将二维 C 数组传递给 python numpy
Passing 2 dimensional C array to python numpy
我需要一些关于将 C 数组传递给 python(numpy) 的帮助。
我有双打 NumRows x NumInputs 的二维数组,似乎 PyArray_SimpleNewFromData
没有以正确的方式转换它 - 很难看到,因为调试器没有显示太多,只有指针。
传递二维数组的正确方法是什么?
int NumRows = X_test.size();
int NumInputs = X_test_row.size();
double **X_test2 = new double*[NumRows];
for(int i = 0; i < NumRows; ++i)
{
X_test2[i] = new double[NumInputs];
}
for(int r = 0; r < NumRows; ++r)
{
for(int c = 0; c < NumInputs; ++c)
{
X_test2[r][c] = X_test[r][c];
}
}
const char *ScriptFName = "100-ABN-PREDICT";
char *FunctionName=NULL;
FunctionName="PredictGBC_DBG";
npy_intp Dims[2];
Dims[0]= NumRows;
Dims[1] = NumInputs;
PyObject *ArgsArray;
PyObject *pName, *pModule, *pDict, *pFunc, *pValue, *pArgs;
int row, col, rows, cols, size, type;
const double* outArray;
double ArrayItem;
//===================
Py_Initialize();
pName = PyBytes_FromString(ScriptFName);
pModule = PyImport_ImportModule(ScriptFName);
if (pModule != NULL)
{
import_array(); // Required for the C-API
ArgsArray = PyArray_SimpleNewFromData (2, Dims, NPY_DOUBLE, X_test2);//SOMETHING WRONG
pDict = PyModule_GetDict(pModule);
pArgs = PyTuple_New (1);
PyTuple_SetItem (pArgs, 0, ArgsArray);
pFunc = PyDict_GetItemString(pDict, FunctionName);
if (pFunc && PyCallable_Check(pFunc))
{
pValue = PyObject_CallObject(pFunc, pArgs);//CRASHING HERE
if (pValue != NULL)
{
rows = PyArray_DIM(pValue, 0);
cols = PyArray_DIM(pValue, 1);
size = PyArray_SIZE(pValue);
type = PyArray_TYPE(pValue);
// get direct access to the array data
//PyObject* m_obj;
outArray = static_cast<const double*>(PyArray_DATA(pValue));
for (row=0; row < rows; row++)
{
ArrayItem = outArray[row];
y_pred.push_back(ArrayItem);
}
}
else
{
y_pred.push_back(EMPTY_VAL);
}
}
else
{
PyErr_Print();
}//pFunc && PyCallable_Check(pFunc)
}//(pModule!=NULL
else
{
PyErr_SetString(PyExc_TypeError, "Cannot call function ?!");
PyErr_Print();
}
Py_DECREF(pValue);
Py_DECREF(pFunc);
Py_DECREF(ArgsArray);
Py_DECREF(pModule);
Py_DECREF(pName);
Py_Finalize ();
您必须将数据复制到连续的内存块。为了表示二维数组,numpy 不使用指向一维数组的指针数组。 Numpy 希望数组存储在连续的内存块中,在(默认情况下)row major order.
如果您使用 PyArray_SimpleNew(...)
创建数组,numpy 会为您分配内存。您必须将 X_test2
复制到此数组,例如,在行上循环使用 std::memcpy
或 std::copy
。
也就是这样改:
ArgsArray = PyArray_SimpleNewFromData (2, Dims, NPY_DOUBLE, X_test2);//SOMETHING WRONG
像这样:
// PyArray_SimpleNew allocates the memory needed for the array.
ArgsArray = PyArray_SimpleNew(2, Dims, NPY_DOUBLE);
// The pointer to the array data is accessed using PyArray_DATA()
double *p = (double *) PyArray_DATA(ArgsArray);
// Copy the data from the "array of arrays" to the contiguous numpy array.
for (int k = 0; k < NumRows; ++k) {
memcpy(p, X_test2[k], sizeof(double) * NumInputs);
p += NumInputs;
}
(看起来 X_test2
是 X_test
的副本,所以你可能想修改上面的代码以直接从 X_test
复制到 numpy 数组。)
我需要一些关于将 C 数组传递给 python(numpy) 的帮助。
我有双打 NumRows x NumInputs 的二维数组,似乎 PyArray_SimpleNewFromData
没有以正确的方式转换它 - 很难看到,因为调试器没有显示太多,只有指针。
传递二维数组的正确方法是什么?
int NumRows = X_test.size();
int NumInputs = X_test_row.size();
double **X_test2 = new double*[NumRows];
for(int i = 0; i < NumRows; ++i)
{
X_test2[i] = new double[NumInputs];
}
for(int r = 0; r < NumRows; ++r)
{
for(int c = 0; c < NumInputs; ++c)
{
X_test2[r][c] = X_test[r][c];
}
}
const char *ScriptFName = "100-ABN-PREDICT";
char *FunctionName=NULL;
FunctionName="PredictGBC_DBG";
npy_intp Dims[2];
Dims[0]= NumRows;
Dims[1] = NumInputs;
PyObject *ArgsArray;
PyObject *pName, *pModule, *pDict, *pFunc, *pValue, *pArgs;
int row, col, rows, cols, size, type;
const double* outArray;
double ArrayItem;
//===================
Py_Initialize();
pName = PyBytes_FromString(ScriptFName);
pModule = PyImport_ImportModule(ScriptFName);
if (pModule != NULL)
{
import_array(); // Required for the C-API
ArgsArray = PyArray_SimpleNewFromData (2, Dims, NPY_DOUBLE, X_test2);//SOMETHING WRONG
pDict = PyModule_GetDict(pModule);
pArgs = PyTuple_New (1);
PyTuple_SetItem (pArgs, 0, ArgsArray);
pFunc = PyDict_GetItemString(pDict, FunctionName);
if (pFunc && PyCallable_Check(pFunc))
{
pValue = PyObject_CallObject(pFunc, pArgs);//CRASHING HERE
if (pValue != NULL)
{
rows = PyArray_DIM(pValue, 0);
cols = PyArray_DIM(pValue, 1);
size = PyArray_SIZE(pValue);
type = PyArray_TYPE(pValue);
// get direct access to the array data
//PyObject* m_obj;
outArray = static_cast<const double*>(PyArray_DATA(pValue));
for (row=0; row < rows; row++)
{
ArrayItem = outArray[row];
y_pred.push_back(ArrayItem);
}
}
else
{
y_pred.push_back(EMPTY_VAL);
}
}
else
{
PyErr_Print();
}//pFunc && PyCallable_Check(pFunc)
}//(pModule!=NULL
else
{
PyErr_SetString(PyExc_TypeError, "Cannot call function ?!");
PyErr_Print();
}
Py_DECREF(pValue);
Py_DECREF(pFunc);
Py_DECREF(ArgsArray);
Py_DECREF(pModule);
Py_DECREF(pName);
Py_Finalize ();
您必须将数据复制到连续的内存块。为了表示二维数组,numpy 不使用指向一维数组的指针数组。 Numpy 希望数组存储在连续的内存块中,在(默认情况下)row major order.
如果您使用 PyArray_SimpleNew(...)
创建数组,numpy 会为您分配内存。您必须将 X_test2
复制到此数组,例如,在行上循环使用 std::memcpy
或 std::copy
。
也就是这样改:
ArgsArray = PyArray_SimpleNewFromData (2, Dims, NPY_DOUBLE, X_test2);//SOMETHING WRONG
像这样:
// PyArray_SimpleNew allocates the memory needed for the array.
ArgsArray = PyArray_SimpleNew(2, Dims, NPY_DOUBLE);
// The pointer to the array data is accessed using PyArray_DATA()
double *p = (double *) PyArray_DATA(ArgsArray);
// Copy the data from the "array of arrays" to the contiguous numpy array.
for (int k = 0; k < NumRows; ++k) {
memcpy(p, X_test2[k], sizeof(double) * NumInputs);
p += NumInputs;
}
(看起来 X_test2
是 X_test
的副本,所以你可能想修改上面的代码以直接从 X_test
复制到 numpy 数组。)