update docs & fixed grammar errors (#120)

README.kr.rst

@@ -254,6 +254,12 @@ tomotopy의 Python3 예제 코드는 https://github.com/bab2min/tomotopy/blob/ma
 
 역사
 -------
+* 0.12.1 (2021-06-20)
+    * `tomotopy.LDAModel.set_word_prior()`가 크래시를 발생시키던 문제를 해결했습니다.
+    * 이제 `tomotopy.LDAModel.perplexity`와 `tomotopy.LDAModel.ll_per_word`가 TermWeight가 ONE이 아닌 경우에도 정확한 값을 반환합니다.
+    * 용어가중치가 적용된 빈도수를 반환하는 `tomotopy.LDAModel.used_vocab_weighted_freq`가 추가되었습니다.
+    * 이제 `tomotopy.LDAModel.summary()`가 단어의 엔트로피뿐만 아니라, 용어 가중치가 적용된 단어의 엔트로피도 함께 보여줍니다.
+
 * 0.12.0 (2021-04-26)
     * 이제 `tomotopy.DMRModel`와 `tomotopy.GDMRModel`가 다중 메타데이터를 지원합니다. (https://github.com/bab2min/tomotopy/blob/main/examples/dmr_multi_label.py 참조)
     * `tomotopy.GDMRModel`의 성능이 개선되었습니다.

README.rst

@@ -260,6 +260,12 @@ meaning you can use it for any reasonable purpose and remain in complete ownersh
 
 History
 -------
+* 0.12.1 (2021-06-20)
+    * An issue where `tomotopy.LDAModel.set_word_prior()` causes a crash has been fixed.
+    * Now `tomotopy.LDAModel.perplexity` and `tomotopy.LDAModel.ll_per_word` return the accurate value when `TermWeight` is not `ONE`.
+    * `tomotopy.LDAModel.used_vocab_weighted_freq` was added, which returns term-weighted frequencies of words.
+    * Now `tomotopy.LDAModel.summary()` shows not only the entropy of words, but also the entropy of term-weighted words.
+
 * 0.12.0 (2021-04-26)
     * Now `tomotopy.DMRModel` and `tomotopy.GDMRModel` support multiple values of metadata (see https://github.com/bab2min/tomotopy/blob/main/examples/dmr_multi_label.py )
     * The performance of `tomotopy.GDMRModel` was improved.

src/TopicModel/LDAModel.hpp

@@ -1069,7 +1069,7 @@ namespace tomoto
 							++df[w];
 						}
 					}
-					totCf = accumulate(this->vocabCf.begin(), this->vocabCf.end(), 0);
+					totCf = std::accumulate(this->vocabCf.begin(), this->vocabCf.end(), 0);
 				}
 				if (_tw == TermWeight::idf)
 				{

src/python/py_CT.cpp

@@ -158,7 +158,7 @@ PyObject* Document_beta(DocumentObject* self, void* closure)
 {
 	return py::handleExc([&]() -> PyObject*
 	{
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `beta` field!" };
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `beta` field!" };
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };
 
 		if (auto ret = docVisit<tomoto::DocumentCTM>(self->getBoundDoc(), [](auto* doc)
@@ -168,6 +168,6 @@ PyObject* Document_beta(DocumentObject* self, void* closure)
 				logf
 			);
 		})) return ret;
-		throw py::AttributeError{ "doc doesn't has `beta` field!" };
+		throw py::AttributeError{ "doc has no `beta` field!" };
 	});
 }

src/python/py_DMR.cpp

@@ -262,7 +262,7 @@ PyObject* Document_DMR_multiMetadata(DocumentObject* self, void* closure)
 				return inst->getMultiMetadataDict().toWord(x);
 			});
 		})) return ret;
-		throw py::AttributeError{ "doc doesn't has `multi_metadata` field!" };
+		throw py::AttributeError{ "doc has no `multi_metadata` field!" };
 	});
 }
 

src/python/py_DT.cpp

@@ -277,15 +277,15 @@ PyObject* Document_eta(DocumentObject* self, void* closure)
 {
 	return py::handleExc([&]() -> PyObject*
 	{
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `eta` field!" };
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `eta` field!" };
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };
 
 		if (auto* ret = docVisit<tomoto::DocumentDTM>(self->getBoundDoc(), [](auto* doc)
 		{
 			return py::buildPyValue(doc->eta.array().data(), doc->eta.array().data() + doc->eta.array().size());
 		})) return ret;
 
-		throw py::AttributeError{ "doc doesn't has `eta` field!" };
+		throw py::AttributeError{ "doc has no `eta` field!" };
 	});
 }
 

src/python/py_LLDA.cpp

@@ -126,7 +126,7 @@ PyObject* Document_labels(DocumentObject* self, void* closure)
 {
 	return py::handleExc([&]()
 	{
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `labels` field!" };
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `labels` field!" };
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };
 
 		if (auto* ret = docVisit<tomoto::DocumentLLDA>(self->getBoundDoc(), [&](auto* doc)
@@ -146,7 +146,7 @@ PyObject* Document_labels(DocumentObject* self, void* closure)
 			return py::buildPyValue(r);
 		})) return ret;
 
-		throw py::AttributeError{ "doc doesn't has `labels` field!" };
+		throw py::AttributeError{ "doc has no `labels` field!" };
 	});
 }
 

src/python/py_utils.cpp

@@ -1136,7 +1136,7 @@ static PyObject* Document_Z(DocumentObject* self, void* closure)
 {
 	return py::handleExc([&]()
 	{
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `topics` field!" };
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `topics` field!" };
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };
 #ifdef TM_HLDA
 		if (auto* ret = Document_HLDA_Z(self, closure)) return ret;
@@ -1145,20 +1145,20 @@ static PyObject* Document_Z(DocumentObject* self, void* closure)
 		if (auto* ret = Document_HDP_Z(self, closure)) return ret;
 #endif
 		if (auto* ret = Document_LDA_Z(self, closure)) return ret;
-		throw py::AttributeError{ "doc doesn't has `topics` field!" };
+		throw py::AttributeError{ "doc has no `topics` field!" };
 	});
 }
 
 static PyObject* Document_metadata(DocumentObject* self, void* closure)
 {
 	return py::handleExc([&]()
 	{
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `metadata` field!" };
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `metadata` field!" };
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };
 #ifdef TM_DMR
 		if (auto* ret = Document_DMR_metadata(self, closure)) return ret;
 #endif
-		throw py::AttributeError{ "doc doesn't has `metadata` field!" };
+		throw py::AttributeError{ "doc has no `metadata` field!" };
 	});
 }
 

src/python/utils.h

@@ -254,13 +254,13 @@ PyObject* Document_##NAME(DocumentObject* self, void* closure)\
 {\
 	return py::handleExc([&]()\
 	{\
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `" #FIELD "` field!" };\
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `" #FIELD "` field!" };\
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };\
 		if (auto* ret = docVisit<DOCTYPE>(self->getBoundDoc(), [](auto* doc)\
 		{\
 			return py::buildPyValue(doc->FIELD);\
 		})) return ret;\
-		throw py::AttributeError{ "doc doesn't has `" #FIELD "` field!" };\
+		throw py::AttributeError{ "doc has no `" #FIELD "` field!" };\
 	});\
 }
 
@@ -269,7 +269,7 @@ PyObject* Document_##NAME(DocumentObject* self, void* closure)\
 {\
 	return py::handleExc([&]()\
 	{\
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `" #FIELD "` field!" };\
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `" #FIELD "` field!" };\
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };\
 		return docVisit<DOCTYPE>(self->getBoundDoc(), [](auto* doc)\
 		{\
@@ -283,13 +283,13 @@ PyObject* Document_##NAME(DocumentObject* self, void* closure)\
 {\
 	return py::handleExc([&]()\
 	{\
-		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc doesn't has `" #FIELD "` field!" };\
+		if (self->corpus->isIndependent()) throw py::AttributeError{ "doc has no `" #FIELD "` field!" };\
 		if (!self->doc) throw py::RuntimeError{ "doc is null!" };\
 		if (auto* ret = docVisit<DOCTYPE>(self->getBoundDoc(), [](auto* doc)\
 		{\
 			return buildPyValueReorder(doc->FIELD, doc->wOrder);\
 		})) return ret;\
-		throw py::AttributeError{ "doc doesn't has `" #FIELD "` field!" }; \
+		throw py::AttributeError{ "doc has no `" #FIELD "` field!" }; \
 	});\
 }
 

tomotopy/documentation.kr.rst

@@ -335,6 +335,12 @@ tomotopy의 Python3 예제 코드는 https://github.com/bab2min/tomotopy/blob/ma
 
 역사
 -------
+* 0.12.1 (2021-06-20)
+    * `tomotopy.LDAModel.set_word_prior()`가 크래시를 발생시키던 문제를 해결했습니다.
+    * 이제 `tomotopy.LDAModel.perplexity`와 `tomotopy.LDAModel.ll_per_word`가 TermWeight가 ONE이 아닌 경우에도 정확한 값을 반환합니다.
+    * 용어가중치가 적용된 빈도수를 반환하는 `tomotopy.LDAModel.used_vocab_weighted_freq`가 추가되었습니다.
+    * 이제 `tomotopy.LDAModel.summary()`가 단어의 엔트로피뿐만 아니라, 용어 가중치가 적용된 단어의 엔트로피도 함께 보여줍니다.
+
 * 0.12.0 (2021-04-26)
     * 이제 `tomotopy.DMRModel`와 `tomotopy.GDMRModel`가 다중 메타데이터를 지원합니다. (https://github.com/bab2min/tomotopy/blob/main/examples/dmr_multi_label.py 참조)
     * `tomotopy.GDMRModel`의 성능이 개선되었습니다.

tomotopy/documentation.rst

@@ -339,6 +339,12 @@ meaning you can use it for any reasonable purpose and remain in complete ownersh
 
 History
 -------
+* 0.12.1 (2021-06-20)
+    * An issue where `tomotopy.LDAModel.set_word_prior()` causes a crash has been fixed.
+    * Now `tomotopy.LDAModel.perplexity` and `tomotopy.LDAModel.ll_per_word` return the accurate value when `TermWeight` is not `ONE`.
+    * `tomotopy.LDAModel.used_vocab_weighted_freq` was added, which returns term-weighted frequencies of words.
+    * Now `tomotopy.LDAModel.summary()` shows not only the entropy of words, but also the entropy of term-weighted words.
+
 * 0.12.0 (2021-04-26)
     * Now `tomotopy.DMRModel` and `tomotopy.GDMRModel` support multiple values of metadata (see https://github.com/bab2min/tomotopy/blob/main/examples/dmr_multi_label.py )
     * The performance of `tomotopy.GDMRModel` was improved.