chore: Update project configuration

.editorconfig

@@ -16,6 +16,10 @@ trim_trailing_whitespace = true
 [*.py]
 indent_size = 4
 
+# Override rules for Juptyer notebooks
+[*.ipynb]
+indent_size = 4
+
 # Override rules for markdown
 [*.md]
 # trailing whitespace is significant in markdown -> do not remove

.gitignore

@@ -193,5 +193,8 @@ pyrightconfig.json
 
 # End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,python
 
-# Ignore dataset due to size
+# Custom
 data/
+cache/
+models/
+flagged/

justfile

@@ -7,13 +7,17 @@
   poetry run pre-commit run --all-files
 
 @install:
-  poetry install --without dev
+  poetry install --only main
 
 @install-dev:
+  poetry self add poetry-plugin-export
   poetry install
 
 @requirements:
   poetry export -f requirements.txt --output requirements.txt --without dev
 
-@run TEXT:
-  poetry run python main.py {{TEXT}}
+@run +TEXT:
+  poetry run python main.py predict --model models/logistic_regression.pkl "{{TEXT}}"
+
+@gui:
+  poetry run gradio app/gui.py

pyproject.toml

@@ -1,10 +1,18 @@
 [tool.poetry]
 name = "sentiment-analysis"
 package-mode = false
+packages = [{ include = "app" }]
 
 [tool.poetry.dependencies]
 python = "^3.12"
 click = "^8.1.7"
+scikit-learn = "^1.4.2"
+gradio = "^4.31.0"
+
+[tool.poetry.group.train.dependencies]
+pandas = "^2.2.2"
+numpy = "^1.26.4"
+seaborn = "^0.13.2"
 
 [tool.poetry.group.dev.dependencies]
 ruff = "^0.4.1"
@@ -18,6 +26,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.ruff]
 extend-include = ["*.ipynb"]
+src = ["app"]
 line-length = 120
 indent-width = 4
 
@@ -97,6 +106,8 @@ ignore = [
   "PT",
   "TD",
   "PERF203", # ignore for now; investigate
+  "T201",    # print
+  "ANN204",  # missing-return-type-special-method
 ]
 select = ["ALL"]
 # Allow unused variables when underscore-prefixed
@@ -108,6 +119,9 @@ convention = "google"
 [tool.ruff.lint.mccabe]
 max-complexity = 12
 
+[tool.ruff.lint.isort]
+known-first-party = ["app"]
+
 [tool.ruff.format]
 docstring-code-format = true