for(i = 0; i < n; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
}
}
return l;
}
void huffman_decoder::decode_file(std::istream & ins, std::ostream & outs) {
inbs = new ibstream(ins);
chars_count = (((size_t)ins.get()) << 8) | ((size_t)ins.get());
if (chars_count == 0) {
return;
}
read_tree(ins);
decode_and_write(outs);
free_resources();
}
std::vector<parse_tree> extract_trees(std::istream& stream)
{
std::vector<parse_tree> results;
read_whitespace(stream);
while (stream)
{
results.emplace_back(read_tree(stream));
read_whitespace(stream);
}
return results;
}
layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
layer l = make_softmax_layer(params.batch, params.inputs, groups);
l.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
l.w = params.w;
l.h = params.h;
l.c = params.c;
l.spatial = option_find_float_quiet(options, "spatial", 0);
l.noloss = option_find_int_quiet(options, "noloss", 0);
return l;
}
static vl_bool read_tree(VlHIKMNode*& node, vl_uint32 height, const char* strSavePath, const char* strInd)
{
node = (VlHIKMNode*)malloc (sizeof(VlHIKMNode)) ;
node-> filter = new CIKMTree();
node-> children = NULL ;
//CString strFileClusterName = strSavePath + "\\" + strInd + ".txt";
char strFileClusterName[MAX_PATH];
strcpy( strFileClusterName, strSavePath );
strcat( strFileClusterName, "\\" );
strcat( strFileClusterName, strInd );
strcat( strFileClusterName, ".txt" );
if(!node->filter->vl_ikm_read_tree( strFileClusterName )){
return FALSE;
}
if (height > 1) {
vl_uint32 K = node->filter->vl_ikm_get_k();
node-> children = (VlHIKMNode**)malloc(sizeof(VlHIKMNode*) * K) ;
for ( vl_uint32 k = 0; k < K; k++ ) {
//CString strIndChild;
//strIndChild.Format( _T("%3d"), k );
//strIndChild.Replace( _T(" "), _T("0") );
//strIndChild = strInd + strIndChild;
char strIndChild[MAX_PATH];
sprintf( strIndChild, "%s%4d", strInd, k );
for ( int c = 0; c < strlen(strIndChild); c++ )
{
if ( strIndChild[c] == ' ')
{
strIndChild[c] = '0';
}
}
if(!read_tree(node->children[k], height-1, strSavePath, strIndChild)){
return FALSE;
}
}
}
return TRUE;
}
int main(int argc, char **argv) {
int64_t i;
if (argc<3) {
printf("Usage: %s box_size tree.dat ...\n", argv[0]);
exit(1);
}
box_size = atof(argv[1]);
init_time_table(0.27, 0.7);
printf("#Scale Id Mvir_acc(Host) Rvir_acc(Host) Mnow Vnow Mlastmm Vlastmm Rlastmm Rlastmm/Rvir Vacc Mistracked? RlastMajM Rlastmillim a_acc a_lastmm a_lastmajm a_lastmillim\n");
for (i=2; i<argc; i++) {
read_tree(argv[i]);
process_tree();
delete_tree();
}
return 0;
}
TREE_T* read_tree_from_file
(char* filename)
{
TREE_T* tree;
FILE* tree_file = NULL;
if (open_file(filename, "r", 1, "tree", "tree", &tree_file) == 0) {
die("Couldn't open the file %s.\n", filename);
}
read_tree(tree_file, &tree);
(void) fclose(tree_file);
if (verbosity >= HIGH_VERBOSE) {
fprintf(stderr, "Read tree: ");
write_tree(tree, stderr);
}
return tree;
}
static void pipe_left(t_node *tree, int *pipe_fd, t_data *data)
{
char *line;
close(pipe_fd[0]);
get_tmpfd(&data->tmp_pipein, "/.temp_pipein");
read_tree(tree->left);
lseek(data->tmp_pipein, 0, SEEK_SET);
while (get_next_line(data->tmp_pipein, &line) > 0)
{
ft_putendl_fd(line, pipe_fd[1]);
ft_strdel(&line);
}
remove_tmp("/.temp_pipein");
if (g_pid.built == 0 || WEXITSTATUS(g_pid.id) != 0)
exit(EXIT_FAILURE);
else
exit(EXIT_SUCCESS);
}
void redirr_proc(t_node *tree)
{
char *file;
int fd;
t_data *data;
file = ft_strtrim(tree->left->word);
data = init_data(0);
if (data->tmp_fdout == -1)
get_tmpfd(&data->tmp_fdout, "/.temp_out");
if (data->tmp_fdout != -1 && (fd = check_file(file)) != -1)
{
add_outfildes(&data->outfildes, file, fd);
read_tree(tree->right);
}
else
{
update_data(&data);
g_pid.built = 0;
}
ft_strdel(&file);
}
int read_archive(FILE *archive, FILE *output, Header *header) {
unsigned long long i;
Node *head = create_node(ALPHABET, 0);
char byte;
read_tree(&head, &header->tree);
output = fopen(header->filename, "wb");
if(output == NULL) {
return 1;
}
Node *current = head;
for(i = 0; i < header->filesize; i++) {
if(i % 8 == 0) {
fread(&byte, sizeof(char), 1, archive);
}
if(byte & TAB[7 - (i % 8)]) {
current = current->right;
} else {
current = current->left;
}
if(current == NULL) {
fprintf(stderr, "Damaged tree\n");
return 1;
}
if(current->ch < ALPHABET) {
fwrite(¤t->ch, sizeof(char), 1, output);
current = head;
}
show_progress(i, header->filesize);
}
fprintf(stderr, "\n");
return 0;
}
vl_bool CHIKMTree::vl_hikm_read_tree(const char* strSavePath)
{
//CString strFileName = strSavePath + "\\cluster.txt";
char strFileName[MAX_PATH];
strcpy( strFileName, strSavePath );
strcat( strFileName, "\\cluster.txt" );
FILE * file = fopen( strFileName,"rb");
if (!file) {
return FALSE;
}
vl_hikm_new_VlHIKMTree();
if(fscanf(file,"%u %u %u %d %d\n", &(m_VlHIKMTree->M), &(m_VlHIKMTree->K), &(m_VlHIKMTree->depth), &(m_VlHIKMTree->max_niters), &(m_VlHIKMTree->verb)) != 5){
return FALSE;
}
fclose(file);
if(!read_tree(m_VlHIKMTree->root, m_VlHIKMTree->depth, strSavePath, "0")){
return FALSE;
}
return TRUE;
}
static size_t read_extension(git_index *index, const char *buffer, size_t buffer_size)
{
const struct index_extension *source;
struct index_extension dest;
size_t total_size;
source = (const struct index_extension *)(buffer);
memcpy(dest.signature, source->signature, 4);
dest.extension_size = ntohl(source->extension_size);
total_size = dest.extension_size + sizeof(struct index_extension);
if (buffer_size - total_size < INDEX_FOOTER_SIZE)
return 0;
/* optional extension */
if (dest.signature[0] >= 'A' && dest.signature[0] <= 'Z') {
/* tree cache */
if (memcmp(dest.signature, INDEX_EXT_TREECACHE_SIG, 4) == 0) {
if (read_tree(index, buffer + 8, dest.extension_size) < GIT_SUCCESS)
return 0;
} else if (memcmp(dest.signature, INDEX_EXT_UNMERGED_SIG, 4) == 0) {
if (read_unmerged(index, buffer + 8, dest.extension_size) < GIT_SUCCESS)
return 0;
}
/* else, unsupported extension. We cannot parse this, but we can skip
* it by returning `total_size */
} else {
/* we cannot handle non-ignorable extensions;
* in fact they aren't even defined in the standard */
return 0;
}
return total_size;
}
gboolean
dfvm_apply(dfilter_t *df, proto_tree *tree)
{
int id, length;
gboolean accum = TRUE;
dfvm_insn_t *insn;
dfvm_value_t *arg1;
dfvm_value_t *arg2;
dfvm_value_t *arg3 = NULL;
dfvm_value_t *arg4 = NULL;
header_field_info *hfinfo;
GList *param1;
GList *param2;
g_assert(tree);
length = df->insns->len;
for (id = 0; id < length; id++) {
AGAIN:
insn = g_ptr_array_index(df->insns, id);
arg1 = insn->arg1;
arg2 = insn->arg2;
switch (insn->op) {
case CHECK_EXISTS:
hfinfo = arg1->value.hfinfo;
while(hfinfo) {
accum = proto_check_for_protocol_or_field(tree,
hfinfo->id);
if (accum) {
break;
}
else {
hfinfo = hfinfo->same_name_next;
}
}
break;
case READ_TREE:
accum = read_tree(df, tree,
arg1->value.hfinfo, arg2->value.numeric);
break;
case CALL_FUNCTION:
arg3 = insn->arg3;
arg4 = insn->arg4;
param1 = NULL;
param2 = NULL;
if (arg3) {
param1 = df->registers[arg3->value.numeric];
}
if (arg4) {
param2 = df->registers[arg4->value.numeric];
}
accum = arg1->value.funcdef->function(param1, param2,
&df->registers[arg2->value.numeric]);
break;
case MK_RANGE:
arg3 = insn->arg3;
mk_range(df,
arg1->value.numeric, arg2->value.numeric,
arg3->value.drange);
break;
case ANY_EQ:
accum = any_test(df, fvalue_eq,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_NE:
accum = any_test(df, fvalue_ne,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_GT:
accum = any_test(df, fvalue_gt,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_GE:
accum = any_test(df, fvalue_ge,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_LT:
accum = any_test(df, fvalue_lt,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_LE:
accum = any_test(df, fvalue_le,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_BITWISE_AND:
accum = any_test(df, fvalue_bitwise_and,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_CONTAINS:
accum = any_test(df, fvalue_contains,
arg1->value.numeric, arg2->value.numeric);
break;
case ANY_MATCHES:
accum = any_test(df, fvalue_matches,
arg1->value.numeric, arg2->value.numeric);
break;
case NOT:
accum = !accum;
break;
case RETURN:
free_register_overhead(df);
return accum;
case IF_TRUE_GOTO:
if (accum) {
id = arg1->value.numeric;
goto AGAIN;
}
break;
case IF_FALSE_GOTO:
if (!accum) {
id = arg1->value.numeric;
goto AGAIN;
}
break;
case PUT_FVALUE:
#if 0
accum = put_fvalue(df,
arg1->value.fvalue, arg2->value.numeric);
break;
#endif
default:
g_assert_not_reached();
break;
}
}
g_assert_not_reached();
return FALSE; /* to appease the compiler */
}
int main(int argc,char **argv)
{
sint i,j,k,n,s;
sint status;
sint result_type;
char c;
char infile[FILENAMELEN+1];
char treefile[FILENAMELEN+1];
float meanid;
FILE *tree;
sint maxres,*gapptr=NULL;
IN_TREEPTR itree;
double dscore;
double meanscore;
double **tmat;
sint window;
sint block_cutoff;
OPT opt;
if(argc!=2) {
fprintf(stdout,"Usage: %s input_aln\n",argv[0]);
exit(1);
}
strcpy(infile,argv[1]);
init_options(&opt);
/* read in the sequences */
seq_input(infile,opt.explicit_type,FALSE,&mult_aln);
if(mult_aln.nseqs<=0) {
error("No sequences in %s\n",infile);
exit(1);
}
window=8;
/* count pairwise residue percent identities */
tmat = (double **) ckalloc( (mult_aln.nseqs+1) * sizeof (double *) );
for(i=0;i<mult_aln.nseqs;i++)
tmat[i] = (double *)ckalloc( (mult_aln.nseqs+1) * sizeof (double) );
meanscore=0;
for (i=0,n=0;i<mult_aln.nseqs;i++) {
for (j=i+1;j<mult_aln.nseqs;j++) {
dscore = countid(mult_aln.seqs[i],mult_aln.seqs[j]);
tmat[j][i] = tmat[i][j] = (100.0 - dscore)/100.0;
n++;
meanscore+=dscore;
}
}
meanscore/=(float)n;
/*if(mult_aln.nseqs<100) block_cutoff=8;
else if(mult_aln.nseqs<250) block_cutoff=6;
else*/ block_cutoff=5;
if(meanscore>50) block_cutoff=50;
/* make a tree from the percent identities (used for sequence weighting) */
strcpy(treefile,infile);
strcat(treefile,".ph");
if((tree = open_explicit_file(treefile))==NULL) exit(1);
guide_tree(tree,mult_aln.seqs,mult_aln.nseqs, tmat, QUICKNJ);
itree=(IN_TREEPTR)ckalloc(sizeof(IN_TREE));
status = read_tree(treefile, mult_aln.seqs, 0, mult_aln.nseqs,itree);
for(i=0;i<mult_aln.nseqs;i++)
ckfree(tmat[i]);
ckfree(tmat);
if (status < 0) exit(1);
seq_weight = calc_seq_weights(0,mult_aln.nseqs,itree,FALSE);
free_tree(itree);
remove(treefile);
/* find the start and end positions of each sequence */
is = (sint *)ckalloc((mult_aln.nseqs+1) * sizeof(sint));
ie = (sint *)ckalloc((mult_aln.nseqs+1) * sizeof(sint));
for(s=0;s<mult_aln.nseqs;s++) {
is[s]=0;
ie[s] = mult_aln.seqs[s].len;
for (i=0; i<mult_aln.seqs[s].len; i++) {
c = mult_aln.seqs[s].data[i];
if (!isalpha(c))
is[s]++;
else
break;
}
for (i=mult_aln.seqs[s].len-1; i>=0; i--) {
c = mult_aln.seqs[s].data[i];
if (!isalpha(c))
ie[s]--;
else
break;
}
}
matrix.format=0;
maxres = get_cl_matrix(FALSE, gon250mt, gapptr, TRUE, 100, &matrix);
all_blocks(infile,window,block_cutoff);
}
void scolon_proc(t_node *tree, int fd_in, int fd_out)
{
read_tree(tree->left, fd_in, fd_out);
read_tree(tree->right, fd_in, fd_out);
}
int main(int argc,char **argv)
{
unsigned int outstrlen=0;
int i,j,k,n;
unsigned int offset,wdim=1,alldim;
unsigned int has_future,*future,**useries,h;
unsigned long count;
long *segment;
char *outstring,*infile,*wcol,*use_array;
double **series,*sermin,*serinter,**dfuture;
ptree *root;
FILE *fout;
if (scan_help(argc,argv))
show_options(argv[0]);
for (i=0;i<argc;i++) {
outstrlen += strlen(argv[i]);
outstrlen++;
}
check_alloc(outstring=(char*)malloc(sizeof(char)*(outstrlen+8)));
sprintf(outstring,"#Prog: ");
offset=7;
for (i=0;i<argc;i++) {
sprintf(outstring+offset,"%s ",argv[i]);
offset += (strlen(argv[i])+1);
}
scan_options(argc,argv);
if (!compdimset)
compdim=pars.DIM;
else
if (compdim > pars.DIM) {
fprintf(stderr,"-C value larger -m Value.\n");
exit(LANGEVIN_MAIN_C_TOO_LARGE);
}
infile=search_datafile(argc,argv,NULL,VERBOSITY);
if (infile == NULL) {
fprintf(stderr,"No input datafile found.\n");
exit(LANGEVIN_MAIN_NO_INPUTFILE);
}
if (OUTFILE == NULL) {
check_alloc(OUTFILE=(char*)calloc(strlen(infile)+5,(size_t)1));
sprintf(OUTFILE,"%s.pru",infile);
}
OUTFILE=test_outfile(OUTFILE);
if (COLUMN == NULL)
series=(double**)get_multi_series(infile,&(pars.LENGTH),EXCLUDE,
&(pars.DIM),"",dimset,VERBOSITY);
else
series=(double**)get_multi_series(infile,&(pars.LENGTH),EXCLUDE,
&(pars.DIM),COLUMN,dimset,VERBOSITY);
check_alloc(sermin=malloc(sizeof(double)*pars.DIM));
check_alloc(serinter=malloc(sizeof(double)*pars.DIM));
rescale_data(series,pars,sermin,serinter);
alldim=pars.DIM;
pars.DIM=compdim;
check_alloc(useries=(unsigned int**)malloc(sizeof(int*)*pars.DIM));
check_alloc(PART=(unsigned int*)malloc(sizeof(int)*pars.DIM));
if (SPART == NULL)
for (i=0;i<pars.DIM;i++)
PART[i]=2;
else
set_part(PART,SPART,pars);
for (i=0;i<pars.DIM;i++) {
check_alloc(useries[i]=(unsigned int*)malloc(sizeof(int)*pars.LENGTH));
for (j=0;j<pars.LENGTH;j++) {
h=(unsigned int)((series[i][j]*(double)PART[i])/serinter[i]);
useries[i][j]=((h<PART[i])?h:(PART[i]-1));
}
}
check_alloc(future=(unsigned int*)malloc(sizeof(int)*pars.LENGTH));
if (WHICHFUTURE>0) {
check_alloc(wcol=(char*)calloc((size_t)10,(size_t)1));
sprintf(wcol,"%u",WHICHFUTURE);
dfuture=(double**)get_multi_series(infile,&(pars.LENGTH),EXCLUDE,
&wdim,wcol,1,0L);
for (i=0;i<pars.LENGTH-1;i++) {
future[i] = (dfuture[0][i]>0.0);
}
future[pars.LENGTH-1]=1;
free(dfuture);
}
else {
for (i=0;i<pars.LENGTH;i++)
future[i]=1;
}
root=make_ptree(PART[0]);
count=0;
check_alloc(segment=(long*)malloc(sizeof(long)*pars.LENGTH));
for (i=0;i<pars.LENGTH;i += ODEPTH) {
has_future=1;
for (j=0;j<ODEPTH;j++)
has_future &= future[i+j];
if (has_future) {
fill_tree(root,useries,pars,i,0,DEPTH,PART);
}
segment[count++]=i;
}
if (scrambleset)
lscramble(segment,count);
check_alloc(use_array=(char*)malloc(sizeof(char)*pars.LENGTH));
for (i=0;i<count;i++) {
n=segment[i];
has_future=1;
for (j=0;j<ODEPTH;j++)
has_future &= future[n+j];
if (has_future) {
h=read_tree(root,useries,pars,n,0,DEPTH);
if (h <= MAXOUT)
use_array[i]=1;
else
use_array[i]=0;
}
else
use_array[i]=2;
}
pars.DIM=alldim;
fout=fopen(OUTFILE,"w");
fprintf(fout,"%s\n",outstring);
fprintf(fout,"#Content: ");
for (i=0;i<pars.DIM;i++)
fprintf(fout,"x%d ",i+1);
fprintf(fout,"future time_index\n");
fflush(fout);
for (i=0;i<count;i++) {
n=segment[i];
if (use_array[i] == 1) {
for (j=0;j<(ODEPTH-1);j++) {
for (k=0;k<pars.DIM;k++)
fprintf(fout,"%f ",series[k][n+j]+sermin[k]);
fprintf(fout,"1 %u\n",n+j);
}
for (k=0;k<pars.DIM;k++)
fprintf(fout,"%f ",series[k][n+ODEPTH-1]+sermin[k]);
if (i<(count-1)) {
if (segment[i+1] == (n+ODEPTH) && use_array[i+1])
fprintf(fout,"1 %u\n",n+ODEPTH-1);
else
fprintf(fout,"0 %u\n",n+ODEPTH-1);
}
else
fprintf(fout,"0 %u\n",n+ODEPTH-1);
}
}
fclose(fout);
}
void run(std::string tree_filename, std::string fasta_filename, std::string model_name) {
Model Mod; // The model
Counts data; // the counts
Parameters Par; // the parameters
std::vector<double> br; // branch lengths
double eps = 1e-8; // The threshold for the EM algorithm.
Parameters Parsim; // used for simulating data.
std::vector<double> brsim; // branch lengths of simulated data.
std::vector<std::vector<double> > Cov; // Covariance matrix
std::vector<double> variances; // The variances
bool simulate;
bool nonident;
std::string parameters_filename;
std::string covariances_filename;
// initialize random number generator with time(0).
random_initialize();
parameters_filename = strip_extension(fasta_filename) + ".dat";
covariances_filename = strip_extension(fasta_filename) + ".cov";
// Creates the pointers to the model-specific functions.
Mod = create_model(model_name);
std::cout << "Model: " << Mod.name << std::endl;
// Reads the tree.
Tree T = read_tree(tree_filename);
// Prints the Tree
std::cout << "Tree:" << std::endl;
print_tree(T);
// Check for possible nonidentifiability issues.
nonident = nonident_warning(T);
// Initialize the parameters for simulation of K81 data for testing
Parsim = create_parameters(T);
if (fasta_filename == ":test") { // if fasta file is :test generate random data.
simulate = true;
// Warn
std::cout << "WARNING: Using simulated data " << std::endl << std::endl;
// Generate random parameters
random_parameters_length(T, Mod, Parsim);
// Simulate the data
data = random_fake_counts(T, 1000, Parsim);
// Prints branch-lengths for future check.
branch_lengths(Parsim, brsim);
std::cout << "Simulated branch lengths:" << std::endl;
print_vector(brsim);
} else { // otherwise read the data
simulate = false;
// Read the counts.
std::cout << "Reading fasta file:" << std::endl;
read_counts(T, data, fasta_filename);
add_pseudocounts(0.01, data);
std::cout << std::endl;
}
// Check whether the data and the tree match.
if (T.nalpha != data.nalpha || T.nleaves != data.nspecies) {
throw std::invalid_argument("The order of the sequences or their number and the phylogenetic tree do not match.");
}
//Par = create_parameters(T);
//print_parameters(Par);
//print_vector(Par.r);
//clock_t
long start_time, end_time;
// Runs the EM algorithm. Par is used as initial parameters.
// After execution, Par contains the MLE computed by the algorithm.
// for local max over multiple iterations
Parameters Parmax = Par;
Model Modmax = Mod;
float likelL = 0.0;
float likelMax = -1000000.0;
float timerec;
float timemax;
int outfiles; //whether to save output
std::cout << "Starting the EM algorithm: " << std::endl;
int s;
int S = 0; //count of cases with neg branches
int iter;
int iterMax;
for (int it_runs = 0; it_runs < 10; it_runs++) {
Par = create_parameters(T);
Mod = create_model(model_name);
std::cout << it_runs << ", " ;
start_time = clock();
std::tie(likelL, iter) = EMalgorithm(T, Mod, Par, data, eps);
end_time = clock();
//print_parameters(Par);
// Choses the best permutation.
guess_permutation(T, Mod, Par);
branch_lengths(Par, br);
//print_vector(br);
s = find_negative(br);
S +=s;
timerec = ((float)end_time - start_time) / CLOCKS_PER_SEC;
//assign the 1st iter time value, inc ase it's the best
if (it_runs == 0){
timemax = timerec;
iterMax = iter;
}
if (likelL > likelMax){
Parmax = Par;
Modmax = Mod;
timemax = timerec;
likelMax = likelL;
iterMax = iter;
}
}
// If parameters are not identifiable, the computation of the covariance matrix will
// fail as the Fisher info matrix will not be invertible.
if (!nonident) {
// Compute the covariance matrix using observed Fisher.
full_MLE_observed_covariance_matrix(T, Modmax, Parmax, data, Cov);
variances.resize(Cov.size());
for(unsigned int i=0; i < Cov.size(); i++) {
variances[i] = Cov[i][i];
}
// OUTPUT Save the sigmas into a file
//save_sigmas_to(covariances_filename, Cov);
}
std::cout << std::endl;
std::cout << "Finished." << std::endl;
std::cout << "Likelihood: " << log_likelihood(T, Parmax, data) << std::endl ;
std::cout << "Time: " << timemax << std::endl << std::endl;
std::cout << "negative branches: " << S << std::endl;
std::cout << "Iter: " << iterMax << std::endl;
//std::cout << "Branch lengths: " << std::endl;
//print_vector(br);
outfiles = 0;
if (!nonident && outfiles) {
std::cout << "Parameter variances: " << std::endl;
print_vector(variances);
}
std::cout << "Newick Tree:" << std::endl;
print_newick_tree(T, br);
// if is a simulation, print the L2 distance !
if (simulate) {
std::cout << "L2 distance: " << parameters_distance(Par, Parsim) << std::endl;
std::cout << "KL divergence: " << KL_divergence(T, Par, Parsim) << std::endl;
std::cout << std::endl;
}
// if it is not a simulation, store the parameters in a file !
if (!simulate && outfiles) {
std::fstream st;
st.precision(15);
st.setf(std::ios::fixed,std::ios::floatfield);
st.open(parameters_filename.c_str(), std::ios::out);
print_parameters(Par, st);
}
}
