refactor: run pre-commit hooks for formating

.gitignore

@@ -1,4 +1,4 @@
-pkg/doc/_autosummary
+doc/_autosummary
 
 .envrc
 .idea

doc/_autosummary/athai.rst

@@ -27,5 +27,6 @@
    :toctree:
    :recursive:
 
+   athai.data_utils
    athai.hello
 

packages.txt

@@ -1,3 +1,3 @@
 nano
 vim
-tree 
+tree

scripts/build-run-local-docker.sh

@@ -12,8 +12,8 @@ echo "Running from ROOT_DIRECTORY: ${ROOT_DIRECTORY}"
 # Export the dependencies managed by Poetry in the requirements.txt format for pip
 poetry export -f requirements.txt -o requirements.txt --without-hashes --only=main
 
-# Re-build the docker image. 
-docker build --label tests -t $CONTAINER_NAME . 
+# Re-build the docker image.
+docker build --label tests -t $CONTAINER_NAME .
 
 # During development ONLY use a `bind mount` to enable
 # editing the code without having to rebuild the container.
@@ -23,6 +23,6 @@ docker run --rm -it                  \
     --mount type=bind,source=${ROOT_DIRECTORY}/src/,target=/app/,readonly       \
     --mount type=bind,source=${ROOT_DIRECTORY}/.streamlit,target=/user/.streamlit,readonly       \
     $CONTAINER_NAME:latest      \
-    $@    
+    $@
 
-popd
+popd

src/apps/streamlit_demo.py

@@ -1,11 +1,13 @@
+import os
+from pathlib import Path
+
 import numpy as np
 import pandas as pd
 import streamlit as st
-import os
-from pathlib import Path
 
 from athai.data_utils import cached_download_csv
 
+
 st.title("Uber pickups in NYC")
 
 DATE_COLUMN = "date/time"
@@ -16,10 +18,11 @@ DATA_URL = (
 
 DATA_PATH = Path(os.environ.get("APP_DATA"))
 
+
 @st.cache_resource
 def load_data(nrows):
-    data = cached_download_csv(DATA_PATH, DATA_URL,
-    nrows=nrows)
+    data = cached_download_csv(DATA_PATH, DATA_URL, nrows=nrows)
+
     def lowercase(x):
         return str(x).lower()
 
@@ -56,4 +59,4 @@ if uploaded_file is not None:
     st.write(len(bytes_data), "bytes")
 
 
-st.markdown("![Kitty](./app/static/cat.jpeg)")
+st.markdown("![Kitty](./app/static/cat.jpeg)")

src/athai/data_utils.py

@@ -1,18 +1,24 @@
+import logging
+import shelve
 from pathlib import Path
+
 import pandas as pd
-import logging
 
-import shelve
 
 logging.basicConfig(level=logging.INFO)
 
-def cached_download_csv(data_path : Path, url : str, **kwargs) -> pd.DataFrame:
+
+def cached_download_csv(data_path: Path, url: str, **kwargs) -> pd.DataFrame:
     shelf_filename = data_path.joinpath("shelf.dat").as_posix()
     try:
-        s = shelve.open(shelf_filename, writeback=True, flag='c')
+        s = shelve.open(shelf_filename, writeback=True, flag="c")
     except Exception as exn:
-        logging.warning("Unexpected exception, by-passing persistent cache :\n" + str())
-        logging.exception("Unexpected exception, while trying to access the shelf")
+        logging.warning(
+            "Unexpected exception, by-passing persistent cache :\n" + str(exn)
+        )
+        logging.exception(
+            "Unexpected exception, while trying to access the shelf"
+        )
         return pd.read_csv(url, **kwargs)
     with s as shelf:
         logging.info(f"Opened or created the shelf file '{shelf_filename}'")
@@ -22,9 +28,8 @@ def cached_download_csv(data_path : Path, url : str, **kwargs) -> pd.DataFrame:
             df = pd.read_csv(url, **kwargs)
             shelf[url] = df
             return df
-        else :  
+        else:
             logging.info(f"Re-using cached URL '{url}'")
             assert isinstance(maybe_cached, pd.DataFrame)
             return maybe_cached
-    # The context manager 'shelf' ensure set value as written back or return 
-
+    # The context manager 'shelf' ensure set value as written back or return