add: deep transformer module (#24)

.github/workflows/build-docs.yml

@@ -11,9 +11,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - name: Install poetry
+        run: |
+          curl -O -sSL https://install.python-poetry.org/install-poetry.py
+          python install-poetry.py -y --version 1.3.1
+          echo "PATH=${HOME}/.poetry/bin:${PATH}" >> $GITHUB_ENV
+          rm install-poetry.py
+      - uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-      - run: pip install poetry==1.3.1
+          cache: "poetry"
+      - run: poetry env use python3.10
       - run: poetry install --with docs
       - run: poetry run mkdocs gh-deploy --force --clean --verbose

.github/workflows/code-cov.yml

@@ -8,13 +8,20 @@ jobs:
     steps:
       - name: Checkout
         uses: actions/checkout@v2
+      - name: Install poetry
+        run: |
+          curl -O -sSL https://install.python-poetry.org/install-poetry.py
+          python install-poetry.py -y --version 1.3.1
+          echo "PATH=${HOME}/.poetry/bin:${PATH}" >> $GITHUB_ENV
+          rm install-poetry.py
       - name: Set up Python 3.10
-        uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         with:
           python-version: "3.10"
+          cache: "poetry"
       - name: Install dependencies and project
         run: |
-          python -m pip install poetry==1.3.1
+          poetry env use python3.10
           poetry install --with test
       - name: Run tests and collect coverage
         run: poetry run pytest --cov src/sk_transformers --cov-report term-missing --cov-report xml

.github/workflows/deploy-package.yml

@@ -12,9 +12,16 @@ jobs:
     environment: deploy-package
     steps:
       - uses: actions/checkout@v2
-      - uses: actions/setup-python@v2
+      - name: Install poetry
+        run: |
+          curl -O -sSL https://install.python-poetry.org/install-poetry.py
+          python install-poetry.py -y --version 1.3.1
+          echo "PATH=${HOME}/.poetry/bin:${PATH}" >> $GITHUB_ENV
+          rm install-poetry.py
+      - uses: actions/setup-python@v4
         with:
           python-version: "3.10"
-      - run: pip install poetry==1.3.1
+          cache: "poetry"
+      - run: poetry env use python3.10
       - run: poetry config pypi-token.pypi ${{ secrets.PYPI_TOKEN }}
       - run: poetry publish --build

.github/workflows/pr-title.yml

@@ -11,7 +11,7 @@ jobs:
     steps:
       - uses: deepakputhraya/action-pr-title@master
         with:
-          regex: "^(build:|ci:|docs:|feat:|fix:|perf:|refactor:|revert:|style:|test:|security:).{12,30}$"
+          regex: "^(add:|build:|ci:|docs:|feat:|fix:|bug:|perf:|refactor:|revert:|style:|test:|security:).{12,60}$"
           min_length: 10
-          max_length: 20
+          max_length: 60
           github_token: "${{ secrets.GITHUB_TOKEN }}"

.github/workflows/pre-commit.yml

@@ -0,0 +1,28 @@
+name: PreCommit
+
+on:
+  pull_request:
+    branches: [develop]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Install poetry
+        run: |
+          curl -O -sSL https://install.python-poetry.org/install-poetry.py
+          python install-poetry.py -y --version 1.3.1
+          echo "PATH=${HOME}/.poetry/bin:${PATH}" >> $GITHUB_ENV
+          rm install-poetry.py
+      - uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+          cache: "poetry"
+      - name: Install dependencies and project
+        run: |
+          poetry env use python3.10
+          poetry install
+      - uses: pre-commit/action@v3.0.0
+        env:
+          SKIP: poetry-lock,poetry-export

.github/workflows/release.yml

@@ -14,4 +14,4 @@ jobs:
           prerelease: true
           default-branch: main
           pull-request-header: ":robot: I have created a release *beep* *boop*. This was predictable."
-          changelog-types: '[{"type":"add","section":"Features","hidden":false},{"type":"feat","section":"Features","hidden":false},{"type":"fix","section":"Bug Fixes","hidden":false},{"type":"chore","section":"Miscellaneous","hidden":true},{"type":"test","section":"Tests","hidden":false},{"type":"ci","section":"CI/CD","hidden":false},{"type":"refactor","section":"Maintenance","hidden":false},{"type":"perf","section":"Maintenance","hidden":false},{"type":"revert","section":"Maintenance","hidden":false},{"type":"docs","section":"Documentation","hidden":false},{"type":"security","section":"Security","hidden":false}]'
+          changelog-types: '[{"type":"merge","section":"Miscellaneous","hidden":true},{"type":"resolve","section":"Miscellaneous","hidden":true},{"type":"add","section":"Features","hidden":false},{"type":"feat","section":"Features","hidden":false},{"type":"fix","section":"Bug Fixes","hidden":false},{"type":"bug","section":"Bug Fixes","hidden":false},{"type":"chore","section":"Miscellaneous","hidden":true},{"type":"test","section":"Tests","hidden":false},{"type":"ci","section":"CI/CD","hidden":false},{"type":"refactor","section":"Maintenance","hidden":false},{"type":"perf","section":"Maintenance","hidden":false},{"type":"revert","section":"Maintenance","hidden":false},{"type":"docs","section":"Documentation","hidden":false},{"type":"security","section":"Security","hidden":false}]'

.github/workflows/testing.yml

@@ -9,17 +9,28 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10"]
 
     steps:
       - uses: actions/checkout@v3
+      - name: Install poetry
+        run: |
+          curl -O -sSL https://install.python-poetry.org/install-poetry.py
+          python install-poetry.py -y --version 1.3.1
+          echo "PATH=${HOME}/.poetry/bin:${PATH}" >> $GITHUB_ENV
+          rm install-poetry.py
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "poetry"
       - name: Set up Python ${{ matrix.python-version }}
         uses: actions/setup-python@v4
         with:
           python-version: ${{ matrix.python-version }}
+          cache: "poetry"
       - name: Install dependencies and project
         run: |
-          python -m pip install poetry==1.3.1
+          poetry env use ${{ matrix.python-version }}
           poetry install --with test
       - name: Check with isort
         run: |

.pre-commit-config.yaml

@@ -1,3 +1,6 @@
+default_language_version:
+  python: python3.10
+
 repos:
   - repo: https://github.com/compilerla/conventional-pre-commit
     rev: v2.1.1
@@ -16,10 +19,12 @@ repos:
             "test",
             "security",
             "perf",
+            "resolve",
+            "merge",
           ]
 
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
@@ -75,7 +80,7 @@ repos:
           - "-r"
 
   - repo: https://github.com/python-poetry/poetry
-    rev: 1.3.1
+    rev: 1.3.0
     hooks:
       - id: poetry-check
       - id: poetry-lock

SECURITY.md

@@ -0,0 +1,10 @@
+@@ -0,0 +1,9 @@
+# Security Policy
+
+## Supported Versions
+
+Patches will be released to the latest major version.
+
+## Reporting a Vulnerability
+
+Please report (suspected) security vulnerabilities to [chris@syhbl.mozmail.com](mailto:chris@syhbl.mozmail.com). If the issue is confirmed, we will release a patch as soon as possible depending on the complexity.

docs/API-reference/transformer/deep_transformer.md

@@ -0,0 +1 @@
+::: sk_transformers.deep_transformer

docs/README.md

@@ -43,6 +43,28 @@ With [Poetry](https://python-poetry.org/):
 poetry install
 ```
 
+## Available transformers
+| Module | Transformer | Description |
+| ------ | ----------- | ----------- |
+|[`Datetime transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/datetime_transformer/)|[`DurationCalculatorTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/datetime_transformer/#sk_transformers.datetime_transformer.DurationCalculatorTransformer)|Calculates the duration between to given dates.|
+|[`Deep transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/deep_transformer/)|[`ToVecTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/deep_transformer/#sk_transformers.deep_transformer.ToVecTransformer)|This transformer trains an [FT-Transformer](https://paperswithcode.com/method/ft-transformer) using the [pytorch-widedeep package](https://github.com/jrzaurin/pytorch-widedeep) and extracts the embeddings from its embedding layer.|
+|[`Encoder transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/encoder_transformer/)|[`MeanEncoderTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/encoder_transformer/#sk_transformers.encoder_transformer.MeanEncoderTransformer)|Scikit-learn API for the [feature-engine MeanEncoder](https://feature-engine.readthedocs.io/en/latest/api_doc/encoding/MeanEncoder.html).|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`AggregateTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.AggregateTransformer)|This transformer uses Pandas groupby method and aggregate to apply function on a column grouped by another column.|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`ColumnDropperTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.ColumnDropperTransformer)|Drops columns from a dataframe using Pandas drop method.|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`DtypeTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.DtypeTransformer)|Transformer that converts a column to a different dtype.|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`FunctionsTransformer`]( https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.FunctionsTransformer)|This transformer is a plain wrapper around the [sklearn.preprocessing.FunctionTransformer](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.FunctionTransformer.html).|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`MapTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.MapTransformer)|This transformer iterates over all columns in the `features` list and applies the given callback to the column. For this it uses the `pandas.Series.map` method.
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`NaNTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.NaNTransformer)|Replace NaN values with a specified value. Internally Pandas fillna method is used.|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`QueryTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.QueryTransformer)|Applies a list of queries to a dataframe. If it operates on a dataset used for supervised learning this transformer should be applied on the dataframe containing `X` and `y`.
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`ValueIndicatorTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.ValueIndicatorTransformer)|Adds a column to a dataframe indicating if a value is equal to a specified value.|
+|[`Generic transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/)|[`ValueReplacerTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/generic_transformer/#sk_transformers.generic_transformer.ValueReplacerTransformer)|Uses Pandas replace method to replace values in a column.|
+[`Number transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/number_transformer/)|[`MathExpressionTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/number_transformer/#sk_transformers.number_transformer.MathExpressionTransformer)|Applies an operation to a column and a given value or column. The operation can be any operation from the `numpy` or `operator` package.
+[`String transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/)|[`EmailTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/#sk_transformers.string_transformer.EmailTransformer)|Transforms an email address into multiple features.|
+[`String transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/)|[`IPAddressEncoderTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/#sk_transformers.string_transformer.IPAddressEncoderTransformer)|Encodes IPv4 and IPv6 strings addresses to a float representation.|
+[`String transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/)|[`PhoneTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/#sk_transformers.string_transformer.PhoneTransformer)|Transforms a phone number into multiple features.|
+[`String transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/)|[`StringSimilarityTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/#sk_transformers.string_transformer.StringSimilarityTransformer)|Calculates the similarity between two strings using the `gestalt pattern matching` algorithm from the `SequenceMatcher` class.|
+[`String transformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/)|[`StringSlicerTransformer`](https://chrislemke.github.io/sk-transformers/API-reference/transformer/string_transformer/#sk_transformers.string_transformer.StringSlicerTransformer)|Slices all entries of specified string features using the slice() function.|
+
 ## Usage
 Let's assume you want to use some method from [NumPy's mathematical functions, to sum up the values of column `foo` and column `bar`. You could
 use the [`MathExpressionTransformer`](https://chrislemke.github.io/sk-transformers/number_transformer-reference/#sk-transformers.transformer.number_transformer.MathExpressionTransformer).

docs/stylesheets/extra.css

@@ -1,5 +1,5 @@
 :root {
-    --md-primary-fg-color: #fc7805;
+    --md-primary-fg-color: #5b90b9;
     --md-primary-fg-color--light: #F501FE;
     --md-primary-fg-color--dark: #3820AA;
 }

mkdocs.yml

@@ -26,8 +26,8 @@ theme:
     repo: fontawesome/brands/github
   name: material
   language: en
-  favicon: assets/images/icon.png
-  logo: assets/images/icon.png
+  favicon: assets/images/robot.png
+  logo: assets/images/robot.png
   features:
     - navigation.tracking
     - navigation.top
@@ -52,7 +52,7 @@ plugins:
   - mkdocstrings:
       handlers:
         python:
-          rendering:
+          options:
             show_root_heading: false
 
 extra_javascript: