void nplist_to_C_double_array(PyArrayObject *in_array,
double *out_list,
int N)
{
NpyIter *in_iter;
NpyIter_IterNextFunc *in_iternext;
double **in_ptr;
int itr;
in_iter = NpyIter_New(in_array, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
in_ptr = (double **) NpyIter_GetDataPtrArray(in_iter);
itr=0;
do {
out_list[itr++] = **in_ptr;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
fail:
return NULL;
}
Fn::NumpyInput::~NumpyInput()
{
if (_iter) {
NpyIter_Deallocate(_iter);
_iter = NULL;
}
}
/**
* parseFloatVec3(vec_in, vec_out)
*
* @param[in] vec_in the python array to extract elements from
* @param[out] vec_out float array of the numbers
* @return true if successful, false if not
*
* Convert a python array type to a 3 element float
* vector.
*/
static bool parseFloatVecN(PyArrayObject *vec_in, float *vec_out, int N)
{
/* verify it is a valid vector */
if (not_doublevector(vec_in))
return false;
if (PyArray_DIM(vec_in,0) != N) {
PyErr_Format(PyExc_ValueError, "Vector length incorrect. Received %ld and expected %d", PyArray_DIM(vec_in,0), N);
return false;
}
NpyIter *iter;
NpyIter_IterNextFunc *iternext;
/* create the iterators */
iter = NpyIter_New(vec_in, NPY_ITER_READONLY, NPY_KEEPORDER,
NPY_NO_CASTING, NULL);
if (iter == NULL)
goto fail;
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
NpyIter_Deallocate(iter);
goto fail;
}
double ** dataptr = (double **) NpyIter_GetDataPtrArray(iter);
/* iterate over the arrays */
int i = 0;
do {
vec_out[i++] = **dataptr;
} while(iternext(iter) && (i < N));
NpyIter_Deallocate(iter);
return true;
fail:
fprintf(stderr, "Parse fail\r\n");
return false;
}
void Fn::NumpyInput::reset()
{
_io = std::make_shared<IO_double>(_dim,_inputType);
// setup numpy iterator
if (_iter) {
NpyIter_Deallocate(_iter);
_iter = NULL;
}
PyArray_Descr* dtype = PyArray_DescrFromType(NPY_DOUBLE);
_iter = NpyIter_New( (PyArrayObject*)_arr, NPY_ITER_READONLY|
NPY_ITER_EXTERNAL_LOOP|
NPY_ITER_REFS_OK,
NPY_KEEPORDER, NPY_UNSAFE_CASTING, dtype );
Py_DECREF(dtype);
if (_iter == NULL) {
throw std::invalid_argument("An unknown error was encountered. Please contact developers.");
}
_iternext = NpyIter_GetIterNext(_iter, NULL);
if (_iternext == NULL) {
NpyIter_Deallocate(_iter);
throw std::invalid_argument("An unknown error was encountered. Please contact developers.");
}
/* The location of the data pointer which the iterator may update */
_dataptr = NpyIter_GetDataPtrArray(_iter);
/* The location of the stride which the iterator may update */
_strideptr = NpyIter_GetInnerStrideArray(_iter);
/* The location of the inner loop size which the iterator may update */
_innersizeptr = NpyIter_GetInnerLoopSizePtr(_iter);
_count = *_innersizeptr;
_data = *_dataptr;
grab();
}
/*
* This function executes all the standard NumPy reduction function
* boilerplate code, just calling assign_identity and the appropriate
* inner loop function where necessary.
*
* operand : The array to be reduced.
* out : NULL, or the array into which to place the result.
* wheremask : NOT YET SUPPORTED, but this parameter is placed here
* so that support can be added in the future without breaking
* API compatibility. Pass in NULL.
* operand_dtype : The dtype the inner loop expects for the operand.
* result_dtype : The dtype the inner loop expects for the result.
* casting : The casting rule to apply to the operands.
* axis_flags : Flags indicating the reduction axes of 'operand'.
* reorderable : If True, the reduction being done is reorderable, which
* means specifying multiple axes of reduction at once is ok,
* and the reduction code may calculate the reduction in an
* arbitrary order. The calculation may be reordered because
* of cache behavior or multithreading requirements.
* keepdims : If true, leaves the reduction dimensions in the result
* with size one.
* subok : If true, the result uses the subclass of operand, otherwise
* it is always a base class ndarray.
* assign_identity : If NULL, PyArray_InitializeReduceResult is used, otherwise
* this function is called to initialize the result to
* the reduction's unit.
* loop : The loop which does the reduction.
* data : Data which is passed to assign_identity and the inner loop.
* buffersize : Buffer size for the iterator. For the default, pass in 0.
* funcname : The name of the reduction function, for error messages.
* errormask : forwarded from _get_bufsize_errmask
*
* TODO FIXME: if you squint, this is essentially an second independent
* implementation of generalized ufuncs with signature (i)->(), plus a few
* extra bells and whistles. (Indeed, as far as I can tell, it was originally
* split out to support a fancy version of count_nonzero... which is not
* actually a reduction function at all, it's just a (i)->() function!) So
* probably these two implementation should be merged into one. (In fact it
* would be quite nice to support axis= and keepdims etc. for arbitrary
* generalized ufuncs!)
*/
NPY_NO_EXPORT PyArrayObject *
PyUFunc_ReduceWrapper(PyArrayObject *operand, PyArrayObject *out,
PyArrayObject *wheremask,
PyArray_Descr *operand_dtype,
PyArray_Descr *result_dtype,
NPY_CASTING casting,
npy_bool *axis_flags, int reorderable,
int keepdims,
int subok,
PyArray_AssignReduceIdentityFunc *assign_identity,
PyArray_ReduceLoopFunc *loop,
void *data, npy_intp buffersize, const char *funcname,
int errormask)
{
PyArrayObject *result = NULL, *op_view = NULL;
npy_intp skip_first_count = 0;
/* Iterator parameters */
NpyIter *iter = NULL;
PyArrayObject *op[2];
PyArray_Descr *op_dtypes[2];
npy_uint32 flags, op_flags[2];
/* Validate that the parameters for future expansion are NULL */
if (wheremask != NULL) {
PyErr_SetString(PyExc_RuntimeError,
"Reduce operations in NumPy do not yet support "
"a where mask");
return NULL;
}
/*
* This either conforms 'out' to the ndim of 'operand', or allocates
* a new array appropriate for this reduction.
*
* A new array with WRITEBACKIFCOPY is allocated if operand and out have memory
* overlap.
*/
Py_INCREF(result_dtype);
result = PyArray_CreateReduceResult(operand, out,
result_dtype, axis_flags,
keepdims, subok, funcname);
if (result == NULL) {
goto fail;
}
/*
* Initialize the result to the reduction unit if possible,
* otherwise copy the initial values and get a view to the rest.
*/
if (assign_identity != NULL) {
/*
* If this reduction is non-reorderable, make sure there are
* only 0 or 1 axes in axis_flags.
*/
if (!reorderable && check_nonreorderable_axes(PyArray_NDIM(operand),
axis_flags, funcname) < 0) {
goto fail;
}
if (assign_identity(result, data) < 0) {
goto fail;
}
op_view = operand;
Py_INCREF(op_view);
}
else {
op_view = PyArray_InitializeReduceResult(result, operand,
axis_flags, reorderable,
&skip_first_count, funcname);
if (op_view == NULL) {
goto fail;
}
/* empty op_view signals no reduction; but 0-d arrays cannot be empty */
if ((PyArray_SIZE(op_view) == 0) || (PyArray_NDIM(operand) == 0)) {
Py_DECREF(op_view);
op_view = NULL;
goto finish;
}
}
/* Set up the iterator */
op[0] = result;
op[1] = op_view;
op_dtypes[0] = result_dtype;
op_dtypes[1] = operand_dtype;
flags = NPY_ITER_BUFFERED |
NPY_ITER_EXTERNAL_LOOP |
NPY_ITER_GROWINNER |
NPY_ITER_DONT_NEGATE_STRIDES |
NPY_ITER_ZEROSIZE_OK |
NPY_ITER_REDUCE_OK |
NPY_ITER_REFS_OK;
op_flags[0] = NPY_ITER_READWRITE |
NPY_ITER_ALIGNED |
NPY_ITER_NO_SUBTYPE;
op_flags[1] = NPY_ITER_READONLY |
NPY_ITER_ALIGNED;
iter = NpyIter_AdvancedNew(2, op, flags,
NPY_KEEPORDER, casting,
op_flags,
op_dtypes,
-1, NULL, NULL, buffersize);
if (iter == NULL) {
goto fail;
}
/* Start with the floating-point exception flags cleared */
PyUFunc_clearfperr();
if (NpyIter_GetIterSize(iter) != 0) {
NpyIter_IterNextFunc *iternext;
char **dataptr;
npy_intp *strideptr;
npy_intp *countptr;
int needs_api;
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
strideptr = NpyIter_GetInnerStrideArray(iter);
countptr = NpyIter_GetInnerLoopSizePtr(iter);
needs_api = NpyIter_IterationNeedsAPI(iter);
/* Straightforward reduction */
if (loop == NULL) {
PyErr_Format(PyExc_RuntimeError,
"reduction operation %s did not supply an "
"inner loop function", funcname);
goto fail;
}
if (loop(iter, dataptr, strideptr, countptr,
iternext, needs_api, skip_first_count, data) < 0) {
goto fail;
}
}
/* Check whether any errors occurred during the loop */
if (PyErr_Occurred() ||
_check_ufunc_fperr(errormask, NULL, "reduce") < 0) {
goto fail;
}
NpyIter_Deallocate(iter);
Py_DECREF(op_view);
finish:
/* Strip out the extra 'one' dimensions in the result */
if (out == NULL) {
if (!keepdims) {
PyArray_RemoveAxesInPlace(result, axis_flags);
}
}
else {
PyArray_ResolveWritebackIfCopy(result); /* prevent spurious warnings */
Py_DECREF(result);
result = out;
Py_INCREF(result);
}
return result;
fail:
PyArray_ResolveWritebackIfCopy(result); /* prevent spurious warnings */
Py_XDECREF(result);
Py_XDECREF(op_view);
if (iter != NULL) {
NpyIter_Deallocate(iter);
}
return NULL;
}
/* unravel_index implementation - see add_newdocs.py */
NPY_NO_EXPORT PyObject *
arr_unravel_index(PyObject *self, PyObject *args, PyObject *kwds)
{
PyObject *indices0 = NULL, *ret_tuple = NULL;
PyArrayObject *ret_arr = NULL;
PyArrayObject *indices = NULL;
PyArray_Descr *dtype = NULL;
PyArray_Dims dimensions={0,0};
NPY_ORDER order = NPY_CORDER;
npy_intp unravel_size;
NpyIter *iter = NULL;
int i, ret_ndim;
npy_intp ret_dims[NPY_MAXDIMS], ret_strides[NPY_MAXDIMS];
char *kwlist[] = {"indices", "dims", "order", NULL};
if (!PyArg_ParseTupleAndKeywords(args, kwds, "OO&|O&:unravel_index",
kwlist,
&indices0,
PyArray_IntpConverter, &dimensions,
PyArray_OrderConverter, &order)) {
goto fail;
}
if (dimensions.len == 0) {
PyErr_SetString(PyExc_ValueError,
"dims must have at least one value");
goto fail;
}
unravel_size = PyArray_MultiplyList(dimensions.ptr, dimensions.len);
if (!PyArray_Check(indices0)) {
indices = (PyArrayObject*)PyArray_FromAny(indices0,
NULL, 0, 0, 0, NULL);
if (indices == NULL) {
goto fail;
}
}
else {
indices = (PyArrayObject *)indices0;
Py_INCREF(indices);
}
dtype = PyArray_DescrFromType(NPY_INTP);
if (dtype == NULL) {
goto fail;
}
iter = NpyIter_New(indices, NPY_ITER_READONLY|
NPY_ITER_ALIGNED|
NPY_ITER_BUFFERED|
NPY_ITER_ZEROSIZE_OK|
NPY_ITER_DONT_NEGATE_STRIDES|
NPY_ITER_MULTI_INDEX,
NPY_KEEPORDER, NPY_SAME_KIND_CASTING,
dtype);
if (iter == NULL) {
goto fail;
}
/*
* Create the return array with a layout compatible with the indices
* and with a dimension added to the end for the multi-index
*/
ret_ndim = PyArray_NDIM(indices) + 1;
if (NpyIter_GetShape(iter, ret_dims) != NPY_SUCCEED) {
goto fail;
}
ret_dims[ret_ndim-1] = dimensions.len;
if (NpyIter_CreateCompatibleStrides(iter,
dimensions.len*sizeof(npy_intp), ret_strides) != NPY_SUCCEED) {
goto fail;
}
ret_strides[ret_ndim-1] = sizeof(npy_intp);
/* Remove the multi-index and inner loop */
if (NpyIter_RemoveMultiIndex(iter) != NPY_SUCCEED) {
goto fail;
}
if (NpyIter_EnableExternalLoop(iter) != NPY_SUCCEED) {
goto fail;
}
ret_arr = (PyArrayObject *)PyArray_NewFromDescr(&PyArray_Type, dtype,
ret_ndim, ret_dims, ret_strides, NULL, 0, NULL);
dtype = NULL;
if (ret_arr == NULL) {
goto fail;
}
if (order == NPY_CORDER) {
if (NpyIter_GetIterSize(iter) != 0) {
NpyIter_IterNextFunc *iternext;
char **dataptr;
npy_intp *strides;
npy_intp *countptr, count;
npy_intp *coordsptr = (npy_intp *)PyArray_DATA(ret_arr);
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
strides = NpyIter_GetInnerStrideArray(iter);
countptr = NpyIter_GetInnerLoopSizePtr(iter);
do {
count = *countptr;
if (unravel_index_loop_corder(dimensions.len, dimensions.ptr,
unravel_size, count, *dataptr, *strides,
coordsptr) != NPY_SUCCEED) {
goto fail;
}
coordsptr += count*dimensions.len;
} while(iternext(iter));
}
}
else if (order == NPY_FORTRANORDER) {
if (NpyIter_GetIterSize(iter) != 0) {
NpyIter_IterNextFunc *iternext;
char **dataptr;
npy_intp *strides;
npy_intp *countptr, count;
npy_intp *coordsptr = (npy_intp *)PyArray_DATA(ret_arr);
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
strides = NpyIter_GetInnerStrideArray(iter);
countptr = NpyIter_GetInnerLoopSizePtr(iter);
do {
count = *countptr;
if (unravel_index_loop_forder(dimensions.len, dimensions.ptr,
unravel_size, count, *dataptr, *strides,
coordsptr) != NPY_SUCCEED) {
goto fail;
}
coordsptr += count*dimensions.len;
} while(iternext(iter));
}
}
else {
PyErr_SetString(PyExc_ValueError,
"only 'C' or 'F' order is permitted");
goto fail;
}
/* Now make a tuple of views, one per index */
ret_tuple = PyTuple_New(dimensions.len);
if (ret_tuple == NULL) {
goto fail;
}
for (i = 0; i < dimensions.len; ++i) {
PyArrayObject *view;
view = (PyArrayObject *)PyArray_New(&PyArray_Type, ret_ndim-1,
ret_dims, NPY_INTP,
ret_strides,
PyArray_BYTES(ret_arr) + i*sizeof(npy_intp),
0, NPY_ARRAY_WRITEABLE, NULL);
if (view == NULL) {
goto fail;
}
Py_INCREF(ret_arr);
if (PyArray_SetBaseObject(view, (PyObject *)ret_arr) < 0) {
Py_DECREF(view);
goto fail;
}
PyTuple_SET_ITEM(ret_tuple, i, PyArray_Return(view));
}
Py_DECREF(ret_arr);
Py_XDECREF(indices);
PyDimMem_FREE(dimensions.ptr);
NpyIter_Deallocate(iter);
return ret_tuple;
fail:
Py_XDECREF(ret_tuple);
Py_XDECREF(ret_arr);
Py_XDECREF(dtype);
Py_XDECREF(indices);
PyDimMem_FREE(dimensions.ptr);
NpyIter_Deallocate(iter);
return NULL;
}
/* ravel_multi_index implementation - see add_newdocs.py */
NPY_NO_EXPORT PyObject *
arr_ravel_multi_index(PyObject *self, PyObject *args, PyObject *kwds)
{
int i, s;
PyObject *mode0=NULL, *coords0=NULL;
PyArrayObject *ret = NULL;
PyArray_Dims dimensions={0,0};
npy_intp ravel_strides[NPY_MAXDIMS];
NPY_ORDER order = NPY_CORDER;
NPY_CLIPMODE modes[NPY_MAXDIMS];
PyArrayObject *op[NPY_MAXARGS];
PyArray_Descr *dtype[NPY_MAXARGS];
npy_uint32 op_flags[NPY_MAXARGS];
NpyIter *iter = NULL;
char *kwlist[] = {"multi_index", "dims", "mode", "order", NULL};
memset(op, 0, sizeof(op));
dtype[0] = NULL;
if (!PyArg_ParseTupleAndKeywords(args, kwds,
"OO&|OO&:ravel_multi_index", kwlist,
&coords0,
PyArray_IntpConverter, &dimensions,
&mode0,
PyArray_OrderConverter, &order)) {
goto fail;
}
if (dimensions.len+1 > NPY_MAXARGS) {
PyErr_SetString(PyExc_ValueError,
"too many dimensions passed to ravel_multi_index");
goto fail;
}
if (!PyArray_ConvertClipmodeSequence(mode0, modes, dimensions.len)) {
goto fail;
}
switch (order) {
case NPY_CORDER:
s = 1;
for (i = dimensions.len-1; i >= 0; --i) {
ravel_strides[i] = s;
s *= dimensions.ptr[i];
}
break;
case NPY_FORTRANORDER:
s = 1;
for (i = 0; i < dimensions.len; ++i) {
ravel_strides[i] = s;
s *= dimensions.ptr[i];
}
break;
default:
PyErr_SetString(PyExc_ValueError,
"only 'C' or 'F' order is permitted");
goto fail;
}
/* Get the multi_index into op */
if (sequence_to_arrays(coords0, op, dimensions.len, "multi_index") < 0) {
goto fail;
}
for (i = 0; i < dimensions.len; ++i) {
op_flags[i] = NPY_ITER_READONLY|
NPY_ITER_ALIGNED;
}
op_flags[dimensions.len] = NPY_ITER_WRITEONLY|
NPY_ITER_ALIGNED|
NPY_ITER_ALLOCATE;
dtype[0] = PyArray_DescrFromType(NPY_INTP);
for (i = 1; i <= dimensions.len; ++i) {
dtype[i] = dtype[0];
}
iter = NpyIter_MultiNew(dimensions.len+1, op, NPY_ITER_BUFFERED|
NPY_ITER_EXTERNAL_LOOP|
NPY_ITER_ZEROSIZE_OK,
NPY_KEEPORDER,
NPY_SAME_KIND_CASTING,
op_flags, dtype);
if (iter == NULL) {
goto fail;
}
if (NpyIter_GetIterSize(iter) != 0) {
NpyIter_IterNextFunc *iternext;
char **dataptr;
npy_intp *strides;
npy_intp *countptr;
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
strides = NpyIter_GetInnerStrideArray(iter);
countptr = NpyIter_GetInnerLoopSizePtr(iter);
do {
if (ravel_multi_index_loop(dimensions.len, dimensions.ptr,
ravel_strides, *countptr, modes,
dataptr, strides) != NPY_SUCCEED) {
goto fail;
}
} while(iternext(iter));
}
ret = NpyIter_GetOperandArray(iter)[dimensions.len];
Py_INCREF(ret);
Py_DECREF(dtype[0]);
for (i = 0; i < dimensions.len; ++i) {
Py_XDECREF(op[i]);
}
PyDimMem_FREE(dimensions.ptr);
NpyIter_Deallocate(iter);
return PyArray_Return(ret);
fail:
Py_XDECREF(dtype[0]);
for (i = 0; i < dimensions.len; ++i) {
Py_XDECREF(op[i]);
}
PyDimMem_FREE(dimensions.ptr);
NpyIter_Deallocate(iter);
return NULL;
}
static PyObject *
PyUFunc_Accumulate(PyUFuncObject *ufunc, PyArrayObject *arr, PyArrayObject *out,
int axis, int otype)
{
PyArrayObject *op[2];
PyArray_Descr *op_dtypes[2] = {NULL, NULL};
int op_axes_arrays[2][NPY_MAXDIMS];
int *op_axes[2] = {op_axes_arrays[0], op_axes_arrays[1]};
npy_uint32 op_flags[2];
int idim, ndim, otype_final;
int needs_api, need_outer_iterator;
NpyIter *iter = NULL, *iter_inner = NULL;
/* The selected inner loop */
PyUFuncGenericFunction innerloop = NULL;
void *innerloopdata = NULL;
const char *ufunc_name = ufunc->name ? ufunc->name : "(unknown)";
/* These parameters come from extobj= or from a TLS global */
int buffersize = 0, errormask = 0;
NPY_BEGIN_THREADS_DEF;
NPY_UF_DBG_PRINT1("\nEvaluating ufunc %s.accumulate\n", ufunc_name);
#if 0
printf("Doing %s.accumulate on array with dtype : ", ufunc_name);
PyObject_Print((PyObject *)PyArray_DESCR(arr), stdout, 0);
printf("\n");
#endif
if (_get_bufsize_errmask(NULL, "accumulate", &buffersize, &errormask) < 0) {
return NULL;
}
/* Take a reference to out for later returning */
Py_XINCREF(out);
otype_final = otype;
if (get_binary_op_function(ufunc, &otype_final,
&innerloop, &innerloopdata) < 0) {
PyArray_Descr *dtype = PyArray_DescrFromType(otype);
PyErr_Format(PyExc_ValueError,
"could not find a matching type for %s.accumulate, "
"requested type has type code '%c'",
ufunc_name, dtype ? dtype->type : '-');
Py_XDECREF(dtype);
goto fail;
}
ndim = PyArray_NDIM(arr);
/*
* Set up the output data type, using the input's exact
* data type if the type number didn't change to preserve
* metadata
*/
if (PyArray_DESCR(arr)->type_num == otype_final) {
if (PyArray_ISNBO(PyArray_DESCR(arr)->byteorder)) {
op_dtypes[0] = PyArray_DESCR(arr);
Py_INCREF(op_dtypes[0]);
}
else {
op_dtypes[0] = PyArray_DescrNewByteorder(PyArray_DESCR(arr),
NPY_NATIVE);
}
}
else {
op_dtypes[0] = PyArray_DescrFromType(otype_final);
}
if (op_dtypes[0] == NULL) {
goto fail;
}
#if NPY_UF_DBG_TRACING
printf("Found %s.accumulate inner loop with dtype : ", ufunc_name);
PyObject_Print((PyObject *)op_dtypes[0], stdout, 0);
printf("\n");
#endif
/* Set up the op_axes for the outer loop */
for (idim = 0; idim < ndim; ++idim) {
op_axes_arrays[0][idim] = idim;
op_axes_arrays[1][idim] = idim;
}
/* The per-operand flags for the outer loop */
op_flags[0] = NPY_ITER_READWRITE |
NPY_ITER_NO_BROADCAST |
NPY_ITER_ALLOCATE |
NPY_ITER_NO_SUBTYPE;
op_flags[1] = NPY_ITER_READONLY;
op[0] = out;
op[1] = arr;
need_outer_iterator = (ndim > 1);
/* We can't buffer, so must do UPDATEIFCOPY */
if (!PyArray_ISALIGNED(arr) || (out && !PyArray_ISALIGNED(out)) ||
!PyArray_EquivTypes(op_dtypes[0], PyArray_DESCR(arr)) ||
(out &&
!PyArray_EquivTypes(op_dtypes[0], PyArray_DESCR(out)))) {
need_outer_iterator = 1;
}
if (need_outer_iterator) {
int ndim_iter = 0;
npy_uint32 flags = NPY_ITER_ZEROSIZE_OK|
NPY_ITER_REFS_OK;
PyArray_Descr **op_dtypes_param = NULL;
/*
* The way accumulate is set up, we can't do buffering,
* so make a copy instead when necessary.
*/
ndim_iter = ndim;
flags |= NPY_ITER_MULTI_INDEX;
/* Add some more flags */
op_flags[0] |= NPY_ITER_UPDATEIFCOPY|NPY_ITER_ALIGNED;
op_flags[1] |= NPY_ITER_COPY|NPY_ITER_ALIGNED;
op_dtypes_param = op_dtypes;
op_dtypes[1] = op_dtypes[0];
NPY_UF_DBG_PRINT("Allocating outer iterator\n");
iter = NpyIter_AdvancedNew(2, op, flags,
NPY_KEEPORDER, NPY_UNSAFE_CASTING,
op_flags,
op_dtypes_param,
ndim_iter, op_axes, NULL, 0);
if (iter == NULL) {
goto fail;
}
/* In case COPY or UPDATEIFCOPY occurred */
op[0] = NpyIter_GetOperandArray(iter)[0];
op[1] = NpyIter_GetOperandArray(iter)[1];
if (PyArray_SIZE(op[0]) == 0) {
if (out == NULL) {
out = op[0];
Py_INCREF(out);
}
goto finish;
}
if (NpyIter_RemoveAxis(iter, axis) != NPY_SUCCEED) {
goto fail;
}
if (NpyIter_RemoveMultiIndex(iter) != NPY_SUCCEED) {
goto fail;
}
}
/* Get the output */
if (out == NULL) {
if (iter) {
op[0] = out = NpyIter_GetOperandArray(iter)[0];
Py_INCREF(out);
}
else {
PyArray_Descr *dtype = op_dtypes[0];
Py_INCREF(dtype);
op[0] = out = (PyArrayObject *)PyArray_NewFromDescr(
&PyArray_Type, dtype,
ndim, PyArray_DIMS(op[1]), NULL, NULL,
0, NULL);
if (out == NULL) {
goto fail;
}
}
}
/*
* If the reduction axis has size zero, either return the reduction
* unit for UFUNC_REDUCE, or return the zero-sized output array
* for UFUNC_ACCUMULATE.
*/
if (PyArray_DIM(op[1], axis) == 0) {
goto finish;
}
else if (PyArray_SIZE(op[0]) == 0) {
goto finish;
}
if (iter && NpyIter_GetIterSize(iter) != 0) {
char *dataptr_copy[3];
npy_intp stride_copy[3];
npy_intp count_m1, stride0, stride1;
NpyIter_IterNextFunc *iternext;
char **dataptr;
int itemsize = op_dtypes[0]->elsize;
/* Get the variables needed for the loop */
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
/* Execute the loop with just the outer iterator */
count_m1 = PyArray_DIM(op[1], axis)-1;
stride0 = 0, stride1 = PyArray_STRIDE(op[1], axis);
NPY_UF_DBG_PRINT("UFunc: Reduce loop with just outer iterator\n");
stride0 = PyArray_STRIDE(op[0], axis);
stride_copy[0] = stride0;
stride_copy[1] = stride1;
stride_copy[2] = stride0;
needs_api = NpyIter_IterationNeedsAPI(iter);
NPY_BEGIN_THREADS_NDITER(iter);
do {
dataptr_copy[0] = dataptr[0];
dataptr_copy[1] = dataptr[1];
dataptr_copy[2] = dataptr[0];
/*
* Copy the first element to start the reduction.
*
* Output (dataptr[0]) and input (dataptr[1]) may point to
* the same memory, e.g. np.add.accumulate(a, out=a).
*/
if (otype == NPY_OBJECT) {
/*
* Incref before decref to avoid the possibility of the
* reference count being zero temporarily.
*/
Py_XINCREF(*(PyObject **)dataptr_copy[1]);
Py_XDECREF(*(PyObject **)dataptr_copy[0]);
*(PyObject **)dataptr_copy[0] =
*(PyObject **)dataptr_copy[1];
}
else {
memmove(dataptr_copy[0], dataptr_copy[1], itemsize);
}
if (count_m1 > 0) {
/* Turn the two items into three for the inner loop */
dataptr_copy[1] += stride1;
dataptr_copy[2] += stride0;
NPY_UF_DBG_PRINT1("iterator loop count %d\n",
(int)count_m1);
innerloop(dataptr_copy, &count_m1,
stride_copy, innerloopdata);
}
} while (iternext(iter));
NPY_END_THREADS;
}
else if (iter == NULL) {
char *dataptr_copy[3];
npy_intp stride_copy[3];
int itemsize = op_dtypes[0]->elsize;
/* Execute the loop with no iterators */
npy_intp count = PyArray_DIM(op[1], axis);
npy_intp stride0 = 0, stride1 = PyArray_STRIDE(op[1], axis);
NPY_UF_DBG_PRINT("UFunc: Reduce loop with no iterators\n");
if (PyArray_NDIM(op[0]) != PyArray_NDIM(op[1]) ||
!PyArray_CompareLists(PyArray_DIMS(op[0]),
PyArray_DIMS(op[1]),
PyArray_NDIM(op[0]))) {
PyErr_SetString(PyExc_ValueError,
"provided out is the wrong size "
"for the reduction");
goto fail;
}
stride0 = PyArray_STRIDE(op[0], axis);
stride_copy[0] = stride0;
stride_copy[1] = stride1;
stride_copy[2] = stride0;
/* Turn the two items into three for the inner loop */
dataptr_copy[0] = PyArray_BYTES(op[0]);
dataptr_copy[1] = PyArray_BYTES(op[1]);
dataptr_copy[2] = PyArray_BYTES(op[0]);
/*
* Copy the first element to start the reduction.
*
* Output (dataptr[0]) and input (dataptr[1]) may point to the
* same memory, e.g. np.add.accumulate(a, out=a).
*/
if (otype == NPY_OBJECT) {
/*
* Incref before decref to avoid the possibility of the
* reference count being zero temporarily.
*/
Py_XINCREF(*(PyObject **)dataptr_copy[1]);
Py_XDECREF(*(PyObject **)dataptr_copy[0]);
*(PyObject **)dataptr_copy[0] =
*(PyObject **)dataptr_copy[1];
}
else {
memmove(dataptr_copy[0], dataptr_copy[1], itemsize);
}
if (count > 1) {
--count;
dataptr_copy[1] += stride1;
dataptr_copy[2] += stride0;
NPY_UF_DBG_PRINT1("iterator loop count %d\n", (int)count);
needs_api = PyDataType_REFCHK(op_dtypes[0]);
if (!needs_api) {
NPY_BEGIN_THREADS_THRESHOLDED(count);
}
innerloop(dataptr_copy, &count,
stride_copy, innerloopdata);
NPY_END_THREADS;
}
}
finish:
Py_XDECREF(op_dtypes[0]);
NpyIter_Deallocate(iter);
NpyIter_Deallocate(iter_inner);
return (PyObject *)out;
fail:
Py_XDECREF(out);
Py_XDECREF(op_dtypes[0]);
NpyIter_Deallocate(iter);
NpyIter_Deallocate(iter_inner);
return NULL;
}
/*********************
* python interface *
*********************/
static PyObject* eeint(PyObject* self, PyObject* args){
/*** input variables ***/
/* dictionary */
PyObject *in_dict;
PyObject *dictList;
PyObject *dictList_fast;
PyObject *pyStr;
PyObject *item;
/* numpy array */
PyArrayObject *in_array1, *in_array2;
NpyIter *in_iter;
NpyIter_IterNextFunc *in_iternext;
/* C data type for input */
int Ngo, Nao;
int N, itr;
/* basis function variables */
double **in_ptr; // address to numpy pointer
double *center; // gaussian center
double *cef; // contraction coefficients
int *ng; // number of gaussians per AO
double *exp; // gaussian exponents
int *lm_xyz; // angular momentum
/* python output variables */
PyObject *py_out;
PyObject *py_out2;
double *data, *overlap;
double element;
int i, j, k, l;
int s, t, u, v, w;
int mat_dim[4];
/* parse numpy array and two integers as argument */
if (!PyArg_ParseTuple(args, "OO!O!",
&in_dict,
&PyArray_Type, &in_array1,
&PyArray_Type, &in_array2
)) return NULL;
if(in_array1 == NULL) return NULL;
/***********************
* Construct input data *
***********************/
/*** access dict_list data ***/
/* exponents */
pyStr = PyString_FromString("exponents");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
Ngo = PySequence_Size(dictList);
exp = (double*) malloc(Ngo * sizeof(double));
for(i=0;i<Ngo;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
exp[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/* coefficients */
pyStr = PyString_FromString("coefficients");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
cef = (double*) malloc(Ngo * sizeof(double));
for(i=0;i<Ngo;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
cef[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/* number of gaussians per shell */
pyStr = PyString_FromString("n_gaussians");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
Nao = PySequence_Size(dictList);
ng = (int*) malloc(Nao * sizeof(int));
for(i=0;i<Nao;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
ng[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/*** end of dict_list data ***/
/*** create the iterators, necessary to access numpy array ***/
/* center */
in_iter = NpyIter_New(in_array1, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
in_ptr = (double **) NpyIter_GetDataPtrArray(in_iter);
center = (double*) malloc(3 * Nao * sizeof(double));
itr=0;
do {
center[itr++] = **in_ptr;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
/* lm_xyz */
in_iter = NpyIter_New(in_array2, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
int **in_ptr2 = (int **) NpyIter_GetDataPtrArray(in_iter);
lm_xyz = (int*) malloc(3 * Nao * sizeof(int));
itr=0;
do {
lm_xyz[itr++] = **in_ptr2;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
/*** end of numpy input data ***/
/***** end of input data construction *****/
/*******************
* construct output *
*******************/
for(i=0;i<4;i++) mat_dim[i] = Nao;
py_out = (PyArrayObject*)
PyArray_FromDims(4, mat_dim, NPY_DOUBLE);
data = pyvector_to_Carrayptrs(py_out);
/* renormalization */
renormalize(center, exp, cef, ng, lm_xyz, Nao);
/* orthogonalize */
// no effect at the moment, for debug purpose
//py_out2 = (PyArrayObject*)
// PyArray_FromDims(2, mat_dim, NPY_DOUBLE);
//overlap = pyvector_to_Carrayptrs(py_out2);
//orthogonalize(overlap, center, exp, cef, ng, lm_xyz, Nao);
#pragma omp parallel private(i, j, k, l, s, t, u, v, w)\
shared(data)
{
#pragma omp for schedule(dynamic)
for(i=0;i<Nao;i++){
for(j=i;j<Nao;j++){
for(k=0;k<Nao;k++){
for(l=k;l<Nao;l++){
if(l+k >= i+j){
s = l + k*Nao + j*Nao*Nao + i*Nao*Nao*Nao;
element = eeMatrix(center, exp, cef, ng, lm_xyz,
Nao, i, j, k, l);
data[s] = element;
// symmetry for (ij|kl)=(ij|lk)=(ji|kl)=(ji|lk)
t = k + l*Nao + j*Nao*Nao + i*Nao*Nao*Nao; //(ij|lk)
u = l + k*Nao + i*Nao*Nao + j*Nao*Nao*Nao; //(ji|kl)
v = k + l*Nao + i*Nao*Nao + j*Nao*Nao*Nao; //(ji|lk)
data[t] = data[s];
data[u] = data[s];
data[v] = data[s];
// symmetry for (ij|kl)=(kl|ij)=(kl|ji)=(lk|ij)=(lk|ji)
t = j + i*Nao + l*Nao*Nao + k*Nao*Nao*Nao; //(kl|ij)
u = i + j*Nao + l*Nao*Nao + k*Nao*Nao*Nao; //(kl|ji)
v = j + i*Nao + k*Nao*Nao + l*Nao*Nao*Nao; //(lk|ij)
w = i + j*Nao + k*Nao*Nao + l*Nao*Nao*Nao; //(lk|ji)
data[t] = data[s];
data[u] = data[s];
data[v] = data[s];
data[w] = data[s];
}
}
}
}
}
} // end of omp loop
/*********************************
* clean up and return the result *
*********************************/
free(exp);
free(cef);
free(ng);
free(center);
free(lm_xyz);
//free(overlap);
Py_INCREF(py_out);
return Py_BuildValue("O", py_out);
/* in case bad things happen */
fail:
Py_XDECREF(py_out);
return NULL;
} // end of eeint function
/*********************
* python interface *
*********************/
static PyObject* eekernel(PyObject* self, PyObject* args){
/*** input variables ***/
/* dictionary */
PyObject *in_dict;
PyObject *dictList;
PyObject *dictList_fast;
PyObject *pyStr;
PyObject *item;
/* list */
PyObject *in_list;
PyObject *list_fast;
/* numpy array */
PyArrayObject *in_array1, *in_array2, *in_array3;
NpyIter *in_iter;
NpyIter_IterNextFunc *in_iternext;
/* C data type for input */
int Ngo, Nao;
int N, itr;
double *Z;
double *R;
/* basis function variables */
double **in_ptr; // address to numpy pointer
double *center; // gaussian center
double *cef; // contraction coefficients
int *ng; // number of gaussians per AO
double *exp; // gaussian exponents
int *lm_xyz; // angular momentum
/* python output variables */
PyObject *py_out;
PyObject *py_out2;
double *data, *overlap;
int i, j, k;
int mat_dim[3];
/* parse numpy array and two integers as argument */
if (!PyArg_ParseTuple(args, "OO!O!O!O",
&in_dict,
&PyArray_Type, &in_array1,
&PyArray_Type, &in_array2,
&PyArray_Type, &in_array3,
&in_list
)) return NULL;
if(in_array1 == NULL) return NULL;
/***********************
* Construct input data *
***********************/
/*** access dict_list data ***/
/* exponents */
pyStr = PyString_FromString("exponents");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
Ngo = PySequence_Size(dictList);
exp = (double*) malloc(Ngo * sizeof(double));
for(i=0;i<Ngo;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
exp[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/* coefficients */
pyStr = PyString_FromString("coefficients");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
cef = (double*) malloc(Ngo * sizeof(double));
for(i=0;i<Ngo;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
cef[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/* number of gaussians per shell */
pyStr = PyString_FromString("n_gaussians");
dictList = PyDict_GetItem(in_dict, pyStr);
dictList_fast = PySequence_Fast(
dictList, "expected a sequence");
Nao = PySequence_Size(dictList);
ng = (int*) malloc(Nao * sizeof(int));
for(i=0;i<Nao;i++){
item = PySequence_Fast_GET_ITEM(dictList_fast, i);
ng[i] = PyFloat_AsDouble(item);
}
Py_DECREF(dictList_fast);
/*** end of dict_list data ***/
/*** access python list data ***/
list_fast = PySequence_Fast(in_list, "expected a sequence");
N = PySequence_Size(in_list);
Z = (double*) malloc(N * sizeof(double));
for(i=0;i<N;i++){
item = PySequence_Fast_GET_ITEM(list_fast, i);
Z[i] = PyFloat_AsDouble(item);
}
Py_DECREF(list_fast);
/*** end of list input data ***/
/*** create the iterators, necessary to access numpy array ***/
/* center */
in_iter = NpyIter_New(in_array1, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
in_ptr = (double **) NpyIter_GetDataPtrArray(in_iter);
center = (double*) malloc(3 * Nao * sizeof(double));
itr=0;
do {
center[itr++] = **in_ptr;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
/* lm_xyz */
in_iter = NpyIter_New(in_array2, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
int **in_ptr2 = (int **) NpyIter_GetDataPtrArray(in_iter);
lm_xyz = (int*) malloc(3 * Nao * sizeof(int));
itr=0;
do {
lm_xyz[itr++] = **in_ptr2;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
/* R */
in_iter = NpyIter_New(in_array3, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
if (in_iter == NULL) goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL){
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
in_ptr = (double **) NpyIter_GetDataPtrArray(in_iter);
R = (double*) malloc(3 * N * sizeof(double));
itr=0;
do {
R[itr++] = **in_ptr;
} while(in_iternext(in_iter));
NpyIter_Deallocate(in_iter);
/*** end of numpy input data ***/
/***** end of input data construction *****/
/*******************
* construct output *
*******************/
mat_dim[0] = Nao;
mat_dim[1] = Nao;
mat_dim[2] = N;
py_out = (PyArrayObject*)
PyArray_FromDims(3, mat_dim, NPY_DOUBLE);
data = pyvector_to_Carrayptrs(py_out);
/* renormalization */
renormalize(center, exp, cef, ng, lm_xyz, Nao);
/* orthogonalize */
// no effect at the moment, for debug purpose
//py_out2 = (PyArrayObject*)
// PyArray_FromDims(2, mat_dim, NPY_DOUBLE);
//overlap = pyvector_to_Carrayptrs(py_out2);
//orthogonalize(overlap, center, exp, cef, ng, lm_xyz, Nao);
#pragma omp parallel private(i, j, k) shared(data)
{
#pragma omp for schedule(dynamic)
for(i=0;i<Nao;i++){
for(j=i;j<Nao;j++){
eeKernel(R, Z, center, exp, cef, &data[Nao*N*i + N*j],
ng, lm_xyz, Nao, N, i, j);
if(j!=i){
for(k=0;k<N;k++)
data[i*N+j*Nao*N + k] = data[j*N+i*Nao*N + k];
}
}
}
} // end of omp loop
/*********************************
* clean up and return the result *
*********************************/
free(exp);
free(cef);
free(ng);
free(center);
free(R);
free(Z);
free(overlap);
Py_INCREF(py_out);
return Py_BuildValue("O", py_out);
/* in case bad things happen */
fail:
Py_XDECREF(py_out);
return NULL;
}
/* python interface */
static PyObject* kernel_matrix(PyObject* self, PyObject* args){
/* input variables */
PyArrayObject *in_array;
NpyIter *in_iter;
NpyIter_IterNextFunc *in_iternext;
PyObject *klargs;
PyObject *seq;
PyObject *item;
double *data;
char *kernel = (char*) malloc(20);
double *kerargs;
int rows, columns, len;
/* python output variables */
PyObject *np_matrix;
double *matrix;
double *xi, *xj;
int vec_dim[1];
int mat_dim[2];
int i, j, itr = 0;
/* parse numpy array and two integers as argument */
if (!PyArg_ParseTuple(args, "O!iis|O",
&PyArray_Type, &in_array, // O!, NpArray
&rows, // i
&columns, // i
&kernel, // s, kernel
/* kernel args */ &klargs)) return NULL;
/***********************
* Construct input data *
***********************/
data = (double*) malloc(rows * columns * sizeof(double));
/* create the iterators, necessary to access numpy array */
in_iter = NpyIter_New(in_array, NPY_ITER_READONLY,
NPY_KEEPORDER, NPY_NO_CASTING, NULL);
/* check input status */
if (in_iter == NULL)
goto fail;
in_iternext = NpyIter_GetIterNext(in_iter, NULL);
if (in_iternext == NULL) {
NpyIter_Deallocate(in_iter);
goto fail;
}
/* interator pointer to actual numpy data */
double **in_dataptr = (double **)
NpyIter_GetDataPtrArray(in_iter);
/* iterate over the arrays */
do {
data[itr++] = **in_dataptr;
} while(in_iternext(in_iter));
/* access python list data */
seq = PySequence_Fast(klargs, "expected a sequence");
len = PySequence_Size(klargs);
kerargs = (double*) malloc(len * sizeof(double));
for(i=0;i<len;i++){
item = PySequence_Fast_GET_ITEM(seq, i);
kerargs[i] = PyFloat_AsDouble(item);
}
Py_DECREF(seq);
/***** end of input data construction *****/
/**************************
* construct output matrix *
**************************/
matrix = (double *) malloc(rows * rows * sizeof(double));
mat_dim[0] = rows;
mat_dim[1] = rows;
vec_dim[0] = columns;
#pragma omp parallel private(i,j,xi,xj) shared(matrix)
{
#pragma omp for
for(i=0;i<rows;i++){
for(j=i;j<rows;j++){
xi = (double*) malloc(columns * sizeof(double));
xj = (double*) malloc(columns * sizeof(double));
/* construct callback input numpy arrays*/
getVector(xi, data, i, columns);
getVector(xj, data, j, columns);
matrix[j+rows*i] = kerEval(kernel,kerargs,xi,xj,columns);
if(i!=j) matrix[i+rows*j] = matrix[j+rows*i];
free(xi);
free(xj);
}
}
}
np_matrix = PyArray_SimpleNewFromData(2, mat_dim,
NPY_DOUBLE, matrix);
/***** end of output matrix construction *****/
/*********************************
* clean up and return the result *
*********************************/
Py_INCREF(np_matrix);
return np_matrix;
NpyIter_Deallocate(in_iter);
/* in case bad things happen */
fail:
Py_XDECREF(np_matrix);
return NULL;
free(data);
free(matrix);
}
/*
* Returns a boolean array with True for input dates which are valid
* business days, and False for dates which are not. This is the
* low-level function which requires already cleaned input data.
*
* dates: An array of dates with 'datetime64[D]' data type.
* out: Either NULL, or an array with 'bool' data type
* in which to place the resulting dates.
* weekmask: A 7-element boolean mask, 1 for possible business days and 0
* for non-business days.
* busdays_in_weekmask: A count of how many 1's there are in weekmask.
* holidays_begin/holidays_end: A sorted list of dates matching '[D]'
* unit metadata, with any dates falling on a day of the
* week without weekmask[i] == 1 already filtered out.
*/
NPY_NO_EXPORT PyArrayObject *
is_business_day(PyArrayObject *dates, PyArrayObject *out,
npy_bool *weekmask, int busdays_in_weekmask,
npy_datetime *holidays_begin, npy_datetime *holidays_end)
{
PyArray_DatetimeMetaData temp_meta;
PyArray_Descr *dtypes[2] = {NULL, NULL};
NpyIter *iter = NULL;
PyArrayObject *op[2] = {NULL, NULL};
npy_uint32 op_flags[2], flags;
PyArrayObject *ret = NULL;
if (busdays_in_weekmask == 0) {
PyErr_SetString(PyExc_ValueError,
"the business day weekmask must have at least one "
"valid business day");
return NULL;
}
/* First create the data types for the dates and the bool output */
temp_meta.base = NPY_FR_D;
temp_meta.num = 1;
dtypes[0] = create_datetime_dtype(NPY_DATETIME, &temp_meta);
if (dtypes[0] == NULL) {
goto fail;
}
dtypes[1] = PyArray_DescrFromType(NPY_BOOL);
if (dtypes[1] == NULL) {
goto fail;
}
/* Set up the iterator parameters */
flags = NPY_ITER_EXTERNAL_LOOP|
NPY_ITER_BUFFERED|
NPY_ITER_ZEROSIZE_OK;
op[0] = dates;
op_flags[0] = NPY_ITER_READONLY | NPY_ITER_ALIGNED;
op[1] = out;
op_flags[1] = NPY_ITER_WRITEONLY | NPY_ITER_ALLOCATE | NPY_ITER_ALIGNED;
/* Allocate the iterator */
iter = NpyIter_MultiNew(2, op, flags, NPY_KEEPORDER, NPY_SAFE_CASTING,
op_flags, dtypes);
if (iter == NULL) {
goto fail;
}
/* Loop over all elements */
if (NpyIter_GetIterSize(iter) > 0) {
NpyIter_IterNextFunc *iternext;
char **dataptr;
npy_intp *strideptr, *innersizeptr;
iternext = NpyIter_GetIterNext(iter, NULL);
if (iternext == NULL) {
goto fail;
}
dataptr = NpyIter_GetDataPtrArray(iter);
strideptr = NpyIter_GetInnerStrideArray(iter);
innersizeptr = NpyIter_GetInnerLoopSizePtr(iter);
do {
char *data_dates = dataptr[0];
char *data_out = dataptr[1];
npy_intp stride_dates = strideptr[0];
npy_intp stride_out = strideptr[1];
npy_intp count = *innersizeptr;
npy_datetime date;
int day_of_week;
while (count--) {
/* Check if it's a business day */
date = *(npy_datetime *)data_dates;
day_of_week = get_day_of_week(date);
*(npy_bool *)data_out = weekmask[day_of_week] &&
!is_holiday(date,
holidays_begin, holidays_end) &&
date != NPY_DATETIME_NAT;
data_dates += stride_dates;
data_out += stride_out;
}
} while (iternext(iter));
}
/* Get the return object from the iterator */
ret = NpyIter_GetOperandArray(iter)[1];
Py_INCREF(ret);
goto finish;
fail:
Py_XDECREF(ret);
ret = NULL;
finish:
Py_XDECREF(dtypes[0]);
Py_XDECREF(dtypes[1]);
if (iter != NULL) {
if (NpyIter_Deallocate(iter) != NPY_SUCCEED) {
Py_XDECREF(ret);
ret = NULL;
}
}
return ret;
}
static PyObject *
geoutils_point_to_polygon_distance(
PyObject *self,
PyObject *args,
PyObject *keywds)
{
static char *kwlist[] = {"cxx", "cyy", /* polygon coords */
"pxx", "pyy", /* points coords */
NULL}; /* sentinel */
PyArrayObject *cxx, *cyy, *pxx, *pyy;
if (!PyArg_ParseTupleAndKeywords(args, keywds, "O!O!O!O!", kwlist,
// polygon coords
&PyArray_Type, &cxx, &PyArray_Type, &cyy,
// points coords
&PyArray_Type, &pxx, &PyArray_Type, &pyy))
return NULL;
PyArray_Descr *double_dtype = PyArray_DescrFromType(NPY_DOUBLE);
// we use the first iterator for iterating over edges of the polygon
PyArrayObject *op_c[5];
npy_uint32 op_flags_c[5];
npy_uint32 flags_c = 0;
NpyIter_IterNextFunc *iternext_c;
PyArray_Descr *op_dtypes_c[] = {double_dtype, double_dtype, double_dtype,
double_dtype, double_dtype};
char **dataptrarray_c;
op_c[0] = cxx;
op_c[1] = cyy;
op_c[2] = NULL; /* length of the edge */
op_c[3] = NULL; /* cos theta (angle between x-axis and the
edge, counterclockwise) */
op_c[4] = NULL; /* sin theta */
op_flags_c[0] = op_flags_c[1] = NPY_ITER_READONLY;
op_flags_c[2] = op_flags_c[3] = op_flags_c[4] \
= NPY_ITER_WRITEONLY | NPY_ITER_ALLOCATE;
NpyIter *iter_c = NpyIter_MultiNew(
5, op_c, flags_c, NPY_KEEPORDER, NPY_NO_CASTING,
op_flags_c, op_dtypes_c);
if (iter_c == NULL) {
Py_DECREF(double_dtype);
return NULL;
}
iternext_c = NpyIter_GetIterNext(iter_c, NULL);
dataptrarray_c = NpyIter_GetDataPtrArray(iter_c);
double bcx, bcy, ecx, ecy, length, cos_theta, sin_theta;
// remember the "end point" of the first segment
ecx = *(double *) dataptrarray_c[0];
ecy = *(double *) dataptrarray_c[1];
// here we ignore the first iteration, this is intentional: we need
// to iterate over edges, not points
while (iternext_c(iter_c))
{
// bcx and bcy are coordinates of the "base point" of the current edge
// vector, ecx and ecy are ones of the "end point" of it
bcx = *(double *) dataptrarray_c[0];
bcy = *(double *) dataptrarray_c[1];
// get the free vector coordinates from the bound one
double vx = ecx - bcx;
double vy = ecy - bcy;
// calculate the length of the edge
length = sqrt(vx * vx + vy * vy);
// calculate cosine and sine of the angle between x-axis
// and the free vector, measured counterclockwise
cos_theta = vx / length;
sin_theta = vy / length;
*(double *) dataptrarray_c[2] = length;
*(double *) dataptrarray_c[3] = cos_theta;
*(double *) dataptrarray_c[4] = sin_theta;
// the "base point" of the current vector is in turn the "end point"
// of the next one
ecx = bcx;
ecy = bcy;
}
// second iterator is over the target points.
// we will collect distance in it as well.
PyArrayObject *op_p[3] = {pxx, pyy, NULL /* distance */};
npy_uint32 op_flags_p[3];
npy_uint32 flags_p = 0;
NpyIter_IterNextFunc *iternext_p;
PyArray_Descr *op_dtypes_p[] = {double_dtype, double_dtype, double_dtype};
char **dataptrarray_p;
op_flags_p[0] = op_flags_p[1] = NPY_ITER_READONLY;
op_flags_p[2] = NPY_ITER_WRITEONLY | NPY_ITER_ALLOCATE;
NpyIter *iter_p = NpyIter_MultiNew(
3, op_p, flags_p, NPY_KEEPORDER, NPY_NO_CASTING,
op_flags_p, op_dtypes_p);
Py_DECREF(double_dtype);
if (iter_p == NULL) {
NpyIter_Deallocate(iter_c);
return NULL;
}
iternext_p = NpyIter_GetIterNext(iter_p, NULL);
dataptrarray_p = NpyIter_GetDataPtrArray(iter_p);
do
{
// loop over points
// minimum distance found
double min_distance = INFINITY;
// point coordinates
double px = *(double *) dataptrarray_p[0];
double py = *(double *) dataptrarray_p[1];
// number of intersections between the ray, starting from the point
// and running along x-axis, with polygon edges. we use that to find
// out whether the point is lying inside the polygon or outside:
// zero or even number of intersections means that point is outside
int intersections = 0;
NpyIter_Reset(iter_c, NULL);
ecx = *(double *) dataptrarray_c[0];
ecy = *(double *) dataptrarray_c[1];
while (iternext_c(iter_c))
{
// loop over edges: again ignore the first iteration
bcx = *(double *) dataptrarray_c[0];
bcy = *(double *) dataptrarray_c[1];
length = *(double *) dataptrarray_c[2];
cos_theta = *(double *) dataptrarray_c[3];
sin_theta = *(double *) dataptrarray_c[4];
if ((px == bcx) && (py == bcy)) {
// point is equal to edge's beginning point, set number
// of intersections to "1", which means "point is inside"
// and quit the loop
intersections = 1;
break;
}
// here we want to check if the ray from the point rightwards
// intersects the current edge. this is only true if one of the
// points of the edge has ordinate equal to or greater than the
// current point's ordinate and another point has smaller one.
// note that we use non-strict equation for only one point: this
// way we don't count intersections for edges that lie on the
// ray and we don't count intersection twice if ray crosses one
// of polygon's vertices.
if (((bcy >= py) && (ecy < py)) || ((ecy >= py) && (bcy < py))) {
// checking for intersection is simple: we solve two line
// equations, where first one represents the edge and second
// one the ray. then we find the abscissa of intersection
// point and compare it to point's abscissa: if it is greater,
// than the edge crosses the ray.
double x_int;
if (cos_theta == 0) {
// edge is purely vertical, intersection point is equal
// to abscissa of any point belonging to it
x_int = bcx;
} else {
// edge's line equation is "y(x) = k*x + b". here "k"
// is the tangent of edge's inclination angle.
double k = sin_theta / cos_theta;
// find the "b" coefficient putting beginning point of the edge
// to the equation with known "k"
double b = bcy - k * bcx;
// find the abscissa of the intersection point between lines
x_int = (py - b) / k;
}
if (x_int > px)
// ray intersects the edge
intersections += 1;
else if (x_int == px) {
// point is lying on the edge, distance is zero, no need
// to continue the loop
intersections = 1;
break;
}
}
ecx = bcx;
ecy = bcy;
// now move the point to the coordinate space of the edge (where
// "base point" of the edge has coordinates (0, 0) and the edge
// itself goes along x axis) using affine transformations
// first translate the coordinates
double px2 = px - bcx;
double py2 = py - bcy;
// then rotate them
double dist_x = px2 * cos_theta + py2 * sin_theta;
double dist_y = - px2 * sin_theta + py2 * cos_theta;
// now dist_y is the perpendicular distance between the point
// and the line, containing the edge. it is negative in case
// when point lies on the right hand side of the edge vector.
// dist_x is the 1d coordinate of the projection of the point
// on that line. sign is negative if the projection is on the
// opposite side from the "end point" of the vector with respect
// to its "base point"
double dist;
if ((0 <= dist_x) && (dist_x <= length)) {
// if point projection falls inside the vector itself,
// the actual shortest distance to the vector is dist_y
dist = fabs(dist_y);
} else {
// otherwise we need to consider both dist_x and dist_y,
// combining them in Pythagorean formula
if (dist_x > length)
// point lies above the "end point" of the vector
// along the line, so closest x-distance to the vector
// is the distance to the end point
dist_x -= length;
dist = sqrt(dist_x * dist_x + dist_y * dist_y);
}
if (dist < min_distance)
// update the "minimum distance so far" variable if needed
min_distance = dist;
}
if (intersections & 0x01)
// odd number of intersections between the ray from the point
// and all the edges means that the point is inside the polygon
*(double *) dataptrarray_p[2] = 0;
else
*(double *) dataptrarray_p[2] = min_distance;
} while (iternext_p(iter_p));
PyArrayObject *result = NpyIter_GetOperandArray(iter_p)[2];
Py_INCREF(result);
if (NpyIter_Deallocate(iter_c) != NPY_SUCCEED
|| NpyIter_Deallocate(iter_p) != NPY_SUCCEED) {
Py_DECREF(result);
return NULL;
}
return (PyObject *) result;
}
