int main(int argc, char *argv[]) {
HashTable ht = newHashTable(65535);
HashTable_put(ht, "1", "two");
HashTable_put(ht, "2", "three");
HashTable_put(ht, "3", "five");
HashTable_put(ht, "4", "seven");
HashTable_put(ht, "5", "eleven");
HashTable_put(ht, "6", "thirteen");
HashTable_put(ht, "7", "seventeen");
HashTable_remove(ht, "1");
HashTable_remove(ht, "2");
HashTable_remove(ht, "6");
HashTable_remove(ht, "7");
HashTable_put(ht, "3", "not allowed");
printf("%s\n", HashTable_get(ht, "1"));
printf("%s\n", HashTable_get(ht, "2"));
printf("%s\n", HashTable_get(ht, "3"));
printf("%s\n", HashTable_get(ht, "4"));
printf("%s\n", HashTable_get(ht, "5"));
printf("%s\n", HashTable_get(ht, "6"));
printf("%s\n", HashTable_get(ht, "7"));
printf("size: %d\n", HashTable_size(ht));
freeHashTable(&ht);
return 0;
}
int main(int argc, char **argv)
{
int i;
struct Hashtable hash_table;
//Allocate memory for a new hash table
newHashTable(&hash_table, HASHTABLE_LENGTH);
printf("New hash table containing no values\n");
//Print the hash table containing no values
for(i=0;i<HASHTABLE_LENGTH;i++){
print_ll(&(hash_table.table[i]));
}
putchar('\n');
//Insert several values into the hash table
insert(&hash_table, "Hello World");
insert(&hash_table, "Hello World");
insert(&hash_table, "Hel World");
insert(&hash_table, "GoodBye");
insert(&hash_table, "GoodBye");
insert(&hash_table, "wangbang");
insert(&hash_table, "Holachola");
insert(&hash_table, "antidis");
printf("Test values inserted printing full hash_table...\n");
//Print the list again
for(i=0;i<HASHTABLE_LENGTH;i++){
print_ll(&(hash_table.table[i]));
}
//Deallocate memory
freeHashTable(&hash_table);
}
void
freeThreadLabelTable(void)
{
if (threadLabels != NULL) {
freeHashTable(threadLabels, stgFree);
threadLabels = NULL;
}
}
void exitStaticPtrTable() {
if (spt) {
freeHashTable(spt, freeSptEntry);
spt = NULL;
#ifdef THREADED_RTS
closeMutex(&spt_lock);
#endif
}
}
void freeStringHashTable(HashTable *t) {
int i;
for (i = 0; i < t->cap; i++) {
LinkedList *l = t->a[i];
while (l) {
tlFree(l->key);
l = l->next;
}
}
freeHashTable(t);
}
void
freeThreadLabelTable(void)
{
ACQUIRE_LOCK(&threadLabels_mutex);
if (threadLabels != NULL) {
freeHashTable(threadLabels, stgFree);
threadLabels = NULL;
}
RELEASE_LOCK(&threadLabels_mutex);
}
void
exitStablePtrTable(void)
{
if (addrToStableHash)
freeHashTable(addrToStableHash, NULL);
addrToStableHash = NULL;
if (stable_ptr_table)
stgFree(stable_ptr_table);
stable_ptr_table = NULL;
SPT_size = 0;
#ifdef THREADED_RTS
closeMutex(&stable_mutex);
#endif
}
int main() {
int capacity = 11, i;
HashTablePtr t = newHashTable(capacity, hashInt, compare);
HashNodePtr node;
putIntoHashTable(t, 1, 1);
putIntoHashTable(t, 2, 2);
putIntoHashTable(t, 3, 3);
putIntoHashTable(t, 4, 4);
putIntoHashTable(t, 5, 5);
printHashTable(t);
for(i = 0; i <= 5; i++) {
HashNodePtr node = getFromHashTable(t, i);
if(node) {
printf("key %d values %d\n", node->key, node->value);
} else {
printf("cann't find key %d\n", i);
}
}
for(i = 11; i <= 16; i++) {
HashNodePtr node = getFromHashTable(t, i);
if(node) {
printf("key %d values %d\n", node->key, node->value);
} else {
printf("cann't find key %d\n", i);
}
}
removeFromHashTable(t, 2);
removeFromHashTable(t, 3);
printHashTable(t);
putIntoHashTable(t, 2, 2);
putIntoHashTable(t, 13, 13);
putIntoHashTable(t, 24, 24);
printHashTable(t);
removeFromHashTable(t, 2);
printHashTable(t);
node = getFromHashTable(t, 13);
printf("key %d values %d\n", node->key, node->value);
node = getFromHashTable(t, 24);
printf("key %d values %d\n", node->key, node->value);
putIntoHashTable(t, 35, 35);
printHashTable(t);
freeHashTable(t);
return 0;
}
void
rehash(HashTable* h)
{
if (h->outOfMemory==0) {
HashTable* h2 = newHashTable(h->size+h->incrementSize);
HashElement *e,*l;
unsigned long sz,hash,i=0;
if (h2==NULL) {
h->outOfMemory=1;
} else {
sz=h2->size;
// make increment of new table same as old
h2->incrementSize=h->incrementSize;
while (i<h->size) {
l = h->hashArray[i]; // get list from old hash table
h->hashArray[i]=NULL;
while (l!=NULL) { // process every entry from old list
e = l; // process first list element
l = l->next; // get the tail of the list
// hash value for entry to be processed
hash = ((unsigned long) e->value) % sz;
e->next = h2->hashArray[hash]; // append entries to new list
h2->hashArray[hash]=e; // set list in new hash table
}
i++;
}
// swap old and new hash table (to keep pointers to old table valid!)
l=(HashElement*) h->hashArray;
// move new hashArray to old hashTable
h->hashArray = h2->hashArray;
// set temporary hashTable to old hashArray
h2->hashArray= (HashElement**)l;
h2->size = h->size; // set temporary hashTable size to old size
h->size = sz; // set hash table size to new size
h->rehashAt = h->size-(h->size/10); // set new rehash size: 90%
// get rid of temporary table, now holding old hashArray
freeHashTable(h2);
}
}
}
//initialize hash table
void initHashTable(HT hashTable, char *dictName, int (*hashFun)(ElemType *word, int size)) {
FILE *fr;
fr = fopen(dictName, "rt");
if (fr == NULL) {
printf("Can't open file\n");
return;
}
Node *table;
int tableSize = TSIZE;
int i;
char word[keySize];
int r;
while (1) {
table = (Node *)malloc(tableSize * sizeof(Node));
hashTable->theList = table;
for(i = tableSize - 1; i >= 0; i--){
hashTable->theList[i].key = malloc(keySize * sizeof(ElemType));
hashTable->theList[i].key[0] = '\0';
//initialize key element?
hashTable->theList[i].next = NULL;
}
while((r = readAWord(fr, word)) != 0) {
tableInsert(hashTable, word, hashFun);
if ((float)(hashTable->nonEmpBucket) / (float)(hashTable->tableSize) > 0.75) {
freeHashTable(hashTable);
tableSize *= 2;
hashTable->tableSize = tableSize;
hashTable->numEntry = 0;
hashTable->nonEmpBucket = 0;
hashTable->maxListLeng = 0;
hashTable->avgListLeng = 0;
break;
}
}
if (r == 0) {
break;
}
}
}
/* Called at the end of execution, to write out the Hpc *.tix file
* for this exection. Safe to call, even if coverage is not used.
*/
void
exitHpc(void) {
debugTrace(DEBUG_hpc,"exitHpc");
if (hpc_inited == 0) {
return;
}
// Only write the tix file if you are the original process.
// Any sub-process from use of fork from inside Haskell will
// not clober the .tix file.
if (hpc_pid == getpid()) {
FILE *f = fopen(tixFilename,"w");
writeTix(f);
}
freeHashTable(moduleHash, (void (*)(void *))freeHpcModuleInfo);
moduleHash = NULL;
stgFree(tixFilename);
tixFilename = NULL;
}
void
updateStablePtrTable(rtsBool full)
{
snEntry *p, *end_stable_ptr_table;
if (full && addrToStableHash != NULL) {
freeHashTable(addrToStableHash,NULL);
addrToStableHash = allocHashTable();
}
end_stable_ptr_table = &stable_ptr_table[SPT_size];
// NOTE: _starting_ at index 1; index 0 is unused.
for (p = stable_ptr_table + 1; p < end_stable_ptr_table; p++) {
if (p->addr == NULL) {
if (p->old != NULL) {
// The target has been garbage collected. Remove its
// entry from the hash table.
removeHashTable(addrToStableHash, (W_)p->old, NULL);
p->old = NULL;
}
}
else if (p->addr < (P_)stable_ptr_table
|| p->addr >= (P_)end_stable_ptr_table) {
// Target still alive, Re-hash this stable name
if (full) {
insertHashTable(addrToStableHash, (W_)p->addr,
(void *)(p - stable_ptr_table));
} else if (p->addr != p->old) {
removeHashTable(addrToStableHash, (W_)p->old, NULL);
insertHashTable(addrToStableHash, (W_)p->addr,
(void *)(p - stable_ptr_table));
}
}
}
}
void plausibilityChecker(tree *tr, analdef *adef)
{
FILE
*treeFile,
*rfFile;
tree
*smallTree = (tree *)rax_malloc(sizeof(tree));
char
rfFileName[1024];
/* init hash table for big reference tree */
hashtable
*h = initHashTable(tr->mxtips * 2 * 2);
/* init the bit vectors we need for computing and storing bipartitions during
the tree traversal */
unsigned int
vLength,
**bitVectors = initBitVector(tr, &vLength);
int
numberOfTreesAnalyzed = 0,
branchCounter = 0,
i;
double
avgRF = 0.0;
/* set up an output file name */
strcpy(rfFileName, workdir);
strcat(rfFileName, "RAxML_RF-Distances.");
strcat(rfFileName, run_id);
rfFile = myfopen(rfFileName, "wb");
assert(adef->mode == PLAUSIBILITY_CHECKER);
/* open the big reference tree file and parse it */
treeFile = myfopen(tree_file, "r");
printBothOpen("Parsing reference tree %s\n", tree_file);
treeReadLen(treeFile, tr, FALSE, TRUE, TRUE, adef, TRUE, FALSE);
assert(tr->mxtips == tr->ntips);
printBothOpen("The reference tree has %d tips\n", tr->ntips);
fclose(treeFile);
/* extract all induced bipartitions from the big tree and store them in the hastable */
bitVectorInitravSpecial(bitVectors, tr->nodep[1]->back, tr->mxtips, vLength, h, 0, BIPARTITIONS_RF, (branchInfo *)NULL,
&branchCounter, 1, FALSE, FALSE);
assert(branchCounter == tr->mxtips - 3);
/* now see how many small trees we have */
treeFile = getNumberOfTrees(tr, bootStrapFile, adef);
checkTreeNumber(tr->numberOfTrees, bootStrapFile);
/* allocate a data structure for parsing the potentially mult-furcating tree */
allocateMultifurcations(tr, smallTree);
/* loop over all small trees */
for(i = 0; i < tr->numberOfTrees; i++)
{
int
numberOfSplits = readMultifurcatingTree(treeFile, smallTree, adef, TRUE);
if(numberOfSplits > 0)
{
unsigned int
entryCount = 0,
k,
j,
*masked = (unsigned int *)rax_calloc(vLength, sizeof(unsigned int)),
*smallTreeMask = (unsigned int *)rax_calloc(vLength, sizeof(unsigned int));
hashtable
*rehash = initHashTable(tr->mxtips * 2 * 2);
double
rf,
maxRF;
int
bCounter = 0,
bips,
firstTaxon,
taxa = 0;
if(numberOfTreesAnalyzed % 100 == 0)
printBothOpen("Small tree %d has %d tips and %d bipartitions\n", i, smallTree->ntips, numberOfSplits);
/* compute the maximum RF distance for computing the relative RF distance later-on */
/* note that here we need to pay attention, since the RF distance is not normalized
by 2 * (n-3) but we need to account for the fact that the multifurcating small tree
will potentially contain less bipartitions.
Hence the normalization factor is obtained as 2 * numberOfSplits, where numberOfSplits is the number of bipartitions
in the small tree.
*/
maxRF = (double)(2 * numberOfSplits);
/* now set up a bit mask where only the bits are set to one for those
taxa that are actually present in the small tree we just read */
/* note that I had to apply some small changes to this function to make it work for
multi-furcating trees ! */
setupMask(smallTreeMask, smallTree->start, smallTree->mxtips);
setupMask(smallTreeMask, smallTree->start->back, smallTree->mxtips);
/* now get the index of the first taxon of the small tree.
we will use this to unambiguously store the bipartitions
*/
firstTaxon = smallTree->start->number;
/* make sure that this bit vector is set up correctly, i.e., that
it contains as many non-zero bits as there are taxa in this small tree
*/
for(j = 0; j < vLength; j++)
taxa += BIT_COUNT(smallTreeMask[j]);
assert(taxa == smallTree->ntips);
/* now re-hash the big tree by applying the above bit mask */
/* loop over hash table */
for(k = 0, entryCount = 0; k < h->tableSize; k++)
{
if(h->table[k] != NULL)
{
entry *e = h->table[k];
/* we resolve collisions by chaining, hence the loop here */
do
{
unsigned int
*bitVector = e->bitVector;
hashNumberType
position;
int
count = 0;
/* double check that our tree mask contains the first taxon of the small tree */
assert(smallTreeMask[(firstTaxon - 1) / MASK_LENGTH] & mask32[(firstTaxon - 1) % MASK_LENGTH]);
/* if the first taxon is set then we will re-hash the bit-wise complement of the
bit vector.
The count variable is used for a small optimization */
if(bitVector[(firstTaxon - 1) / MASK_LENGTH] & mask32[(firstTaxon - 1) % MASK_LENGTH])
{
//hash complement
for(j = 0; j < vLength; j++)
{
masked[j] = (~bitVector[j]) & smallTreeMask[j];
count += BIT_COUNT(masked[j]);
}
}
else
{
//hash this vector
for(j = 0; j < vLength; j++)
{
masked[j] = bitVector[j] & smallTreeMask[j];
count += BIT_COUNT(masked[j]);
}
}
/* note that padding the last bits is not required because they are set to 0 automatically by smallTreeMask */
/* make sure that we will re-hash the canonic representation of the bipartition
where the bit for firstTaxon is set to 0!
*/
assert(!(masked[(firstTaxon - 1) / MASK_LENGTH] & mask32[(firstTaxon - 1) % MASK_LENGTH]));
/* only if the masked bipartition of the large tree is a non-trivial bipartition (two or more bits set to 1
will we re-hash it */
if(count > 1)
{
/* compute hash */
position = oat_hash((unsigned char *)masked, sizeof(unsigned int) * vLength);
position = position % rehash->tableSize;
/* re-hash to the new hash table that contains the bips of the large tree, pruned down
to the taxa contained in the small tree
*/
insertHashPlausibility(masked, rehash, vLength, position);
}
entryCount++;
e = e->next;
}
while(e != NULL);
}
}
/* make sure that we tried to re-hash all bipartitions of the original tree */
assert(entryCount == (unsigned int)(tr->mxtips - 3));
/* now traverse the small tree and count how many bipartitions it shares
with the corresponding induced tree from the large tree */
/* the following function also had to be modified to account for multi-furcating trees ! */
bips = bitVectorTraversePlausibility(bitVectors, smallTree->start->back, smallTree->mxtips, vLength, rehash, &bCounter, firstTaxon, smallTree, TRUE);
/* compute the relative RF */
rf = (double)(2 * (numberOfSplits - bips)) / maxRF;
assert(numberOfSplits >= bips);
assert(rf <= 1.0);
avgRF += rf;
if(numberOfTreesAnalyzed % 100 == 0)
printBothOpen("Relative RF tree %d: %f\n\n", i, rf);
fprintf(rfFile, "%d %f\n", i, rf);
/* I also modified this assertion, we nee to make sure here that we checked all non-trivial splits/bipartitions
in the multi-furcating tree whech can be less than n - 3 ! */
assert(bCounter == numberOfSplits);
/* free masks and hast table for this iteration */
rax_free(smallTreeMask);
rax_free(masked);
freeHashTable(rehash);
rax_free(rehash);
numberOfTreesAnalyzed++;
}
}
printBothOpen("Number of small trees skipped: %d\n\n", tr->numberOfTrees - numberOfTreesAnalyzed);
printBothOpen("Average RF distance %f\n\n", avgRF / (double)numberOfTreesAnalyzed);
printBothOpen("Total execution time: %f secs\n\n", gettime() - masterTime);
printBothOpen("\nFile containing all %d pair-wise RF distances written to file %s\n\n", numberOfTreesAnalyzed, rfFileName);
fclose(treeFile);
fclose(rfFile);
/* free the data structure used for parsing the potentially multi-furcating tree */
freeMultifurcations(smallTree);
rax_free(smallTree);
freeBitVectors(bitVectors, 2 * tr->mxtips);
rax_free(bitVectors);
freeHashTable(h);
rax_free(h);
}
//
// Check whether we can unload any object code. This is called at the
// appropriate point during a GC, where all the heap data is nice and
// packed together and we have a linked list of the static objects.
//
// The check involves a complete heap traversal, but you only pay for
// this (a) when you have called unloadObj(), and (b) at a major GC,
// which is much more expensive than the traversal we're doing here.
//
void checkUnload (StgClosure *static_objects)
{
nat g, n;
HashTable *addrs;
StgClosure* p;
const StgInfoTable *info;
ObjectCode *oc, *prev, *next;
gen_workspace *ws;
StgClosure* link;
if (unloaded_objects == NULL) return;
ACQUIRE_LOCK(&linker_unloaded_mutex);
// Mark every unloadable object as unreferenced initially
for (oc = unloaded_objects; oc; oc = oc->next) {
IF_DEBUG(linker, debugBelch("Checking whether to unload %" PATH_FMT "\n",
oc->fileName));
oc->referenced = rtsFalse;
}
addrs = allocHashTable();
for (p = static_objects; p != END_OF_STATIC_OBJECT_LIST; p = link) {
p = UNTAG_STATIC_LIST_PTR(p);
checkAddress(addrs, p);
info = get_itbl(p);
link = *STATIC_LINK(info, p);
}
// CAFs on revertible_caf_list are not on static_objects
for (p = (StgClosure*)revertible_caf_list;
p != END_OF_CAF_LIST;
p = ((StgIndStatic *)p)->static_link) {
p = UNTAG_STATIC_LIST_PTR(p);
checkAddress(addrs, p);
}
for (g = 0; g < RtsFlags.GcFlags.generations; g++) {
searchHeapBlocks (addrs, generations[g].blocks);
searchHeapBlocks (addrs, generations[g].large_objects);
for (n = 0; n < n_capabilities; n++) {
ws = &gc_threads[n]->gens[g];
searchHeapBlocks(addrs, ws->todo_bd);
searchHeapBlocks(addrs, ws->part_list);
searchHeapBlocks(addrs, ws->scavd_list);
}
}
#ifdef PROFILING
/* Traverse the cost centre tree, calling checkAddress on each CCS/CC */
searchCostCentres(addrs, CCS_MAIN);
/* Also check each cost centre in the CC_LIST */
CostCentre *cc;
for (cc = CC_LIST; cc != NULL; cc = cc->link) {
checkAddress(addrs, cc);
}
#endif /* PROFILING */
// Look through the unloadable objects, and any object that is still
// marked as unreferenced can be physically unloaded, because we
// have no references to it.
prev = NULL;
for (oc = unloaded_objects; oc; oc = next) {
next = oc->next;
if (oc->referenced == 0) {
if (prev == NULL) {
unloaded_objects = oc->next;
} else {
prev->next = oc->next;
}
IF_DEBUG(linker, debugBelch("Unloading object file %" PATH_FMT "\n",
oc->fileName));
freeObjectCode(oc);
} else {
IF_DEBUG(linker, debugBelch("Object file still in use: %"
PATH_FMT "\n", oc->fileName));
prev = oc;
}
}
freeHashTable(addrs, NULL);
RELEASE_LOCK(&linker_unloaded_mutex);
}
void doAllInOne(tree *tr, analdef *adef)
{
int i, n, bestIndex, bootstrapsPerformed;
#ifdef _WAYNE_MPI
int
bootStopTests = 1,
j,
bootStrapsPerProcess = 0;
#endif
double loopTime;
int *originalRateCategories;
int *originalInvariant;
#ifdef _WAYNE_MPI
int slowSearches, fastEvery;
#else
int slowSearches, fastEvery = 5;
#endif
int treeVectorLength = -1;
topolRELL_LIST *rl;
double bestLH, mlTime, overallTime;
long radiusSeed = adef->rapidBoot;
FILE *f;
char bestTreeFileName[1024];
hashtable *h = (hashtable*)NULL;
unsigned int **bitVectors = (unsigned int**)NULL;
boolean bootStopIt = FALSE;
double pearsonAverage = 0.0;
pInfo *catParams = allocParams(tr);
pInfo *gammaParams = allocParams(tr);
unsigned int vLength;
n = adef->multipleRuns;
#ifdef _WAYNE_MPI
if(n % processes != 0)
n = processes * ((n / processes) + 1);
#endif
if(adef->bootStopping)
{
h = initHashTable(tr->mxtips * 100);
treeVectorLength = adef->multipleRuns;
bitVectors = initBitVector(tr, &vLength);
}
rl = (topolRELL_LIST *)rax_malloc(sizeof(topolRELL_LIST));
initTL(rl, tr, n);
originalRateCategories = (int*)rax_malloc(tr->cdta->endsite * sizeof(int));
originalInvariant = (int*)rax_malloc(tr->cdta->endsite * sizeof(int));
initModel(tr, tr->rdta, tr->cdta, adef);
if(adef->grouping)
printBothOpen("\n\nThe topologies of all Bootstrap and ML trees will adhere to the constraint tree specified in %s\n", tree_file);
if(adef->constraint)
printBothOpen("\n\nThe topologies of all Bootstrap and ML trees will adhere to the bifurcating backbone constraint tree specified in %s\n", tree_file);
#ifdef _WAYNE_MPI
long parsimonySeed0 = adef->parsimonySeed;
long replicateSeed0 = adef->rapidBoot;
n = n / processes;
#endif
for(i = 0; i < n && !bootStopIt; i++)
{
#ifdef _WAYNE_MPI
j = i + n * processID;
tr->treeID = j;
#else
tr->treeID = i;
#endif
tr->checkPointCounter = 0;
loopTime = gettime();
#ifdef _WAYNE_MPI
if(i == 0)
{
if(parsimonySeed0 != 0)
adef->parsimonySeed = parsimonySeed0 + 10000 * processID;
adef->rapidBoot = replicateSeed0 + 10000 * processID;
radiusSeed = adef->rapidBoot;
}
#endif
if(i % 10 == 0)
{
if(i > 0)
reductionCleanup(tr, originalRateCategories, originalInvariant);
if(adef->grouping || adef->constraint)
{
FILE *f = myfopen(tree_file, "rb");
assert(adef->restart);
if (! treeReadLenMULT(f, tr, adef))
exit(-1);
fclose(f);
}
else
makeParsimonyTree(tr, adef);
tr->likelihood = unlikely;
if(i == 0)
{
double t;
onlyInitrav(tr, tr->start);
treeEvaluate(tr, 1);
t = gettime();
modOpt(tr, adef, FALSE, 5.0);
#ifdef _WAYNE_MPI
printBothOpen("\nTime for BS model parameter optimization on Process %d: %f seconds\n", processID, gettime() - t);
#else
printBothOpen("\nTime for BS model parameter optimization %f\n", gettime() - t);
#endif
memcpy(originalRateCategories, tr->cdta->rateCategory, sizeof(int) * tr->cdta->endsite);
memcpy(originalInvariant, tr->invariant, sizeof(int) * tr->cdta->endsite);
if(adef->bootstrapBranchLengths)
{
if(tr->rateHetModel == CAT)
{
copyParams(tr->NumberOfModels, catParams, tr->partitionData, tr);
assert(tr->cdta->endsite == tr->originalCrunchedLength);
catToGamma(tr, adef);
modOpt(tr, adef, TRUE, adef->likelihoodEpsilon);
copyParams(tr->NumberOfModels, gammaParams, tr->partitionData, tr);
gammaToCat(tr);
copyParams(tr->NumberOfModels, tr->partitionData, catParams, tr);
}
else
{
assert(tr->cdta->endsite == tr->originalCrunchedLength);
}
}
}
}
computeNextReplicate(tr, &adef->rapidBoot, originalRateCategories, originalInvariant, TRUE, TRUE);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 1);
computeBOOTRAPID(tr, adef, &radiusSeed);
#ifdef _WAYNE_MPI
saveTL(rl, tr, j);
#else
saveTL(rl, tr, i);
#endif
if(adef->bootstrapBranchLengths)
{
double
lh = tr->likelihood;
if(tr->rateHetModel == CAT)
{
copyParams(tr->NumberOfModels, tr->partitionData, gammaParams, tr);
catToGamma(tr, adef);
resetBranches(tr);
onlyInitrav(tr, tr->start);
treeEvaluate(tr, 2.0);
gammaToCat(tr);
copyParams(tr->NumberOfModels, tr->partitionData, catParams, tr);
tr->likelihood = lh;
}
else
{
treeEvaluate(tr, 2.0);
tr->likelihood = lh;
}
}
printBootstrapResult(tr, adef, TRUE);
loopTime = gettime() - loopTime;
writeInfoFile(adef, tr, loopTime);
if(adef->bootStopping)
#ifdef _WAYNE_MPI
{
int
nn = (i + 1) * processes;
if((nn > START_BSTOP_TEST) &&
(i * processes < FC_SPACING * bootStopTests) &&
((i + 1) * processes >= FC_SPACING * bootStopTests)
)
{
MPI_Barrier(MPI_COMM_WORLD);
concatenateBSFiles(processes, bootstrapFileName);
MPI_Barrier(MPI_COMM_WORLD);
bootStopIt = computeBootStopMPI(tr, bootstrapFileName, adef, &pearsonAverage);
bootStopTests++;
}
}
#else
bootStopIt = bootStop(tr, h, i, &pearsonAverage, bitVectors, treeVectorLength, vLength, adef);
#endif
}
#ifdef _WAYNE_MPI
MPI_Barrier(MPI_COMM_WORLD);
bootstrapsPerformed = i * processes;
bootStrapsPerProcess = i;
concatenateBSFiles(processes, bootstrapFileName);
removeBSFiles(processes, bootstrapFileName);
MPI_Barrier(MPI_COMM_WORLD);
#else
bootstrapsPerformed = i;
#endif
rax_freeParams(tr->NumberOfModels, catParams);
rax_free(catParams);
rax_freeParams(tr->NumberOfModels, gammaParams);
rax_free(gammaParams);
if(adef->bootStopping)
{
freeBitVectors(bitVectors, 2 * tr->mxtips);
rax_free(bitVectors);
freeHashTable(h);
rax_free(h);
}
{
double t;
printBothOpenMPI("\n\n");
if(adef->bootStopping)
{
if(bootStopIt)
{
switch(tr->bootStopCriterion)
{
case FREQUENCY_STOP:
printBothOpenMPI("Stopped Rapid BS search after %d replicates with FC Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("Pearson Average of %d random splits: %f\n",BOOTSTOP_PERMUTATIONS , pearsonAverage);
break;
case MR_STOP:
printBothOpenMPI("Stopped Rapid BS search after %d replicates with MR-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_STOP:
printBothOpenMPI("Stopped Rapid BS search after %d replicates with MRE-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_IGN_STOP:
printBothOpenMPI("Stopped Rapid BS search after %d replicates with MRE_IGN-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
default:
assert(0);
}
}
else
{
switch(tr->bootStopCriterion)
{
case FREQUENCY_STOP:
printBothOpenMPI("Rapid BS search did not converge after %d replicates with FC Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("Pearson Average of %d random splits: %f\n",BOOTSTOP_PERMUTATIONS , pearsonAverage);
break;
case MR_STOP:
printBothOpenMPI("Rapid BS search did not converge after %d replicates with MR-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_STOP:
printBothOpenMPI("Rapid BS search did not converge after %d replicates with MRE-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_IGN_STOP:
printBothOpenMPI("Rapid BS search did not converge after %d replicates with MR_IGN-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
default:
assert(0);
}
}
}
t = gettime() - masterTime;
printBothOpenMPI("Overall Time for %d Rapid Bootstraps %f seconds\n", bootstrapsPerformed, t);
printBothOpenMPI("Average Time per Rapid Bootstrap %f seconds\n", (double)(t/((double)bootstrapsPerformed)));
if(!adef->allInOne)
{
printBothOpenMPI("All %d bootstrapped trees written to: %s\n", bootstrapsPerformed, bootstrapFileName);
#ifdef _WAYNE_MPI
MPI_Finalize();
#endif
exit(0);
}
}
/* ML-search */
mlTime = gettime();
double t = mlTime;
printBothOpenMPI("\nStarting ML Search ...\n\n");
/***CLEAN UP reduction stuff */
reductionCleanup(tr, originalRateCategories, originalInvariant);
/****/
#ifdef _WAYNE_MPI
restoreTL(rl, tr, n * processID);
#else
restoreTL(rl, tr, 0);
#endif
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, TRUE, adef->likelihoodEpsilon);
#ifdef _WAYNE_MPI
if(bootstrapsPerformed <= 100)
fastEvery = 5;
else
fastEvery = bootstrapsPerformed / 20;
for(i = 0; i < bootstrapsPerformed; i++)
rl->t[i]->likelihood = unlikely;
for(i = 0; i < bootStrapsPerProcess; i++)
{
j = i + n * processID;
if(i % fastEvery == 0)
{
restoreTL(rl, tr, j);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 1);
optimizeRAPID(tr, adef);
saveTL(rl, tr, j);
}
}
#else
for(i = 0; i < bootstrapsPerformed; i++)
{
rl->t[i]->likelihood = unlikely;
if(i % fastEvery == 0)
{
restoreTL(rl, tr, i);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 1);
optimizeRAPID(tr, adef);
saveTL(rl, tr, i);
}
}
#endif
printBothOpenMPI("Fast ML optimization finished\n\n");
t = gettime() - t;
#ifdef _WAYNE_MPI
printBothOpen("Fast ML search on Process %d: Time %f seconds\n\n", processID, t);
j = n * processID;
qsort(&(rl->t[j]), n, sizeof(topolRELL*), compareTopolRell);
restoreTL(rl, tr, j);
#else
printBothOpen("Fast ML search Time: %f seconds\n\n", t);
qsort(&(rl->t[0]), bootstrapsPerformed, sizeof(topolRELL*), compareTopolRell);
restoreTL(rl, tr, 0);
#endif
t = gettime();
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, TRUE, adef->likelihoodEpsilon);
slowSearches = bootstrapsPerformed / 5;
if(bootstrapsPerformed % 5 != 0)
slowSearches++;
slowSearches = MIN(slowSearches, 10);
#ifdef _WAYNE_MPI
if(processes > 1)
{
if(slowSearches % processes == 0)
slowSearches = slowSearches / processes;
else
slowSearches = (slowSearches / processes) + 1;
}
for(i = 0; i < slowSearches; i++)
{
j = i + n * processID;
restoreTL(rl, tr, j);
rl->t[j]->likelihood = unlikely;
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 1.0);
thoroughOptimization(tr, adef, rl, j);
}
#else
for(i = 0; i < slowSearches; i++)
{
restoreTL(rl, tr, i);
rl->t[i]->likelihood = unlikely;
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 1.0);
thoroughOptimization(tr, adef, rl, i);
}
#endif
/*************************************************************************************************************/
if(tr->rateHetModel == CAT)
{
catToGamma(tr, adef);
modOpt(tr, adef, TRUE, adef->likelihoodEpsilon);
}
bestIndex = -1;
bestLH = unlikely;
#ifdef _WAYNE_MPI
for(i = 0; i < slowSearches; i++)
{
j = i + n * processID;
restoreTL(rl, tr, j);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 2);
printBothOpen("Slow ML Search %d Likelihood: %f\n", j, tr->likelihood);
if(tr->likelihood > bestLH)
{
bestLH = tr->likelihood;
bestIndex = j;
}
}
/*printf("processID = %d, bestIndex = %d; bestLH = %f\n", processID, bestIndex, bestLH);*/
#else
for(i = 0; i < slowSearches; i++)
{
restoreTL(rl, tr, i);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 2);
printBothOpen("Slow ML Search %d Likelihood: %f\n", i, tr->likelihood);
if(tr->likelihood > bestLH)
{
bestLH = tr->likelihood;
bestIndex = i;
}
}
#endif
printBothOpenMPI("Slow ML optimization finished\n\n");
t = gettime() - t;
#ifdef _WAYNE_MPI
printBothOpen("Slow ML search on Process %d: Time %f seconds\n", processID, t);
#else
printBothOpen("Slow ML search Time: %f seconds\n", t);
#endif
t = gettime();
restoreTL(rl, tr, bestIndex);
resetBranches(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 2);
Thorough = 1;
tr->doCutoff = FALSE;
treeOptimizeThorough(tr, 1, 10);
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, TRUE, adef->likelihoodEpsilon);
t = gettime() - t;
#ifdef _WAYNE_MPI
printBothOpen("Thorough ML search on Process %d: Time %f seconds\n", processID, t);
#else
printBothOpen("Thorough ML search Time: %f seconds\n", t);
#endif
#ifdef _WAYNE_MPI
bestLH = tr->likelihood;
printf("\nprocessID = %d, bestLH = %f\n", processID, bestLH);
if(processes > 1)
{
double *buffer;
int bestProcess;
buffer = (double *)rax_malloc(sizeof(double) * processes);
for(i = 0; i < processes; i++)
buffer[i] = unlikely;
buffer[processID] = bestLH;
for(i = 0; i < processes; i++)
MPI_Bcast(&buffer[i], 1, MPI_DOUBLE, i, MPI_COMM_WORLD);
bestLH = buffer[0];
bestProcess = 0;
for(i = 1; i < processes; i++)
if(buffer[i] > bestLH)
{
bestLH = buffer[i];
bestProcess = i;
}
rax_free(buffer);
if(processID != bestProcess)
{
MPI_Finalize();
exit(0);
}
}
#endif
printBothOpen("\nFinal ML Optimization Likelihood: %f\n", tr->likelihood);
printBothOpen("\nModel Information:\n\n");
printModelParams(tr, adef);
strcpy(bestTreeFileName, workdir);
strcat(bestTreeFileName, "RAxML_bestTree.");
strcat(bestTreeFileName, run_id);
Tree2String(tr->tree_string, tr, tr->start->back, TRUE, TRUE, FALSE, FALSE, TRUE, adef, SUMMARIZE_LH, FALSE, FALSE, FALSE, FALSE);
f = myfopen(bestTreeFileName, "wb");
fprintf(f, "%s", tr->tree_string);
fclose(f);
if(adef->perGeneBranchLengths)
printTreePerGene(tr, adef, bestTreeFileName, "w");
overallTime = gettime() - masterTime;
mlTime = gettime() - mlTime;
printBothOpen("\nML search took %f secs or %f hours\n", mlTime, mlTime / 3600.0);
printBothOpen("\nCombined Bootstrap and ML search took %f secs or %f hours\n", overallTime, overallTime / 3600.0);
printBothOpen("\nDrawing Bootstrap Support Values on best-scoring ML tree ...\n\n");
freeTL(rl);
rax_free(rl);
calcBipartitions(tr, adef, bestTreeFileName, bootstrapFileName);
overallTime = gettime() - masterTime;
printBothOpen("Program execution info written to %s\n", infoFileName);
printBothOpen("All %d bootstrapped trees written to: %s\n\n", bootstrapsPerformed, bootstrapFileName);
printBothOpen("Best-scoring ML tree written to: %s\n\n", bestTreeFileName);
if(adef->perGeneBranchLengths && tr->NumberOfModels > 1)
printBothOpen("Per-Partition branch lengths of best-scoring ML tree written to %s.PARTITION.0 to %s.PARTITION.%d\n\n", bestTreeFileName, bestTreeFileName,
tr->NumberOfModels - 1);
printBothOpen("Best-scoring ML tree with support values written to: %s\n\n", bipartitionsFileName);
printBothOpen("Best-scoring ML tree with support values as branch labels written to: %s\n\n", bipartitionsFileNameBranchLabels);
printBothOpen("Overall execution time for full ML analysis: %f secs or %f hours or %f days\n\n", overallTime, overallTime/3600.0, overallTime/86400.0);
#ifdef _WAYNE_MPI
MPI_Finalize();
#endif
exit(0);
}
void doBootstrap(tree *tr, analdef *adef, rawdata *rdta, cruncheddata *cdta)
{
int
bootstrapsPerformed,
i,
n,
treeVectorLength = -1;
unsigned int
vLength = 0;
#ifdef _WAYNE_MPI
int
j,
bootStopTests = 1;
#endif
double loopTime, pearsonAverage;
hashtable *h = (hashtable*)NULL;
unsigned int **bitVectors = (unsigned int **)NULL;
boolean bootStopIt = FALSE;
n = adef->multipleRuns;
#ifdef _WAYNE_MPI
if(n % processes != 0)
n = processes * ((n / processes) + 1);
adef->multipleRuns = n;
#endif
if(adef->bootStopping)
{
h = initHashTable(tr->mxtips * 100);
bitVectors = initBitVector(tr, &vLength);
treeVectorLength = adef->multipleRuns;
}
#ifdef _WAYNE_MPI
long parsimonySeed0 = adef->parsimonySeed;
long replicateSeed0 = adef->rapidBoot;
long bootstrapSeed0 = adef->boot;
n = n / processes;
#endif
for(i = 0; i < n && !bootStopIt; i++)
{
loopTime = gettime();
#ifdef _WAYNE_MPI
if(i == 0)
{
if(parsimonySeed0 != 0)
adef->parsimonySeed = parsimonySeed0 + 10000 * processID;
adef->rapidBoot = replicateSeed0 + 10000 * processID;
adef->boot = bootstrapSeed0 + 10000 * processID;
}
j = i + n*processID;
singleBootstrap(tr, j, adef, rdta, cdta);
#else
singleBootstrap(tr, i, adef, rdta, cdta);
#endif
loopTime = gettime() - loopTime;
writeInfoFile(adef, tr, loopTime);
if(adef->bootStopping)
#ifdef _WAYNE_MPI
{
int
nn = (i + 1) * processes;
if((nn > START_BSTOP_TEST) &&
(i * processes < FC_SPACING * bootStopTests) &&
((i + 1) * processes >= FC_SPACING * bootStopTests)
)
{
MPI_Barrier(MPI_COMM_WORLD);
concatenateBSFiles(processes, bootstrapFileName);
MPI_Barrier(MPI_COMM_WORLD);
bootStopIt = computeBootStopMPI(tr, bootstrapFileName, adef, &pearsonAverage);
bootStopTests++;
}
}
#else
bootStopIt = bootStop(tr, h, i, &pearsonAverage, bitVectors, treeVectorLength, vLength, adef);
#endif
}
#ifdef _WAYNE_MPI
MPI_Barrier(MPI_COMM_WORLD);
bootstrapsPerformed = i * processes;
if(processID == 0)
{
if(!adef->bootStopping)
concatenateBSFiles(processes, bootstrapFileName);
removeBSFiles(processes, bootstrapFileName);
}
MPI_Barrier(MPI_COMM_WORLD);
#else
bootstrapsPerformed = i;
#endif
adef->multipleRuns = bootstrapsPerformed;
if(adef->bootStopping)
{
freeBitVectors(bitVectors, 2 * tr->mxtips);
rax_free(bitVectors);
freeHashTable(h);
rax_free(h);
if(bootStopIt)
{
switch(tr->bootStopCriterion)
{
case FREQUENCY_STOP:
printBothOpenMPI("Stopped Standard BS search after %d replicates with FC Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("Pearson Average of %d random splits: %f\n",BOOTSTOP_PERMUTATIONS , pearsonAverage);
break;
case MR_STOP:
printBothOpenMPI("Stopped Standard BS search after %d replicates with MR-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_STOP:
printBothOpenMPI("Stopped Standard BS search after %d replicates with MRE-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_IGN_STOP:
printBothOpenMPI("Stopped Standard BS search after %d replicates with MRE_IGN-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
default:
assert(0);
}
}
else
{
switch(tr->bootStopCriterion)
{
case FREQUENCY_STOP:
printBothOpenMPI("Standard BS search did not converge after %d replicates with FC Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("Pearson Average of %d random splits: %f\n",BOOTSTOP_PERMUTATIONS , pearsonAverage);
break;
case MR_STOP:
printBothOpenMPI("Standard BS search did not converge after %d replicates with MR-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_STOP:
printBothOpenMPI("Standard BS search did not converge after %d replicates with MRE-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
case MRE_IGN_STOP:
printBothOpenMPI("Standard BS search did not converge after %d replicates with MR_IGN-based Bootstopping criterion\n", bootstrapsPerformed);
printBothOpenMPI("WRF Average of %d random splits: %f\n", BOOTSTOP_PERMUTATIONS, pearsonAverage);
break;
default:
assert(0);
}
}
}
}
//
// Check whether we can unload any object code. This is called at the
// appropriate point during a GC, where all the heap data is nice and
// packed together and we have a linked list of the static objects.
//
// The check involves a complete heap traversal, but you only pay for
// this (a) when you have called unloadObj(), and (b) at a major GC,
// which is much more expensive than the traversal we're doing here.
//
void checkUnload (StgClosure *static_objects)
{
nat g, n;
HashTable *addrs;
StgClosure* p;
const StgInfoTable *info;
ObjectCode *oc, *prev, *next;
gen_workspace *ws;
StgClosure* link;
if (unloaded_objects == NULL) return;
// Mark every unloadable object as unreferenced initially
for (oc = unloaded_objects; oc; oc = oc->next) {
IF_DEBUG(linker, debugBelch("Checking whether to unload %" PATH_FMT "\n",
oc->fileName));
oc->referenced = rtsFalse;
}
addrs = allocHashTable();
for (p = static_objects; p != END_OF_STATIC_LIST; p = link) {
checkAddress(addrs, p);
info = get_itbl(p);
link = *STATIC_LINK(info, p);
}
for (g = 0; g < RtsFlags.GcFlags.generations; g++) {
searchHeapBlocks (addrs, generations[g].blocks);
searchHeapBlocks (addrs, generations[g].large_objects);
for (n = 0; n < n_capabilities; n++) {
ws = &gc_threads[n]->gens[g];
searchHeapBlocks(addrs, ws->todo_bd);
searchHeapBlocks(addrs, ws->part_list);
searchHeapBlocks(addrs, ws->scavd_list);
}
}
// Look through the unloadable objects, and any object that is still
// marked as unreferenced can be physically unloaded, because we
// have no references to it.
prev = NULL;
for (oc = unloaded_objects; oc; prev = oc, oc = next) {
next = oc->next;
if (oc->referenced == 0) {
if (prev == NULL) {
unloaded_objects = oc->next;
} else {
prev->next = oc->next;
}
IF_DEBUG(linker, debugBelch("Unloading object file %" PATH_FMT "\n",
oc->fileName));
freeObjectCode(oc);
} else {
IF_DEBUG(linker, debugBelch("Object file still in use: %"
PATH_FMT "\n", oc->fileName));
}
}
freeHashTable(addrs, NULL);
}
void cleanupIdMap() {
freeStringHashTable(idToIntMap);
freeHashTable(intToIdMap);
}
void computeBIGRAPID (tree *tr, analdef *adef, boolean estimateModel)
{
unsigned int
vLength = 0;
int
i,
impr,
bestTrav,
rearrangementsMax = 0,
rearrangementsMin = 0,
thoroughIterations = 0,
fastIterations = 0;
double lh, previousLh, difference, epsilon;
bestlist *bestT, *bt;
#ifdef _TERRACES
/* store the 20 best trees found in a dedicated list */
bestlist
*terrace;
/* output file names */
char
terraceFileName[1024],
buf[64];
#endif
hashtable *h = (hashtable*)NULL;
unsigned int **bitVectors = (unsigned int**)NULL;
if(tr->searchConvergenceCriterion)
{
bitVectors = initBitVector(tr, &vLength);
h = initHashTable(tr->mxtips * 4);
}
bestT = (bestlist *) rax_malloc(sizeof(bestlist));
bestT->ninit = 0;
initBestTree(bestT, 1, tr->mxtips);
bt = (bestlist *) rax_malloc(sizeof(bestlist));
bt->ninit = 0;
initBestTree(bt, 20, tr->mxtips);
#ifdef _TERRACES
/* initialize the tree list and the output file name for the current tree search/replicate */
terrace = (bestlist *) rax_malloc(sizeof(bestlist));
terrace->ninit = 0;
initBestTree(terrace, 20, tr->mxtips);
sprintf(buf, "%d", bCount);
strcpy(terraceFileName, workdir);
strcat(terraceFileName, "RAxML_terrace.");
strcat(terraceFileName, run_id);
strcat(terraceFileName, ".BS.");
strcat(terraceFileName, buf);
printf("%s\n", terraceFileName);
#endif
initInfoList(50);
difference = 10.0;
epsilon = 0.01;
Thorough = 0;
if(estimateModel)
{
if(adef->useBinaryModelFile)
{
readBinaryModel(tr);
evaluateGenericInitrav(tr, tr->start);
treeEvaluate(tr, 2);
}
else
{
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, FALSE, 10.0);
}
}
else
treeEvaluate(tr, 2);
printLog(tr, adef, FALSE);
saveBestTree(bestT, tr);
if(!adef->initialSet)
bestTrav = adef->bestTrav = determineRearrangementSetting(tr, adef, bestT, bt);
else
bestTrav = adef->bestTrav = adef->initial;
if(estimateModel)
{
if(adef->useBinaryModelFile)
treeEvaluate(tr, 2);
else
{
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, FALSE, 5.0);
}
}
else
treeEvaluate(tr, 1);
saveBestTree(bestT, tr);
impr = 1;
if(tr->doCutoff)
tr->itCount = 0;
while(impr)
{
recallBestTree(bestT, 1, tr);
if(tr->searchConvergenceCriterion)
{
int bCounter = 0;
if(fastIterations > 1)
cleanupHashTable(h, (fastIterations % 2));
bitVectorInitravSpecial(bitVectors, tr->nodep[1]->back, tr->mxtips, vLength, h, fastIterations % 2, BIPARTITIONS_RF, (branchInfo *)NULL,
&bCounter, 1, FALSE, FALSE);
assert(bCounter == tr->mxtips - 3);
if(fastIterations > 0)
{
double rrf = convergenceCriterion(h, tr->mxtips);
if(rrf <= 0.01) /* 1% cutoff */
{
printBothOpen("ML fast search converged at fast SPR cycle %d with stopping criterion\n", fastIterations);
printBothOpen("Relative Robinson-Foulds (RF) distance between respective best trees after one succseful SPR cycle: %f%s\n", rrf, "%");
cleanupHashTable(h, 0);
cleanupHashTable(h, 1);
goto cleanup_fast;
}
else
printBothOpen("ML search convergence criterion fast cycle %d->%d Relative Robinson-Foulds %f\n", fastIterations - 1, fastIterations, rrf);
}
}
fastIterations++;
treeEvaluate(tr, 1.0);
saveBestTree(bestT, tr);
printLog(tr, adef, FALSE);
printResult(tr, adef, FALSE);
lh = previousLh = tr->likelihood;
treeOptimizeRapid(tr, 1, bestTrav, adef, bt);
impr = 0;
for(i = 1; i <= bt->nvalid; i++)
{
recallBestTree(bt, i, tr);
treeEvaluate(tr, 0.25);
difference = ((tr->likelihood > previousLh)?
tr->likelihood - previousLh:
previousLh - tr->likelihood);
if(tr->likelihood > lh && difference > epsilon)
{
impr = 1;
lh = tr->likelihood;
saveBestTree(bestT, tr);
}
}
}
if(tr->searchConvergenceCriterion)
{
cleanupHashTable(h, 0);
cleanupHashTable(h, 1);
}
cleanup_fast:
Thorough = 1;
impr = 1;
recallBestTree(bestT, 1, tr);
if(estimateModel)
{
if(adef->useBinaryModelFile)
treeEvaluate(tr, 2);
else
{
evaluateGenericInitrav(tr, tr->start);
modOpt(tr, adef, FALSE, 1.0);
}
}
else
treeEvaluate(tr, 1.0);
while(1)
{
recallBestTree(bestT, 1, tr);
if(impr)
{
printResult(tr, adef, FALSE);
rearrangementsMin = 1;
rearrangementsMax = adef->stepwidth;
if(tr->searchConvergenceCriterion)
{
int bCounter = 0;
if(thoroughIterations > 1)
cleanupHashTable(h, (thoroughIterations % 2));
bitVectorInitravSpecial(bitVectors, tr->nodep[1]->back, tr->mxtips, vLength, h, thoroughIterations % 2, BIPARTITIONS_RF, (branchInfo *)NULL,
&bCounter, 1, FALSE, FALSE);
assert(bCounter == tr->mxtips - 3);
if(thoroughIterations > 0)
{
double rrf = convergenceCriterion(h, tr->mxtips);
if(rrf <= 0.01) /* 1% cutoff */
{
printBothOpen("ML search converged at thorough SPR cycle %d with stopping criterion\n", thoroughIterations);
printBothOpen("Relative Robinson-Foulds (RF) distance between respective best trees after one succseful SPR cycle: %f%s\n", rrf, "%");
goto cleanup;
}
else
printBothOpen("ML search convergence criterion thorough cycle %d->%d Relative Robinson-Foulds %f\n", thoroughIterations - 1, thoroughIterations, rrf);
}
}
thoroughIterations++;
}
else
{
rearrangementsMax += adef->stepwidth;
rearrangementsMin += adef->stepwidth;
if(rearrangementsMax > adef->max_rearrange)
goto cleanup;
}
treeEvaluate(tr, 1.0);
previousLh = lh = tr->likelihood;
saveBestTree(bestT, tr);
printLog(tr, adef, FALSE);
treeOptimizeRapid(tr, rearrangementsMin, rearrangementsMax, adef, bt);
impr = 0;
for(i = 1; i <= bt->nvalid; i++)
{
recallBestTree(bt, i, tr);
treeEvaluate(tr, 0.25);
#ifdef _TERRACES
/* save all 20 best trees in the terrace tree list */
saveBestTree(terrace, tr);
#endif
difference = ((tr->likelihood > previousLh)?
tr->likelihood - previousLh:
previousLh - tr->likelihood);
if(tr->likelihood > lh && difference > epsilon)
{
impr = 1;
lh = tr->likelihood;
saveBestTree(bestT, tr);
}
}
}
cleanup:
#ifdef _TERRACES
{
double
bestLH = tr->likelihood;
FILE
*f = myfopen(terraceFileName, "w");
/* print out likelihood of best tree found */
printf("best tree: %f\n", tr->likelihood);
/* print out likelihoods of 20 best trees found during the tree search */
for(i = 1; i <= terrace->nvalid; i++)
{
recallBestTree(terrace, i, tr);
/* if the likelihood scores are smaller than some epsilon 0.000001
print the tree to file */
if(ABS(bestLH - tr->likelihood) < 0.000001)
{
printf("%d %f\n", i, tr->likelihood);
Tree2String(tr->tree_string, tr, tr->start->back, FALSE, TRUE, FALSE, FALSE, FALSE, adef, NO_BRANCHES, FALSE, FALSE, FALSE, FALSE);
fprintf(f, "%s\n", tr->tree_string);
}
}
fclose(f);
/* increment tree search counter */
bCount++;
}
#endif
if(tr->searchConvergenceCriterion)
{
freeBitVectors(bitVectors, 2 * tr->mxtips);
rax_free(bitVectors);
freeHashTable(h);
rax_free(h);
}
freeBestTree(bestT);
rax_free(bestT);
freeBestTree(bt);
rax_free(bt);
#ifdef _TERRACES
/* free terrace tree list */
freeBestTree(terrace);
rax_free(terrace);
#endif
freeInfoList();
printLog(tr, adef, FALSE);
printResult(tr, adef, FALSE);
}
void
freeFileLocking(void)
{
freeHashTable(obj_hash, freeLock);
freeHashTable(fd_hash, NULL);
}
/* ========================================================================== */
int main(int argc, char* argv[]) {
int filenum=1;
int initdepth=1;
// check command line arguments
if (argcheck(argc,argv) == 1){
exit(1);
}
char *starturl = argv[1];
char *targetdir = argv[2];
int depth = atoi(argv[3]);
//initialize our hashtables and url list
HashTable *myhashtable;
List *mylist;
myhashtable=initializeHashTable();
mylist=initializelist();
// init curl
curl_global_init(CURL_GLOBAL_ALL);
// setup seed page
WebPage *startpage = createWebPage(starturl,0);
// get seed webpage. If the url is invalid, quit and send an error message.
if ( GetWebPage(startpage) == 0 ){
printf("The url that you entered was invalid. Please try again.");
free(startpage->html);
free(startpage);
exit(1);
}
// write seed file
createfile(startpage,targetdir,filenum);
filenum++;
// add seed page to hashtable
insertHashTable(myhashtable,startpage->url);
// extract urls from seed page
if( depth > 0 ){
parseHTML(startpage,mylist,myhashtable,initdepth);
}
// while there are urls to crawl
while ( mylist->head != NULL ){
// get next url from list
WebPage *nextpage = listpop(mylist);
int currdepth = nextpage->depth;
// get webpage for url
// If the url is invalid, quit and free the memory
if (GetWebPage(nextpage) != 0 ){
createfile(nextpage,targetdir,filenum);
filenum++;
// extract urls from webpage
if ( currdepth < depth ){
parseHTML(nextpage, mylist, myhashtable, currdepth+1);
}
}
free(nextpage->html);
free(nextpage->url);
free(nextpage);
sleep(SLEEPTIME);
}
// cleanup curl
free(startpage->html);
free(startpage);
freeHashTable(myhashtable);
freelist(mylist);
curl_global_cleanup();
return 0;
}
void plausibilityChecker(tree *tr, analdef *adef)
{
FILE
*treeFile,
*rfFile;
tree
*smallTree = (tree *)rax_malloc(sizeof(tree));
char
rfFileName[1024];
int
numberOfTreesAnalyzed = 0,
i;
double
avgRF = 0.0,
sumEffectivetime = 0.0;
/* set up an output file name */
strcpy(rfFileName, workdir);
strcat(rfFileName, "RAxML_RF-Distances.");
strcat(rfFileName, run_id);
rfFile = myfopen(rfFileName, "wb");
assert(adef->mode == PLAUSIBILITY_CHECKER);
/* open the big reference tree file and parse it */
treeFile = myfopen(tree_file, "r");
printBothOpen("Parsing reference tree %s\n", tree_file);
treeReadLen(treeFile, tr, FALSE, TRUE, TRUE, adef, TRUE, FALSE);
assert(tr->mxtips == tr->ntips);
/*************************************************************************************/
/* Preprocessing Step */
double
preprocesstime = gettime();
/* taxonToLabel[2*tr->mxtips - 2];
Array storing all 2n-2 labels from the preordertraversal: (Taxonnumber - 1) -> (Preorderlabel) */
int
*taxonToLabel = (int *)rax_malloc((2*tr->mxtips - 2) * sizeof(int)),
/* taxonHasDeg[2*tr->mxtips - 2]
Array used to store the degree of every taxon, is needed to extract Bipartitions from multifurcating trees
(Taxonnumber - 1) -> (degree of node(Taxonnumber)) */
*taxonHasDeg = (int *)rax_calloc((2*tr->mxtips - 2),sizeof(int)),
/* taxonToReduction[2*tr->mxtips - 2];
Array used for reducing bitvector and speeding up extraction:
(Taxonnumber - 1) -> (0..1 (increment count of taxa appearing in small tree))
(Taxonnumber - 1) -> (0..1 (increment count of inner nodes appearing in small tree)) */
*taxonToReduction = (int *)rax_malloc((2*tr->mxtips - 2) * sizeof(int));
int
newcount = 0; //counter used for correct traversals
/* labelToTaxon[2*tr->mxtips - 2];
is used to translate between Perorderlabel and p->number: (Preorderlabel) -> (Taxonnumber) */
int
*labelToTaxon = (int *)rax_malloc((2*tr->mxtips - 2) * sizeof(int));
/* Preorder-Traversal of the large tree */
preOrderTraversal(tr->start->back,tr->mxtips, tr->start->number, taxonToLabel, labelToTaxon, &newcount);
newcount = 0; //counter set to 0 to be now used for Eulertraversal
/* eulerIndexToLabel[4*tr->mxtips - 5];
Array storing all 4n-5 PreOrderlabels created during eulertour: (Eulerindex) -> (Preorderlabel) */
int*
eulerIndexToLabel = (int *)rax_malloc((4*tr->mxtips - 5) * sizeof(int));
/* taxonToEulerIndex[tr->mxtips];
Stores all indices of the first appearance of a taxa in the eulerTour: (Taxonnumber - 1) -> (Index of the Eulertour where Taxonnumber first appears)
is used for efficient computation of the Lowest Common Ancestor during Reconstruction Step
*/
int*
taxonToEulerIndex = (int *)rax_malloc((tr->mxtips) * sizeof(int));
/* Init taxonToEulerIndex and taxonToReduction */
int
ix;
for(ix = 0; ix < tr->mxtips; ++ix)
taxonToEulerIndex[ix] = -1;
for(ix = 0; ix < (2*tr->mxtips - 2); ++ix)
taxonToReduction[ix] = -1;
/* Eulertraversal of the large tree*/
unrootedEulerTour(tr->start->back,tr->mxtips, eulerIndexToLabel, taxonToLabel, &newcount, taxonToEulerIndex);
/* Creating RMQ Datastructure for efficient retrieval of LCAs, using Johannes Fischers Library rewritten in C
Following Files: rmq.h,rmqs.c,rmqs.h are included in Makefile.RMQ.gcc */
RMQ_succinct(eulerIndexToLabel,4*tr->mxtips - 5);
double
preprocessendtime = gettime() - preprocesstime;
/* Proprocessing Step End */
/*************************************************************************************/
printBothOpen("The reference tree has %d tips\n", tr->ntips);
fclose(treeFile);
/* now see how many small trees we have */
treeFile = getNumberOfTrees(tr, bootStrapFile, adef);
checkTreeNumber(tr->numberOfTrees, bootStrapFile);
/* allocate a data structure for parsing the potentially mult-furcating tree */
allocateMultifurcations(tr, smallTree);
/* loop over all small trees */
for(i = 0; i < tr->numberOfTrees; i++)
{
int
numberOfSplits = readMultifurcatingTree(treeFile, smallTree, adef, TRUE);
if(numberOfSplits > 0)
{
int
firstTaxon;
double
rec_rf,
maxRF;
if(numberOfTreesAnalyzed % 100 == 0)
printBothOpen("Small tree %d has %d tips and %d bipartitions\n", i, smallTree->ntips, numberOfSplits);
/* compute the maximum RF distance for computing the relative RF distance later-on */
/* note that here we need to pay attention, since the RF distance is not normalized
by 2 * (n-3) but we need to account for the fact that the multifurcating small tree
will potentially contain less bipartitions.
Hence the normalization factor is obtained as n-3 + numberOfSplits, where n-3 is the number
of bipartitions of the pruned down large reference tree for which we know that it is
bifurcating/strictly binary */
maxRF = (double)(2 * numberOfSplits);
/* now get the index of the first taxon of the small tree.
we will use this to unambiguously store the bipartitions
*/
firstTaxon = smallTree->start->number;
/***********************************************************************************/
/* Reconstruction Step */
double
time_start = gettime();
/* Init hashtable to store Bipartitions of the induced subtree */
/*
using smallTree->ntips instead of smallTree->mxtips yields faster code
e.g. 120 versus 128 seconds for 20,000 small trees on my laptop
*/
hashtable
*s_hash = initHashTable(smallTree->ntips * 4);
/* smallTreeTaxa[smallTree->ntips];
Stores all taxa numbers from smallTree into an array called smallTreeTaxa: (Index) -> (Taxonnumber) */
int*
smallTreeTaxa = (int *)rax_malloc((smallTree->ntips) * sizeof(int));
/* counter is set to 0 for correctly extracting taxa of the small tree */
newcount = 0;
int
newcount2 = 0;
/* seq2[2*smallTree->ntips - 2];
stores PreorderSequence of the reference smalltree: (Preorderindex) -> (Taxonnumber) */
int*
seq2 = (int *)rax_malloc((2*smallTree->ntips - 2) * sizeof(int));
/* used to store the vectorLength of the bitvector */
unsigned int
vectorLength;
/* extract all taxa of the smalltree and store it into an array,
also store all counts of taxa and nontaxa in taxonToReduction */
rec_extractTaxa(smallTreeTaxa, taxonToReduction, smallTree->start, smallTree->mxtips, &newcount, &newcount2);
rec_extractTaxa(smallTreeTaxa, taxonToReduction, smallTree->start->back, smallTree->mxtips, &newcount, &newcount2);
/* counter is set to 0 to correctly preorder traverse the small tree */
newcount = 0;
/* Preordertraversal of the small tree and save its sequence into seq2 for later extracting the bipartitions, it
also stores information about the degree of every node */
rec_preOrderTraversalMulti(smallTree->start->back,smallTree->mxtips, smallTree->start->number, seq2, taxonHasDeg, &newcount);
/* calculate the bitvector length */
if(smallTree->ntips % MASK_LENGTH == 0)
vectorLength = smallTree->ntips / MASK_LENGTH;
else
vectorLength = 1 + (smallTree->ntips / MASK_LENGTH);
unsigned int
**bitVectors = rec_initBitVector(smallTree, vectorLength);
/* store all non trivial bitvectors using an subtree approach for the induced subtree and
store it into a hashtable, this method was changed for multifurcation */
rec_extractBipartitionsMulti(bitVectors, seq2, newcount,tr->mxtips, vectorLength, smallTree->ntips,
firstTaxon, s_hash, taxonToReduction, taxonHasDeg, numberOfSplits);
/* counter is set to 0 to be used for correctly storing all EulerIndices */
newcount = 0;
/* smallTreeTaxonToEulerIndex[smallTree->ntips];
Saves all first Euler indices for all Taxons appearing in small Tree:
(Index) -> (Index of the Eulertour where the taxonnumber of the small tree first appears) */
int*
smallTreeTaxonToEulerIndex = (int *)rax_malloc((smallTree->ntips) * sizeof(int));
/* seq[(smallTree->ntips*2) - 1]
Stores the Preordersequence of the induced small tree */
int*
seq = (int *)rax_malloc((2*smallTree->ntips - 1) * sizeof(int));
/* iterate through all small tree taxa */
for(ix = 0; ix < smallTree->ntips; ix++)
{
int
taxanumber = smallTreeTaxa[ix];
/* To create smallTreeTaxonToEulerIndex we filter taxonToEulerIndex for taxa in the small tree*/
smallTreeTaxonToEulerIndex[newcount] = taxonToEulerIndex[taxanumber-1];
/* Saves all Preorderlabel of the smalltree taxa in seq*/
seq[newcount] = taxonToLabel[taxanumber-1];
newcount++;
}
/* sort the euler indices to correctly calculate LCA */
//quicksort(smallTreeTaxonToEulerIndex,0,newcount - 1);
qsort(smallTreeTaxonToEulerIndex, newcount, sizeof(int), sortIntegers);
//printf("newcount2 %i \n", newcount2);
/* Iterate through all small tree taxa */
for(ix = 1; ix < newcount; ix++)
{
/* query LCAs using RMQ Datastructure */
seq[newcount - 1 + ix] = eulerIndexToLabel[query(smallTreeTaxonToEulerIndex[ix - 1],smallTreeTaxonToEulerIndex[ix])];
/* Used for dynamic programming. We save an index for every inner node:
For example the reference tree has 3 inner nodes which we saves them as 0,1,2.
Now we calculate for example 5 LCA to construct the induced subtree, which are also inner nodes.
Therefore we mark them as 3,4,5,6,7 */
taxonToReduction[labelToTaxon[seq[newcount - 1 + ix]] - 1] = newcount2;
newcount2 += 1;
}
/* sort to construct the Preordersequence of the induced subtree */
//quicksort(seq,0,(2*smallTree->ntips - 2));
qsort(seq, (2 * smallTree->ntips - 2) + 1, sizeof(int), sortIntegers);
/* calculates all bipartitions of the reference small tree and count how many bipartition it shares with the induced small tree */
int
rec_bips = rec_findBipartitions(bitVectors, seq,(2*smallTree->ntips - 1), labelToTaxon, tr->mxtips, vectorLength, smallTree->ntips, firstTaxon, s_hash, taxonToReduction);
/* Reconstruction Step End */
/***********************************************************************************/
double
effectivetime = gettime() - time_start;
/*
if(numberOfTreesAnalyzed % 100 == 0)
printBothOpen("Reconstruction time: %.10f secs\n\n", effectivetime);
*/
/* compute the relative RF */
rec_rf = (double)(2 * (numberOfSplits - rec_bips)) / maxRF;
assert(numberOfSplits >= rec_bips);
avgRF += rec_rf;
sumEffectivetime += effectivetime;
if(numberOfTreesAnalyzed % 100 == 0)
printBothOpen("Relative RF tree %d: %f\n\n", i, rec_rf);
fprintf(rfFile, "%d %f\n", i, rec_rf);
/* free masks and hast table for this iteration */
rec_freeBitVector(smallTree, bitVectors);
rax_free(bitVectors);
freeHashTable(s_hash);
rax_free(s_hash);
rax_free(smallTreeTaxa);
rax_free(seq);
rax_free(seq2);
rax_free(smallTreeTaxonToEulerIndex);
numberOfTreesAnalyzed++;
}
}
printBothOpen("Number of small trees skipped: %d\n\n", tr->numberOfTrees - numberOfTreesAnalyzed);
printBothOpen("Average RF distance %f\n\n", avgRF / (double)numberOfTreesAnalyzed);
printBothOpen("Large Tree: %i, Number of SmallTrees analyzed: %i \n\n", tr->mxtips, numberOfTreesAnalyzed);
printBothOpen("Total execution time: %f secs\n\n", gettime() - masterTime);
printBothOpen("File containing all %d pair-wise RF distances written to file %s\n\n", numberOfTreesAnalyzed, rfFileName);
printBothOpen("execution stats:\n\n");
printBothOpen("Accumulated time Effective algorithm: %.5f sec \n", sumEffectivetime);
printBothOpen("Average time for effective: %.10f sec \n",sumEffectivetime / (double)numberOfTreesAnalyzed);
printBothOpen("Preprocessingtime: %0.5f sec \n\n", preprocessendtime);
fclose(treeFile);
fclose(rfFile);
/* free the data structure used for parsing the potentially multi-furcating tree */
freeMultifurcations(smallTree);
rax_free(smallTree);
rax_free(taxonToLabel);
rax_free(taxonToEulerIndex);
rax_free(labelToTaxon);
rax_free(eulerIndexToLabel);
rax_free(taxonToReduction);
rax_free(taxonHasDeg);
}
