Merge pull request #19 from bab2min/develop

Develop

README.kr.rst

@@ -30,7 +30,7 @@ tomotopy 란?
 
 더 자세한 정보는 https://bab2min.github.io/tomotopy/index.kr.html 에서 확인하시길 바랍니다.
 
-tomotopy의 가장 최신버전은 0.4.0 입니다.
+tomotopy의 가장 최신버전은 0.4.1 입니다.
 
 시작하기
 ---------------
@@ -197,6 +197,9 @@ tomotopy의 Python3 예제 코드는 https://github.com/bab2min/tomotopy/blob/ma
 
 역사
 -------
+* 0.4.1 (2019-11-27)
+    * `tomotopy.PLDAModel` 생성자의 버그를 수정했습니다.
+
 * 0.4.0 (2019-11-18)
     * `tomotopy.PLDAModel`와 `tomotopy.HLDAModel` 토픽 모델이 새로 추가되었습니다.
 

README.rst

@@ -31,7 +31,7 @@ The current version of `tomoto` supports several major topic models including
 
 Please visit https://bab2min.github.io/tomotopy to see more information.
 
-The most recent version of tomotopy is 0.4.0.
+The most recent version of tomotopy is 0.4.1.
 
 Getting Started
 ---------------
@@ -202,6 +202,9 @@ meaning you can use it for any reasonable purpose and remain in complete ownersh
 
 History
 -------
+* 0.4.1 (2019-11-27)
+    * A bug at init function of `tomotopy.PLDAModel` was fixed.
+
 * 0.4.0 (2019-11-18)
     * New models including `tomotopy.PLDAModel` and `tomotopy.HLDAModel` were added into the package.
 

setup.py

@@ -50,7 +50,7 @@
 setup(
     name='tomotopy',
 
-    version='0.4.0',
+    version='0.4.1',
 
     description='Tomoto, The Topic Modeling Tool for Python',
     long_description=long_description,

src/python/PyUtils.h

@@ -1,10 +1,14 @@
 #pragma once
 #include <Python.h>
+#include <frameobject.h>
 #include <type_traits>
 #include <vector>
 #include <tuple>
+#include <set>
 #include <limits>
 #include <exception>
+#include <string>
+#include <iostream>
 
 namespace py
 {
@@ -184,4 +188,36 @@ namespace py
 		}
 		return ret;
 	}
-}
+
+	class WarningLog
+	{
+		std::set<std::tuple<std::string, int, std::string>> printed;
+
+		WarningLog()
+		{
+		}
+	public:
+		static WarningLog& get()
+		{
+			thread_local WarningLog inst;
+			return inst;
+		}
+
+		void printOnce(std::ostream& ostr, const std::string& msg)
+		{
+			auto frame = PyEval_GetFrame();
+			auto key = std::make_tuple(
+				std::string{ PyUnicode_AsUTF8(frame->f_code->co_filename) }, 
+				PyFrame_GetLineNumber(frame),
+				msg);
+
+			if (!printed.count(key))
+			{
+				ostr << std::get<0>(key) << "(" << std::get<1>(key) << "): " << std::get<2>(key) << std::endl;
+				printed.insert(key);
+			}
+		}
+	};
+}
+
+#define PRINT_WARN(msg) do{ py::WarningLog::get().printOnce(std::cerr, msg); } while(0)

src/python/py_DMR.cpp

@@ -41,6 +41,7 @@ static PyObject* DMR_addDoc(TopicModelObject* self, PyObject* args, PyObject *kw
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::IDMRModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -71,6 +72,7 @@ static PyObject* DMR_makeDoc(TopicModelObject* self, PyObject* args, PyObject *k
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::IDMRModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };

src/python/py_LDA.cpp

@@ -42,6 +42,7 @@ static PyObject* LDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *kw
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::ILDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -70,6 +71,7 @@ static PyObject* LDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *k
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::ILDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };

src/python/py_LLDA.cpp

@@ -40,6 +40,7 @@ static PyObject* LLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *k
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::ILLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -48,9 +49,10 @@ static PyObject* LLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *k
 		vector<string> labels;
 		if(argLabels)
 		{
+			if (PyUnicode_Check(argLabels)) PRINT_WARN("[warn] 'labels' should be an iterable of str.");
 			if (!(iter2 = PyObject_GetIter(argLabels)))
 			{
-				throw runtime_error{ "words must be an iterable of str." };
+				throw runtime_error{ "'labels' must be an iterable of str." };
 			}
 			py::AutoReleaser arIter2{ iter2 };
 			labels = py::makeIterToVector<string>(iter2);
@@ -78,6 +80,7 @@ static PyObject* LLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::ILLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -86,9 +89,10 @@ static PyObject* LLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *
 		vector<string> labels;
 		if (argLabels)
 		{
+			if (PyUnicode_Check(argLabels)) PRINT_WARN("[warn] 'labels' should be an iterable of str.");
 			if (!(iter2 = PyObject_GetIter(argLabels)))
 			{
-				throw runtime_error{ "words must be an iterable of str." };
+				throw runtime_error{ "'labels' must be an iterable of str." };
 			}
 			py::AutoReleaser arIter2{ iter2 };
 			labels = py::makeIterToVector<string>(iter2);

src/python/py_MGLDA.cpp

@@ -44,6 +44,7 @@ static PyObject* MGLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::IMGLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -73,6 +74,7 @@ static PyObject* MGLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::IMGLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };

src/python/py_PLDA.cpp

@@ -11,7 +11,7 @@ static int PLDA_init(TopicModelObject *self, PyObject *args, PyObject *kwargs)
 	float alpha = 0.1, eta = 0.01, sigma = 1, alphaEpsilon = 1e-10;
 	size_t seed = random_device{}();
 	static const char* kwlist[] = { "tw", "min_cf", "rm_top", "latent_topics", "topics_per_label", "alpha", "eta", "seed", nullptr };
-	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|nnnnffffn", (char**)kwlist, &tw, &minCnt, &rmTop,
+	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|nnnnnffn", (char**)kwlist, &tw, &minCnt, &rmTop,
 		&numLatentTopics, &numTopicsPerLabel, &alpha, &eta, &seed)) return -1;
 	try
 	{
@@ -41,6 +41,7 @@ static PyObject* PLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *k
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::IPLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -49,9 +50,10 @@ static PyObject* PLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *k
 		vector<string> labels;
 		if(argLabels)
 		{
+			if (PyUnicode_Check(argLabels)) PRINT_WARN("[warn] 'labels' should be an iterable of str.");
 			if (!(iter2 = PyObject_GetIter(argLabels)))
 			{
-				throw runtime_error{ "words must be an iterable of str." };
+				throw runtime_error{ "'labels' must be an iterable of str." };
 			}
 			py::AutoReleaser arIter2{ iter2 };
 			labels = py::makeIterToVector<string>(iter2);
@@ -79,6 +81,7 @@ static PyObject* PLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::IPLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };
@@ -87,9 +90,10 @@ static PyObject* PLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *
 		vector<string> labels;
 		if (argLabels)
 		{
+			if (PyUnicode_Check(argLabels)) PRINT_WARN("[warn] 'labels' should be an iterable of str.");
 			if (!(iter2 = PyObject_GetIter(argLabels)))
 			{
-				throw runtime_error{ "words must be an iterable of str." };
+				throw runtime_error{ "'labels' must be an iterable of str." };
 			}
 			py::AutoReleaser arIter2{ iter2 };
 			labels = py::makeIterToVector<string>(iter2);

src/python/py_SLDA.cpp

@@ -115,6 +115,7 @@ static PyObject* SLDA_addDoc(TopicModelObject* self, PyObject* args, PyObject *k
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		if (self->isPrepared) throw runtime_error{ "cannot add_doc() after train()" };
 		auto* inst = static_cast<tomoto::ISLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "'words' must be an iterable of str." };
@@ -151,6 +152,7 @@ static PyObject* SLDA_makeDoc(TopicModelObject* self, PyObject* args, PyObject *
 	{
 		if (!self->inst) throw runtime_error{ "inst is null" };
 		auto* inst = static_cast<tomoto::ISLDAModel*>(self->inst);
+		if (PyUnicode_Check(argWords)) PRINT_WARN("[warn] 'words' should be an iterable of str.");
 		if (!(iter = PyObject_GetIter(argWords)))
 		{
 			throw runtime_error{ "words must be an iterable of str." };

tomotopy/documentation.kr.rst

@@ -16,7 +16,7 @@ tomotopy 란?
 * Hierarchical PA (`tomotopy.HPAModel`)
 * Correlated Topic Model (`tomotopy.CTModel`)
 
-tomotopy의 가장 최신버전은 0.4.0 입니다.
+tomotopy의 가장 최신버전은 0.4.1 입니다.
 
 .. image:: https://badge.fury.io/py/tomotopy.svg
 
@@ -239,6 +239,9 @@ tomotopy의 Python3 예제 코드는 https://github.com/bab2min/tomotopy/blob/ma
 
 역사
 -------
+* 0.4.1 (2019-11-27)
+    * `tomotopy.PLDAModel` 생성자의 버그를 수정했습니다.
+
 * 0.4.0 (2019-11-18)
     * `tomotopy.PLDAModel`와 `tomotopy.HLDAModel` 토픽 모델이 새로 추가되었습니다.
 

tomotopy/documentation.rst

@@ -16,7 +16,7 @@ The current version of `tomoto` supports several major topic models including
 * Hierarchical PA (`tomotopy.HPAModel`)
 * Correlated Topic Model (`tomotopy.CTModel`).
 
-The most recent version of tomotopy is 0.4.0.
+The most recent version of tomotopy is 0.4.1.
 
 .. image:: https://badge.fury.io/py/tomotopy.svg
 
@@ -242,6 +242,9 @@ meaning you can use it for any reasonable purpose and remain in complete ownersh
 
 History
 -------
+* 0.4.1 (2019-11-27)
+    * A bug at init function of `tomotopy.PLDAModel` was fixed.
+
 * 0.4.0 (2019-11-18)
     * New models including `tomotopy.PLDAModel` and `tomotopy.HLDAModel` were added into the package.