make release-tag: Merge branch 'main' into stable

Author: amontanez24

.github/workflows/integration.yml

@@ -6,7 +6,7 @@ on:
     types: [opened, reopened]
 
 jobs:
-  unit:
+  integration:
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:

HISTORY.md

@@ -1,5 +1,43 @@
 # History
 
+## v0.15.1 - 2024-08-13
+
+### Bugs Fixed
+
+* X-axis for the bar plot should be labeled `Value` instead of `Category` - Issue [#620](https://github.com/sdv-dev/SDMetrics/issues/620) by @R-Palazzo
+* LinAlgError when plotting data that is constant - Issue [#616](https://github.com/sdv-dev/SDMetrics/issues/616) by @R-Palazzo
+* Wrong chart title when generating a box plot for just the real data using `get_column_pair_plot()`  - Issue [#615](https://github.com/sdv-dev/SDMetrics/issues/615) by @R-Palazzo
+
+### New Features
+
+* Better error message when passing an SDV Metadata object - Issue [#610](https://github.com/sdv-dev/SDMetrics/issues/610) by @R-Palazzo
+* Check that every property score are index-free - Issue [#583](https://github.com/sdv-dev/SDMetrics/issues/583) by @R-Palazzo
+
+## v0.15.0 - 2024-07-15
+
+This release adds support for NumPy 2.0! Additionally, the visualization utilities no longer require both real and synthetic data to be provided, and they can now be used to visualize only real or only synthetic data.
+
+### Maintenance
+
+* Switch to using ruff for Python linting and code formatting - Issue [#536](https://github.com/sdv-dev/SDMetrics/issues/536) by @gsheni
+* Change job names in integration workflow to "integration" - Issue [#577](https://github.com/sdv-dev/SDMetrics/issues/577) by @rwedge
+* Cap numpy to less than 2.0.0 until SDMetrics supports - Issue [#591](https://github.com/sdv-dev/SDMetrics/issues/591) by @gsheni
+
+### Internal
+
+* Switch to using ruff for Python linting and code formatting - Issue [#536](https://github.com/sdv-dev/SDMetrics/issues/536) by @gsheni
+
+### New Features
+
+* Allow me to visualize just the real or synthetic data - Issue [#581](https://github.com/sdv-dev/SDMetrics/issues/581) by @lajohn4747
+* Update Referential Integrity metric to support NaNs in child column  - Issue [#587](https://github.com/sdv-dev/SDMetrics/issues/587) by @R-Palazzo
+* Add support for numpy 2.0.0 - Issue [#593](https://github.com/sdv-dev/SDMetrics/issues/593) by @R-Palazzo
+
+### Bugs Fixed
+
+* ColumnPairTrends score depends on the data index - Issue [#582](https://github.com/sdv-dev/SDMetrics/issues/582) by @R-Palazzo
+* Datetime columns set to Object pandas dtype breaks LSTMDetection - Issue [#584](https://github.com/sdv-dev/SDMetrics/issues/584) by @fealho
+
 ## v0.14.1 - 2024-05-13
 
 This release patches a bug on the `LSTMDetection` metric.

Makefile

@@ -80,14 +80,12 @@ install-develop: clean-build clean-pyc ## install the package in editable mode a
 # LINT TARGETS
 
 .PHONY: lint
-lint: ## check style with flake8 and isort
+lint:
 	invoke lint
 
 .PHONY: fix-lint
-fix-lint: ## fix lint issues using autoflake, autopep8, and isort
-	find sdmetrics tests -name '*.py' | xargs autoflake --in-place --remove-all-unused-imports --remove-unused-variables
-	autopep8 --in-place --recursive --aggressive sdmetrics tests
-	isort --apply --atomic sdmetrics tests
+fix-lint:
+	invoke fix-lint
 
 
 # TEST TARGETS

conda/meta.yaml

@@ -1,4 +1,4 @@
-{% set version = '0.14.1' %}
+{% set version = '0.15.1.dev1' %}
 
 package:
   name: "{{ name|lower }}"

latest_requirements.txt

@@ -1,7 +1,7 @@
 copulas==0.11.0
-numpy==1.26.4
+numpy==2.0.1
 pandas==2.2.2
-plotly==5.22.0
-scikit-learn==1.4.2
-scipy==1.13.0
-tqdm==4.66.4
+plotly==5.23.0
+scikit-learn==1.5.1
+scipy==1.13.1
+tqdm==4.66.5

pyproject.toml

@@ -76,32 +76,7 @@ dev = [
     'watchdog>=1.0.1,<5',
 
     # style check
-    'flake8>=3.7.7,<8',
-    'flake8-absolute-import>=1.0,<2',
-    'flake8-builtins>=1.5.3,<3',
-    'flake8-comprehensions>=3.6.1,<4',
-    'flake8-debugger>=4.0.0,<5',
-    'flake8-docstrings>=1.5.0,<2',
-    'flake8-eradicate>=1.1.0,<2',
-    'flake8-fixme>=1.1.1,<1.2',
-    'flake8-mock>=0.3,<1',
-    'flake8-multiline-containers>=0.0.18,<0.1',
-    'flake8-mutable>=1.2.0,<1.3',
-    'flake8-expression-complexity>=0.0.9,<0.1',
-    'flake8-print>=4.0.0,<4.1',
-    'flake8-pytest-style>=2.0.0,<3',
-    'flake8-quotes>=3.3.0,<4',
-    'flake8-sfs>=0.0.3,<2',
-    'flake8-variables-names>=0.0.4,<0.1',
-    'dlint>=0.11.0,<1',
-    'isort>=5.13.2,<6',
-    'pandas-vet>=0.2.3,<2024',
-    'pep8-naming>=0.12.1,<1',
-    'pydocstyle>=6.1.1,<7',
-
-    # fix style issues
-    'autoflake>=1.1,<3',
-    'autopep8>=1.4.3,<3',
+    'ruff>=0.3.2,<1',
 
     # distribute on PyPI
     'twine>=1.10.0,<6',
@@ -159,7 +134,7 @@ convention = 'google'
 add-ignore = ['D107', 'D407', 'D417']
 
 [tool.bumpversion]
-current_version = "0.14.1"
+current_version = "0.15.1.dev1"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',
@@ -199,3 +174,65 @@ replace = "version = '{new_version}'"
 [build-system]
 requires = ['setuptools', 'wheel']
 build-backend = "setuptools.build_meta"
+
+[tool.ruff]
+preview = true
+line-length = 100
+indent-width = 4
+src = ["sdmetrics"]
+exclude = [
+    "docs",
+    ".tox",
+    ".git",
+    "__pycache__",
+    ".ipynb_checkpoints",
+    "tasks.py",
+]
+
+[tool.ruff.lint]
+select = [
+    # Pyflakes
+    "F",
+    # Pycodestyle
+    "E",
+    "W",
+    # pydocstyle
+    "D",
+    # isort
+    "I001",
+    # print statements
+    "T201",
+    # pandas-vet
+    "PD"
+]
+ignore = [
+    "E501",
+    # pydocstyle
+    "D107",  # Missing docstring in __init__
+    "D417",   # Missing argument descriptions in the docstring, this is a bug from pydocstyle: https://github.com/PyCQA/pydocstyle/issues/449
+    "PD901",
+    "PD101",
+]
+
+[tool.ruff.format]
+quote-style = "single"
+indent-style = "space"
+preview = true
+docstring-code-format = true
+docstring-code-line-length = "dynamic"
+
+[tool.ruff.lint.isort]
+known-first-party = ["sdmetrics"]
+lines-between-types = 0
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401", "E402", "F403", "F405", "E501", "I001"]
+"errors.py" = ["D105"]
+"tests/**.py" = ["D", "W505"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 100
+max-line-length = 100

sdmetrics/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'MIT Data To AI Lab'
 __email__ = '[email protected]'
-__version__ = '0.14.1'
+__version__ = '0.15.1.dev1'
 
 import sys
 import warnings as python_warnings
@@ -15,7 +15,15 @@
 import pandas as pd
 
 from sdmetrics import (
-    column_pairs, demos, goal, multi_table, reports, single_column, single_table, timeseries)
+    column_pairs,
+    demos,
+    goal,
+    multi_table,
+    reports,
+    single_column,
+    single_table,
+    timeseries,
+)
 from sdmetrics.demos import load_demo
 
 __all__ = [

sdmetrics/base.py

@@ -1,4 +1,5 @@
 """BaseMetric class."""
+
 import numpy as np
 
 from sdmetrics.goal import Goal
@@ -97,8 +98,10 @@ def normalize(cls, raw_score):
             score = 1 / (1 + np.exp(-raw_score))
 
         if score is None or score < 0 or score > 1:
-            raise AssertionError(f'This should be unreachable. The score {score} should be'
-                                 f'a value between 0 and 1.')
+            raise AssertionError(
+                f'This should be unreachable. The score {score} should be'
+                f'a value between 0 and 1.'
+            )
 
         if cls.goal == Goal.MINIMIZE:
             return 1.0 - score

sdmetrics/column_pairs/__init__.py

@@ -2,11 +2,14 @@
 
 from sdmetrics.column_pairs.base import ColumnPairsMetric
 from sdmetrics.column_pairs.statistical.cardinality_boundary_adherence import (
-    CardinalityBoundaryAdherence)
+    CardinalityBoundaryAdherence,
+)
 from sdmetrics.column_pairs.statistical.contingency_similarity import ContingencySimilarity
 from sdmetrics.column_pairs.statistical.correlation_similarity import CorrelationSimilarity
 from sdmetrics.column_pairs.statistical.kl_divergence import (
-    ContinuousKLDivergence, DiscreteKLDivergence)
+    ContinuousKLDivergence,
+    DiscreteKLDivergence,
+)
 from sdmetrics.column_pairs.statistical.referential_integrity import ReferentialIntegrity
 
 __all__ = [

sdmetrics/column_pairs/statistical/__init__.py

@@ -1,11 +1,14 @@
 """Statistical Metrics to compare column pairs."""
 
 from sdmetrics.column_pairs.statistical.cardinality_boundary_adherence import (
-    CardinalityBoundaryAdherence)
+    CardinalityBoundaryAdherence,
+)
 from sdmetrics.column_pairs.statistical.contingency_similarity import ContingencySimilarity
 from sdmetrics.column_pairs.statistical.correlation_similarity import CorrelationSimilarity
 from sdmetrics.column_pairs.statistical.kl_divergence import (
-    ContinuousKLDivergence, DiscreteKLDivergence)
+    ContinuousKLDivergence,
+    DiscreteKLDivergence,
+)
 from sdmetrics.column_pairs.statistical.referential_integrity import ReferentialIntegrity
 
 __all__ = [