Fixed build and test failures

myui · myui · commit a7b4201f9440 · 2024-09-19T11:06:03.000+09:00
diff --git a/.gitignore b/.gitignore
@@ -1,125 +1,12 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-
-# C extensions
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-share/python-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-MANIFEST
-
-# PyInstaller
-#  Usually these files are written by a python script from a template
-#  before PyInstaller builds the exe, so as to inject date/other infos into it.
-*.manifest
-*.spec
-
-# Installer logs
-pip-log.txt
-pip-delete-this-directory.txt
+*.lock
 
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-*.py,cover
-.hypothesis/
-.pytest_cache/
-cover/
-
-# Translations
-*.mo
-*.pot
-
-# Django stuff:
-*.log
-local_settings.py
-db.sqlite3
-db.sqlite3-journal
-
-# Flask stuff:
-instance/
-.webassets-cache
-
-# Scrapy stuff:
-.scrapy
-
-# Sphinx documentation
-docs/_build/
-
-# PyBuilder
-.pybuilder/
+# Generated by Cargo
+# will have compiled files and executables
+debug/
 target/
 
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# pyenv
-#   For a library or package, you might want to ignore these files since the code is
-#   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-
-# pipenv
-#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
-#   However, in case of collaboration, if having platform-specific dependencies or dependencies
-#   having no cross-platform support, pipenv may install dependencies that don't work, or not
-#   install all needed dependencies.
-#Pipfile.lock
-
-# poetry
-#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
-#   This is especially recommended for binary packages to ensure reproducibility, and is more
-#   commonly ignored for libraries.
-#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-#poetry.lock
-
-# pdm
-#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
-#pdm.lock
-#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
-#   in version control.
-#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
-.pdm.toml
-.pdm-python
-.pdm-build/
-
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-__pypackages__/
-
-# Celery stuff
-celerybeat-schedule
-celerybeat.pid
-
-# SageMath parsed files
-*.sage.py
+# These are backup files generated by rustfmt
+**/*.rs.bk
 
 # Environments
 .env
@@ -129,34 +16,12 @@ venv/
 ENV/
 env.bak/
 venv.bak/
+.python-version
 
-# Spyder project settings
-.spyderproject
-.spyproject
-
-# Rope project settings
-.ropeproject
-
-# mkdocs documentation
-/site
-
-# mypy
-.mypy_cache/
-.dmypy.json
-dmypy.json
-
-# Pyre type checker
-.pyre/
-
-# pytype static type analyzer
-.pytype/
-
-# Cython debug symbols
-cython_debug/
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
 
-# PyCharm
-#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
-#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
-#  and can be added to the global gitignore or merged into this file.  For a more nuclear
-#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
+# C extensions
+*.so
diff --git a/Cargo.toml b/Cargo.toml
@@ -1,18 +1,19 @@
 [package]
-name = "slim_mse"
+name = "rtrec"
 version = "0.1.0"
-edition = "2018"
+edition = "2021"
 
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 [lib]
 name = "rtrec"  # This should match the module name
-path = "src/rtrec/lib.rs"
+path = "src/lib.rs"
 crate-type = ["cdylib"]
 
 [dependencies]
-ndarray = "0.15" # For numerical operations
+# ndarray = "0.15"
 
 [dependencies.pyo3]
-version = "0.18"
+version = "0.19"
 features = ["extension-module"]
 
 [package.metadata.maturin]
diff --git a/dockerfiles/requirements.txt b/dockerfiles/requirements.txt
@@ -2,9 +2,7 @@ numpy
 scipy
 scikit-learn
 pandas
-matplotlib
-
-hnswlib
+#hnswlib
 
 pytest
 
@@ -16,3 +14,4 @@ jupyter
 jupyterlab
 ipywidgets
 
+matplotlib
diff --git a/pyproject.toml b/pyproject.toml
@@ -5,14 +5,32 @@ description = "An realtime recommendation system supporting online updates"
 authors = [
     { name = "myui", email = "myui@apache.org" }
 ]
-dependencies = [
-    "cython>=3.0.11",
-    "numpy>=2.1.0",
-    "pandas>=2.2.2"
-]
 readme = "README.md"
 requires-python = ">= 3.8"
+dependencies = [
+    "numpy>=2.1.1",
+    "scipy>=1.14.1",
+    "scikit-learn>=1.5.2",
+    "pandas>=2.2.2",
+]
+
+[project.urls]
+homepage = "https://github.com/myui/rtrec"
+repository = "https://github.com/myui/rtrec"
 
 [build-system]
-requires = ["maturin>=0.13"]
+requires = ["maturin>=0.13,<2.0"]
 build-backend = "maturin"
+
+[tool.rye]
+managed = true
+dev-dependencies = [
+    "pytest>=8.3.3",
+]
+
+[tool.maturin]
+python-source = "."
+module-name = "rtrec._lowlevel"
+
+# "extension-module" tells pyo3 we want to build an extension module (skips linking against libpython.so)
+features = ["pyo3/extension-module"]
diff --git a/pytest.ini b/pytest.ini
@@ -0,0 +1,2 @@
+[pytest]
+pythonpath = .
diff --git a/rtrec/__init__.py b/rtrec/__init__.py
@@ -0,0 +1,3 @@
+from rtrec._lowlevel import SlimMSE
+
+__all__ = ["SlimMSE"]
diff --git a/rtrec/utils/datasets.py b/rtrec/utils/datasets.py
@@ -23,7 +23,7 @@ def get_user_items(self, user_id: int) -> Counter[float]:
         """
         return self.interactions.get(user_id, self.empty)
 
-    def get_user_item_rating(self, user_id: int, item_id: int, default_count: float = 0.0) -> float:
+    def get_user_item_count(self, user_id: int, item_id: int, default_count: float = 0.0) -> float:
         """
         Get the interaction count for a specific user-item pair.
         """
diff --git a/rtrec/utils/matrix.py b/rtrec/utils/matrix.py
@@ -46,7 +46,6 @@ def row_sum(self, row: int) -> float:
     def get_column(self, col: int) -> List[float]:
         return [self.data.get((row, col), 0) for row in range(self.max_row)]
 
-    @DeprecationWarning
     def to_csr(self) -> csr_matrix:
         if not self.data:
             return csr_matrix((0, 0))
diff --git a/src/datasets.rs b/src/datasets.rs
diff --git a/src/ftrl.rs b/src/ftrl.rs
diff --git a/src/lib.rs b/src/lib.rs
@@ -6,7 +6,7 @@ use slim::SlimMSE;
 use pyo3::prelude::*;
 
 #[pymodule]
-fn rtrec(_py: Python, m: &PyModule) -> PyResult<()> {
+fn _lowlevel(_py: Python, m: &PyModule) -> PyResult<()> {
     m.add_class::<SlimMSE>()?;
     Ok(())
 }
diff --git a/src/rtrec/mod.rs b/src/rtrec/mod.rs
diff --git a/src/slim.rs b/src/slim.rs
diff --git a/tests/test_slim_rs.py b/tests/test_slim_rs.py
@@ -0,0 +1,67 @@
+import pytest
+from rtrec import SlimMSE  # Ensure this matches the module name in your Rust crate.
+
+@pytest.fixture
+def slim():
+    # Create a SlimMse instance with example hyperparameters
+    return SlimMSE(alpha=0.1, beta=1.0, lambda1=0.0002, lambda2=0.0001)
+
+def test_fit(slim):
+    # Sample user interactions for fitting
+    interactions = [
+        (0, 1, 5.0),
+        (0, 2, 3.0),
+        (1, 1, 4.0),
+        (1, 3, 2.0)
+    ]
+    # Fit the model with sample interactions
+    slim.fit(interactions)
+
+    # Check empirical loss is greater than 0 after fitting
+    assert slim.get_empirical_loss() > 0.0
+
+def test_predict_rating(slim):
+    # Add interactions
+    interactions = [
+        (0, 1, 5.0),
+        (0, 2, 3.0),
+    ]
+    slim.fit(interactions)
+
+    # Predict rating for a known interaction
+    predicted_rating = slim.predict_rating(0, 1)
+    assert isinstance(predicted_rating, float)
+
+def test_recommend(slim):
+    # Add interactions
+    interactions = [
+        (0, 1, 5.0),
+        (0, 2, 3.0),
+        (0, 3, 4.0)
+    ]
+    slim.fit(interactions)
+
+    # Get top-k recommendations for a user
+    recommendations = slim.recommend(0, top_k=2)
+
+    # Check that we have the correct number of recommendations
+    assert len(recommendations) == 2
+    # Ensure the recommendations are a list of integers
+    assert all(isinstance(item_id, int) for item_id in recommendations)
+
+def test_get_empirical_loss(slim):
+    # Before any interaction, empirical loss should be zero
+    assert slim.get_empirical_loss() == 0.0
+
+    # Add interactions
+    interactions = [
+        (0, 1, 5.0),
+        (0, 2, 3.0),
+    ]
+    slim.fit(interactions)
+
+    # Check empirical loss is greater than 0
+    assert slim.get_empirical_loss() > 0.0
+
+if __name__ == "__main__":
+    pytest.main()
diff --git a/tests/utils/test_regularization.py b/tests/utils/test_regularization.py

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	`+from rtrec._lowlevel import SlimMSE`
	`2`	`+`
	`3`	`+__all__ = ["SlimMSE"]`