Loggerの導入

pre-commitの設定をpyproject.tomlに移動

.pre-commit-config.yaml

@@ -3,17 +3,15 @@ repos:
     rev: 23.3.0
     hooks:
       - id: black
-        args: ["--line-length", "120", "."]
   - repo: https://github.com/pycqa/flake8
     rev: 6.0.0
     hooks:
       - id: flake8
-        args: ["--max-line-length", "120"]
+        additional_dependencies: [flake8-pyproject]
   - repo: https://github.com/pycqa/isort
     rev: 5.12.0
     hooks:
       - id: isort
-        args: ["--profile", "black", "--filter-files", "--multi-line", "3"]
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.4.1
     hooks:

pyproject.toml

@@ -19,9 +19,26 @@ jupyterlab = "^4.0.2"
 [tool.poetry.group.dev.dependencies]
 ipywidgets = "^8.0.6"
 pre-commit = "^3.3.3"
+black = "^23.3.0"
+flake8 = "^6.0.0"
+isort = "^5.12.0"
+mypy = "^1.4.1"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
+
+[tool.black]
+line-length = 120
+
+[tool.isort]
+profile = "black"
+filter_files = true
+multi_line_output = 3
+
+[tool.flake8]
+max_line_length = 120
+
+[tool.mypy]

tools/extract-products.py

@@ -1,31 +1,36 @@
+import logging
 import pathlib
 
 import pandas as pd
 
+logging.basicConfig(format="%(asctime)s %(message)s", datefmt="%m/%d/%Y %I:%M:%S %p")
+LOGGER = logging.getLogger(__name__)
+LOGGER.setLevel(logging.INFO)
+
 
 def main():
-    print("Starting to create JSONL file from esci-data products...")
+    LOGGER.info("Starting to create JSONL file from esci-data products...")
     esci_path = pathlib.Path("./esci-data/shopping_queries_dataset")
-    print(" Reading parquet file...")
+    LOGGER.info(" Reading parquet file...")
     df_products = pd.read_parquet(esci_path.joinpath("shopping_queries_dataset_products.parquet"))
 
-    print(" Making output path...")
+    LOGGER.info(" Making output path...")
     output_path = pathlib.Path("./esci-raw-jsonl/products")
     output_path.mkdir(exist_ok=True, parents=True)
 
-    print(" Extracting products data that product_locale is 'jp'...")
+    LOGGER.info(" Extracting products data that product_locale is 'jp'...")
     df_products[df_products["product_locale"] == "jp"].to_json(
         output_path.joinpath("esci-data-products-jp.json"), orient="records", lines=True
     )
-    print(" Extracting products data that product_locale is 'us'...")
+    LOGGER.info(" Extracting products data that product_locale is 'us'...")
     df_products[df_products["product_locale"] == "us"].to_json(
         output_path.joinpath("esci-data-products-us.json"), orient="records", lines=True
     )
-    print(" Extracting products data that product_locale is 'es'...")
+    LOGGER.info(" Extracting products data that product_locale is 'es'...")
     df_products[df_products["product_locale"] == "es"].to_json(
         output_path.joinpath("esci-data-products-es.json"), orient="records", lines=True
     )
-    print("Finish extract-products")
+    LOGGER.info("Finish extract-products")
 
 
 if __name__ == "__main__":