Add the file structure for this project, the basics of tests, github …

…actions, documentation

.github/workflows/docs.yaml

@@ -0,0 +1,27 @@
+name: Deploy docs to gh-pages
+
+on:
+  workflow_dispatch:
+  push:
+    branches:
+      - dev
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    name: Deploy docs to gh-pages
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+
+      - name: Deploy
+        uses: mhausenblas/mkdocs-deploy-gh-pages@master
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          CONFIG_FILE: docs/mkdocs.yml
+          REQUIREMENTS: docs/site_assets/requirements.txt

.github/workflows/pytest.yaml

@@ -0,0 +1,57 @@
+name: Unit Tests
+
+on: [push]
+
+jobs:
+  test:
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      matrix:
+        os: ["ubuntu-latest", "macos-latest"]
+        python-version: ["3.9", "3.10"]
+    steps:
+      #----------------------------------------------
+      #       check-out repo and set-up python
+      #----------------------------------------------
+      - name: Check out repository
+        uses: actions/checkout@v4
+      - name: Set up python ${{ matrix.python-version }}
+        id: setup-python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      #----------------------------------------------
+      #  -----  install & configure poetry  -----
+      #----------------------------------------------
+      - name: Install Poetry
+        uses: snok/install-poetry@v1
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+      #----------------------------------------------
+      #       load cached venv if cache exists
+      #----------------------------------------------
+      - name: Load cached venv
+        id: cached-poetry-dependencies
+        uses: actions/cache@v3
+        with:
+          path: .venv
+          key: venv-${{ runner.os }}-${{ steps.setup-python.outputs.python-version }}-${{ hashFiles('**/poetry.lock') }}
+      #----------------------------------------------
+      # install dependencies if cache does not exist
+      #----------------------------------------------
+      - name: Install dependencies
+        if: steps.cached-poetry-dependencies.outputs.cache-hit != 'true'
+        run: poetry install --no-interaction --no-root
+      #----------------------------------------------
+      # install your root project, if required
+      #----------------------------------------------
+      - name: Install additional dependencies
+        run: |
+          poetry install --no-interaction
+      #----------------------------------------------
+      #    add matrix specifics and run test suite
+      #----------------------------------------------
+      - name: Run tests
+        run: poetry run pytest tests/ --verbose

.gitignore

@@ -0,0 +1,4 @@
+# Mac OS-specific storage files
+.DS_Store
+
+__pycache__/

README.md

@@ -1,2 +1,42 @@
 # nlp-link
 A python package to semantically link two lists of texts.
+
+
+## Set-up
+
+In setting up this project we ran:
+```
+conda create --name nlp-link pip python=3.9
+conda activate nlp-link
+pip install poetry
+```
+
+```
+poetry init
+
+```
+
+```
+poetry install
+
+```
+
+## Tests
+
+To run tests:
+
+```
+poetry run pytest tests/
+```
+
+## Documentation
+
+Docs for this repo are automatically published to gh-pages branch via. Github actions after a PR is merged into dev. We use Material for MkDocs for these. Nothing needs to be done to update these.
+
+However, if you are editing the docs you can test them out locally by running
+
+```
+cd guidelines
+pip install -r docs/requirements.txt  
+mkdocs serve
+```

docs/README.md

@@ -0,0 +1,5 @@
+# nlp-link
+
+Documentation for NLP Link
+
+- [Page1](./page1.md)

docs/mkdocs.yaml

@@ -0,0 +1,44 @@
+site_name: NLP Link
+site_description: A python package to semantically link two lists of texts..
+site_url: https://nestauk.github.io/nlp-link
+repo_name: nestauk/nlp-link
+repo_url: https://github.com/nestauk/nlp-link
+extra:
+  homepage: https://nestauk.github.io/nlp-link
+docs_dir: .
+extra_css:
+  - site_assets/style.css
+theme:
+  name: material
+  # disable_nav_previous_next: true
+  # disable_footer: false
+  logo: site_assets/nesta_logo.png
+  favicon: site_assets/nesta_logo.png
+  features:
+    - navigation.instant
+    - navigation.tracking
+    # - navigation.tabs
+    - navigation.sections
+    - navigation.top
+  font:
+    text: Century Gothic
+  palette:
+    - media: "(prefers-color-scheme: light)"
+      scheme: default
+      primary: custom
+      accent: custom
+      toggle:
+        icon: material/weather-night
+        name: Switch to dark mode
+    - media: "(prefers-color-scheme: dark)"
+      scheme: slate
+      primary: amber
+      accent: pink
+      toggle:
+        icon: material/weather-sunny
+        name: Switch to light mode
+nav:
+  - Home: README.md
+  - Page 1: page1.md
+plugins:
+  - same-dir

docs/page1.md

@@ -0,0 +1 @@
+## Title

docs/site_assets/requirements.txt

@@ -0,0 +1,3 @@
+mkdocs
+mkdocs-material
+mkdocs-same-dir

docs/site_assets/style.css

@@ -0,0 +1,10 @@
+@import url('https://fonts.cdnfonts.com/css/century-gothic');
+html,
+body,
+[class*="css"] {
+  font-family: "Century Gothic";
+}
+:root {
+  --md-primary-fg-color: #18A48C;
+  --md-accent-fg-color: #EB003B;
+}

nlp_link/linker.py

@@ -0,0 +1,12 @@
+import pandas as pd
+
+import random
+
+def link_lists(list_1, list_2):
+	"""
+	Mock linker
+	"""
+	list_1_index = list(range(len(list_1)))
+	list_2_index = list(range(len(list_2)))
+
+	return [(i, random.choice(list_1_index)) for i in list_2_index]

pyproject.toml

@@ -0,0 +1,21 @@
+[tool.poetry]
+name = "nlp-link"
+version = "0.1.0"
+description = "A python package to semantically link two lists of texts."
+authors = ["Nesta <[email protected]>"]
+readme = "README.md"
+packages = [{include = "nlp_link"}]
+
+[tool.poetry.dependencies]
+python = "^3.9"
+scikit-learn = "^1.4.2"
+pandas = "^2.2.2"
+sentence-transformers = "^2.1.0"
+torch = "^1.10.0"
+pytest = "^8.2.0"
+tqdm = "^4.64.1"
+numpy = "^1.24.1"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

tests/test_linker.py

@@ -0,0 +1,10 @@
+from nlp_link.linker import link_lists
+
+def test_link_lists():
+
+	list_1 = ["dog", "cat"]
+	list_2 = ["kitten", "puppy"]
+	linked = link_lists(list_1, list_2)
+
+	assert len(linked) == len(list_1)
+