0.9.1

- Use logging throughout
- Review docstrings and add type hints
- Make some methods private
- Use Pandas merge when geocoding postcodes for better performance
- Minor bug fixes and performance improvements

README.md

@@ -2,7 +2,7 @@
 
 Geocode various geographical entities including postcodes and LLSOAs. Reverse-geocode to LLSOA or GSP/GNode.
 
-*Latest Version: 0.9.0*
+*Latest Version: 0.9.1*
 
 ## What is this repository for?
 

example.py

@@ -1,3 +1,6 @@
+import os
+import logging
+
 from geocode import Geocoder
 
 def main():
@@ -40,4 +43,8 @@ def main():
             print(f"    {lat:.3f}, {lon:.3f}")
 
 if __name__ == "__main__":
+    log_fmt = "%(asctime)s [%(levelname)s] [%(filename)s:%(funcName)s] - %(message)s"
+    fmt = os.environ.get("GEOCODE_LOGGING_FMT", log_fmt)
+    datefmt = os.environ.get("GEOCODE_LOGGING_DATEFMT", "%Y-%m-%dT%H:%M:%SZ")
+    logging.basicConfig(format=fmt, datefmt=datefmt, level=os.environ.get("LOGLEVEL", "DEBUG"))
     main()

geocode/bng2latlon.py

@@ -43,11 +43,11 @@ def main():
     with open(options.infile, "r") as fid:
         df = pd.read_csv(fid)
     with Geocoder(progress_bar=True) as geo:
-        lons, lats = geo.bng2latlon(df["eastings"].to_numpy(), df["northings"].to_numpy())
+        lons, lats = geo._bng2latlon(df["eastings"].to_numpy(), df["northings"].to_numpy())
     df["latitude"] = lats
     df["longitude"] = lons
     df.to_csv(options.outfile, index=False)
-    print(f"Finished, time taken: {TIME.time() - timerstart} seconds")
+    print(f"Finished, time taken: {TIME.time() - timerstart:.1f} seconds")
 
 if __name__ == "__main__":
     main()

geocode/latlons2gsp.py

@@ -55,7 +55,7 @@ def main():
     columns = row.index.to_list() + list(l.keys())
     output = pd.DataFrame(output, columns=columns)
     output.to_csv(options.outfile, index=False)
-    print(f"Finished, time taken: {TIME.time() - timerstart} seconds")
+    print(f"Finished, time taken: {TIME.time() - timerstart:.1f} seconds")
 
 if __name__ == "__main__":
     main()

geocode/latlons2llsoa.py

@@ -49,7 +49,7 @@ def main():
         df["llsoacd"] = geo.reverse_geocode_llsoa(df[["latitude", "longitude"]].to_numpy(),
                                                   options.datazones)
     df.to_csv(options.outfile, index=False)
-    print(f"Finished, time taken: {TIME.time() - timerstart} seconds")
+    print(f"Finished, time taken: {TIME.time() - timerstart:.1f} seconds")
 
 if __name__ == "__main__":
     main()

geocode/postcodes2latlon.py

@@ -41,9 +41,8 @@ def main():
     timerstart = TIME.time()
     options = parse_options()
     with open(options.infile, "r") as fid:
-        df = pd.read_csv(fid)
+        df = pd.read_csv(fid).iloc[:100]
     with Geocoder(progress_bar=True) as geo:
-        # import pdb; pdb.set_trace()
         results = geo.geocode(postcodes=df["postcode"].to_numpy())
         lats = [r[0] if r[0] is not None else pd.NA for r in results]
         lons = [r[1] if r[1] is not None else pd.NA for r in results]
@@ -52,7 +51,7 @@ def main():
     df["longitude"] = lons
     df["geocode_status"] = status
     df.to_csv(options.outfile, index=False)
-    print(f"Finished, time taken: {TIME.time() - timerstart} seconds")
+    print(f"Finished, time taken: {TIME.time() - timerstart:.1f} seconds")
 
 if __name__ == "__main__":
     main()

setup.py

@@ -24,7 +24,7 @@
     # Versions should comply with PEP440.  For a discussion on single-sourcing
     # the version across setup.py and the project code, see
     # https://packaging.python.org/en/latest/single_source_version.html
-    version="0.9.0",
+    version="0.9.1",
 
     description="Geocode postcodes, addresses or LLSOA using the Code Point Open database and GMaps API.",
     long_description=long_description,