feat: LangChain Matching (#2)

* LangChain based matching
* Basic boolean output parser
* CLI for experimenting
* Hard coded prompt

.github/workflows/frp-cli.yaml

@@ -0,0 +1,106 @@
+name: FRP-cli
+
+on:
+  workflow_dispatch:
+  push:
+    paths:
+      - 'packages/frp-cli/**'
+    branches:
+      - main
+    tags:
+      - "v*.*.*"
+  pull_request:
+    paths:
+      - 'packages/frp-cli/**'
+    branches:
+      - main
+
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    name: Check for Linting Errors
+    defaults:
+      run:
+        working-directory: packages/frp-cli
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.9"
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry install --with dev
+
+      - name: Lint
+        run: poetry run flake8
+
+  build:
+    runs-on: ubuntu-latest
+    name: Build
+    defaults:
+      run:
+        working-directory: packages/frp-cli
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.9"
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          cd ../frp
+          poetry install
+          cd ../frp-cli
+          poetry install --with dev
+
+      - name: Build
+        run: poetry build
+
+  type-checking:
+    runs-on: ubuntu-latest
+    name: Run Type Checking
+    defaults:
+      run:
+        working-directory: packages/frp-cli
+
+    steps:
+      - name: Checkout Repository
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.event.pull_request.head.ref }}
+
+      - name: Setup Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: "3.9"
+
+      - name: Install Dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          cd ../frp
+          poetry config virtualenvs.create false
+          poetry install
+          cd ../frp-cli
+          poetry install --with dev
+
+      - name: Type Checking
+        run: poetry run mypy frp_cli/

.gitignore

@@ -1 +1,2 @@
 venv/
+__pycache__/

packages/frp-cli/.flake8

@@ -0,0 +1,3 @@
+[flake8]
+max-line-length = 160
+per-file-ignores = __init__.py:F401

packages/frp-cli/.gitignore

@@ -0,0 +1,3 @@
+dist/
+*.pyc
+data/

packages/frp-cli/frp_cli/__init__.py

@@ -0,0 +1 @@
+from frp_cli.main import main

packages/frp-cli/frp_cli/main.py

@@ -0,0 +1,68 @@
+from argparse import ArgumentParser, BooleanOptionalAction
+from pathlib import Path
+from frp import FRPScholarlyAnalysis, Matcher
+
+
+def scholarly_analysis(input_csv: Path, frp_title: str, frp_year: int, save_results: bool, save_output: Path) -> None:
+    if not input_csv.exists():
+        print('File {} does not exist'.format(input_csv))
+        exit(1)
+
+    # Make the matcher
+    matcher = Matcher()
+
+    # Run the analysis
+    analyzer = FRPScholarlyAnalysis(matcher)
+
+    # Collect the results
+    results = analyzer.run_frp_analysis(input_csv, frp_title, frp_year)
+
+    # If the user wants the data saved, save it to the output location
+    if save_results:
+        results.to_csv(save_output)
+
+    print(results['Part of FRP'])
+
+
+def main():
+    parser = ArgumentParser()
+
+    # Sub parser for the different commands
+    sub_parser = parser.add_subparsers(dest='command', required=True)
+
+    # Command: scholarly
+    scholarly_parser = sub_parser.add_parser('scholarly')
+    scholarly_parser.add_argument('--input',
+                                  required=True,
+                                  help='Input CSV')
+    scholarly_parser.add_argument('--frp-title',
+                                  required=False,
+                                  default='Leveraging AI to Examine Disparities and Bias in Health Care',
+                                  help='Name of the FRP to run matching against')
+    scholarly_parser.add_argument('--frp-year',
+                                  required=False,
+                                  default=2022,
+                                  type=int,
+                                  help='Year to start (inclusive) considering articles')
+    scholarly_parser.add_argument('--save-output',
+                                  required=False,
+                                  default=False,
+                                  action=BooleanOptionalAction,
+                                  help='Flag if the results of the matching should be stored')
+    scholarly_parser.add_argument('--output-csv',
+                                  required=False,
+                                  default='data/scholarly_matching_results.csv',
+                                  help='Where to store the results of the matching')
+
+    args = parser.parse_args()
+
+    # Determine the correct command to run
+    if args.command == 'scholarly':
+        scholarly_analysis(Path(args.input), args.frp_title, args.frp_year, args.save_output, Path(args.output_csv))
+        return
+    else:
+        print('Command {} not recognized'.format(args.command))
+
+
+if __name__ == '__main__':
+    main()