Method GDMRModelObject

src/python/handler/py_GDMR.cpp:20–76

}

GDMRModelObject::GDMRModelObject(size_t tw, size_t minCnt, size_t minDf, size_t rmTop,
	size_t k, PyObject* degrees, PyObject* alpha, float eta, float sigma, float sigma0, float alphaEps,
	float orderDecay, PyObject* range,
	PyObject* seed, PyObject* corpus, PyObject* transform)
{
	tomoto::GDMRArgs margs;
	margs.k = k;
	if (alpha) margs.alpha = broadcastObj<tomoto::Float>(alpha, margs.k,
		[&]() { return "`alpha` must be an instance of `float` or `List[float]` with length `k` (given " + py::repr(alpha) + ")"; }
	);
	margs.eta = eta;
	margs.sigma = sigma;
	margs.sigma0 = sigma0;
	margs.alphaEps = alphaEps;
	margs.orderDecay = orderDecay;
	if (seed && seed != Py_None && !py::toCpp<size_t>(seed, margs.seed))
	{
		throw py::ValueError{ "`seed` must be an integer or None." };
	}

	if (degrees && degrees != Py_None && !py::toCpp<vector<uint64_t>>(degrees, margs.degrees))
	{
		throw py::ValueError{ "`degrees` must be an iterable of int." };
	}

	auto inst = tomoto::IGDMRModel::create((tomoto::TermWeight)tw, margs);
	if (!inst) throw py::ValueError{ "unknown `tw` value" };
	this->inst = std::move(inst);
	this->isPrepared = false;
	this->seedGiven = !!seed;
	this->minWordCnt = minCnt;
	this->minWordDf = minDf;
	this->removeTopWord = rmTop;
	
	if (range && range != Py_None)
	{
		vector<tomoto::Float> vMin, vMax;
		py::UniqueObj rangeIter{ PyObject_GetIter(range) }, item;
		if (!rangeIter) throw py::ValueError{ "`metadata_range` must be a list of pairs." };
		while (item = py::UniqueObj{ PyIter_Next(rangeIter.get()) })
		{
			vector<tomoto::Float> r;
			if (!py::toCpp(item.get(), r))
			{
				throw py::ValueError{ "`metadata_range` must be a list of pairs." };
			}
			if (r.size() != 2) throw py::ValueError{ "`metadata_range` must be a list of pairs." };
			vMin.emplace_back(r[0]);
			vMax.emplace_back(r[1]);
		}
		if (vMin.size() != margs.degrees.size()) throw py::ValueError{ "`len(metadata_range)` must be equal to `len(degrees)`" };

		inst->setMdRange(vMin, vMax);
	}

	insertCorpus(corpus, transform);
}