void fit_halo_profile(struct halo *HALO)
{
double c=0, r=0, rho0, rho0_halo, rs, chi, gof, per;
double *x, *y, *e, *R, *y_th, *x_bin, *y_bin, *e_bin, rMin, rMax;
int bins, skip, N, j=0;
r = HALO->Rvir;
c = HALO->c;
bins = HALO->n_bins;
skip = HALO->neg_r_bins;
N = bins - skip;
rho0 = HALO->rho0;
rs = HALO->r2;
x = (double*) calloc(N, sizeof(double));
y = (double*) calloc(N, sizeof(double));
e = (double*) calloc(N, sizeof(double));
R = (double*) calloc(N, sizeof(double));
for(j=0; j<N; j++)
{
x[j] = HALO->radius[j+skip];
y[j] = HALO->rho[j+skip];
e[j] = HALO->err[j+skip];
R[j] = HALO->radius[j+skip]/r;
}
best_fit_nfw(rho0, rs, N, x, y, e);
HALO->fit_nfw.rho0 = rho0;
HALO->fit_nfw.rs = rs;
HALO->fit_nfw.c = HALO->Rvir/rs;
y_th = (double*) calloc(bins-skip,sizeof(double));
for(j=skip; j<bins; j++)
{
y_th[j-skip] = nfw(HALO->radius[j], HALO->fit_nfw.rs, HALO->fit_nfw.rho0);
//fprintf(stderr, "%d) R=%e, %e %e %e\n", j, R[j-skip], rho0, y[j-skip], y_th[j-skip]);
}
// Various estimators for the goodness of fit
chi = chi_square(y_th, y, e, N);
gof = goodness_of_fit(y_th, y, N);
per = percentage_error(y_th, y, N);
chi /= (double) (bins-skip);
HALO->fit_nfw.chi = chi;
HALO->fit_nfw.gof = gof;
HALO->fit_nfw.per = per;
x_bin = (double*) calloc(BIN_PROFILE+1, sizeof(double));
y_bin = (double*) calloc(BIN_PROFILE, sizeof(double));
e_bin = (double*) calloc(BIN_PROFILE, sizeof(double));
rMin = 2 * Rvir_frac_min;
rMax = F_MAX * 1.01; //HALO->radius[bins-1]/r;
x_bin = log_stepper(rMin, rMax, BIN_PROFILE+1);
average_bin(R, y, x_bin, y_bin, e_bin, BIN_PROFILE+1, N);
for(j=0; j<BIN_PROFILE; j++)
{
HALO->nfw.x[j] = 0.5 * (x_bin[j] + x_bin[j+1]);
HALO->nfw.y[j] = y_bin[j];
//fprintf(stderr, "%d %e %e\n", j, x_bin[j+1], y_bin[j]);
}
free(x);
free(y);
free(R);
free(y_th);
free(e);
// fprintf(stderr, "ThisTask=%d, skip=%d, bins=%d, rho=%f, rs=%f, ChiSquare=%lf, Red=%lf\n",
// ThisTask, skip, bins, rho0, rs, chi_sq, chi_sq/(bins-skip));
}
static int goodness_of_fit_test(FREQ *f,int m,int n)
{
int i,j;
double a,x2;
if (n!=2)
{
sprintf(sbuf,"\nTable must have 2 columns (expected and observed) frquencies!");
sur_print(sbuf); WAIT; return(-1);
}
if (m<2)
{
sprintf(sbuf,"\nTable must have at least two rows!");
sur_print(sbuf); WAIT; return(-1);
}
e=(double *)muste_malloc(m*sizeof(double));
ecum=(double *)muste_malloc(m*sizeof(double));
o=(int *)muste_malloc(m*sizeof(int));
n2=0; for (i=0; i<m; ++i) { o[i]=f[i]; n2+=o[i]; }
n1=0; for (i=0; i<m; ++i) n1+=f[i+m];
a=(double)n2/(double)n1;
for (i=0; i<m; ++i) e[i]=a*f[i+m];
a=0.0; for (i=0; i<m; ++i) { a+=e[i]; ecum[i]=a; }
for (i=0; i<m; ++i) ecum[i]/=ecum[m-1];
g_print=&sur_print;
x2=chi_square(m);
// Rprintf("\nx2=%g n2=%d",x2,n2); getch();
maxcount=1000000L;
i=spfind("SIMUMAX");
if (i>=0) maxcount=atol(spb[i]);
i=rand_init(); if (i<0) return(-1);
conf_level=0.95;
i=spfind("CONF");
if (i>=0) conf_level=atof(spb[i]);
if (conf_level<0.8 || conf_level>=1.0)
{
sur_print("\nError in CONF=p! Confidence level p must be 0.8<p<1");
WAIT; return(-1);
}
conf_coeff=muste_inv_std(1.0-(1.0-conf_level)/2);
disp0fit(m,n,x2);
dn=10000L;
i=spfind("GAP");
if (i>=0) dn=atol(spb[i]);
count=0L; pcount=0L; dcount=0L; ecount=0L;
while (1)
{
++count; ++dcount;
for (i=0; i<m; ++i) o[i]=0;
for (j=0; j<n2; ++j)
{
a=(*rand1)();
i=0;
while (a>ecum[i]) ++i;
++o[i];
}
// Rprintf("\no: "); for (i=0; i<m; ++i) Rprintf("%d ",o[i]);
// a=chi_square(m); Rprintf("\na=%g",a);
if (chi_square(m)>=x2) ++pcount;
if (dcount>=dn)
{
tab_disp();
if (count>=maxcount) break;
if (sur_kbhit()) { sur_getch(); break; }
WAIT;
dcount=0;
}
}
// Rprintf("\np=%g",(double)pcount/(double)count); getch();
g_print=&print_line;
output_open(eout);
disp0fit(m,n,x2);
tab_disp();
output_close(eout);
return(1);
}
void split(tree *t, char *Inname,char *Outname)
{
FILE *Infile, *NextInfile1, *NextInfile2, *Outfile;
char *S, *T ,*Copy;
int *B;
int i, j, k, N, N1, N2, maxi, tempnofile ;
int String_Len;
char Outname1[20], Outname2[20];
double max, Sum;
fpos_t pos;
Infile = fopen (Inname, "r");
if (Infile == NULL)
{
fprintf (stderr, "ERROR: Unable to open file %s\n", Inname);
exit (EXIT_FAILURE);
}
String_Len = 1 + Stop_Position - Start_Position;
/* initialize frequencies for consensus */
for(i=0;i<String_Len;i++)
for(j=0;j<4;j++)
V[i][j]=0;
T = (char *) malloc((MAX_STRING_LEN+1)*sizeof(char));
MemCheck(T,"T");
S = (char *) malloc((MAX_STRING_LEN+1)*sizeof(char));
MemCheck(S,"S");
N = 0;
while (fgets (T, MAX_STRING_LEN, Infile) != NULL)
{
sscanf (T, "%*s %s", S);
assert (strlen (S) == NUM_POSITIONS);
strncpy (T, S + Start_Position, String_Len);
T [String_Len] = '\0';
N++;
B = basetoint(T,String_Len);
/* compute frequencies for each position */
for(i=0;i<String_Len;i++)
V[i][B[i]]++;
free(B);
}
t->no=N;
/* compute consensus */
for(i=0;i<String_Len;i++)
{
max=0;
for(j=0;j<4;j++)
if(V[i][j]>max)
{
C[i]=j;
max=V[i][j];
}
}
/*compute match between consensus and variable at position j */
for(i=0;i<String_Len;i++)
for(j=0;j<String_Len;j++)
for(k=0;k<4;k++)
M[i][j][k]=0;
/*pos=0;
fsetpos(Infile,&pos);*/
rewind(Infile);
while (fgets (T, MAX_STRING_LEN, Infile) != NULL)
{
sscanf (T, "%*s %s", S);
assert (strlen (S) == NUM_POSITIONS);
strncpy (T, S + Start_Position, String_Len);
T [String_Len] = '\0';
B = basetoint(T,String_Len);
for(i=0;i<String_Len;i++)
if(C[i]==B[i])
for(j=0;j<String_Len;j++)
M[i][j][B[j]]++;
free(B);
}
/* for each position compute the chi_square and where to do the partition */
max=0;
maxi=-1;
for(i=0;i<String_Len;i++)
if(W[i])
{
Sum=0;
W[i]=0;
for(j=0;j<String_Len;j++)
{
/*printf("i=%d,j=%d,Ci=%d,Vj0=%d,Vj1=%d,Vj2=%d,Vj3=%d,Mij0=%d,Mij1=%d,Mij2=%d,Mij3=%d\n",i,j,C[i],V[j][0],V[j][1],V[j][2],V[j][3],M[i][j][0],M[i][j][1],M[i][j][2],M[i][j][3]);
fflush(stdout);*/
if(W[j])
Sum+=chi_square(i,j);
}
W[i]=1;
if(Sum>max)
{
max=Sum;
maxi=i;
}
}
printf("Consens %d pe poz %d\n",C[maxi],maxi);
/* open output files */
sprintf(Outname1,"%s%d",Outname,Nofile + 1);
sprintf(Outname2,"%s%d",Outname,Nofile + 2);
NextInfile1 = fopen (Outname1, "w");
if (NextInfile1 == NULL)
{
fprintf (stderr, "ERROR: Unable to open file %s\n", Outname1);
exit (EXIT_FAILURE);
}
NextInfile2 = fopen (Outname2, "w");
if (NextInfile2 == NULL)
{
fprintf (stderr, "ERROR: Unable to open file %s\n", Outname2);
exit (EXIT_FAILURE);
}
Copy = (char *) malloc((MAX_STRING_LEN+1)*sizeof(char));
MemCheck(Copy,"Copy");
N1=0;
N2=0;
/* split into 2 leaves if necessary */
/*pos=0;
fsetpos(Infile,&pos);*/
rewind(Infile);
while (fgets (T, MAX_STRING_LEN, Infile) != NULL)
{
strcpy(Copy,T);
sscanf (T, "%*s %s", S);
assert (strlen (S) == NUM_POSITIONS);
strncpy (T, S + Start_Position, String_Len);
T [String_Len] = '\0';
B = basetoint(T,String_Len);
if(B[maxi] == C[maxi])
{
N1++;
fprintf(NextInfile1,"%s",Copy);
}
else
{
N2++;
fprintf(NextInfile2,"%s",Copy);
}
}
free(S);
free(T);
free(Copy);
fclose(NextInfile1);
fclose(NextInfile2);
printf("Frunze de %d si %d componente\n",N1,N2);
tempnofile=Nofile;
Nofile+=2;
//if(N1+N2>224)
//if(N1+N2>1000)
if(N1>400 && N2>400)
{ t->consens=C[maxi];
t->poz=maxi;
t->left = (tree *) malloc(sizeof(tree));
if (t->left == NULL) {fprintf(stderr,"%s: Memory allocation for tree failure.\n"); abort();}
(t->left)->val=tempnofile+1;
(t->left)->consens=-1;
(t->left)->poz=-1;
(t->left)->no=N1;
(t->left)->left=NULL;
(t->left)->right=NULL;
if(N1>350)
{
W[maxi]=0;
split(t->left,Outname1,Outname);
}
W[maxi]=1;
t->right = (tree *) malloc(sizeof(tree));
if (t->right == NULL) {fprintf(stderr,"%s: Memory allocation for tree failure.\n"); abort();}
(t->right)->val=tempnofile+2;
(t->right)->consens=-1;
(t->right)->poz=-1;
(t->right)->no=N2;
(t->right)->left=NULL;
(t->right)->right=NULL;
if(N2>350) split(t->right,Outname2,Outname);
}
fclose(Infile);
}
void postprocessing()
{
long int i,num;
int j,k,l,s,isNew;
double eva,p_value;
int* loci;
loci=new int[iEpiModel];
vector<double> record;
record.resize(iEpiModel+2);
cout<<"Post-processing"<<endl;
cout<<"Dealing with top ranking SNP sets"<<endl;
num=comb_num(iLociModel,iEpiModel);
cout<<"Number of interatcions evaluated: "<<num*iTopModel<<endl;
int** combination;
combination=new int*[num];
for(i=0;i<num;i++)
combination[i]=new int[iEpiModel];
combination=throughout(iLociModel,iEpiModel,combination);
for(i=iTopModel-1;i>=0;i--)
{
for(j=0;j<num;j++)
{
for(k=0;k<iEpiModel;k++)
{
loci[k]=loci_TopModel[i][combination[j][k]];
}
eva=chi_square(loci,iEpiModel);
p_value=1-gsl_cdf_chisq_P(eva,pow(3,iEpiModel)-1);
if(p_value<pvalue)
{
isNew=1;
for(l=0;l<interactions.size();l++)
{
if(fabs(eva-interactions[l][iEpiModel])<0.00000001)
{
isNew=0;
break;
}
}
if(isNew)
{
for(s=0;s<iEpiModel;s++)
{
record[s]=(double)loci[s];
}
record[iEpiModel]=eva;
record[iEpiModel+1]=p_value;
interactions.push_back(record);
}
}
}
}
for(i=0;i<num;i++)
delete []combination[i];
delete []combination;
cout<<"Dealing with top ranking loci"<<endl;
num=comb_num(iTopLoci,iEpiModel);
//cout<<"hello"<<endl;
int** combination1;
combination1=new int*[num];
for(i=0;i<num;i++)
combination1[i]=new int[iEpiModel];
combination1=throughout(iTopLoci,iEpiModel,combination1);
cout<<"Number of interactions evaluated: "<<num<<endl;
for(i=0;i<num;i++)
{
for(j=0;j<iEpiModel;j++)
{
loci[j]=loci_TopLoci[combination1[i][j]];
//cout<<loci[j]<<" ";
}
//cout<<endl;
eva=chi_square(loci,iEpiModel);
p_value=1-gsl_cdf_chisq_P(eva,pow(3,iEpiModel)-1);
if(p_value<pvalue)
{
isNew=1;
for(l=0;l<interactions.size();l++)
{
if(fabs(eva-interactions[l][iEpiModel])<0.00000001)
{
isNew=0;
break;
}
}
if(isNew)
{
for(s=0;s<iEpiModel;s++)
{
record[s]=(double)loci[s];
}
record[iEpiModel]=eva;
record[iEpiModel+1]=p_value;
interactions.push_back(record);
}
}
}
for(i=0;i<num;i++)
delete []combination1[i];
delete []combination1;
}
void project::UpdatePheromone()
{
int i,j,k,tag;
for(i=0;i<iLociCount;i++)
SNPdata.pheromone[i]=SNPdata.pheromone[i]*(1-rou);
double eva;
int* locidata;
locidata=new int[iLociModel];
for(i=0;i<iAntCount;i++)
{
for(j=1;j<=iLociModel;j++)
{
locidata[j-1]=ants[i].tabu[j];
}
eva=chi_square(locidata,iLociModel)/100;
for(j=0;j<iLociModel;j++)
{
SNPdata.pheromone[locidata[j]]+=eva;
}
if(eva>eva_TopModel[0])
{
tag=1;
for(j=0;j<iTopModel;j++)
{
if(fabs(eva-eva_TopModel[j])<0.000001)
{
tag=0;
break;
}
}
if(tag)
{
eva_TopModel[0]=eva_TopModel[1];
for(j=0;j<iLociModel;j++)
loci_TopModel[0][j]=loci_TopModel[1][j];
k=1;
while(k<iTopModel && eva>eva_TopModel[k])
{
eva_TopModel[k-1]=eva_TopModel[k];
for(j=0;j<iLociModel;j++)
loci_TopModel[k-1][j]=loci_TopModel[k][j];
k++;
}
eva_TopModel[k-1]=eva;
for(j=0;j<iLociModel;j++)
loci_TopModel[k-1][j]=locidata[j];
}
}
}
//#################update cdf##################
double * prob;
double temp=0;
prob=new double[iLociCount];
for(i=0;i<iLociCount;i++)
{
temp+=pow(SNPdata.pheromone[i],alpha);
prob[i]=temp;
}
for(i=0;i<iLociCount-1;i++)
{
SNPdata.cdf[i+1]=prob[i]/temp;
}
delete [] prob;
delete [] locidata;
}
int main(int argc, char* argv[]){
if (argc != 1){
fprintf( stderr, "Usage: %s\n", argv[0]);
exit(EXIT_FAILURE);
}
int i;
/* data directory */
char data_dir[256];
snprintf(data_dir, 256, "../data/");
/* load the pointing list */
char plist_filename[256];
snprintf(plist_filename, 256, "%stodo_list.ascii.dat", data_dir);
int N_plist;
POINTING *plist;
load_pointing_list(plist_filename, &N_plist, &plist);
/* Read star data for each pointing */
for(i = 0; i < N_plist; i++){
char data_filename[256];
snprintf(data_filename, 256, "%sstar_%s.ascii.dat", data_dir, plist[i].ID);
load_data(data_filename, &plist[i].N_data, &plist[i].data);
}
fprintf(stderr, "Star data loaded from %s\n", data_dir);
/* Read model data for each pointing,
here each file starts with uniformly distributed random */
for(i = 0; i < N_plist; i++){
char model_filename[256];
snprintf(model_filename, 256, "%suniform_%s.ascii.dat", data_dir, plist[i].ID);
load_data(model_filename, &plist[i].N_model, &plist[i].model);
}
fprintf(stderr, "Uniform model data loaded from %s\n", data_dir);
/* initialize model parameters */
PARAMETERS params;
params.N_parameters = 5; /* Total number of free paramters. */
params.thindisk_type = 1; /* turn on thin disk */
params.thindisk_r0 = 2.475508;
params.thindisk_z0 = 0.241209;
params.thindisk_n0 = 1.0;
params.thickdisk_type = 1; /* turn on thick disk */
params.thickdisk_r0 = 2.417346;
params.thickdisk_z0 = 0.694395;
params.thickdisk_n0 = 0.106672;
params.halo_type = 0; /* turn off halo */
fprintf(stderr, "Set initial parameters..\n");
int mcmc_steps, efficiency_counter;
double efficiency;
MCMC *mcmc_chain;
double chi2, delta_chi2;
int dof;
mcmc_steps = 500000;
mcmc_chain = calloc(mcmc_steps, sizeof(MCMC));
FILE *file_chain_realtime;
file_chain_realtime = fopen("./data/mcmc.dat", "a");
fprintf(stderr, "Allocate MCMC chain..Max steps = %d \n", mcmc_steps);
/* set the first element as the initial parameters.
Then calculate the chi2 for the initial parameters. */
mcmc_chain[0].params = params;
set_weights(mcmc_chain[0].params, plist, N_plist);
/* allocate space for correlation function calculation */
/* This also does a first time correlation calculation of initial parameters. */
/* DD pairs may only calculated once here but not later. */
correlation_initialize(plist, N_plist);
/* load the jackknife fractional errors */
load_errors(plist, N_plist);
mcmc_chain[0].dof = degrees_of_freedom(plist, N_plist, params);
mcmc_chain[0].chi2 = chi_square(plist, N_plist);
fprintf(stderr, "initial: chi2 = %le \n", mcmc_chain[0].chi2);
fprintf(stderr, "Start MCMC calculation..\n");
/* Markov chain loop */
efficiency_counter = 1;
for(i = 1; i < mcmc_steps; i++){
/* update new positions in paramter space */
params = update_parameters(mcmc_chain[i - 1].params);
/* recalculate weights */
set_weights(params, plist, N_plist);
/* recalculate correlation functions */
calculate_correlation(plist, N_plist);
/* get chi squares */
dof = degrees_of_freedom(plist, N_plist, params);
chi2 = chi_square(plist, N_plist);
delta_chi2 = chi2 - mcmc_chain[i - 1].chi2;
fprintf(stderr, "delta_chi2 = %le \n", delta_chi2);
if(delta_chi2 <= 0.0){
/* if delta chisquare is smaller then record*/
mcmc_chain[i].params = params;
mcmc_chain[i].chi2 = chi2;
mcmc_chain[i].dof = dof;
efficiency_counter++;
}
else{
/* if delta chisquare is bigger then use probability to decide */
/* !!! replace with GSL random generator later !!! */
double tmp = (double)rand() / (double)RAND_MAX; /* a random number in [0,1] */
if (tmp < exp(- delta_chi2 / 2.0)){
mcmc_chain[i].params = params;
mcmc_chain[i].chi2 = chi2;
mcmc_chain[i].dof = dof;
efficiency_counter++;
}
else{
/* record the old position. */
mcmc_chain[i] = mcmc_chain[i - 1];
}
}
efficiency = (float) efficiency_counter / i;
/* print out progress */
/* if(i % (mcmc_steps / 100) == 0){ */
/* fprintf(stderr, "MCMC... %d / %d: chi2 = %lf \n", i, mcmc_steps, chi2); */
/* } */
fprintf(stderr, "MCMC... %d / %d: efficiency = %lf \n z0_thin = %lf, r0_thin = %lf, z0_thick = %lf, r0_thick = %lf, n0_thick = %lf \n chi2 = %lf, dof = %d, chi2_reduced = %lf \n\n",
i, mcmc_steps, efficiency, params.thindisk_z0, params.thindisk_r0, params.thickdisk_z0, params.thickdisk_r0, params.thickdisk_n0, chi2, dof, chi2/dof);
MCMC tmp_mc;
PARAMETERS tmp_p;
tmp_mc = mcmc_chain[i];
tmp_p = tmp_mc.params;
// fprintf(stderr, "Made it here\n");
// fprintf(file_chain_realtime, "%d\t%lf\t%lf\t%lf\t%lf\t%lf\t%lf\t%d\t%lf\n",
// i+50000, tmp_p.thindisk_r0, tmp_p.thindisk_z0, tmp_p.thickdisk_r0, tmp_p.thickdisk_z0, tmp_p.thickdisk_n0,
// tmp_mc.chi2, (int)tmp_mc.dof, tmp_mc.chi2/dof);
// fprintf(stderr, "Printed to file.\n");
// if(i % 50 == 0){
// fflush(file_chain_realtime);
// }
} /* end of mcmc */
output_mcmc(mcmc_chain, mcmc_steps);
fprintf(stderr, "End MCMC calculation..\n");
for(i = 0; i < N_plist; i++){
free(plist[i].data);
free(plist[i].model);
free(plist[i].corr);
}
free(plist);
free(mcmc_chain);
return EXIT_SUCCESS;
}
