float simple_liner_regression(np::ndarray a, np::ndarray b, np::ndarray c) {
int nd1 = a.get_nd();
int nd2 = b.get_nd();
if (nd1 != 1 || nd2 != 1)
throw std::runtime_error("a and b must be 1-dimensional");
if ( (a.get_dtype() != np::dtype::get_builtin<double>()) ||
(b.get_dtype() != np::dtype::get_builtin<double>()) )
throw std::runtime_error("a and b must be float64 array");
size_t N = a.shape(0);
if ( N != b.shape(0) )
throw std::runtime_error(" a and b must be same size");
double *p = reinterpret_cast<double *>(a.get_data());
std::vector<float> x;
for(int i=0;i<N;i++) x.push_back(*p++);
double *q = reinterpret_cast<double *>(b.get_data());
std::vector<float> y;
for(int i=0;i<N;i++) y.push_back(*q++);
// 回帰系数の計算
float a1 = calc_covariance(x,y) / calc_variance(x);
float a0 = calc_mean(y) - a1 * calc_mean(x);
double *r = reinterpret_cast<double *>(c.get_data());
*r = a0; r++;
*r = a1;
}
// Here's a simple wrapper function for fill1. It requires that the passed
// NumPy array be exactly what we're looking for - no conversion from nested
// sequences or arrays with other data types, because we want to modify it
// in-place.
void wrap_fill1(np::ndarray const & array) {
if (array.get_dtype() != np::dtype::get_builtin<double>()) {
PyErr_SetString(PyExc_TypeError, "Incorrect array data type");
p::throw_error_already_set();
}
if (array.get_nd() != 2) {
PyErr_SetString(PyExc_TypeError, "Incorrect number of dimensions");
p::throw_error_already_set();
}
fill1(reinterpret_cast<double*>(array.get_data()),
array.shape(0), array.shape(1),
array.strides(0) / sizeof(double), array.strides(1) / sizeof(double));
}
float u_variance(np::ndarray a) {
int nd = a.get_nd();
if (nd != 1)
throw std::runtime_error("a must be 1-dimensional");
if (a.get_dtype() != np::dtype::get_builtin<double>())
throw std::runtime_error("a must be float64 array");
size_t N = a.shape(0);
double *p = reinterpret_cast<double *>(a.get_data());
std::vector<float> x;
for(int i=0;i<N;i++) x.push_back(*p++);
return calc_u_variance(x);
}
float covariance(np::ndarray a, np::ndarray b) {
int nd1 = a.get_nd();
int nd2 = b.get_nd();
if (nd1 != 1 || nd2 != 1)
throw std::runtime_error("a and b must be 1-dimensional");
if ( (a.get_dtype() != np::dtype::get_builtin<double>()) ||
(b.get_dtype() != np::dtype::get_builtin<double>()) )
throw std::runtime_error("a and b must be float64 array");
size_t N = a.shape(0);
if ( N != b.shape(0) )
throw std::runtime_error(" a and b must be same size");
double *p = reinterpret_cast<double *>(a.get_data());
std::vector<float> x;
for(int i=0;i<N;i++) x.push_back(*p++);
double *q = reinterpret_cast<double *>(b.get_data());
std::vector<float> y;
for(int i=0;i<N;i++) y.push_back(*q++);
return calc_covariance(x,y);
}
// Here's the wrapper for fill2; it's a little more complicated because we need
// to check the flags and create the array of pointers.
void wrap_fill2(np::ndarray const & array) {
if (array.get_dtype() != np::dtype::get_builtin<double>()) {
PyErr_SetString(PyExc_TypeError, "Incorrect array data type");
p::throw_error_already_set();
}
if (array.get_nd() != 2) {
PyErr_SetString(PyExc_TypeError, "Incorrect number of dimensions");
p::throw_error_already_set();
}
if (!(array.get_flags() & np::ndarray::C_CONTIGUOUS)) {
PyErr_SetString(PyExc_TypeError, "Array must be row-major contiguous");
p::throw_error_already_set();
}
double * iter = reinterpret_cast<double*>(array.get_data());
int rows = array.shape(0);
int cols = array.shape(1);
boost::scoped_array<double*> ptrs(new double*[rows]);
for (int i = 0; i < rows; ++i, iter += cols) {
ptrs[i] = iter;
}
fill2(ptrs.get(), array.shape(0), array.shape(1));
}
