void handle_tf
( mclx* mx
, mcxTing* sa
)
{ mclgTF* transform = mclgTFparse(NULL, sa)
; if (!transform)
mcxErr(me, "tf spec does not parse")
; else
mclgTFexec(mx, transform)
; mclgTFfree(&transform)
; }
static void vary_threshold
( mcxIO* xf
, FILE* fp
, int vary_a
, int vary_z
, int vary_s
, int vary_n
, unsigned mode
)
{ dim cor_i = 0, j
; int step
; mclx* mx
; unsigned long noe
; pval* allvals
; dim n_allvals = 0
; double sum_vals = 0.0
; mx = mclxRead(xf, EXIT_ON_FAIL)
; mcxIOclose(xf)
; if (transform)
mclgTFexec(mx, transform)
; noe = mclxNrofEntries(mx)
; allvals = mcxAlloc(noe * sizeof allvals[0], EXIT_ON_FAIL)
; if (!weight_scale)
{ if (mode == 'c')
weight_scale = 1.0
; else
weight_scale = vary_n
; }
n_allvals = get_n_sort_allvals(mx, allvals, noe, &sum_vals, FALSE)
; if (mode == 'c')
{ double smallest = n_allvals ? allvals[n_allvals-1] : -DBL_MAX
; if (vary_a * 1.0 / vary_n < smallest)
{ while (vary_a * 1.0 / vary_n < smallest)
vary_a++
; vary_a--
; }
mcxTell
( me
, "smallest correlation is %.2f, using starting point %.2f"
, smallest
, vary_a * 1.0 / vary_n
)
; }
if (output_flags & OUTPUT_TABLE)
{
;fprintf(fp, "L\tD\tR\tS\tcce\tEWmean\tEWmed\tEWiqr\tNDmean\tNDmed\tNDiqr\tCCF\t%s\n", mode == 'k' ? "kNN" : mode == 'l' ? "N" : "Cutoff")
;} else
{ if (output_flags & OUTPUT_KEY)
{
;fprintf(fp, "-------------------------------------------------------------------------------\n")
;fprintf(fp, " L Percentage of nodes in the largest component\n")
;fprintf(fp, " D Percentage of nodes in components of size at most %d [-div option]\n", (int) divide_g)
;fprintf(fp, " R Percentage of nodes not in L or D: 100 - L -D\n")
;fprintf(fp, " S Percentage of nodes that are singletons\n")
;fprintf(fp, " cce Expected size of component, nodewise [ sum(sz^2) / sum^2(sz) ]\n")
;fprintf(fp, "*EW Edge weight traits (mean, median and IQR, all scaled!)\n")
;fprintf(fp, " Scaling is used to avoid printing of fractional parts throughout.\n")
;fprintf(fp, " The scaling factor is %.2f [-report-scale option]\n", weight_scale)
;fprintf(fp, " ND Node degree traits [mean, median and IQR]\n")
;fprintf(fp, " CCF Clustering coefficient %s\n", compute_flags & COMPUTE_CLCF ? "(not computed; use --clcf to include this)" : "")
;fprintf(fp, " eff Induced component efficiency %s\n", compute_flags & COMPUTE_EFF ? "(not computed; use --eff to include this)" : "")
;if (mode == 'c')
fprintf(fp, "Cutoff The threshold used.\n")
;else if (mode == 't')
fprintf(fp, "*Cutoff The threshold with scale factor %.2f and fractional parts removed\n", weight_scale)
;else if (mode == 'k')
fprintf(fp, "k-NN The knn parameter\n")
;else if (mode == 'l')
fprintf(fp, "N The knn parameter (merge mode)\n")
;else if (mode == 'n')
fprintf(fp, "ceil The ceil parameter\n")
;fprintf(fp, "Total number of nodes: %lu\n", (ulong) N_COLS(mx))
;}
fprintf(fp, "-------------------------------------------------------------------------------\n")
;fprintf(fp, " L D R S cce *EWmean *EWmed *EWiqr NDmean NDmed NDiqr CCF eff %6s \n", mode == 'k' ? "k-NN" : mode == 'l' ? "N" : mode == 'n' ? "Ceil" : "Cutoff")
;fprintf(fp, "-------------------------------------------------------------------------------\n")
; }
for (step = vary_a; step <= vary_z; step += vary_s)
{ double cutoff = step * 1.0 / vary_n
; double eff = -1.0
; mclv* nnodes = mclvCanonical(NULL, N_COLS(mx), 0.0)
; mclv* degree = mclvCanonical(NULL, N_COLS(mx), 0.0)
; dim i, n_sample = 0
; double cor, y_prev, iqr = 0.0
; mclx* cc = NULL, *res = NULL
; mclv* sz, *ccsz = NULL
; int step2 = vary_z + vary_a - step
; sum_vals = 0.0
; if (mode == 't' || mode == 'c')
mclxSelectValues(mx, &cutoff, NULL, MCLX_EQT_GQ)
, res = mx
; else if (mode == 'k')
{ res = rebase_g ? mclxCopy(mx) : mx
; mclxKNNdispatch(res, step2, n_thread_l, 1)
; }
else if (mode == 'l')
{ res = mx
; mclxKNNdispatch(res, step2, n_thread_l, 0)
; }
else if (mode == 'n')
{ res = rebase_g ? mclxCopy(mx) : mx
; mclv* cv = mclgCeilNB(res, step2, NULL, NULL, NULL)
; mclvFree(&cv)
; }
sz = mclxColSizes(res, MCL_VECTOR_COMPLETE)
; mclvSortDescVal(sz)
; cc = clmUGraphComponents(res, NULL) /* fixme: user has to specify -tf '#max()' if graph is directed */
; if (cc)
{ ccsz = mclxColSizes(cc, MCL_VECTOR_COMPLETE)
; if (compute_flags & COMPUTE_EFF)
{ clmPerformanceTable pftable
; clmPerformance(mx, cc, &pftable)
; eff = pftable.efficiency
; }
}
if (mode == 't' || mode == 'c')
{ for
(
; n_allvals > 0 && allvals[n_allvals-1] < cutoff
; n_allvals--
)
; sum_vals = 0.0
; for (i=0;i<n_allvals;i++)
sum_vals += allvals[i]
; }
else if (mode == 'k' || mode == 'n' || mode == 'l')
{ n_allvals = get_n_sort_allvals(res, allvals, noe, &sum_vals, FALSE)
; }
levels[cor_i].sim_median= mcxMedian(allvals, n_allvals, sizeof allvals[0], pval_get_double, &iqr)
; levels[cor_i].sim_iqr = iqr
; levels[cor_i].sim_mean = n_allvals ? sum_vals / n_allvals : 0.0
; levels[cor_i].nb_median = mcxMedian(sz->ivps, sz->n_ivps, sizeof sz->ivps[0], ivp_get_double, &iqr)
; levels[cor_i].nb_iqr = iqr
; levels[cor_i].nb_mean = mclvSum(sz) / N_COLS(res)
; levels[cor_i].cc_exp = cc ? mclvPowSum(ccsz, 2.0) / N_COLS(res) : 0
; levels[cor_i].nb_sum = mclxNrofEntries(res)
; if (compute_flags & COMPUTE_CLCF)
{ mclv* clcf = mclgCLCFdispatch(res, n_thread_l)
; levels[cor_i].clcf = mclvSum(clcf) / N_COLS(mx)
; mclvFree(&clcf)
; }
else
levels[cor_i].clcf = 0.0
; levels[cor_i].threshold = mode == 'k' || mode == 'l' || mode == 'n' ? step2 : cutoff
; levels[cor_i].bigsize = cc ? cc->cols[0].n_ivps : 0
; levels[cor_i].n_single = 0
; levels[cor_i].n_edge = n_allvals
; levels[cor_i].n_lq = 0
; if (cc)
for (i=0;i<N_COLS(cc);i++)
{ dim n = cc->cols[N_COLS(cc)-1-i].n_ivps
; if (n == 1)
levels[cor_i].n_single++
; if (n <= divide_g)
levels[cor_i].n_lq += n
; else
break
; }
if (levels[cor_i].bigsize <= divide_g)
levels[cor_i].bigsize = 0
; y_prev = sz->ivps[0].val
/* wiki says:
A scale-free network is a network whose degree distribution follows a power
law, at least asymptotically. That is, the fraction P(k) of nodes in the
network having k connections to other nodes goes for large values of k as P(k)
~ k^−g where g is a constant whose value is typically in the range 2<g<3,
although occasionally it may lie outside these bounds.
*/
; for (i=1;i<sz->n_ivps;i++)
{ double y = sz->ivps[i].val
; if (y > y_prev - 0.5)
continue /* same as node degree seen last */
; nnodes->ivps[n_sample].val = log( (i*1.0) / (1.0*N_COLS(res))) /* x = #nodes >= k, as fraction */
; degree->ivps[n_sample].val = log(y_prev ? y_prev : 1) /* y = k = degree of node */
; n_sample++
;if(0)fprintf(stderr, "k=%.0f\tn=%d\t%.3f\t%.3f\n", (double) y_prev, (int) i, (double) nnodes->ivps[n_sample-1].val, (double) degree->ivps[n_sample-1].val)
; y_prev = y
; }
nnodes->ivps[n_sample].val = 0
; nnodes->ivps[n_sample++].val = log(y_prev ? y_prev : 1)
;if(0){fprintf(stderr, "k=%.0f\tn=%d\t%.3f\t%.3f\n", (double) sz->ivps[sz->n_ivps-1].val, (int) N_COLS(res), (double) nnodes->ivps[n_sample-1].val, (double) degree->ivps[n_sample-1].val)
;}
; mclvResize(nnodes, n_sample)
; mclvResize(degree, n_sample)
; cor = pearson(nnodes, degree, n_sample)
; levels[cor_i].degree_cor = cor * cor
;if(0)fprintf(stdout, "cor at cutoff %.2f %.3f\n\n", cutoff, levels[cor_i-1].degree_cor)
; mclvFree(&nnodes)
; mclvFree(°ree)
; mclvFree(&sz)
; mclvFree(&ccsz)
; mclxFree(&cc)
; if(output_flags & OUTPUT_TABLE)
{ fprintf
( fp
, "%lu\t%lu\t%lu\t%lu\t%lu"
"\t%6g\t%6g\t%6g"
"\t%6g\t%lu\t%6g"
, (ulong) levels[cor_i].bigsize
, (ulong) levels[cor_i].n_lq
, (ulong) N_COLS(mx) - levels[cor_i].bigsize - levels[cor_i].n_lq
, (ulong) levels[cor_i].n_single
, (ulong) levels[cor_i].cc_exp
, (double) levels[cor_i].sim_mean
, (double) levels[cor_i].sim_median
, (double) levels[cor_i].sim_iqr
, (double) levels[cor_i].nb_mean
, (ulong) levels[cor_i].nb_median
, (double) levels[cor_i].nb_iqr
)
; if (compute_flags & COMPUTE_CLCF) fprintf(fp, "\t%6g", levels[cor_i].clcf) ; else fputs("\tNA", fp)
; if (eff >= 0.0) fprintf(fp, "\t%4g", eff) ; else fputs("\tNA", fp)
; fprintf(fp, "\t%6g", (double) levels[cor_i].threshold)
; fputc('\n', fp)
; }
else
{ fprintf
( fp
, "%3d %3d %3d %3d %7d "
"%7.0f %7.0f %6.0f"
"%6.1f %6.0f %6.0f"
, 0 ? 1 : (int) (0.5 + (100.0 * levels[cor_i].bigsize) / N_COLS(mx))
, 0 ? 1 : (int) (0.5 + (100.0 * levels[cor_i].n_lq) / N_COLS(mx))
, 0 ? 1 : (int) (0.5 + (100.0 * (N_COLS(mx) - levels[cor_i].bigsize - levels[cor_i].n_lq)) / N_COLS(mx))
, 0 ? 1 : (int) (0.5 + (100.0 * levels[cor_i].n_single) / N_COLS(mx))
, 0 ? 1 : (int) (0.5 + levels[cor_i].cc_exp)
, 0 ? 1.0 : (double) (levels[cor_i].sim_mean * weight_scale)
, 0 ? 1.0 : (double) (levels[cor_i].sim_median * weight_scale)
, 0 ? 1.0 : (double) (levels[cor_i].sim_iqr * weight_scale)
, 0 ? 1.0 : (double) (levels[cor_i].nb_mean )
, 0 ? 1.0 : (double) (levels[cor_i].nb_median + 0.5 )
, 0 ? 1.0 : (double) (levels[cor_i].nb_iqr + 0.5 )
)
; if (compute_flags & COMPUTE_CLCF)
fprintf(fp, " %3d", 0 ? 1 : (int) (0.5 + (100.0 * levels[cor_i].clcf)))
; else
fputs(" -", fp)
; if (eff >= 0.0)
fprintf(fp, " %3d", (int) (0.5 + 1000 * eff))
; else
fputs(" -", fp)
; if (mode == 'c')
fprintf(fp, "%8.2f\n", (double) levels[cor_i].threshold)
; else if (mode == 't')
fprintf(fp, "%8.0f\n", (double) levels[cor_i].threshold * weight_scale)
; else if (mode == 'k' || mode == 'n' || mode == 'l')
fprintf(fp, "%8.0f\n", (double) levels[cor_i].threshold)
; }
; cor_i++
; if (res != mx)
mclxFree(&res)
; }
if (!(output_flags & OUTPUT_TABLE))
{ if (weefreemen)
{
fprintf(fp, "-------------------------------------------------------------------------------\n")
;fprintf(fp, "The graph below plots the R^2 squared value for the fit of a log-log plot of\n")
;fprintf(fp, "<node degree k> versus <#nodes with degree >= k>, for the network resulting\n")
;fprintf(fp, "from applying a particular %s cutoff.\n", mode == 'c' ? "correlation" : "similarity")
;fprintf(fp, "-------------------------------------------------------------------------------\n")
; for (j=0;j<cor_i;j++)
{ dim jj
; for (jj=30;jj<=100;jj++)
{ char c = ' '
; if (jj * 0.01 < levels[j].degree_cor && (jj+1.0) * 0.01 > levels[j].degree_cor)
c = 'X'
; else if (jj % 5 == 0)
c = '|'
; fputc(c, fp)
; }
if (mode == 'c')
fprintf(fp, "%8.2f\n", (double) levels[j].threshold)
; else
fprintf(fp, "%8.0f\n", (double) levels[j].threshold * weight_scale)
; }
fprintf(fp, "|----+----|----+----|----+----|----+----|----+----|----+----|----+----|--------\n")
;fprintf(fp, "| R^2 0.4 0.5 0.6 0.7 0.8 0.9 | 1.0 -o)\n")
;fprintf(fp, "+----+----+----+----+----+---------+----+----+----+----+----+----+----+ /\\\\\n")
;fprintf(fp, "| 2 4 6 8 2 4 6 8 | 2 4 6 8 | 2 4 6 8 | 2 4 6 8 | 2 4 6 8 | 2 4 6 8 | _\\_/\n")
;fprintf(fp, "+----+----|----+----|----+----|----+----|----+----|----+----|----+----+--------\n")
; }
else
fprintf(fp, "-------------------------------------------------------------------------------\n")
; }
mclxFree(&mx)
; mcxFree(allvals)
; }
static mcxstatus collectMain
( int argc
, const char* argv[]
)
{ aggr* collect = NULL
; int a
; dim i, collect_n = 0
; mclTab* tab = NULL
; double avg = 0.0
; mclx* aggr = NULL, *mx = NULL
/* mcxHash* map = NULL */
; mcxIO* xfout = mcxIOnew(out_g, "w")
; mcxIOopen(xfout, EXIT_ON_FAIL)
; if
( transform_spec
&& (!(transform = mclgTFparse(NULL, transform_spec)))
)
mcxDie(1, me, "input -tf spec does not parse")
; if (xftab_g)
tab = mclTabRead(xftab_g, NULL, EXIT_ON_FAIL)
/* map not used; perhaps someday we want to map labels to indexes?
* in that case, we could also simply reverse the tab when reading ..
, map = mclTabHash(tab)
*/
; if (!collect_g)
mcxDie(1, me, "require one of --paste, --add-column, --add-matrix")
; if (argc)
{ if (collect_g == 'm')
{ mcxIO* xf = mcxIOnew(argv[0], "r")
; mcxIOopen(xf, EXIT_ON_FAIL)
; aggr = mclxRead(xf, EXIT_ON_FAIL)
; mcxIOfree(&xf)
; }
else
collect_n = do_a_file(&collect, argv[0], 0)
; }
if (tab && collect_n != N_TAB(tab) + (header_g ? 1 : 0))
mcxErr
( me
, "tab has differing size (%lu vs %lu), continuing anyway"
, (ulong) N_TAB(tab)
, (ulong) (collect_n ? collect_n -1 : 0)
)
; for (a=1;a<argc;a++)
{ if (collect_g == 'm')
{ mcxIO* xf = mcxIOnew(argv[a], "r")
; mcxIOopen(xf, EXIT_ON_FAIL)
; mx = mclxRead(xf, EXIT_ON_FAIL)
; mclxAugment(aggr, mx, fltop_g)
; mcxIOfree(&xf)
; mclxFree(&mx)
; }
else
do_a_file(&collect, argv[a], collect_n)
; }
if (collect_g == 'm')
{ if (transform)
mclgTFexec(aggr, transform)
; if (mcx_wb_g)
mclxbWrite(aggr, xfout, EXIT_ON_FAIL)
; else
mclxWrite(aggr, xfout, MCLXIO_VALUE_GETENV, EXIT_ON_FAIL)
; mcxIOclose(xfout)
; exit(0)
; }
/* fimxe: dispatch on binary_g */
for (i=0;i<collect_n;i++)
{ const char* lb = collect[i].label
; if (!i && collect[i].columns && collect_g != 'p')
{ fprintf(xfout->fp, "%s\t%s\n", lb, collect[i].columns->str)
; continue
; }
if (tab && (!header_g || i > 0))
{ unsigned u = atoi(lb)
; lb = mclTabGet(tab, u, NULL)
; if (TAB_IS_NA(tab, lb))
mcxDie(1, me, "no label found for index %ld - abort", (long) u)
; }
if (summary_g)
avg += collect[i].val
; else
{ if (collect_g == 'p')
fprintf(xfout->fp, "%s%s\n", lb, collect[i].columns->str)
; else
fprintf(xfout->fp, "%s\t%.8g\n", lb, collect[i].val)
; }
}
if (summary_g && collect_n)
{ dim middle1 = (collect_n-1)/2, middle2 = collect_n/2
; qsort(collect, collect_n, sizeof collect[0], aggr_cmp_val)
; avg /= collect_n
; fprintf /* --summary option is a bit rubbish interface-wise */
( xfout->fp
, "%g %g %g %g\n"
, collect[0].val
, (collect[middle1].val + collect[middle2].val) / 2
, collect[collect_n-1].val
, avg
)
; }
return STATUS_OK
; }
