feat: add --debug flag, improve logging & help

closes #9

Author: fspoettel

README.md

@@ -39,6 +39,12 @@ pip install .
 ```
 Usage: geoclustering [OPTIONS] FILENAME
 
+  Tool to cluster geolocations. A cluster is created when a certain number of
+  points (--size) each are within a given distance (--distance) of at least
+  one other point in the cluster. Input is supplied as a csv file. At a
+  minimum, each row needs to have a 'lat' and a 'lon' column. Other rows are
+  reflected to the output.
+
 Options:
   -d, --distance FLOAT            (in km) Max. distance between two points in
                                   a cluster.  [required]
@@ -52,6 +58,7 @@ Options:
                                   Default: dbscan
   --open                          Open the generated visualization in the
                                   default browser automatically.
+  --debug                         Print debug output.
   --help                          Show this message and exit.
 ```
 

geoclustering/__main__.py

@@ -1,12 +1,20 @@
+from pathlib import Path
 import click
+import os
 import webbrowser
 
 import geoclustering.clustering as clustering
 import geoclustering.encoding as encoding
 import geoclustering.io as io
 
 
-@click.command()
+def print_debug(s):
+    click.secho(s, fg="bright_black")
+
+
+@click.command(
+    help="Tool to cluster geolocations. A cluster is created when a certain number of points (--size) each are within a given distance (--distance) of at least one other point in the cluster. Input is supplied as a csv file. At a minimum, each row needs to have a 'lat' and a 'lon' column. Other rows are reflected to the output."
+)
 @click.option(
     "--distance",
     "-d",
@@ -43,9 +51,15 @@
     is_flag=True,
     help="Open the generated visualization in the default browser automatically.",
 )
+@click.option("--debug", is_flag=True, help="Print debug output.")
 @click.argument("filename", type=click.Path(exists=True))
-def main(distance, size, output, filename, algorithm, open):
+def main(distance, size, output, filename, algorithm, open, debug):
+    if debug:
+        print_debug(f"Reading input from {Path(filename).absolute()}")
+
     df = io.read_csv_file(filename)
+    if debug:
+        print_debug(f"Read {len(df)} valid coordinates")
 
     clusters = clustering.cluster_locations(
         df=df, algorithm=algorithm, radius_km=distance, min_cluster_size=size
@@ -55,14 +69,18 @@ def main(distance, size, output, filename, algorithm, open):
         click.echo("Did not find clusters matching input parameters.")
         return
 
+    print_debug(f"Found {len(clusters)} valid clusters using {algorithm}")
+
     encoded = encoding.encode_clusters(clusters)
 
     io.write_output_file(output, "result.txt", encoded["string"])
     io.write_output_file(output, "result.json", encoded["json"])
     io.write_output_file(output, "result.geojson", encoded["geojson"])
     vis = io.write_visualization(output, "result.html", encoded["geojson"])
+    click.echo(f"Output files saved to {Path(output).absolute()}")
 
     if open:
+        print_debug(f"Opening visualization in default browser")
         webbrowser.open_new_tab("file://" + str(vis.absolute()))
 
 

geoclustering/io.py

@@ -2,9 +2,22 @@
 from pathlib import Path
 from pkg_resources import resource_filename
 import json
-import json
 import pandas as pd
 import numpy as np
+import os
+import sys
+
+
+class HiddenPrints:
+    """Disables stdout prints for a block of code."""
+
+    def __enter__(self):
+        self._original_stdout = sys.stdout
+        sys.stdout = open(os.devnull, "w")
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        sys.stdout.close()
+        sys.stdout = self._original_stdout
 
 
 def is_valid_lat(val: str) -> bool:
@@ -64,7 +77,10 @@ def write_output_file(dirname, filename, data):
 
 def write_visualization(dirname, filename, data):
     """Write a visualization, ensuring parent directories."""
-    map = KeplerGl()
+    # Hide kepler stdout output.
+    with HiddenPrints():
+        map = KeplerGl()
+
     map.add_data(data=data, name="clusters")
 
     # config configures a default color scheme for our clusters layer.
@@ -73,6 +89,9 @@ def write_visualization(dirname, filename, data):
         map.config = json.loads(f.read())
 
     filepath = ensure_file_path(dirname, filename)
-    map.save_to_html(file_name=str(filepath), center_map=True)
+
+    # Hide kepler stdout output.
+    with HiddenPrints():
+        map.save_to_html(file_name=str(filepath), center_map=True)
 
     return filepath