/*
* percent_rank
* return fraction between 0 and 1 inclusive,
* which is described as (RK - 1) / (NR - 1), where RK is the current row's
* rank and NR is the total number of rows, per spec.
*/
Datum
window_percent_rank(PG_FUNCTION_ARGS)
{
WindowObject winobj = PG_WINDOW_OBJECT();
rank_context *context;
bool up;
int64 totalrows = WinGetPartitionRowCount(winobj);
Assert(totalrows > 0);
up = rank_up(winobj);
context = (rank_context *)
WinGetPartitionLocalMemory(winobj, sizeof(rank_context));
if (up)
context->rank = WinGetCurrentPosition(winobj) + 1;
/* return zero if there's only one row, per spec */
if (totalrows <= 1)
PG_RETURN_FLOAT8(0.0);
PG_RETURN_FLOAT8((float8) (context->rank - 1) / (float8) (totalrows - 1));
}
/*
* cume_dist
* return fraction betweeen 0 and 1 inclusive,
* which is described as NP / NR, where NP is the number of rows preceding or
* peers to the current row, and NR is the total number of rows, per spec.
*/
Datum
window_cume_dist(PG_FUNCTION_ARGS)
{
WindowObject winobj = PG_WINDOW_OBJECT();
rank_context *context;
bool up;
int64 totalrows = WinGetPartitionRowCount(winobj);
Assert(totalrows > 0);
up = rank_up(winobj);
context = (rank_context *)
WinGetPartitionLocalMemory(winobj, sizeof(rank_context));
if (up || context->rank == 1)
{
/*
* The current row is not peer to prior row or is just the first, so
* count up the number of rows that are peer to the current.
*/
int64 row;
context->rank = WinGetCurrentPosition(winobj) + 1;
/*
* start from current + 1
*/
for (row = context->rank; row < totalrows; row++)
{
if (!WinRowsArePeers(winobj, row - 1, row))
break;
context->rank++;
}
}
PG_RETURN_FLOAT8((float8) context->rank / (float8) totalrows);
}
/*
* ntile
* compute an exact numeric value with scale 0 (zero),
* ranging from 1 (one) to n, per spec.
*/
Datum
window_ntile(PG_FUNCTION_ARGS)
{
WindowObject winobj = PG_WINDOW_OBJECT();
ntile_context *context;
context = (ntile_context *)
WinGetPartitionLocalMemory(winobj, sizeof(ntile_context));
if (context->ntile == 0)
{
/* first call */
int64 total;
int32 nbuckets;
bool isnull;
total = WinGetPartitionRowCount(winobj);
nbuckets = DatumGetInt32(WinGetFuncArgCurrent(winobj, 0, &isnull));
/*
* per spec: If NT is the null value, then the result is the null
* value.
*/
if (isnull)
PG_RETURN_NULL();
/*
* per spec: If NT is less than or equal to 0 (zero), then an
* exception condition is raised.
*/
if (nbuckets <= 0)
ereport(ERROR,
(errcode(ERRCODE_INVALID_ARGUMENT_FOR_NTILE),
errmsg("argument of ntile must be greater than zero")));
context->ntile = 1;
context->rows_per_bucket = 0;
context->boundary = total / nbuckets;
if (context->boundary <= 0)
context->boundary = 1;
else
{
/*
* If the total number is not divisible, add 1 row to leading
* buckets.
*/
context->remainder = total % nbuckets;
if (context->remainder != 0)
context->boundary++;
}
}
context->rows_per_bucket++;
if (context->boundary < context->rows_per_bucket)
{
/* ntile up */
if (context->remainder != 0 && context->ntile == context->remainder)
{
context->remainder = 0;
context->boundary -= 1;
}
context->ntile += 1;
context->rows_per_bucket = 1;
}
PG_RETURN_INT32(context->ntile);
}
static Datum
kmeans_impl(PG_FUNCTION_ARGS, bool initial_mean_supplied)
{
WindowObject winobj = PG_WINDOW_OBJECT();
kmeans_context *context;
int64 curpos, rowcount;
rowcount = WinGetPartitionRowCount(winobj);
context = (kmeans_context *)
WinGetPartitionLocalMemory(winobj,
sizeof(kmeans_context) + sizeof(int) * rowcount);
if (!context->isdone)
{
int dim, k, N;
Datum arg;
bool isnull, isout;
myvector inputs, mean, maxlist, minlist;
int *r;
int i, a;
ArrayType *x;
arg = WinGetFuncArgCurrent(winobj, 0, &isnull);
if (!isnull)
x = DatumGetArrayTypeP(
WinGetFuncArgCurrent(winobj, 0, &isnull));
KMEANS_CHECK_V(x, ARR_DIMS(x)[0], isnull);
dim = ARR_DIMS(x)[0];
k = DatumGetInt32(WinGetFuncArgCurrent(winobj, 1, &isnull));
/*
* Since window function ignores STRICT mark,
* return NULL simply.
*/
if (isnull || k <= 0)
{
context->isdone = true;
context->isnull = true;
PG_RETURN_NULL();
}
N = (int) WinGetPartitionRowCount(winobj);
inputs = (myvector) palloc(SIZEOF_V(dim) * N);
maxlist = (myvector) palloc(SIZEOF_V(dim));
minlist = (myvector) palloc(SIZEOF_V(dim));
for (i = 0; i < N; i++)
{
x = DatumGetArrayTypeP(
WinGetFuncArgInPartition(winobj, 0, i,
WINDOW_SEEK_HEAD, false, &isnull, &isout));
KMEANS_CHECK_V(x, dim, isnull);
memcpy(&inputs[i * dim], ARR_DATA_PTR(x), SIZEOF_V(dim));
/* update min/max for later use of init mean */
for (a = 0; a < dim; a++)
{
if (i == 0 || maxlist[a] < inputs[i * dim + a])
maxlist[a] = inputs[i * dim + a];
if (i == 0 || minlist[a] > inputs[i * dim + a])
minlist[a] = inputs[i * dim + a];
}
}
/*
* initial mean vectors. need improve how to define them.
*/
mean = (myvector) palloc(SIZEOF_V(dim) * k);
/* only the result is stored in the partition local memory */
r = context->result;
if (initial_mean_supplied)
{
ArrayType *init = DatumGetArrayTypeP(
WinGetFuncArgCurrent(winobj, 2, &isnull));
/*
* we can accept 1d or 2d array as mean vectors.
*/
if (isnull || ARR_HASNULL(init) ||
!((ARR_NDIM(init) == 2 && ARR_DIMS(init)[0] == k &&
ARR_DIMS(init)[1] == dim) ||
(ARR_NDIM(init) == 1 &&
ARR_DIMS(init)[0] == k * dim)))
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("initial mean vector must be 2d without NULL element")));
memcpy(mean, ARR_DATA_PTR(init), SIZEOF_V(dim) * k);
}
else
{
initialize_mean(inputs, dim, N, k, mean, r);
kmeans_debug(mean, dim, k);
}
/* run it! */
calc_kmeans(inputs, dim, N, k, mean, r);
context->isdone = true;
}
if (context->isnull)
PG_RETURN_NULL();
curpos = WinGetCurrentPosition(winobj);
PG_RETURN_INT32(context->result[curpos]);
}
