Merge pull request #98 from bab2min/dev

fixed numpy version & fixed #62
bab2min · Mar 1, 2021 · ccae9aa · ccae9aa
2 parents 77fcff0 + c46e975
commit ccae9aa
Show file tree

Hide file tree

Showing 9 changed files with 56 additions and 54 deletions.
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -40,12 +40,12 @@ jobs:
         TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
-        /opt/python/cp38-cp38/bin/python -m pip install twine wheel numpy
+        /opt/python/cp38-cp38/bin/python -m pip install twine wheel numpy==`/opt/python/cp38-cp38/bin/python test/numpy_version.py`
         /opt/python/cp38-cp38/bin/python setup.py sdist
         /opt/python/cp38-cp38/bin/python -m twine upload dist/*.tar.gz
         for cp in cp35-cp35m cp36-cp36m cp37-cp37m cp38-cp38 cp39-cp39
         do
-          /opt/python/${cp}/bin/python -m pip install twine wheel numpy
+          /opt/python/${cp}/bin/python -m pip install twine wheel numpy==`/opt/python/${cp}/bin/python test/numpy_version.py`
           /opt/python/${cp}/bin/python setup.py build bdist_wheel
           auditwheel repair dist/*-${cp}-linux_x86_64.whl
         done
@@ -84,7 +84,7 @@ jobs:
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
         export AUDITWHEEL_PLAT=many
-        python -m pip install twine wheel numpy
+        python -m pip install twine wheel numpy==`python test/numpy_version.py`
         python setup.py bdist_wheel
         twine upload dist/*
 
@@ -122,6 +122,6 @@ jobs:
         TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
-        python -m pip install twine wheel numpy
+        python -m pip install twine wheel numpy==$(python test/numpy_version.py)
         python setup.py bdist_wheel
         twine upload dist/*
diff --git a/.github/workflows/deploy_test.yml b/.github/workflows/deploy_test.yml
@@ -39,12 +39,12 @@ jobs:
         TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
-        /opt/python/cp35-cp35m/bin/python -m pip install twine wheel numpy
+        /opt/python/cp35-cp35m/bin/python -m pip install twine wheel numpy==`/opt/python/cp35-cp35m/bin/python test/numpy_version.py`
         /opt/python/cp35-cp35m/bin/python setup.py sdist
         /opt/python/cp35-cp35m/bin/python -m twine upload --repository testpypi dist/*.tar.gz
         for cp in cp35-cp35m cp36-cp36m cp37-cp37m cp38-cp38
         do
-          /opt/python/${cp}/bin/python -m pip install twine wheel numpy
+          /opt/python/${cp}/bin/python -m pip install twine wheel numpy==`/opt/python/${cp}/bin/python test/numpy_version.py`
           /opt/python/${cp}/bin/python setup.py build bdist_wheel
           auditwheel repair dist/*-${cp}-linux_x86_64.whl
         done
@@ -83,7 +83,7 @@ jobs:
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
         export AUDITWHEEL_PLAT=many
-        python -m pip install twine wheel numpy
+        python -m pip install twine wheel numpy==`python test/numpy_version.py`
         python setup.py bdist_wheel
         twine upload --repository testpypi dist/*
 
@@ -121,6 +121,6 @@ jobs:
         TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
         TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
       run: |
-        python -m pip install twine wheel numpy
+        python -m pip install twine wheel numpy==$(python test/numpy_version.py)
         python setup.py bdist_wheel
         twine upload --repository testpypi dist/*
diff --git a/.github/workflows/generate_documentation.yml b/.github/workflows/generate_documentation.yml
@@ -39,7 +39,7 @@ jobs:
         mv variant/include/mapbox include/
     - name: build
       run: |
-        python3 -m pip install numpy
+        python3 -m pip install numpy==1.10.4
         python3 -m pip install pdoc3==0.8.4
         export TOMOTOPY_LANG=${{ matrix.language }}
         python3 setup.py install

diff --git a/.github/workflows/pull_request_test.yml b/.github/workflows/pull_request_test.yml
@@ -40,7 +40,7 @@ jobs:
         mv variant/include/mapbox include/
     - name: Build
       run: |
-        /opt/python/${{ matrix.cp }}/bin/python -m pip install numpy
+        /opt/python/${{ matrix.cp }}/bin/python -m pip install numpy==`/opt/python/${{ matrix.cp }}/bin/python test/numpy_version.py`
         /opt/python/${{ matrix.cp }}/bin/python setup.py build install
     - name: Test
       run: |
@@ -76,7 +76,7 @@ jobs:
         mv variant-1.1.3/include/mapbox include/
     - name: Build
       run: |
-        python -m pip install numpy
+        python -m pip install numpy==`python test/numpy_version.py`
         python setup.py build install
     - name: Test
       run: |
@@ -115,7 +115,7 @@ jobs:
         mv variant-1.1.3/include/mapbox include/
     - name: Build
       run: |
-        python -m pip install numpy
+        python -m pip install numpy==$(python test/numpy_version.py)
         python setup.py build install
     - name: Archive binary
       uses: actions/upload-artifact@v2

diff --git a/setup.py b/setup.py
@@ -93,10 +93,10 @@
         "Operating System :: POSIX",
         "Operating System :: MacOS"
     ],
-    install_requires=['numpy>=1.10.0'],
+    install_requires=['numpy>=1.11.0'],
     keywords='NLP,Topic Model',
 
-    packages = ['tomotopy'],
+    packages=['tomotopy'],
     include_package_data=True,
-    ext_modules = modules
+    ext_modules=modules
 )
diff --git a/src/TopicModel/HDPModel.hpp b/src/TopicModel/HDPModel.hpp
@@ -403,52 +403,40 @@ namespace tomoto
 			if (_tw != TermWeight::one) doc.wordWeights.resize(wordSize);
 		}
 
-		template<bool _Infer>
+		template<bool _infer>
 		void updateStateWithDoc(typename BaseClass::Generator& g, _ModelState& ld, _RandGen& rgs, _DocType& doc, size_t i) const
 		{
-			// generate tables for each topic when inferring
-			if (_Infer)
+			Tid t;
+			std::vector<double> dist;
+			dist.emplace_back(this->alpha);
+			for (auto& d : doc.numTopicByTable) dist.emplace_back(d.num);
+			std::discrete_distribution<Tid> ddist{ dist.begin(), dist.end() };
+			t = ddist(rgs);
+			if (t == 0)
 			{
-				if (i < this->K)
+				// new table
+				Tid k;
+				if (_infer)
 				{
-					Tid t = i;
-					if (isLiveTopic(i))
+					std::uniform_int_distribution<> theta{ 0, this->K - 1 };
+					do
 					{
-						t = doc.addNewTable(i);
-					}
-					else
-					{
-						t = std::uniform_int_distribution<size_t>{ 0, doc.getNumTable() - 1 }(rgs);
-					}
-					++ld.numTableByTopic[doc.numTopicByTable[t].topic];
-					++ld.totalTable;
-					doc.Zs[i] = t;
-				}
-				else doc.Zs[i] = std::uniform_int_distribution<size_t>{ 0, doc.getNumTable() - 1 }(rgs);
-			}
-			// generate tables following CRP
-			else
-			{
-				Tid t;
-				std::vector<double> dist;
-				dist.emplace_back(this->alpha);
-				for (auto& d : doc.numTopicByTable) dist.emplace_back(d.num);
-				std::discrete_distribution<Tid> ddist{ dist.begin(), dist.end() };
-				t = ddist(rgs);
-				if (t == 0)
-				{
-					// new table
-					Tid k = g.theta(rgs);
-					t = doc.addNewTable(k);
-					++ld.numTableByTopic[k];
-					++ld.totalTable;
+						k = theta(rgs);
+					} while (!isLiveTopic(k));
 				}
 				else
 				{
-					t -= 1;
+					k = g.theta(rgs);
 				}
-				doc.Zs[i] = t;
+				t = doc.addNewTable(k);
+				++ld.numTableByTopic[k];
+				++ld.totalTable;
+			}
+			else
+			{
+				t -= 1;
 			}
+			doc.Zs[i] = t;
 			addWordTo<1>(ld, doc, i, doc.words[i], doc.Zs[i], doc.numTopicByTable[doc.Zs[i]].topic);
 		}
 

diff --git a/src/TopicModel/TopicModel.hpp b/src/TopicModel/TopicModel.hpp
@@ -373,7 +373,7 @@ namespace tomoto
 		{
 			if (doc.words.empty()) return -1;
 			if (!doc.docUid.empty() && uidMap.count(doc.docUid))
-				throw exception::InvalidArgument{ "there is a document with uid = " + std::string{ doc.docUid } + " already." };
+				throw exception::InvalidArgument{ "there is a document with uid = '" + std::string{ doc.docUid } + "' already." };
 			size_t maxWid = *std::max_element(doc.words.begin(), doc.words.end());
 			if (vocabCf.size() <= maxWid)
 			{
@@ -383,7 +383,7 @@ namespace tomoto
 			for (auto w : doc.words) ++vocabCf[w];
 			std::unordered_set<Vid> uniq{ doc.words.begin(), doc.words.end() };
 			for (auto w : uniq) ++vocabDf[w];
-			uidMap.emplace(doc.docUid, docs.size());
+			if (!doc.docUid.empty()) uidMap.emplace(doc.docUid, docs.size());
 			docs.emplace_back(std::forward<_DocTy>(doc));
 			return docs.size() - 1;
 		}

diff --git a/src/Utils/SharedString.hpp b/src/Utils/SharedString.hpp
@@ -109,7 +109,7 @@ namespace tomoto
 
 		bool empty() const
 		{
-			return ptr == nullptr;
+			return ptr == nullptr || size() == 0;
 		}
 
 		operator std::string() const

diff --git a/test/numpy_version.py b/test/numpy_version.py
@@ -0,0 +1,14 @@
+
+def get_old_numpy_version():
+    import sys
+
+    py_version = sys.version_info
+    if py_version >= (3, 9): return '1.20.0'
+    if py_version >= (3, 8): return '1.18.0'
+    if py_version >= (3, 7): return '1.15.0'
+    if py_version >= (3, 6): return '1.12.0'
+    if py_version >= (3, 5): return '1.11.0'
+    return '1.10.0'
+
+if __name__ == '__main__':
+    print(get_old_numpy_version())