Not sure all this is actually used

src/datapipe.py

@@ -1,41 +1,32 @@
-# AUTOGENERATED! DO NOT EDIT! File to edit: nbs/01_datapipe.ipynb (unless otherwise specified).
-
-__all__ = ['calc_walk_stats', 'load_and_cache_raw_walk_data']
-
-# Cell
 import os
 import pandas as pd
 import activityio as aio
 from dateutil.parser import parse
 import datetime as dt
 import sqlite3 as sql
 from pathlib import Path
-#import tomli
 
 
-# Cell
 def calc_walk_stats(walk_data):
     total_time = dt.timedelta(0)
     total_distance = 0
-
-    for iHike, hike in enumerate(walk_data):
+    for hike in walk_data:
         total_time += hike.index.max()
         # print(iHike+1, walk_date[iHike], hike.index.max(), hike['dist'].max() / 1e3)
-        total_distance += hike['dist'].max()
+        total_distance += hike["dist"].max()
     total_distance /= 1e3
 
-    start_coord = walk_data[0][['lat', 'lon']].iloc[0].tolist()
-    end_coord = walk_data[-1][['lat', 'lon']].iloc[-1].tolist()
+    start_coord = walk_data[0][["lat", "lon"]].iloc[0].tolist()
+    end_coord = walk_data[-1][["lat", "lon"]].iloc[-1].tolist()
     return total_time, total_distance, start_coord, end_coord
 
 
-# TODO: use st.cache() and also look to pre-load and cache/feather data (or similar) - NB: use of @st.cache() below didn't work
 def load_and_cache_raw_walk_data(walk_name, sample_freq, conn):
-    RAW_FIT_FILE_PATH = 'icloud/Data/HealthFit/FIT'
-    fit_dir = Path.home()/RAW_FIT_FILE_PATH
-    data_dir = fit_dir/walk_name[0:3]
+    RAW_FIT_FILE_PATH = "icloud/Data/HealthFit/FIT"
+    fit_dir = Path.home() / RAW_FIT_FILE_PATH
+    data_dir = fit_dir / walk_name[:3]
     print(data_dir.ls())
-    data_files = [file for file in os.listdir(data_dir) if file.endswith('.fit')]
+    data_files = [file for file in os.listdir(data_dir) if file.endswith(".fit")]
     walk_files = sorted(data_files)
     print(walk_files)
 
@@ -45,15 +36,17 @@ def load_and_cache_raw_walk_data(walk_name, sample_freq, conn):
     for iFile, file in enumerate(walk_files):
         walk_df = pd.DataFrame(aio.read(data_dir + file))
         walk_data.append(walk_df)
-        walk_date.append(parse(file[0:17]))
-        walk_df['WalkName'] = walk_name
-        walk_df['WalkNumber'] = iFile
-        walk_df[['alt', 'dist', 'lat', 'lon', 'speed', 'WalkName', 'WalkNumber']].to_sql('walks', conn, if_exists='append', index=False)
-
+        walk_date.append(parse(file[:17]))
+        walk_df["WalkName"] = walk_name
+        walk_df["WalkNumber"] = iFile
+        walk_df[
+            ["alt", "dist", "lat", "lon", "speed", "WalkName", "WalkNumber"]
+        ].to_sql("walks", conn, if_exists="append", index=False)
     total_time, total_distance, start_coord, end_coord = calc_walk_stats(walk_data)
     walk_stats = [total_time, total_distance, start_coord, end_coord]
-    #print(start_coord)
     walk_merged = pd.concat(walk_data)
-    points = walk_merged[['lat', 'lon']].values.tolist()
-    points = [tuple(point) for ipoint, point in enumerate(points) if ipoint % sample_freq == 0]
-    return walk_data, walk_date, walk_files, points, walk_stats
+    points = walk_merged[["lat", "lon"]].values.tolist()
+    points = [
+        tuple(point) for ipoint, point in enumerate(points) if ipoint % sample_freq == 0
+    ]
+    return walk_data, walk_date, walk_files, points, walk_stats