Merge pull request #56 from vc1492a/dev

merge dev into feature branch

.gitignore

@@ -6,12 +6,168 @@ nasaValve
 rel_research
 PyNomaly/loop_dev.py
 /PyNomaly.egg-info/
-.pytest_cache
-build
-htmlcov/
-*.egg
 *.pyc
-.coverage
 *.coverage.*
 .coveragerc
-venv/
+
+# 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
+
+# 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/
+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/#use-with-ide
+.pdm.toml
+
+# 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
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# 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/
+
+# 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/
+

tests/test_loop.py

@@ -51,6 +51,28 @@ def X_n8() -> np.ndarray:
  return X
 
 
+@pytest.fixture()
+def X_n20_scores() -> tuple[np.ndarray, np.ndarray]:
+ """
+ Fixture that returns a tuple containing a 20 element numpy array
+ and the precalculated loOP scores based on that array.
+ :return: tuple(input_data,exptected_scores)
+ """
+ input_data = np.array([0.02059752, 0.32629926, 0.63036653, 0.94409321,
+ 0.63251097, 0.47598494, 0.80204026, 0.34845067,
+ 0.81556468, 0.89183, 0.25210317, 0.11460502,
+ 0.19953434, 0.36955067, 0.06038041, 0.34527368,
+ 0.56621582, 0.90533649, 0.33773613, 0.71573306])
+
+ expected_scores = np.array([0.6356276742921594, 0.0, 0.0,
+ 0.48490790006974044, 0.0, 0.0, 0.0, 0.0,
+ 0.021728288376168012, 0.28285086151683225,
+ 0.0, 0.18881886507113213, 0.0, 0.0,
+ 0.45350246469681843, 0.0, 0.07886635748113013,
+ 0.3349068501560546, 0.0, 0.0])
+ return (input_data, expected_scores)
+
+
 @pytest.fixture()
 def X_n120() -> np.ndarray:
  """
@@ -122,6 +144,18 @@ def test_loop(X_n8) -> None:
  assert np.min(score[-2:]) > np.max(score[:-2])
 
 
+def test_regression(X_n20_scores) -> None:
+ """
+ Tests for potential regression errors by comparing current results
+ to the exptected results. Any changes to the code should still return
+ the same result given the same dataset
+ """
+ input_data, expected_scores = X_n20_scores
+ clf = loop.LocalOutlierProbability(input_data).fit()
+ scores = clf.local_outlier_probabilities
+ assert np.array_equal(scores, expected_scores)
+
+
 def test_loop_performance(X_n120) -> None:
  """
  Using a set of known anomalies (labels), tests the performance (using
@@ -170,7 +204,7 @@ def test_input_nodata(X_n140_outliers) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "Data or a distance matrix must be provided."
+ 0] == "Data or a distance matrix must be provided."
 
 
 def test_input_incorrect_type(X_n140_outliers) -> None:
@@ -192,8 +226,8 @@ def test_input_incorrect_type(X_n140_outliers) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "Argument 'n_neighbors' is not of type (<class 'int'>, " \
-  "<class 'numpy.integer'>)."
+ 0] == "Argument 'n_neighbors' is not of type (<class 'int'>, " \
+ "<class 'numpy.integer'>)."
 
 
 def test_input_neighbor_zero(X_n120) -> None:
@@ -213,7 +247,7 @@ def test_input_neighbor_zero(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "n_neighbors must be greater than 0. Fit with 10 instead."
+ 0] == "n_neighbors must be greater than 0. Fit with 10 instead."
 
 
 def test_input_distonly(X_n120) -> None:
@@ -236,8 +270,8 @@ def test_input_distonly(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "A neighbor index matrix and distance matrix must both " \
-  "be provided when not using raw input data."
+ 0] == "A neighbor index matrix and distance matrix must both " \
+ "be provided when not using raw input data."
 
 
 def test_input_neighboronly(X_n120) -> None:
@@ -260,7 +294,7 @@ def test_input_neighboronly(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "Data or a distance matrix must be provided."
+ 0] == "Data or a distance matrix must be provided."
 
 
 def test_input_too_many(X_n120) -> None:
@@ -284,8 +318,8 @@ def test_input_too_many(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "Only one of the following may be provided: data or a " \
-  "distance matrix (not both)."
+ 0] == "Only one of the following may be provided: data or a " \
+ "distance matrix (not both)."
 
 
 def test_distance_neighbor_shape_mismatch(X_n120) -> None:
@@ -318,8 +352,8 @@ def test_distance_neighbor_shape_mismatch(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "The shape of the distance and neighbor " \
-  "index matrices must match."
+ 0] == "The shape of the distance and neighbor " \
+ "index matrices must match."
 
 
 def test_input_neighbor_mismatch(X_n120) -> None:
@@ -345,10 +379,10 @@ def test_input_neighbor_mismatch(X_n120) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "The shape of the distance or " \
-  "neighbor index matrix does not " \
-  "match the number of neighbors " \
-  "specified."
+ 0] == "The shape of the distance or " \
+ "neighbor index matrix does not " \
+ "match the number of neighbors " \
+ "specified."
 
 
 def test_loop_dist_matrix(X_n120) -> None:
@@ -509,13 +543,13 @@ def test_missing_values() -> None:
  assert len(record_b) == 1
  # check that the message matches
  assert record_b[0].message.args[
-  0] == "Method does not support missing values in input data."
+ 0] == "Method does not support missing values in input data."
 
 
 def test_small_cluster_size(X_n140_outliers) -> None:
  """
- Test to ensure that the program exits when the specified number of neighbors
- is larger than the smallest cluster size in the input data.
+ Test to ensure that the program exits when the specified number of
+ neighbors is larger than the smallest cluster size in the input data.
  :param X_n140_outliers: A pytest Fixture that generates 140 observations.
  :return: None
  """
@@ -541,10 +575,10 @@ def test_small_cluster_size(X_n140_outliers) -> None:
  assert len(record_b) == 1
  # check that the message matches
  assert record_b[0].message.args[
-  0] == "Number of neighbors specified larger than smallest " \
-  "cluster. Specify a number of neighbors smaller than " \
-  "the smallest cluster size (observations in smallest " \
-  "cluster minus one)."
+ 0] == "Number of neighbors specified larger than smallest " \
+ "cluster. Specify a number of neighbors smaller than " \
+ "the smallest cluster size (observations in smallest " \
+ "cluster minus one)."
 
 
 def test_stream_fit(X_n140_outliers) -> None:
@@ -634,8 +668,8 @@ def test_stream_cluster(X_n140_outliers) -> None:
  assert len(record) == 1
  # check that the message matches
  assert record[0].message.args[
-  0] == "Stream approach does not support clustered data. " \
-  "Automatically refit using single cluster of points."
+ 0] == "Stream approach does not support clustered data. " \
+ "Automatically refit using single cluster of points."
 
 
 def test_stream_performance(X_n140_outliers) -> None: