Updates

.flake8

@@ -0,0 +1,8 @@
+[flake8]
+exclude = docs/*
+max-line-length = 88
+extend-ignore = E203
+ignore = E501,W504,W503
+per-file-ignores =
+    **/__init__.py:F401
+    **/tests/*:D

.github/workflows/build_docs.yml

@@ -8,15 +8,15 @@ on:
 name: Build Docs
 jobs:
   build_docs:
-    name: 3.7 build docs
+    name: 3.8 build docs
     runs-on: ubuntu-latest
     steps:
-      - name: Set up python 3.7
-        uses: actions/setup-python@v2
+      - name: Set up python 3.8
+        uses: actions/setup-python@v4
         with:
-          python-version: 3.7
+          python-version: 3.8
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
@@ -28,8 +28,7 @@ jobs:
           sudo apt install -y graphviz
           pip config --site set global.progress_bar off
           python -m pip install --upgrade pip
-          python -m pip install -e .
-          python -m pip install -r dev-requirements.txt
+          python -m pip install .[dev]
       - name: Build docs
         run: |
           make -C docs/ html

.github/workflows/entry_point_test.yml

@@ -9,23 +9,23 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python_version: ["3.7", "3.8", "3.9"]
+        python_version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
       - name: Set up python ${{ matrix.python_version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python_version }}
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
       - name: Build source distribution
-        run: make package_autonormalize
+        run: make package
       - name: Install package
         run: |
           pip config --site set global.progress_bar off
           python -m pip install --upgrade pip
-          python -m pip install -e unpacked_sdist/
+          python -m pip install unpacked_sdist/
       - name: Test entry point
         run: make entry-point-test

.github/workflows/lint_check.yml

@@ -12,23 +12,21 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python_version: ["3.9"]
+        python_version: ["3.11"]
     steps:
       - name: Set up python ${{ matrix.python_version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python_version }}
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
       - name: Install autonormalize with dev, and test requirements
         run: |
           pip config --site set global.progress_bar off
           python -m pip install --upgrade pip
-          python -m pip install -e .
-          python -m pip install -r dev-requirements.txt
-          python -m pip install -r test-requirements.txt
+          python -m pip install .[dev]
       - name: Run lint test
         run: make lint

.github/workflows/release.yml

@@ -8,7 +8,7 @@ jobs:
     name: PyPI Release
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: PyPI Upload
       uses: FeatureLabs/gh-action-pypi-upload@v1
       env:

.github/workflows/release_notes_updated.yml

@@ -26,10 +26,10 @@ jobs:
           print('::set-output name=is_dev::' + str(is_dev))
       - if: ${{ steps.branch.outputs.is_dev == 'True' }}
         name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
       - if: ${{ steps.branch.outputs.is_dev == 'True' }}
         name: Check if release notes were updated
-        run: cat docs/source/release_notes.rst | grep ":pr:\`${{ github.event.number }}\`"
+        run: cat docs/source/release_notes.rst | grep ":pr:\`${{ github.event.number }}\`"

.github/workflows/unit_tests_with_latest_deps.yml

@@ -1,51 +1,50 @@
+name: Unit Tests - Latest Dependencies
 on:
   pull_request:
     types: [opened, synchronize]
   push:
     branches:
       - main
-
-name: Unit Tests - Latest Dependencies
+env:
+  PYARROW_IGNORE_TIMEZONE: 1
+  ALTERYX_OPEN_SRC_UPDATE_CHECKER: False
 jobs:
   unit_tests:
     name: Unit Tests - Python ${{ matrix.python-version }}
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.7", "3.8", "3.9"]
+        python-version: ["3.8", "3.9", "3.10", "3.11"]
     steps:
       - name: Set up python ${{ matrix.python_version }}
-        uses: actions/setup-python@v2
+        uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python_version }}
       - name: Checkout repository
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           ref: ${{ github.event.pull_request.head.ref }}
           repository: ${{ github.event.pull_request.head.repo.full_name }}
       - name: Build source distribution
-        run: make package_autonormalize
+        run: make package
       - name: Install package with test requirements
         run: |
           sudo python -m pip config --site set global.progress_bar off
           python -m pip install --upgrade pip
-          sudo apt update && sudo apt install -y graphviz
-          python -m pip install -e unpacked_sdist/
-          python -m pip install -r unpacked_sdist/test-requirements.txt
-      - if: ${{ matrix.python_version == 3.7 }}
+          sudo apt update
+          sudo apt install -y graphviz
+          python -m pip install "unpacked_sdist/[test]"
+      - if: ${{ matrix.python_version == 3.8 }}
         name: Run unit tests with code coverage
         run: |
-          python -m pip install "$(cat dev-requirements.txt | grep codecov)"
-          coverage erase
           cd unpacked_sdist/
           coverage erase
-          pytest autonormalize/ -n 2 --cov=autonormalize --cov-config=../.coveragerc
-        env:
-          PYARROW_IGNORE_TIMEZONE: 1
-          ALTERYX_OPEN_SRC_UPDATE_CHECKER: False
-      - if: ${{ matrix.python_version == 3.7 }}
+          pytest autonormalize/ -n auto --cov=autonormalize --cov-config=../pyproject.toml --cov-report=xml:../coverage.xml
+      - if: ${{ matrix.python_version == 3.8 }}
         name: Upload coverage to Codecov
-        uses: codecov/codecov-action@v1
+        uses: codecov/codecov-action@v3
         with:
-          fail_ci_if_error: true
           token: ${{ secrets.CODECOV_TOKEN }}
+          fail_ci_if_error: true
+          files: ${{ github.workspace }}/coverage.xml
+          verbose: true

.gitignore

@@ -1,4 +1,5 @@
 .DS_Store
+unpacked_sdist/
 
 # IDE
 .vscode

.pre-commit-config.yaml

@@ -0,0 +1,37 @@
+exclude: ^LICENSE/|\.(html|csv|svg|md|txt|json)$
+default_stages: [commit]
+repos:
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.5.0
+    hooks:
+      - id: nbstripout
+        entry: nbstripout
+        language: python
+        types: [jupyter]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/MarcoGorelli/absolufy-imports
+    rev: v0.3.1
+    hooks:
+      - id: absolufy-imports
+        files: ^autonormalize/
+  - repo: https://github.com/asottile/add-trailing-comma
+    rev: v2.2.3
+    hooks:
+      - id: add-trailing-comma
+        name: Add trailing comma
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.10.1
+    hooks:
+      - id: isort
+        args: [--settings-path=./pyproject.toml]
+  - repo: https://github.com/python/black
+    rev: 22.6.0
+    hooks:
+      - id: black
+        args: [--target-version=py311]
+        additional_dependencies: [".[jupyter]"]
+        types_or: [python, jupyter]

Makefile

@@ -4,37 +4,51 @@ clean:
 	find . -name '*.pyc' -delete
 	find . -name __pycache__ -delete
 	find . -name '*~' -delete
+	find . -name '.coverage.*' -delete
 
 .PHONY: entry-point-test
 entry-point-test:
-	cd ~ && python -c "from featuretools import autonormalize"
+	cd ~ && python -c "from autonormalize import autonormalize"
 
 .PHONY: lint
 lint:
-	flake8 autonormalize && isort --check-only autonormalize
+	isort --check-only autonormalize
+	black autonormalize docs/source -t py311 --check
+	flake8 autonormalize
 
 .PHONY: lint-fix
 lint-fix:
-	autopep8 --in-place --recursive --max-line-length=100 --exclude="*/migrations/*" --select="E225,E303,E302,E203,E128,E231,E251,E271,E127,E126,E301,W291,W293,E226,E306,E221,E261,E111,E114" autonormalize
+	black autonormalize docs/source -t py311
 	isort autonormalize
 
 .PHONY: test
-test: lint
-	pytest autonormalize/
+test:
+	pytest autonormalize/ -n auto
 
 .PHONY: testcoverage
-testcoverage: lint
-		pytest autonormalize/ --cov=autonormalize
+testcoverage:
+	pytest autonormalize/ -n auto --cov=autonormalize
 
 .PHONY: installdeps
-installdeps:
+installdeps: upgradepip
 	pip install --upgrade pip
-	pip install -e .
-	pip install -r dev-requirements.txt
-
-.PHONY: package_autonormalize
-package_autonormalize:
-	python setup.py sdist
-	$(eval DT_VERSION=$(shell python setup.py --version))
-	tar -zxvf "dist/autonormalize-${DT_VERSION}.tar.gz"
-	mv "autonormalize-${DT_VERSION}" unpacked_sdist
+	pip install -e ".[dev]"
+
+.PHONY: upgradepip
+upgradepip:
+	python -m pip install --upgrade pip
+
+.PHONY: upgradebuild
+upgradebuild:
+	python -m pip install --upgrade build
+
+.PHONY: upgradesetuptools
+upgradesetuptools:
+	python -m pip install --upgrade setuptools
+
+.PHONY: package
+package: upgradepip upgradebuild upgradesetuptools
+	python -m build
+	$(eval PACKAGE=$(shell python -c "from pep517.meta import load; metadata = load('.'); print(metadata.version)"))
+	tar -zxvf "dist/autonormalize-${PACKAGE}.tar.gz"
+	mv "autonormalize-${PACKAGE}" unpacked_sdist

autonormalize/.gitignore

@@ -2,4 +2,4 @@
 *.csv
 *.pyc
 
-__pycache__/
+__pycache__/

autonormalize/__init__.py

@@ -1,5 +1,4 @@
 # flake8: noqa
-from .autonormalize import *
-from .classes import Dependencies
-
-__version__ = '2.0.1'
+from autonormalize.version import __version__
+from autonormalize.autonormalize import *
+from autonormalize.classes import Dependencies

autonormalize/autonormalize.py

@@ -1,7 +1,7 @@
 import featuretools as ft
 
-from . import dfd, normalize
-from .classes import Dependencies
+from autonormalize import dfd, normalize
+from autonormalize.classes import Dependencies
 
 
 def find_dependencies(df, accuracy=0.98, index=None):
@@ -92,7 +92,7 @@ def make_entityset(df, dependencies, name=None, time_index=None):
 
     while stack != []:
         current = stack.pop()
-        if (current.df.ww.schema is None):
+        if current.df.ww.schema is None:
             current.df.ww.init(index=current.index[0], name=current.index[0])
 
         current_df_name = current.df.ww.name
@@ -101,13 +101,15 @@ def make_entityset(df, dependencies, name=None, time_index=None):
         else:
             dataframes[current_df_name] = (current.df, current.index[0])
         for child in current.children:
-            if (child.df.ww.schema is None):
+            if child.df.ww.schema is None:
                 child.df.ww.init(index=child.index[0], name=child.index[0])
             child_df_name = child.df.ww.name
             # add to stack
             # add relationship
             stack.append(child)
-            relationships.append((child_df_name, child.index[0], current_df_name, child.index[0]))
+            relationships.append(
+                (child_df_name, child.index[0], current_df_name, child.index[0]),
+            )
 
     return ft.EntitySet(name, dataframes, relationships)
 
@@ -163,10 +165,16 @@ def normalize_entityset(es, accuracy=0.98):
     # to normalize while preserving existing relationships
 
     if len(es.dataframes) > 1:
-        raise ValueError('There is more than one dataframe in this EntitySet')
+        raise ValueError("There is more than one dataframe in this EntitySet")
     if len(es.dataframes) == 0:
-        raise ValueError('This EntitySet is empty')
+        raise ValueError("This EntitySet is empty")
 
     df = es.dataframes[0]
-    new_es = auto_entityset(df, accuracy, index=df.ww.index, name=es.id, time_index=df.ww.time_index)
+    new_es = auto_entityset(
+        df,
+        accuracy,
+        index=df.ww.index,
+        name=es.id,
+        time_index=df.ww.time_index,
+    )
     return new_es